Updated on 2021/04/02

写真a

 
AKAI Naoki
 
Organization
Graduate School of Engineering Aerospace Engineering 3 Assistant Professor
Graduate School
Graduate School of Engineering
Undergraduate School
School of Engineering Mechanical and Aerospace Engineering
Title
Assistant Professor
Contact information
メールアドレス
External link

Degree 1

  1. Dr. Engineering ( 2016.3   Utsunomiya University ) 

Research Areas 1

  1. Informatics / Robotics and intelligent system  / robotics, intelligent systems

Current Research Project and SDGs 1

  1. ロボットの知能化に関する研究

Committee Memberships 2

  1.   機械学会技術委員会名  

    2018.4 - 2020.3   

  2.   つくばチャレンジ実行委員会  

    2016.4   

Awards 2

  1. 赤崎賞

  2. 名古屋大学COI産学官イノベーション賞

 

Papers 64

  1. Modeling Eye-Gaze Behavior of Electric Wheelchair Drivers via Inverse Reinforcement Learning Reviewed

    Yamato Maekawa, Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020     page: 1 - 7   2020.9

     More details

    Authorship:Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)  

    © 2020 IEEE. It is intuitively obvious that eye-gaze behaviors of experienced drivers are different from those of novice drivers. However, it is not easy to understand the difference in their behavior quantitatively. In this work, we present an explainable eye-gaze behavior modeling method for electric wheelchair drivers based on Inverse Reinforcement Learning (IRL). We first create feature maps that represent risk factors during driving. These feature maps are able to represent not only to what but also from where drivers pay attention. IRL uses the feature maps to learn the reward representing the eyegaze behaviors and allows us to see important features via the automatic acquisition of the reward. Through analysis of the learned model, we show quantitative evidence that eye-gaze behaviors of experienced drivers are better-balanced by paying attention to multiple risks.

    DOI: 10.1109/ITSC45102.2020.9294255

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/itsc/itsc2020.html#MaekawaAHMDKIM20

  2. Extracting Human-Like Driving Behaviors from Expert Driver Data Using Deep Learning Reviewed

    Kyle Sama, Yoichi Morales, Hailong Liu, Naoki Akai, Alexander Carballo, Eijiro Takeuchi, Kazuya Takeda

    IEEE Transactions on Vehicular Technology   Vol. 69 ( 9 ) page: 9315 - 9329   2020.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC  

    © 1967-2012 IEEE. This paper introduces a method to extract driving behaviors from a human expert driver which are applied to an autonomous agent to reproduce proactive driving behaviors. Deep learning techniques were used to extract latent features from the collected data. Extracted features were clustered into behaviors and used to create velocity profiles allowing an autonomous driving agent could drive in a human-like manner. By using proactive driving behaviors, the agent could limit potential sources of discomfort such as jerk and uncomfortable velocities. Additionally, we proposed a method to compare trajectories where not only the geometric similarity is considered, but also velocity, acceleration and jerk. Experimental results in a simulator implemented in ROS show that the autonomous agent built with the driving behaviors was capable of driving similarly to expert human drivers.

    DOI: 10.1109/TVT.2020.2980197

    Web of Science

    Scopus

  3. Semantic Localization Considering Uncertainty of Object Recognition Reviewed

    Naoki Akai, Takatsugu Hirayama, Hiroshi Murase

    IEEE Robotics and Automation Letters   Vol. 5 ( 3 ) page: 4384 - 4391   2020.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC  

    © 2016 IEEE. Semantics can be leveraged in ego-vehicle localization to improve robustness and accuracy because objects with the same labels can be correctly matched with each other. Object recognition has significantly improved owing to advances in machine learning algorithms. However, perfect object recognition is still challenging in real environments. Hence, the uncertainty of object recognition must be considered in localization. This letter proposes a novel localization method that integrates a supervised object recognition method, which predicts probabilistic distributions over object classes for individual sensor measurements, into the Bayesian network for localization. The proposed method uses the estimated probabilities and Dirichlet distribution to calculate the likelihood for estimating an ego-vehicle pose. Consequently, the uncertainty can be handled in localization. We present an implementation example of the proposed method using a particle filter and deep-neural-network-based point cloud semantic segmentation and evaluate it by simulation and the SemanticKITTI dataset. Experimental results show that the proposed method can accurately generate likelihood distribution even when object recognition accuracy is degraded, and its estimation accuracy is the highest compared to that of two conventional methods.

    DOI: 10.1109/LRA.2020.2998403

    Web of Science

    Scopus

  4. Hybrid Localization using Model- and Learning-Based Methods: Fusion of Monte Carlo and E2E Localizations via Importance Sampling Reviewed

    Naoki Akai, Takatsugu Hirayama, Hiroshi Murase

    Proceedings - IEEE International Conference on Robotics and Automation     page: 6469 - 6475   2020.5

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)  

    © 2020 IEEE. This paper proposes a hybrid localization method that fuses Monte Carlo localization (MCL) and convolutional neural network (CNN)-based end-to-end (E2E) localization. MCL is based on particle filter and requires proposal distributions to sample the particles. The proposal distribution is generally predicted using a motion model. However, because the motion model cannot handle unanticipated errors, the predicted distribution is sometimes inaccurate. The use of other ideal proposal distributions, such as the measurement model, can improve robustness against such unanticipated errors. This technique is called importance sampling (IS). However, it is difficult to sample the particles from such ideal distributions because they are not represented in the closed form. Recent works have proved that CNNs with dropout layers represent the posterior distributions over their outputs conditioned on the inputs and the CNN predictions are equivalent to sampling the outputs from the posterior. Therefore, the proposed method utilizes a CNN to sample the particles and fuses them with MCL via IS. Consequently, the advantages of both MCL and E2E localization can be simultaneously leveraged while preventing their disadvantages. Experiments demonstrate that the proposed method can smoothly estimate the robot pose, similar to the model-based method, and quickly re-localize it from the failures, similar to the learning-based method.

    DOI: 10.1109/ICRA40945.2020.9196568

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/icra/icra2020.html#AkaiHM20

  5. 3D Monte Carlo Localization with Efficient Distance Field Representation for Automated Driving in Dynamic Environments Reviewed

    Naoki Akai, Takatsugu Hirayama, Hiroshi Murase

    IEEE Intelligent Vehicles Symposium, Proceedings     page: 1859 - 1866   2020

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)  

    © 2020 IEEE. This paper presents a LiDAR-based 3D Monte Carlo localization (MCL) with an efficient distance field (DF) representation method. To implement 3D MCL, high computing capacity is required because the likelihood of many pose candidates, i.e., particles, must be calculated in real time by comparing sensor measurements and a map. Additionally, a large-scale map is needed for allocation to embedded computers since autonomous vehicles are required to navigate wide areas. These make it difficult for 3D MCL implementation. This paper first presents an efficient DF representation method while considering the 3D LiDAR-based localization characteristics. Because each DF voxel has the closest distance from occupied voxels, swift comparison of the sensor measurements and map can be achieved. Consequently, 3D MCL using the likelihood field model (LFM) can be executed in real time. Furthermore, this paper presents a method for improving the localization robustness to environmental changes without increasing memory and computational cost from that of the LFM-based MCL. Through experiments using the SemanticKITTI dataset, we show that the presented method can efficiently and robustly work in dynamic environments.

    DOI: 10.1109/IV47402.2020.9304679

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/ivs/ivs2020.html#AkaiHM20

  6. Automatic Interaction Detection between Vehicles and Vulnerable Road Users during Turning at an Intersection Reviewed International coauthorship

    Hao Cheng, Hailong Liu, Fumito Shinmura, Naoki Akai, Hiroshi Murase, Takatsugu Hirayama

    IEEE Intelligent Vehicles Symposium, Proceedings     page: 912 - 918   2020

     More details

    Authorship:Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)  

    © 2020 IEEE. Interaction detection between vehicles and vulnerable road users (e.g. pedestrians and cyclists) is important for e.g. safety control and autonomous driving. However, there are many challenges for automatically detecting interactions, such as the ambiguity of defining when interaction is required in dynamic traffic activities among different road users and the lack of labeled data for training a machine learning detector. To overcome the challenges, we introduce a way to define whether or not interaction is required in various traffic scenes and create a large real-world dataset from a very challenging intersection. A sequence-to-sequence method that uses the object information and motion information of the traffic scenes extracted by a state-of-the-art object detector and from optical flow, respectively, is proposed for automatic interaction detection. The proposed method generates a probability of interaction at each short interval (< 0.1 s) that represents the changing of interaction along a sequence. We obtain a baseline model that differentiates no interaction from interaction on the basis of the location and road user type from the detected object information. Compared with the baseline model, the empirical results of the proposed method demonstrate very accurate predictions for vehicle turning sequences with varying length.

    DOI: 10.1109/IV47402.2020.9304554

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/ivs/ivs2020.html#ChengLSAMH20

  7. An analysis of how driver experience affects eye-gaze behavior for robotic wheelchair operation Reviewed

    Yamato Maekawa, Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019     page: 4443 - 4451   2019.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE COMPUTER SOC  

    © 2019 IEEE. Drivers obtain information on surrounding environment using their eyesights. Experienced eye-gaze behavior is needed when driving at places where multiple risks exist to prepare for and avoid them. In this work, we analyze the change in eye-gaze behavior in such situations while a driver gains experience on the operation of a robotic wheelchair. Accurate distance information in the traffic environment is important to analyze the eye-gaze behavior. However, almost all previous works analyze eye-gaze behavior in a 2D environment, so they could not obtain accurate distance information. For this reason, we analyze eye-gaze behavior in 3D space. Concretely, we developed a novel eye-gaze behavior analysis platform based on a robotic wheelchair and estimated the driver's attention in 3D space. We try to analyze the eye-gaze behavior considering a useful field-of-view in 3D space based on the distance information instead of only the fixation point to investigate the objects that a driver implicitly pays attention to and from where s/he focuses on them. Results show that novice drivers pay attention to a single risk at a time. In contrast, they pay more attention to multiple risks simultaneously as they gain experience. Additionally, we discuss what features are effective to model the eye-gaze behavior based on the results.

    DOI: 10.1109/ICCVW.2019.00545

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/iccvw/iccvw2019.html#MaekawaAHMDKIM19

  8. Misalignment Recognition Using Markov Random Fields With Fully Connected Latent Variables for Detecting Localization Failures Reviewed

    Naoki Akai, Luis Yoichi Morales, Takatsugu Hirayam, Hiroshi Murase

    IEEE ROBOTICS AND AUTOMATION LETTERS   Vol. 4 ( 4 ) page: 3955 - 3962   2019.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC  

    Recognizing misalignment between sensor measurements and objects that exist on a map due to inaccuracies in localization estimation is challenging. This can be attributed to the fact that the sensor measurements are individually modeled for solving the localization problem, resulting in entire relations of the measurements being ignored. This letter proposes a misalignment recognition method using Markov random fields with fully connected latent variables for the detection of localization failures. The proposed method estimates the classes of each sensor measurement that are aligned, misaligned, and obtained from unknown obstacles. The full connection allows us to consider the entire relation of the measurements. A misalignment can be exactly recognized even when partial sensor measurements overlap with mapped objects. Based on the class estimation results, we are able to distinguish whether the localization has failed or not. The proposed method was compared with six alternative methods, including a convolutional neural network, using datasets composed of success and failure localization samples. Experimental results show that the classification accuracy of the localization samples using the proposed method exceeds 95% and outperforms the other examined methods.

    DOI: 10.1109/LRA.2019.2929999

    Web of Science

  9. Safety Criteria Analysis for Negotiating Blind Corners in Personal Mobility Vehicles Based on Driver's Attention Simulation on 3D Map Reviewed

    Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Hiroshi Murase

    2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019     page: 2367 - 2374   2019.10

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2019 IEEE. In this study, we attempt to establish the numerical safety criteria for negotiating blind corners in personal mobility vehicles (PMVs). Safety should be the most important consideration in designing autonomous PMVs. However, determining the suitable trade-off between safety and speed is a weighty concern because speed is significantly compromised when performing overly safe navigation. We analyze the driving behavior of a robotic PMV operated by a human driver. The robotic PMV can measure the driver's gaze, and allows us to recognize both the pose of the PMV and the driver's visual attention on a 3D map. As a result, the occluded areas for the driver can be estimated. Then, potential colliding hazard obstacles (PCHOs) are simulated based on the occlusion. PCHOs refer to occluded obstacles that the driver encounters suddenly with which he cannot avoid collision. The participants of our experiments were one skillful and three non-skilled ones. Experimental results demonstrate that similar PCHOs are observed even when the driving styles of the participants are different. Additionally, the existence of a boundary that distinguishes expected and unexpected obstacles is indicated by investigating the parameters of the PCHOs. Finally, we conclude that the boundary could be utilized as a numerical criterion for ensuring safety while negotiating blind corners.

    DOI: 10.1109/ITSC.2019.8917163

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/itsc/itsc2019.html#AkaiHMM19

  10. Driving behavior modeling based on hidden markov models with driver's eye-gaze measurement and ego-vehicle localization Reviewed

    Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Yasuhiro Akagi, Hailong Liu, Hiroshi Murase

    IEEE Intelligent Vehicles Symposium, Proceedings   Vol. 2019-June   page: 949 - 956   2019.6

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2019 IEEE. This paper presents a comparison of driving behavior modeling methods based on hidden Markov models (HMMs) with driver's eye-gaze measurement and ego-vehicle localization. Original HMMs are sometimes insufficient to model real-world scenarios. To overcome these limitations, extended HMMs have been proposed, e.g., autoregressive input-output HMMs (AIOHMMs). This paper first details AIOHMMs and presents ways to use them for driving behavior modeling. We compare the performance for behavior modeling and maneuver discrimination for six types of HMMs. The driving data for this work was gathered in our university campus with a car-like vehicle. Experimental results suggest that the hidden states can properly represent the average of the driving actions when the driving behaviors are accurately modeled by the HMMs. It is also suggested that surrounding and past information can be used to flexibly model the relationship between driving actions and related information.

    DOI: 10.1109/IVS.2019.8814287

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/ivs/ivs2019.html#AkaiHMALM19

  11. Learning How to Drive in Blind Intersections from Human Data Reviewed

    Kyle Sama, Yoichi Morales, Naoki Akai, Eijiro Takeuchi, Kazuya Takeda

    Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018     page: 317 - 324   2019.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2018 IEEE. In this paper we present a method to learn how to drive in different types of blind intersections using expert driving data. We cluster different intersections based on the velocity of how drivers approach them, and train a linear SVM classifier for each class of intersection. Through clustering we found that there were three different classes of intersections in typical residential areas in Japan. We used inverse reinforcement learning (IRL) to build a driving model for each type of intersection. The models were trained from 308 trajectories traversed by 5 different drivers. The models and policies were implemented and evaluated in a ROS simulator where the agent is provided a global path, and upon it reaching an intersection, it selects the appropriate trained policy. By doing this, the simulated autonomous vehicle can perform proactive safe driving behaviors when approaching blind intersections.

    DOI: 10.1109/SMC.2018.00064

    Web of Science

    Scopus

  12. Driving Behavior Modeling Based on Hidden Markov Models with Driver's Eye-Gaze Measurement and Ego-Vehicle Localization Reviewed

    Akai Naoki, Hirayama Takatsugu, Morales Luis Yoichi, Akagi Yasuhiro, Liu Hailong, Murase Hiroshi

    2019 30TH IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV19)     page: 949 - 956   2019

     More details

    Authorship:Lead author, Corresponding author  

    Web of Science

  13. Safety Criteria Analysis for Negotiating Blind Corners in Personal Mobility Vehicles Based on Driver's Attention Simulation on 3D Map

    Akai Naoki, Hirayama Takatsugu, Morales Luis Yoichi, Murase Hiroshi

    2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC)     page: 2367 - 2374   2019

     More details

  14. Mobile Robot Localization Considering Class of Sensor Observations

    Naoki Akai, Luis Yoichi Morales, Hiroshi Murase

    IEEE International Conference on Intelligent Robots and Systems     page: 3159 - 3166   2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2018 IEEE. Localization robustness against environment dynamics is significant for robots to achieve autonomous navigation in unmodified environments. A basic method of improving the robustness of a robot is considering the sensor observations obtained from mapped obstacles and using them for localizing the robot's pose. This study proposes an observation model that considers the class of sensor observations, where 'class' categorizes the sensor observations as those obtained from mapped and unmapped obstacles. In the proposed approach, the robot's pose and the class are estimated simultaneously. As a result, the robot's pose can be localized using the sensor observations obtained only from mapped obstacles. First, we evaluated the performance of the proposed approach using simulations. Further, we tested the proposed approach in a real-world mobile robot navigation competition, called 'Tsukuba Challenge,' held in Japan. The robustness and effectiveness of the proposed approach against environment dynamics were verified from the experimental results.

    DOI: 10.1109/IROS.2018.8594146

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/iros/iros2018.html#AkaiMM18

  15. Personal Mobility Vehicle Autonomous Navigation Through Pedestrian Flow: A Data Driven Approach for Parameter Extraction

    Yoichi Morales, Naoki Akai, Hiroshi Murase

    IEEE International Conference on Intelligent Robots and Systems     page: 3438 - 3444   2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2018 IEEE. In this paper we present a data driven approach for safe and smooth autonomous navigation of a personal mobility vehicle (PMV) when facing moving obstacles such as people and bicycles in public pedestrian paths. In a period of three months, data from five different persons driving the robotic PMV in an outdoor environment while facing pedestrians were collected. 2465 clean tracks around the vehicle together with PMVs trajectories were collected. We performed an analysis of the parameters involved for human-driven smooth navigation. Relevant parameters regarding PMV-Human interaction included distance to moving objects, passing side and velocities. Moreover, data suggests the existence of a social navigational distance for the PWv. For autonomous navigation we implemented a Frenet planner to achieve safe and smooth navigation for the passenger and pedestrians around. Experimental results in real pedestrian paths show that the PMV is capable of smoothly following its path while facing pedestrians and bicycles.

    DOI: 10.1109/IROS.2018.8593902

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/iros/iros2018.html#MoralesAM18

  16. A Slope-robust Cascaded Ground Segmentation in 3D Point Cloud for Autonomous Vehicles

    Patiphon Narksri, Eijiro Takeuchi, Yoshiki Ninomiya, Yoichi Morales, Naoki Akai, Nobuo Kawaguchi

    IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC   Vol. 2018-November   page: 497 - 504   2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2018 IEEE. In this paper, a slope-robust cascaded ground segmentation in 3D point cloud for autonomous vehicles is presented. In many challenging terrains encountered by autonomous vehicles where the ground does not have a simple planar shape such as sloped roads, many existing ground segmentation algorithms fail. The proposed algorithm aims to correctly segment ground points in scans where these challenging terrains are present. The proposed method consists of two main steps. First, filtering the majority of non-ground points using the geometry of the sensor and the distance between consecutive rings in the scan. In the second step, multi-region RANSAC plane fitting is used to separate remaining non-ground points from ground points in the scan. The 3D data was taken and partially labeled for quantitative evaluation. The experimental results were outstanding as the proposed algorithm could segment the ground correctly in various challenging terrains. The proposed algorithm could correctly segment ground points in the scan even in sloped terrains and achieved higher accuracy than other algorithms used in the evaluation.

    DOI: 10.1109/ITSC.2018.8569534

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/itsc/itsc2018.html#NarksriTNMAK18

  17. Towards Predictive Driving through Blind Intersections

    Luis Yoichi Morales, Akai Naoki, Yuki Yoshihara, Hiroshi Murase

    IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC   Vol. 2018-November   page: 716 - 722   2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2018 IEEE. This paper presents an approach for predictive driving when facing blind intersections based on expert data. Expert drivers anticipate and avoid potential dangerous situations. In most cases these complex behaviors cannot be reproduced by state of the art planning approaches. We present an analysis of expert drivers while passing through blind intersections, we extract useful driving features to model the intersection and propose a cost function based on those features. We use inverse reinforcement learning to extract a feature-based cost function and learn its parameters from driver data. Finally, feature weights are computed based on collected expert driving data (using 211 trajectories). Evaluation was performed in terms of trajectory and speed using modified Hausdorff distance. Experimental results show that the planner is capable of computing trajectories comparable to those ones of the expert drivers when facing blind intersections.

    DOI: 10.1109/ITSC.2018.8569931

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/itsc/itsc2018.html#SaikiAYM18

  18. Toward Localization-Based Automated Driving in Highly Dynamic Environments: Comparison and Discussion of Observation Models

    Naoki Akai, Luis Yoichi Morales, Takatsugu Hirayama, Hiroshi Murase

    IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC   Vol. 2018-November   page: 2215 - 2222   2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2018 IEEE. To robustly localize the pose of an ego vehicle within a dynamic environment, it is important to model the sensor measurements precisely, including changes in the environment. This study describes the observation models developed for localization performed in highly dynamic environments, and presents the results of comparing these models. In this study, four observation models, including our previously proposed model, were compared by conducting a simulation. The models had different ways of coping with changes in the environment, and produced different results. Moreover, the comparison results revealed that each model had its own advantages and disadvantages. Finally, we demonstrated that our previously proposed model can achieve satisfactory performance in terms of computation complexity and estimation accuracy.

    DOI: 10.1109/ITSC.2018.8569967

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/itsc/itsc2018.html#AkaiMHM18

  19. Driving Feature Extraction and Behavior Classification Using an Autoencoder to Reproduce the Velocity Styles of Experts

    Kyle Sama, Yoichi Morales, Naoki Akai, Hailong Liu, Eijiro Takeuchi, Kazuya Takeda

    IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC   Vol. 2018-November   page: 1337 - 1343   2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2018 IEEE. In this paper we present a work on encoding, clustering and modeling expert driver behaviors to be reproduced by an autonomous driving car agent. We collected speed, brake, steering wheel and acceleration data from an expert driving in typical Japanese suburban areas. We grouped together consecutive data in a sliding window as the input to a fully connected deep autoencoder for dimension reduction. We then clustered the encoded driving data into 9 different behaviors. For each behavior class, we modeled the speed using a fit of same clustered data and tested the models in a ROS car simulator. Results show that the models created from the clusters could represent different driving behaviors on various roads. Experimental simulations show that the proposed approach can reproduce speed behavior comparable to that of the expert drivers even in new environments.

    DOI: 10.1109/ITSC.2018.8569245

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/itsc/itsc2018.html#SamaMALTT18

  20. Simultaneous pose and reliability estimation using convolutional neural network and Rao–Blackwellized particle filter

    Naoki Akai, Luis Yoichi Morales, Hiroshi Murase

    Advanced Robotics   Vol. 32 ( 17 ) page: 930 - 944   2018.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:TAYLOR & FRANCIS LTD  

    © 2018, © 2018 Taylor & Francis and The Robotics Society of Japan. In this study, we propose a novel localization approach that simultaneously estimates the reliability of estimation results. In the approach, a convolutional neural network (CNN) is used to make decision whether the localization process has failed or not. We train the CNN using a dataset that includes successful localization results and faults. However, the decision will contain some noise and many misdetection results may occur when the decision made by the CNN is used directly to detect faults. Therefore, we estimate both a robot's pose and reliability of the localization results based on the decision. To simultaneously estimate the robot's pose and reliability, we propose a new graphical model and implement a Rao–Blackwellized particle filter based on the model. We evaluated the proposed approach based on simulations and actual environments, which showed that the reliability estimated by the proposed approach can be used as an exact criterion for detecting localization faults. In addition, we show that the proposed approach can be applied in actual environments even when a dataset created from a simulation is used to train the CNN.

    DOI: 10.1080/01691864.2018.1509726

    Web of Science

    Scopus

    Other Link: https://dblp.uni-trier.de/db/journals/ar/ar32.html#AkaiSM18

  21. End-to-End Autonomous Mobile Robot Navigation with Model-Based System Support

    Carballo Alexander, Seiya Shunya, Lambert Jacob, Darweesh Hatem, Narksri Patiphon, Morales Luis Yoichi, Akai Naoki, Takeuchi Eijiro, Takeda Kazuya

    JOURNAL OF ROBOTICS AND MECHATRONICS   Vol. 30 ( 4 ) page: 563 - 583   2018.8

     More details

  22. Tsukuba Challenge 2017 Dynamic Object Tracks Dataset for Pedestrian Behavior Analysis

    Lambert Jacob, Liang Leslie, Morales Luis Yoichi, Akai Naoki, Carballo Alexander, Takeuchi Eijiro, Narksri Patiphon, Seiya Shunya, Takeda Kazuya

    JOURNAL OF ROBOTICS AND MECHATRONICS   Vol. 30 ( 4 ) page: 598 - 612   2018.8

     More details

  23. Teaching-Playback Navigation Without a Consistent Map

    Akai Naoki, Morales Luis Yoichi, Murase Hiroshi

    JOURNAL OF ROBOTICS AND MECHATRONICS   Vol. 30 ( 4 ) page: 591 - 597   2018.8

     More details

  24. End-to-end autonomous mobile robot navigation with model-based system support

    Alexander Carballo, Shunya Seiya, Jacob Lambert, Hatem Darweesh, Patiphon Narksri, Luis Yoichi Morales, Naoki Akai, Eijiro Takeuchi, Kazuya Takeda

    Journal of Robotics and Mechatronics   Vol. 30 ( 4 ) page: 563 - 583   2018.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:FUJI TECHNOLOGY PRESS LTD  

    © 2018, Fuji Technology Press. All rights reserved. Autonomous mobile robot navigation in real unmodified outdoor areas frequented by people on their business, children playing, fast running bicycles, and even robots, remains a difficult challenge. For eleven years, the Tsukuba Challenge Real World Robot Challenge (RWRC) has brought together robots, researchers, companies, government, and ordinary citizens, under the same outdoor space to push forward the limits of autonomous mobile robots. For the Tsukuba Challenge 2017 participation, our team proposed to study the problem of sensors-to-actuators navigation (also called End-to-End), this is, having the robot to navigate towards the destination on a complex path, not only moving straight but also turning at intersections. End-to-End (E2E) navigation was implemented using a convolutional neural network (CNN): the robot learns how to go straight, turn left, and turn right, using camera images and trajectory data. E2E network training and evaluation was performed at Nagoya University, on similar outdoor conditions to that of Tsukuba Challenge 2017 (TC2017). Even thought E2E was trained on a different environment and conditions, the robot successfully followed the designated trajectory in the TC2017 course. Learning how to follow the road no matter the environment is of the key attributes of E2E based navigation. Our E2E does not perform obstacle avoidance and can be affected by illumination and seasonal changes. Therefore, to improve safety and add fault tolerance measures, we developed an E2E navigation approach with model-based system as backup. The model-based system is based on our open source autonomous vehicle software adapted to use on a mobile robot. In this work we describe our approach, implementation, experiences and main contributions.

    DOI: 10.20965/jrm.2018.p0563

    Web of Science

    Scopus

    CiNii Article

  25. Tsukuba challenge 2017 dynamic object tracks dataset for pedestrian behavior analysis

    Jacob Lambert, Leslie Liang, Luis Yoichi Morales, Naoki Akai, Alexander Carballo, Eijiro Takeuchi, Patiphon Narksri, Shunya Seiya, Kazuya Takeda

    Journal of Robotics and Mechatronics   Vol. 30 ( 4 ) page: 598 - 612   2018.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:FUJI TECHNOLOGY PRESS LTD  

    © 2018, Fuji Technology Press. All rights reserved. Navigation in social environments, in the absence of traffic rules, is the difficult task at the core of the annual Tsukuba Challenge. In this context, a better understanding of the soft rules that influence social dynamics is key to improve robot navigation. Prior research attempts to model social behavior through microscopic interactions, but the resulting emergent behavior depends heavily on the initial conditions, in particular the macroscopic setting. As such, data-driven studies of pedestrian behavior in a fixed environment may provide key insight into this macroscopic aspect, but appropriate data is scarcely available. To support this stream of research, we release an open-source dataset of dynamic object trajectories localized in a map of 2017 Tsukuba Challenge environment. A data collection platform equipped with lidar, camera, IMU, and odometry repeatedly navigated the challenge’s course, recording observations of passersby. Using a background map, we localized ourselves in the environment, removed the static background from the point cloud data, clustered the remaining points into dynamic objects and tracked their movements over time. In this work, we present the Tsukuba Challenge Dynamic Object Tracks dataset, which features nearly 10,000 trajectories of pedestrians, cyclists, and other dynamic agents, in particular autonomous robots. We provide a 3D map of the environment used as global frame for all trajectories. For each trajectory, we provide at regular time intervals an estimated position, velocity, heading, and rotational velocity, as well as bounding boxes for the objects and segmented lidar point clouds. As additional contribution, we provide a discussion which focuses on some discernible macroscopic patterns in the data.

    DOI: 10.20965/jrm.2018.p0598

    Web of Science

    Scopus

    CiNii Article

  26. Teaching-playback navigation without a consistent map

    Naoki Akai, Luis Yoichi Morales, Hiroshi Murase

    Journal of Robotics and Mechatronics   Vol. 30 ( 4 ) page: 591 - 597   2018.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:FUJI TECHNOLOGY PRESS LTD  

    © 2018, Fuji Technology Press. All rights reserved. This paper presents a teaching-playback navigation method that does not require a consistent map built using simultaneous localization and mapping (SLAM). Many open source projects related to autonomous navigation including SLAM have been made available recently; however, autonomous mobile robot navigation in large-scale environments is still difficult because it is difficult to build a consistent map. The navigation method presented in this paper uses several partial maps to represent an environment map. In other words, the complex mapping process is not necessary to begin autonomous navigation. In addition, the trajectory that the robot travels in the mapping phase can be directly used as a target path. As a result, teaching-playback autonomous navigation can be achieved without any off-line processes. We tested the navigation method using log data taken in the environment of the Tsukuba Challenge and the testing results show its performance. We provide source code for the navigation method, which includes modules required for autonomous navigation (https://github. com/NaokiAkai/AutoNavi).

    DOI: 10.20965/jrm.2018.p0591

    Web of Science

    Scopus

    CiNii Article

  27. Retrieving a driving model based on clustered intersection data

    Kyle Sama, Yoichi Morales, Naoki Akai, Eijiro Takeuchi, Kazuya Takeda

    2018 3rd International Conference on Control and Robotics Engineering, ICCRE 2018     page: 222 - 226   2018.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2018 IEEE. In order for autonomous vehicles to learn how to naturally navigate through an intersection, we present a method of learning from expert drivers using inverse reinforcement learning. We cluster different intersections according to how experts drive through them and train a model based on each class of intersection. With these models to choose from, as the agent encounters various situations, it can retrieve the corresponding model and execute the most fit policy. The models were trained from 308 trajectories recorded from 5 different drivers at 3 intersections. These clusters were then used to classify a further 5 more intersections. The approach is evaluated in a simulator where we provide a global path to be followed by the vehicle where at each intersection it drives according to the trained policies.

    DOI: 10.1109/ICCRE.2018.8376469

    Web of Science

    Scopus

  28. Autonomous driving based on accurate localization using multilayer LiDAR and dead reckoning

    Naoki Akai, Luis Yoichi Morales, Takuma Yamaguchi, Eijiro Takeuchi, Yuki Yoshihara, Hiroyuki Okuda, Tatsuya Suzuki, Yoshiki Ninomiya

    IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC   Vol. 2018-March   page: 1 - 6   2018.3

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2017 IEEE. In this study, we developed an autonomous driving system for mountainous public roads. Three-dimensional normal distribution transform (NDT) scan matching is employed for localization and a model predictive controller is utilized for vehicle motion control. In order to increase the robustness of the localization method, the estimated poses are computed by an extended Kalman filter using dead reckoning and NDT information. The uncertainty of the pose estimated by NDT is determined by using the Hessian matrix computed in the optimization process for scan matching. We conducted experiments in a public road environment over 20 times and all of the tests were successful. The experimental results confirmed that the autonomous driving system can operate reliably in mountainous public roads. In addition, the evaluation results obtained for the localization method showed that accurate and robust localization can be achieved in mountainous rural environments.

    DOI: 10.1109/ITSC.2017.8317797

    Web of Science

    Scopus

  29. Driving Feature Extraction and Behavior Classification Using an Autoencoder to Reproduce the Velocity Styles of Experts

    Sama Kyle, Morales Yoichi, Akai Naoki, Liu Hailong, Takeuchi Eijiro, Takeda Kazuya

    2018 21ST INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)     page: 1337 - 1343   2018

     More details

  30. A Slope-robust Cascaded Ground Segmentation in 3D Point Cloud for Autonomous Vehicles

    Narksri Patiphon, Takeuchi Eijiro, Ninomiya Yoshiki, Morales Yoichi, Akai Naoki, Kawaguchi Nobuo

    2018 21ST INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)     page: 497 - 504   2018

     More details

  31. Mobile Robot Localization Considering Class of Sensor Observations

    Akai Naoki, Morales Luis Yoichi, Murase Hiroshi

    2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)     page: 3159 - 3166   2018

     More details

  32. Toward Localization-Based Automated Driving in Highly Dynamic Environments: Comparison and Discussion of Observation Models

    Akai Naoki, Morales Luis Yoichi, Hirayama Takatsugu, Murase Hiroshi

    2018 21ST INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)     page: 2215 - 2222   2018

     More details

  33. Retrieving a Driving Model Based on Clustered Intersection Data

    Sama Kyle, Morales Yoichi, Akai Naoki, Takeuchi Eijiro, Takeda Kazuya

    2018 3RD INTERNATIONAL CONFERENCE ON CONTROL AND ROBOTICS ENGINEERING (ICCRE)     page: 222 - 226   2018

     More details

  34. Personal Mobility Vehicle Autonomous Navigation through Pedestrian Flow: A Data Driven Approach for Parameter Extraction

    Morales Yoichi, Akai Naoki, Murase Hiroshi

    2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)     page: 3438 - 3444   2018

     More details

  35. Autonomous predictive driving for blind intersections

    Yuki Yoshihara, Yoichi Morales, Naoki Akai, Eijiro Takeuchi, Yoshiki Ninomiya

    IEEE International Conference on Intelligent Robots and Systems   Vol. 2017-September   page: 3452 - 3459   2017.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2017 IEEE. This paper presents a model for safe driving at blind intersections and its integration to a local planner based on a Frenet frame. The model predicts potential moving obstacles from blind intersections to proactively slow down to avoid potential collisions. The derivation of the model is described and its parameters are detailed. The local planner computes smooth trajectories with smooth velocity profiles so that the vehicle can follow the paths without jerk and sudden accelerations resulting in safe and comfortable navigation. Experimental results in simulation and in the real field with an autonomous car, show that the proposed predictive driving framework can reproduce human expert driver's trajectories and velocities when facing blind intersections.

    DOI: 10.1109/IROS.2017.8206185

    Web of Science

    Scopus

  36. Localization based on multiple visual-metric maps

    Adi Sujiwo, Eijiro Takeuchi, Luis Yoichi Morales, Naoki Akai, Yoshiki Ninomiya, Masato Edahiro

    IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems   Vol. 2017-November   page: 212 - 219   2017.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2017 IEEE. This paper presents a fusion of monocular camera-based metric localization, IMU and odometry in dynamic environments of public roads. We build multiple vision-based maps and use them at the same time in localization phase. For the mapping phase, visual maps are built by employing ORB-SLAM and accurate metric positioning from LiDAR-based NDT scan matching. This external positioning is utilized to correct for scale drift inherent in all vision-based SLAM methods. Next in the localization phase, these embedded positions are used to estimate the vehicle pose in metric global coordinates using solely monocular camera. Furthermore, to increase system robustness we also proposed utilization of multiple maps and sensor fusion with odometry and IMU using particle filter method. Experimental testing were performed through public road environment as far as 170 km at different times of day to evaluate and compare localization results of vision-only, GNSS and sensor fusion methods. The results show that sensor fusion method offers lower average errors than GNSS and better coverage than vision-only one.

    DOI: 10.1109/MFI.2017.8170431

    Web of Science

    Scopus

  37. 3D magnetic field mapping in large-scale indoor environment using measurement robot and Gaussian processes

    Naoki Akai, Koichi Ozaki

    2017 International Conference on Indoor Positioning and Indoor Navigation, IPIN 2017   Vol. 2017-January   page: 1 - 7   2017.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2017 IEEE. Magnetic fields are used for localization and navigation in the field of robotics. In recent years, because of the spread of mobile devices equipped with magnetic sensors (e.g., smart phones), the use of magnetic fields has been extensive, especially for position tracking of mobile devices. One example application of such tracking is in identifying the position of a person with a mobile device. Development of this application requires a three-dimensional (3D) magnetic map that represents the magnetic distribution of a 3D environment since the device moves around in 3D space. It is, however, difficult to construct a 3D magnetic map of a large-scale environment because measuring the magnetic field is time consuming and expensive. In this paper we propose an efficient method for mapping the 3D magnetic field of a large-scale environment. The method uses a mobile manipulator to measure the 3D magnetic field, enabling 3D magnetic data to be automatically collected. Moreover, the method uses Gaussian processes (GPS) for regression of the magnetic field. In this study, we first evaluate the performance of the GPS and then describe the measurement robot. In an experiment, a 3D magnetic field of an indoor environment is visualized by using this method and the performance of the presented method is demonstrated.

    DOI: 10.1109/IPIN.2017.8115960

    Web of Science

    Scopus

  38. Open Source Integrated Planner for Autonomous Navigation in Highly Dynamic Environments

    Darweesh Hatem, Takeuchi Eijiro, Takeda Kazuya, Ninomiya Yoshiki, Sujiwo Adi, Morales Luis Yoichi, Akai Naoki, Tomizawa Tetsuo, Kato Shinpei

    JOURNAL OF ROBOTICS AND MECHATRONICS   Vol. 29 ( 4 ) page: 668 - 684   2017.8

     More details

  39. Robust and Accurate Monocular Vision-Based Localization in Outdoor Environments of Real-World Robot Challenge

    Sujiwo Adi, Takeuchi Eijiro, Morales Luis Yoichi, Akai Naoki, Darweesh Hatem, Ninomiya Yoshiki, Edahiro Masato

    JOURNAL OF ROBOTICS AND MECHATRONICS   Vol. 29 ( 4 ) page: 685 - 696   2017.8

     More details

  40. Open source integrated planner for autonomous navigation in highly dynamic environments

    Hatem Darweesh, Eijiro Takeuchi, Kazuya Takeda, Yoshiki Ninomiya, Adi Sujiwo, Luis Yoichi Morales, Naoki Akai, Tetsuo Tomizawa, Shinpei Kato

    Journal of Robotics and Mechatronics   Vol. 29 ( 4 ) page: 668 - 684   2017.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:FUJI TECHNOLOGY PRESS LTD  

    © 2017, Fuji Technology Press. All rights reserved. Planning is one of the cornerstones of autonomous robot navigation. In this paper we introduce an open source planner called “OpenPlanner” for mobile robot navigation, composed of a global path planner, a behavior state generator and a local planner. Open-Planner requires a map and a goal position to compute a global path and execute it while avoiding obstacles. It can also trigger behaviors, such as stopping at traffic lights. The global planner generates smooth, global paths to be used as a reference, after considering traffic costs annotated in the map. The local planner generates smooth, obstacle-free local trajectories which are used by a trajectory tracker to achieve low level control. The behavior state generator handles situations such as path tracking, object following, obstacle avoidance, emergency stopping, stopping at stop signs and traffic light negotiation. OpenPlanner is evaluated in simulation and field experimentation using a non-holonomic Ackerman steering-based mobile robot. Results from simulation and field experimentation indicate that OpenPlanner can generate global and local paths dynamically, navigate smoothly through a highly dynamic environments and operate reliably in real time. OpenPlanner has been implemented in the Autoware open source autonomous driving framework’s Robot Operating System (ROS).

    DOI: 10.20965/jrm.2017.p0668

    Web of Science

    Scopus

    CiNii Article

  41. Robust and accurate monocular vision-based localization in outdoor environments of real-world robot challenge

    Adi Sujiwo, Eijiro Takeuchi, Luis Yoichi Morales, Naoki Akai, Hatem Darweesh, Yoshiki Ninomiya, Masato Edahiro

    Journal of Robotics and Mechatronics   Vol. 29 ( 4 ) page: 685 - 696   2017.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:FUJI TECHNOLOGY PRESS LTD  

    © 2017, Fuji Technology Press. All rights reserved. This paper describes our approach to perform robust monocular camera metric localization in the dynamic environments of Tsukuba Challenge 2016. We address two issues related to vision-based navigation. First, we improved the coverage by building a custom vocabulary out of the scene and improving upon place recognition routine which is key for global localization. Second, we established possibility of lifelong localization by using previous year’s map. Experimental results show that localization coverage was higher than 90% for six different data sets taken in different years, while localization average errors were under 0.2 m. Finally, the average of coverage for data sets tested with maps taken in different years was of 75%.

    DOI: 10.20965/jrm.2017.p0685

    Web of Science

    Scopus

    CiNii Article

  42. Proactive driving modeling in blind intersections based on expert driver data

    Yoichi Morales, Yuki Yoshihara, Naoki Akai, Eijiro Takeuchi, Yoshiki Ninomiya

    IEEE Intelligent Vehicles Symposium, Proceedings     page: 901 - 907   2017.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2017 IEEE. This paper presents a model for velocity control in blind corners and intersections based on expert driver data. Accurate expert driver data was collected with a car equipped with a 3D LiDAR and high definition maps. A model based on human expert driver data is used to control the velocity of the ego-vehicle when facing blind intersections. The model regulates ego-vehicle velocity based on the visibility of the road at the blind intersection. As the vehicle approximates the intersection and crossing roads are not visible, the vehicle slows down, then as the roads become visible the vehicle accelerates. Experimental results show the performance of the velocity model compared towards 270 trajectories taken from 7 expert drivers towards 6 different intersections without mandatory stops.

    DOI: 10.1109/IVS.2017.7995830

    Web of Science

    Scopus

  43. Robust localization using 3D NDT scan matching with experimentally determined uncertainty and road marker matching

    Naoki Akai, Luis Yoichi Morales, Eijiro Takeuchi, Yuki Yoshihara, Yoshiki Ninomiya

    IEEE Intelligent Vehicles Symposium, Proceedings     page: 1356 - 1363   2017.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2017 IEEE. In this paper, we present a localization approach that is based on a point-cloud matching method (normal distribution transform 'NDT') and road-marker matching based on the light detection and ranging intensity. Point-cloud map-based localization methods enable autonomous vehicles to accurately estimate their own positions. However, accurate localization and 'matching error' estimations cannot be performed when the appearance of the environment changes, and this is common in rural environments. To cope with these inaccuracies, in this work, we propose to estimate the error of NDT scan matching beforehand (off-line). Then, as the vehicle navigates in the environment, the appropriate uncertainty is assigned to the scan matching. 3D NDT scan matching utilizes the uncertainty information that is estimated off-line, and is combined with a road-marker matching approach using a particle-filtering algorithm. As a result, accurate localization can be performed in areas in which 3D NDT failed. In addition, the uncertainty of the localization is reduced. Experimental results show the performance of the proposed method.

    DOI: 10.1109/IVS.2017.7995900

    Web of Science

    Scopus

  44. 3D Magnetic Field Mapping in Large-Scale Indoor Environment Using Measurement Robot and Gaussian Processes

    Akai Naoki, Ozaki Koichi

    2017 INTERNATIONAL CONFERENCE ON INDOOR POSITIONING AND INDOOR NAVIGATION (IPIN)     2017

     More details

  45. Autonomous Predictive Driving for Blind Intersections

    Yoshihara Yuki, Morales Yoichi, Akai Naoki, Takeuchi Eijiro, Ninomiya Yoshiki

    2017 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)     page: 3452 - 3459   2017

     More details

  46. Autonomous Driving Based on Accurate Localization Using Multilayer LiDAR and Dead Reckoning

    Akai Naoki, Morales Luis Yoichi, Yamaguchi Takuma, Takeuchi Eijiro, Yoshihara Yuki, Okuda Hiroyuki, Suzuki Tatsuya, Ninomiya Yoshiki

    2017 IEEE 20TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)     2017

     More details

  47. Localization Based on Multiple Visual-Metric Maps

    Sujiwo Adi, Takeuchi Eijiro, Morales Luis Yoichi, Akai Naoki, Ninomiya Yoshiki, Edahiro Masato

    2017 IEEE INTERNATIONAL CONFERENCE ON MULTISENSOR FUSION AND INTEGRATION FOR INTELLIGENT SYSTEMS (MFI)     page: 212 - 219   2017

     More details

  48. Robust Localization Using 3D NDT Scan Matching with Experimentally Determined Uncertainty and Road Marker Matching

    Akai Naoki, Morales Luis Yoichi, Takeuchi Eijiro, Yoshihara Yuki, Ninomiya Yoshiki

    2017 28TH IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV 2017)     page: 1356 - 1363   2017

     More details

  49. Proactive Driving Modeling in Blind Intersections based on Expert Driver Data

    Morales Yoichi, Yoshihara Yuki, Akai Naoki, Takeuchi Eijiro, Ninomiya Yoshiki

    2017 28TH IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV 2017)     page: 901 - 907   2017

     More details

  50. Pure pursuit revisited: Field testing of autonomous vehicles in urban areas

    Hiroki Ohta, Naoki Akai, Eijiro Takeuchi, Shinpei Kato, Masato Edahiro

    Proceedings - 4th IEEE International Conference on Cyber-Physical Systems, Networks, and Applications, CPSNA 2016     page: 7 - 12   2016.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2016 IEEE. In this paper, we aim to explore path following. We implement a path following component by referring to the existing Pure Pursuit algorithm. Using the simulation and field operational test, we identified the problem in the path following component. The main problems identified were with respect to vehicles meandering off the path, turning a corner, and the instability of steering control. Therefore, we apply some modifications to the Pure Pursuit[1] algorithm. We have also conducted the simulation and field operational tests again to evaluate these modifications.

    DOI: 10.1109/CPSNA.2016.10

    Web of Science

    Scopus

  51. Development of Autonomous Mobile Robot that Can Navigate in Rainy Situations

    Akai Naoki, Kakigi Yasunari, Yoneyama Shogo, Ozaki Koichi

    JOURNAL OF ROBOTICS AND MECHATRONICS   Vol. 28 ( 4 ) page: 441 - 450   2016.8

     More details

  52. Development of autonomous mobile robot that can navigate in rainy situations

    Naoki Akai, Yasunari Kakigi, Shogo Yoneyama, Koichi Ozaki

    Journal of Robotics and Mechatronics   Vol. 28 ( 4 ) page: 441 - 450   2016.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:FUJI TECHNOLOGY PRESS LTD  

    © 2016, Journal of Robotics and Mechatronics. All rights reserved. The Real World Robot Challenge (RWRC), a technical challenge for mobile outdoor robots, has robots automatically navigate a predetermined path over 1 km with the objective of detecting specific persons. RWRC 2015 was conducted in the rain and every robot could not complete the mission. This was because sensors on the robots detected raindrops and the robots then generated unexpected behavior, indicating the need to study the influence of rain on mobile navigation systems – a study clearly not yet sufficient. We begin by describing our robot’s waterproofing function, followed by investigating the influence of rain on the external sensors commonly used in mobile robot navigation and discuss how the robot navigates autonomous in the rain. We conducted navigation experiments in artificial and actual rainy environments and those results showed that the robot navigates stably in the rain.

    DOI: 10.20965/jrm.2016.p0441

    Web of Science

    Scopus

    CiNii Article

  53. A navigation method based on topological magnetic and geometric maps for outdoor mobile robots

    Naoki Akai, Koichi Ozaki

    2015 IEEE/SICE International Symposium on System Integration, SII 2015     page: 352 - 357   2016.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2015 IEEE. This paper proposes a novel navigation method based on topological magnetic and geometric maps for outdoor mobile robots. In this method, a state of a robot is represented by a travel distance and a lateral error, which is a distance from the travel path to the robot. In order to estimate the travel distance, a magnetic map which represents a magnetic field of the travel path is used. Since the magnetic field does not depend on moving objects, the travel distance can be robustly estimated against changes in geometric situations. However, deviating from the travel path is a fatal problem since the magnetic map does not record other magnetic fields of the travel path. To compensate this deviation, the lateral error is estimated by using geometric landmarks. Since this estimation is performed after the travel distance estimate, the lateral error can be stably estimated even if many moving objects surround the robot. As a result, the robot exactly navigates the travel path. Simulation and actual experiments are conducted to show the effectiveness and performance of the proposed method.

    DOI: 10.1109/SII.2015.7404945

    Web of Science

    Scopus

  54. Gaussian processes for magnetic map-based localization in large-scale indoor environments

    Naoki Akai, Koichi Ozaki

    IEEE International Conference on Intelligent Robots and Systems   Vol. 2015-December   page: 4459 - 4464   2015.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2015 IEEE. The magnetic field that exists in an indoor environment includes rich magnetic fluctuations because buildings contain many magnetized materials (e.g., steel frames). These fluctuations can be used as landmarks, the use of which requires the creation of a magnetic map representing the distribution of the magnetic field. It is, however, difficult to build a large-scale magnetic map because of the narrow measurement range of a magnetic sensor. This paper proposes an efficient method for collecting magnetic data using a mobile robot and a method for building a magnetic map using Gaussian processes. The use of these methods make it possible to build a large-scale magnetic map efficiently. Moreover, this paper presents a particle filter-based localization method based on the magnetic map. The presented system enables a robot to identify its own position in large-scale buildings. Experiments are used to demonstrate the performance and usefulness of the presented system.

    DOI: 10.1109/IROS.2015.7354010

    Web of Science

    Scopus

  55. Color Extraction Using Multiple Photographs taken with Different Exposure Time in RWRC

    Kenji Yamauchi, Naoki Akai, Koichi Ozaki

    Journal of Robotics and Mechatronics   Vol. 27 ( 4 ) page: 365 - 373   2015

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:FUJI TECHNOLOGY PRESS LTD  

    Copyright 2015, Fuji Technology Press , All Rights Reserved. Extracting the color of a target object from images in environments with different illumination conditions, such as outdoors, is difficult because color performance changes easily. The novel color extraction we propose enables the exact color of a target object to be extracted using multiple photographs taken with different exposure times. The object’s color performance transits due to changes in exposure time. This transition is the same as when environmental light sources do not change significantly. In outdoor environment, most situations are regarded as that situation. We first indicate this in an experimental analysis, then detail our proposal. Our method evaluates transition and realizes precise color extraction of target objects in outdoors. We apply this method to an orange cap in the Tsukuba Real-World Robot Challenge. Through experiments, we show that the cap is detected accurately in different environments and discuss the method’s effectiveness and usefulness in the real world.

    DOI: 10.20965/jrm.2015.p0365

    Web of Science

    Scopus

  56. Development of Mobile Robot “SARA” that Completed Mission in Real World Robot Challenge 2014

    Naoki Akai, Kenji Yamauchi, Kazumichi Inoue, Yasunari Kakigi, Yuki Abe, Koichi Ozaki

    Journal of Robotics and Mechatronics   Vol. 27 ( 4 ) page: 327 - 336   2015

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:FUJI TECHNOLOGY PRESS LTD  

    Copyright 2015, Fuji Technology Press , All Rights Reserved. Held in Japan every year since 2007, the Real World Robot Challenge (RWRC) is a technical challenge for mobile robots. Every robot is given the missions of traveling a long distance and finding specific persons autonomously. The robots must also have an affinity for people and be remotely monitored. In order to complete the missions, we developed a new mobile robot, SARA, which we entered in RWRC 2014. The robot successfully completed all of the missions of the challenge. In this paper, the systems we implemented are detailed. Moreover, results of experiments and of the challenge are presented, and knowledges we gained through the experience are discussed.

    DOI: 10.20965/jrm.2015.p0327

    Web of Science

    Scopus

  57. Development of magnetic navigation method based on distributed control system using magnetic and geometric landmarks

    Naoki Akai, Sam Ann Rahok, Kazumichi Inoue, Koichi Ozaki

    Intensive Care Medicine   Vol. 1 ( 1 ) page: 1 - 11   2014.11

     More details

    Publishing type:Research paper (scientific journal)  

    © 2014, Akai et al.; licensee Springer. Background: In order for a robot to autonomously run in outdoor environments, a robust and stable navigation method is necessary. Especially, to run in real-world environments, robustness against moving objects is important since many pedestrians and bicycles come and go. Magnetic field, which is not influenced by the moving objects, is considered to be an effective information for autonomous navigation.Methods: Localization technique using a magnetic map, which records ambient magnetic field, has been proposed. The magnetic map is expressed as a linear map. When using this linear magnetic map, swerving from the desired path is a fatal problem. It is because that the magnetic map contains only magnetic data on a desired path. In the paper, we propose a novel navigation method which allows a robot to precisely navigate on a desired path even if localization is performed on the basis of the linear magnetic map. The navigation is performed by using a control method based on a DCS (Distributed Control System). In the system, several navigation modules are executed in parallel, and they independently control the robot by using magnetic and geometric landmarks.Results and discussion: We conducted three navigation experiments. Our robot could perfectly accomplish all navigation even if it was disturbed by many moving objects during the navigation.Conclusions: The control method based on the DCS could switch the navigation module for controlling the robot to cope against the change of its surroundings. The precise and robust navigation was achieved with the proposed method.

    DOI: 10.1186/s40648-014-0021-8

    Scopus

  58. The realization and evaluation of the reins' control method

    Qingsong Han, Naoki Akai, Kazumichi Inoue, Koichi Ozaki

    Proceedings of the 2014 9th IEEE Conference on Industrial Electronics and Applications, ICIEA 2014     page: 621 - 623   2014.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2014 IEEE. Realizing robots' controlling in controlling way of saving dof has a broad prospect and applied space using control technology. The paper discussed controlling horses using reins as inspiration, realizing the operation of mobile equipment of reins' control. The experiment confirmed the feasibility of operation by the first stage; Comparing the operating system of reins with the operating system of games' handle that people are very familiar by the experimental research of the second stage, getting the conclusion that the operating of reins is equivalent to handles' operation, and the evaluations of the implementation is better than the handles'. The test results show that the control system is very accordant for intuitive feelings of the user of mobile devices' control demand, and can skillfully master the main point of the operation in a very short time. The results of studying provide a useful way of thinking for the development and evaluation of the personal mobile way.

    DOI: 10.1109/ICIEA.2014.6931238

    Web of Science

    Scopus

  59. Autonomous mobile robot MAUV – mission achievement on Tsukuba challenge 2011, 12 and 13

    Naoki Akai, Kazumichi Inoue, Sam Ann Rahok, Masatoshi Shinohara, Koichi Ozaki

    Journal of Robotics and Mechatronics   Vol. 26 ( 5 ) page: 657 - 658   2014.10

     More details

    Publishing type:Research paper (scientific journal)  

    © 2014, Fuji Technology Press. All rights reserved. We developed MAUV, an autonomous mobile robot that has navigation using two types of landmarks; ambient magnetic and geometric. This enables the robot to localize robustly in actual outdoor environments. The robot achieved missions in Tsukuba Challenge 2011, 12, and 13.

    DOI: 10.20965/jrm.2014.p0657

    Scopus

  60. Development of a personal mobility robot “NENA”

    Kazumichi Inoue, Naoki Akai, Koichi Ozaki

    Journal of Robotics and Mechatronics   Vol. 26 ( 5 )   2014.10

     More details

    Publishing type:Research paper (scientific journal)  

    © 2014, Fuji Technology Press. All rights reserved. A mobility robot “NENA” which can carry one person was developed by Utsunomiya University. The robot was developed based on the concept called “Design Framework” and it allowed the robot to equip with functions needed for manual driving and autonomous running and acceptable design for people. The robot fulfilled safety required for mobility robots used in the Tsukuba Mobility Robot Experimental Zone.

    DOI: 10.20965/jrm.2014.p0659

    Scopus

  61. Autonomous navigation based on magnetic and geometric landmarks on environmental structure in real world

    Naoki Akai, Kazumichi Inoue, Koichi Ozaki

    Journal of Robotics and Mechatronics   Vol. 26 ( 2 ) page: 158 - 165   2014.4

     More details

    Publishing type:Research paper (scientific journal)  

    For the Real World Robot Challenge (RWRC) 2013, a new task was established: every robot was required to search for designated persons. In this paper, therefore, we consider the difficulty of the task and construct a navigation strategy to achieve the task. To navigate a robot on the basis of the strategy, long distance navigation is necessary. We have developed a unique navigation method based on magnetic and geometric landmarks on environmental structures in various locations. This method allows a robot to robustly localize by evaluating the reliability of magnetic and geometric landmarks. By using this method, a robot can navigate stably, even if there are no existing landmarks to serve as objects. We achieved autonomous navigation over long distances and successfully searched out designated persons as the challenge of the RWRC2013. This paper presents our navigation method and discusses long distance navigation using the method.

    DOI: 10.20965/jrm.2014.p0158

    Scopus

  62. Person detection method based on color layout in real world robot challenge 2013

    Kenji Yamauchi, Naoki Akai, Ryutaro Unai, Kazumichi Inoue, Koichi Ozaki

    Journal of Robotics and Mechatronics   Vol. 26 ( 2 ) page: 151 - 157   2014.4

     More details

    Publishing type:Research paper (scientific journal)  

    In Real World Robot Challenge 2013, a mission was added that had robots search for a person wearing clothes featuring unique colors. We focus on the layout of such clothes with the aim of detecting persons wearing them by applying color extraction. Color extraction is improved by preprocessing of a clipping image from the robot's vision and possibly extracting colors worn by target persons stably in natural light. Persons are detected by simply evaluating the layout of target colors. Our robots were equipped with person detection for this challenge and have detected all targeted persons. This paper describes considerations about person detection performance based on pre- and postchallenge results.

    DOI: 10.20965/jrm.2014.p0151

    Scopus

  63. Precise color extraction method based on color transition due to change in exposure time

    Kenji Yamauchi, Naoki Akai, Koichi Ozaki

    2014 IEEE/SICE International Symposium on System Integration, SII 2014     page: 275 - 280   2014.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    © 2014 IEEE. This paper proposes a novel color extraction method using multiple images taken with different exposure time. Although using the multiple images is a famous technique to recover a high dynamic range radiance map, we do not use it. Alternatively, we focus on that any color performance is uniformly transited by changing exposure time even if under various illumination conditions. In this paper, we indicate it experimentally and develop a color extraction method with this characteristic. In the experiment, we set orange color as desired color and conducted color extraction to orange, red, and yellow colors in outdoor environments. Our proposed method exactly extracted only orange color from images under extreme exposure conditions.

    DOI: 10.1109/SII.2014.7028050

    Web of Science

    Scopus

  64. Monte Carlo localization using magnetic sensor and lidar for real world navigation

    Naoki Akai, Satoshi Hoshino, Kazumichi Inoue, Koichi Ozaki

    2013 IEEE/SICE International Symposium on System Integration, SII 2013     page: 682 - 687   2013

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    For realizing more stable outdoor navigation for mobile robots, this paper proposes a localization method using a magnetic sensor and a Light Detection and Ranging (LIDAR). In the proposed method, Monte Carlo Localization (MCL) using the LIDAR and a determination method of a heading direction using the ambient magnetic field are combined. In other words, the proposal distribution becomes dense at the true state of the robot by using the ambient magnetic field. The determination method is based on the advantage of the magnetic navigation proposed by us. By the proposed method, the robot enabled to navigate with accuracy in the outdoor environment, since the robust localization is realized. The effectiveness of the proposed method is shown through experiments. Moreover, two robots implemented the proposed method achieved the task of Real World Robot Challenge 2012. This means that the proposed method is effective for real world navigation. © 2013 IEEE.

    DOI: 10.1109/sii.2013.6776657

    Web of Science

    Scopus

▼display all

MISC 50

  1. GPS×カメラ×地図 初歩の自己位置推定 第2部 初めての自己位置推定ロボティクス 第6章 自己位置推定ツール 6)3D点群とモデルで推定!粒子フィルタ

    赤井直紀

    トランジスタ技術   Vol. 56 ( 10 )   2020

     More details

    Authorship:Lead author, Corresponding author   Language:English  

    J-GLOBAL

  2. Detection of Misalignment Using Markov Random Field with Fully Connected Latent Variables in LiDAR-Based Localization

    赤井直紀, 平山高嗣, 村瀬洋

    日本機械学会ロボティクス・メカトロニクス講演会講演論文集(CD-ROM)   Vol. 2020 ( 0 ) page: 2P1 - K14   2020

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    <p>This paper presents a misalignment recognition method using a Markov random field with fully connected latent variables for LiDAR-based localization. The major difficulty for the misalignment recognition is that considering entire relation of sensor measurement in localization is impossible because it must be assumed that the sensor measurement is independent to one another. The presented method enables to consider the entire relation via the fully connected latent variables. This paper also presents a calculation method of localization failure probability based on the misalignment recognition. Experiments show that the presented method can exactly detect misalignment even though partial sensor measurement overlaps with a map and can exactly recognize success and failure localization results.</p>

    DOI: 10.1299/jsmermd.2020.2P1-K14

    CiNii Article

    J-GLOBAL

  3. GPS×カメラ×地図 初歩の自己位置推定 第2部 初めての自己位置推定ロボティクス 第7章 自己位置推定ツール 7)推定結果の信頼度を数値化!ニューラル・ネットワーク

    赤井直紀

    トランジスタ技術   Vol. 56 ( 10 )   2020

     More details

    Language:Japanese  

    J-GLOBAL

  4. 確率的自己位置推定法における機械学習の併用

    赤井直紀, 平山高嗣, 村瀬洋

    日本ロボット学会学術講演会予稿集(CD-ROM)   Vol. 37th   2019

     More details

  5. Driving Behavior Modeling Using Autoregressive Input-Output Hidden Markov Models

    AKAI Naoki, HIRAYAMA Takatsugu, MORALES Luis Yoichi, AKAGI Yasuhiro, LIU Hailong, MURASE Hiroshi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2019 ( 0 ) page: 2A1 - E05   2019

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    <p>This paper presents a driving behavior modeling method using autoregressive input-output hidden Markov models (AIOHMMs). First, model parameter learning and discrimination ways using the AIOHMMs are detailed. In experiments, we model four driving maneuvers with driver's eye-gaze and ego-vehicle localization information and compare maneuver discrimination performances by four types of HMMs. Additionally, we discuss modeling performance by the AIOHMMs through the experiments.</p>

    DOI: 10.1299/jsmermd.2019.2A1-E05

    CiNii Article

    J-GLOBAL

  6. 視対象との3次元位置関係に着目した電動車いす運転者の視行動分析

    前川大和, 赤井直紀, 平山高嗣, MORALES Luis Yoichi, 出口大輔, 川西康友, 井手一郎, 村瀬洋

    電気・電子・情報関係学会東海支部連合大会講演論文集(CD-ROM)   Vol. 2019   2019

     More details

  7. 電動車いす運転の習熟に伴う視行動変化の分析

    前川大和, 赤井直紀, MORALES Luis Yoichi, 平山高嗣, 出口大輔, 川西康友, 井手一郎, 村瀬洋

    電子情報通信学会大会講演論文集(CD-ROM)   Vol. 2019   2019

     More details

  8. 観測物体のクラスを考慮した自己位置推定

    赤井直紀, MORALES Luis Yoichi, 平山高嗣, 村瀬洋

    ロボティクスシンポジア予稿集   Vol. 24th   2019

     More details

  9. Reliability Estimation for Self-Vehicle Pose Recognition Result Using LiDAR

    Akai Naoki, Morales Luis Yoichi, Hirayama Takatsugu, Murase Hiroshi

    Transactions of Society of Automotive Engineers of Japan   Vol. 50 ( 2 ) page: 609 - 615   2019

     More details

    Language:Japanese   Publisher:Society of Automotive Engineers of Japan  

    This paper presents a reliability estimation method of localization results. In the method, an egovehicle pose and reliability are treated as hidden variables and are estimated simultaneously via Rao- Blackwellized particle filter (RBPF). The ego-vehicle pose is estimated by a sampling-based method, i.e., particle filter, and the reliability is estimated by an analytical method using prediction results of convolutional neural network (CNN). The CNN learns whether localization has failed or not and its output is used as an observable variable to estimate the reliability in the RBPF. Through experiments, it is shown that the estimated reliability could be used as an exact criterion for describing successful and fault localization results.

    DOI: 10.11351/jsaeronbun.50.609

    CiNii Article

    CiNii Books

  10. Localization Considering Known and Unknown Classes of Observed Objects on a Geometric Map

    赤井直紀, モラレスルイス 洋一, 平山高嗣, 村瀬洋

    計測自動制御学会論文集   Vol. 55 ( 11 ) page: 745 - 753   2019

     More details

    Language:Japanese   Publisher:The Society of Instrument and Control Engineers  

    <p>This paper presents a localization approach that simultaneously estimates a robot's pose and class of sensor observations, where "class" categorizes the sensor observations as those obtained from known and unknown objects on a given geometric map. The proposed approach is implemented using Rao-Blackwellized particle filtering algorithm. The robot's pose can be robustly estimated utilizing sensor observations obtained from the only known objects by the simultaneous estimation. The proposed approach is efficient in terms of computational complexity because its complexity is same as that of the likelihood field model. Performance of the proposed approach was shown through experiments using a 2D LiDAR simulator.</p>

    DOI: 10.9746/sicetr.55.745

    CiNii Article

    CiNii Books

    J-GLOBAL

  11. 完全自動運転実現のための信頼度付き自己位置推定の提案

    赤井直紀, 平山高嗣, 村瀬洋

    計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)   Vol. 2019   2019

     More details

  12. Driving Intelligence for Automated Vehicles and Future Perspective

    Journal of the Japanese Society for Artificial Intelligence   Vol. 34 ( 2 ) page: 206 - 214   2019

     More details

    Language:Japanese   Publisher:The Japanese Society for Artificial Intelligence  

    DOI: 10.11517/jjsai.34.2_206

    CiNii Article

    CiNii Books

    J-GLOBAL

    Other Link: http://id.nii.ac.jp/1004/00009675/

  13. 整合性の取れた地図を要しない移動ロボットのためのティーチングプレイバックナビゲーション

    赤井直紀, モラレスルイス洋一, 平山高嗣, 村瀬洋

    日本ロボット学会学術講演会予稿集(CD-ROM)   Vol. 36th   2018

     More details

  14. 自車両位置認識結果の信頼度推定

    赤井直紀, MORALES Luis Yoichi, 平山高嗣, 村瀬洋

    自動車技術会大会学術講演会講演予稿集(CD-ROM)   Vol. 2018   2018

     More details

  15. Simultaneous Localization and Its Reliability Estimation using CNN and RBPF

    AKAI Naoki, MORALES Luis Yoichi, MURASE Hiroshi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2018 ( 0 ) page: 1A1 - J01   2018

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    <p>This paper presents a novel localization approach that simultaneously estimates a robot's pose and reliability of its estimation. To estimate the reliability, a convolutional neural network (CNN) is used as a decision maker for distinguishing whether localization has failed. The CNN, however, sometimes makes wrong decisions. To reduce influence of the wrong decisions, Rao-Blackwellized particle filter (RBPF) is employed. The reliability can be robustly estimated using the RBPF and it exactly describes successful and failure localization results. Exact performance of the reliability is shown through the experiments.</p>

    DOI: 10.1299/jsmermd.2018.1A1-J01

    CiNii Article

    J-GLOBAL

  16. High-Accurate Localization INS and Using Multilayer LiDAR for Autonomous Cars

    Akai Naoki, Takeuchi Eijiro, Yamaguchi Takuma, Morales Luis Yoichi, Yoshihara Yuki, Okuda Hiroyuki, Suzuki Tatsuya, Ninomiya Yoshiki

    Transactions of Society of Automotive Engineers of Japan   Vol. 49 ( 3 ) page: 675 - 681   2018

     More details

    Language:Japanese   Publisher:Society of Automotive Engineers of Japan  

    This paper presents a high-accuracy localization method for autonomous cars. In the method, we use inertial navigation system (INS) and a multilayer light detection and ranging. Three-dimensional normal distributions transform scan matching is employed and its estimation result is fused with the result from INS on the basis of a Kalman filtering algorithm. To determine uncertainty of the scan matching result, we utilize Hessian of the cost function. The localization method robustly estimates smooth and accurate vehicle trajectory. We conducted autonomous driving demonstrations with the method in public roads and these results are used to show the performance.

    DOI: 10.11351/jsaeronbun.49.675

    CiNii Article

    CiNii Books

  17. 死角からの飛び出しリスクと自動運転経路計画の統合

    吉原佑器, MORALES SAIKI Luis Y., 赤井直紀, 竹内栄二朗, 二宮芳樹

    自動車技術会大会学術講演会講演予稿集(CD-ROM)   Vol. 2017   2017

     More details

  18. 自動運転におけるLiDARベースの位置推定手法の課題と動向

    赤井直紀

    月刊車載テクノロジー   Vol. 5 ( 2 ) page: 56 - 61   2017

     More details

    Language:Japanese   Publisher:技術情報協会  

    CiNii Article

    J-GLOBAL

  19. Field Testing of Self-Driving Vehicles: Lessons Learned on Localization

    橘川雄樹, 加藤真平, 赤井直紀, 竹内栄二朗, 枝廣正人

    IATSS Review (International Association of Traffic and Safety Sciences)   Vol. 42 ( 2 ) page: 130 - 135   2017

     More details

  20. INSとマルチレイヤーLIDARを用いた高精度自己位置推定に基づく一般公道での自動運転

    赤井直紀, 竹内栄二朗, 山口拓真, MORALES Luis Yoichi, 吉原佑器, 奥田裕之, 鈴木達也, 二宮芳樹

    自動車技術会大会学術講演会講演予稿集(CD-ROM)   Vol. 2017   2017

     More details

  21. 死角によって生じる危険度コスト関数の検討

    吉原佑器, 竹内栄二朗, 赤井直紀, 二宮芳樹

    自動車技術会大会学術講演会講演予稿集(CD-ROM)   Vol. 2016   2016

     More details

  22. Color Extracition Using Hue and Saturation Transitions Obtained From Multiple Exposure Images:-Verification of Specific Color Clothes Recognision in Tsukuba Challenge-

    HIJIKATA Masaaki, AKAI Naoki, KAKIGI Yasunari, OZAKI Kouichi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2016 ( 0 ) page: 2A1 - 19b2   2016

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    <p>Extracting predetermined colors under various illumination conditions like outdoor is difficult. To overcome the problem, we focused on color transition which is obtained by changing camera's exposure and proposed a color extraction method using it. Although this method improves color extraction accuracy from simple color extraction methods which uses a color space such as xy chromaticity diagram or HSV color space, some problems still exist. The objective of this study is to extend this method and evaluate its performance. To extend this method, we propose a new color extraction method using two color transitions, hue and saturation transitions. This performance is evaluated by applying it to a task of the Tsukuba Challenge that is to a find person who wears specific color clothes.</p>

    DOI: 10.1299/jsmermd.2016.2A1-19b2

    CiNii Article

    J-GLOBAL

  23. A Loop-Closure Detection Method Based on Localization Using Residual Magnetism

    Akai Naoki, Ozaki Koichi

    Journal of the Robotics Society of Japan   Vol. 34 ( 6 ) page: 397 - 403   2016

     More details

    Language:Japanese   Publisher:The Robotics Society of Japan  

    This paper proposes a novel loop-closure detection method based on localization using residual magnetism. Although the method uses only a magnetic sensor as external sensor, accurate loop-closure detection can be performed. This is because that precisely distinguishing of magnetic pattern is realized by using normalized cross-correlation. In addition, the method has usefulness that loop-closure detection is executed so fast. The effectiveness and usefulness of the method are shown through experiments.

    DOI: 10.7210/jrsj.34.397

    CiNii Article

    CiNii Books

    J-GLOBAL

  24. Development of Autonomous Mobile Robot that is Capable of Navigation Using LIDAR in Rainy Situations

    KAKIGI Yasunari, AKAI Naoki, YONEYAMA Shogo, OZAKI Koichi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2016 ( 0 ) page: 1A1 - 07b4   2016

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    <p>A LIDAR is commonly used for autonomous mobile navigation. It detects raindrops under rainy situations since its output laser beams collide the drops. This influences against performance of the navigation, for example obstacle avoidance. In this study, we first investigate influence of rain against the LIDAR and then propose a coping method, which contains two ways, for reducing the rain's influence. The first way is a hardware-based coping method that is to add additional waterproof parts. The second way is a software-based coping method that is to remove raindrops from the LIDAR readings like a filtering algorithm. By using these methods, number of raindrop detection is significantly reduced. As a result, autonomous navigation can be performed in rainy situations and its performance is verified in a man-made environment.</p>

    DOI: 10.1299/jsmermd.2016.1A1-07b4

    CiNii Article

    J-GLOBAL

  25. つくばチャレンジ2016における名古屋大学の取組

    赤井直紀, DARWEESH Hatem, 太田裕貴, SUJIWO Adi, 橘川雄樹, 安藤智仁, 山田献二朗, MORALES Luis Yoichi, 竹内栄二朗, 二宮芳樹, 冨沢哲雄, 加藤真平

    計測自動制御学会システムインテグレーション部門講演会(CD-ROM)   Vol. 17th   2016

     More details

  26. 先読み運転支援を可能にするための自車両位置推定

    赤井直紀, 竹内栄二朗, SUJIWO Adi, 吉原佑器, MORALES Luis Yoichi, 二宮芳樹

    自動車技術会大会学術講演会講演予稿集(CD-ROM)   Vol. 2016   2016

     More details

  27. 先読み運転支援を可能にするための空間認識

    竹内栄二朗, 吉原佑器, 赤井直紀, MORALES SAIKI Luis Yoichi, 二宮芳樹

    自動車技術会大会学術講演会講演予稿集(CD-ROM)   Vol. 2016   2016

     More details

  28. 先読み運転支援を可能にするための危険評価

    吉原佑器, MORALES Luis Y., 赤井直紀, 竹内栄二朗, 二宮芳樹

    自動車技術会大会学術講演会講演予稿集(CD-ROM)   Vol. 2016   2016

     More details

  29. 2A2-M05 Trajectory Estimation of Mobile Robot Using Magnetic Field and Environmental Map Building

    AKAI Naoki, OZAKI Koichi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2015 ( 0 ) page: _2A2 - M05_1-_2A2-M05_4   2015

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    A SLAM (Simultaneous Localization and Mapping) problem is major in mobile robotics field about past two decades. In order to solve the problem, a camera and a LIDAR (Light Detection and Ranging) are generally used. In contrast, this paper proposes a new solution for the problem using a magnetic sensor. Our method is simple since an observation model in RBPF (Rao-Blackwellized Particle Filter)-SLAM is replaced by that of a magnetic sensor. However, magnetic sensor-based SLAM has a problem that is so narrow measurement range of the sensor. To deal with the problem, we use a heuristic method to determine surround magnetic field. We conducted experiments in actual outdoor environments including loops and verified its accuracy by using a LIDAR. Through the experiments, it was shwon that our method can close loops and build consistent maps; magnetic and geometric.

    DOI: 10.1299/jsmermd.2015._2A2-M05_1

    CiNii Article

    J-GLOBAL

  30. 色・勾配情報に基づく茎画素検出とエネルギー最小化に基づく茎認識

    熊谷秀樹, 赤井直紀, 尾崎功一

    日本ロボット学会学術講演会予稿集(CD-ROM)   Vol. 33rd   2015

     More details

  31. 磁場の実験的解析と自律移動法への応用

    赤井直紀, 尾崎功一

    日本ロボット学会学術講演会予稿集(CD-ROM)   Vol. 33rd   2015

     More details

  32. 異なる露光時間で撮影された画像を用いた照度変化にロバストな色抽出つくばチャレンジ2015における色抽出に基づく探索対象の検出

    土方優明, 赤井直紀, 尾崎功一

    計測自動制御学会システムインテグレーション部門講演会(CD-ROM)   Vol. 16th   2015

     More details

  33. Development of Mobile Robot to Accomplish Task in Actual Environments

    赤井直紀, 山内健司, 井上一道, 宇内隆太郎, 山本条太郎, 尾崎功一

    計測自動制御学会論文集   Vol. 51 ( 1 ) page: 24 - 31   2015

     More details

    Language:Japanese   Publisher:The Society of Instrument and Control Engineers  

    In Tsukuba Challenge 2013, every robot had to navigate on a given path and detect specific persons wearing showy color clothes. There are many ideal functions for achieving the mission. It is, however, difficult to implement all ideal functions since complex algorithms are required. This paper, therefore, considers simplified functions for achieving the mission even if complex algorithms are not implemented. Our robot can run long distance by using a unique localization method which uses both of magnetic and geometric landmarks. Moreover, it can detect the target based on a color extraction method. These abilities enable the robot to exactly work the simple functions. Through the experiments, it is shown that our robot can exactly achieve the given mission by using only the simplified functions.

    DOI: 10.9746/sicetr.51.24

    CiNii Article

    CiNii Books

    J-GLOBAL

  34. 1P1-V08 Sensor Layout Determination based on Simulation of Stress and Distortion Distributions for Developing Whole Haptic Armor

    KAKIGI Yasunari, AKAI Naoki, INOUE Kazumichi, OZAKI Kouichi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2015 ( 0 ) page: _1P1 - V08_1-_1P1-V08_3   2015

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    This report describes development of a mobile robot's armor which is enable to detect pushing or touching with any objects on its surface. In order to achieve the purpose, it is necessary to design suitable layout of strain gauges as haptic sensors on the armor when changing surface of the armor such as widely bends or distortion with pushing. The armor should be shapely, and it is to be desired that number of haptic sensors is reduced. Therefore, it is required to detect efficiently changing on the surface by haptic sensors in even small number. In this report, it is shown that the layout by 34 sets of strain gauges as haptic sensors is designed based on analysis of stress on surface of the armor.

    DOI: 10.1299/jsmermd.2015._1P1-V08_1

    CiNii Article

    J-GLOBAL

  35. つくばチャレンジのタスク簡略化とそれに基づくナビゲーション戦略

    赤井直紀, 米山翔悟, 柿木泰成, 尾崎功一

    計測自動制御学会システムインテグレーション部門講演会(CD-ROM)   Vol. 16th   2015

     More details

  36. 環境磁場を利用した自己位置推定と観測の信頼性評価に基づくマルチナビゲータによる自律移動

    赤井直紀, 尾崎功一

    ロボティクスシンポジア予稿集   Vol. 19th   2014

     More details

  37. 1A1-Q03 Development of the bipedal robot reproduced biarticular muscle with pneumatic cylinders(Walking Robot)

    NAKAMURA Takuya, TAKAHASHI Yohei, AKAI Naoki, ABE Yuki, OZAKI Koichi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2014 ( 0 ) page: _1A1 - Q03_1-_1A1-Q03_4   2014

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    Since powerful actuators are required for legged robots in practical use, it is considered that air cylinders, which have high power weight ratio, are suitable. In the report, we design a biped robot using air cylinders as actuators. For controlling air cylinders, it is difficult to apply them for mechanism of robots, since they have not enough precise positioning. Each air cylinder is attached to two links and imitates a bi-articular muscle. By the imitation, position definition precision is increased, even if the air cylinder is used as actuators. Moreover, air cylinders have damper function, and this function can be utilized for absorbing impact from a floor. This report shows these effectiveness by some inspections.

    DOI: 10.1299/jsmermd.2014._1A1-Q03_1

    CiNii Article

    J-GLOBAL

  38. 磁場ノイズを用いた自己位置推定法の有用性検証とそれに基づく自律移動法に関する考察

    赤井直紀, 尾崎功一

    日本ロボット学会学術講演会予稿集(CD-ROM)   Vol. 32nd   2014

     More details

  39. Implementation of Magnetic Navigation Method based on Experimental Analysis of Magnetic Field

    赤井直紀, RAHOK Sam Ann, 片寄浩平, 島田遼, 井上一道, 尾崎功一

    日本ロボット学会誌   Vol. 32 ( 4 ) page: 395 - 402   2014

     More details

    Language:Japanese   Publisher:The Robotics Society of Japan  

    In practical use of automatic guided vehicles, magnetic markers are widely used. However, an approach of which pattern of magnetic intensity in usual environment is defined as landmarks is not investigated. This reason is that it is difficult to be known environmental magnetic field since magnetic intensity is invisible. This paper shows investigation of environmental magnetic field in actual environment and describes implementation of the magnetic based navigation, magnetic navigation method. As the magnetic investigation, magnetic intensity of the mounted devices in a mobile robot was measured, and condition of efficient layout of the devices was obtained. By the measurement of environmental magnetic field in mentioned condition, pattern of magnetic intensity that is suitable as a landmark is shown in this paper. The mobile robot records magnetic intensity on its travel path as magnetic map, and achieves stable navigation based on the magnetic map. In this paper, performance of the magnetic navigation method is shown by an experiment.

    DOI: 10.7210/jrsj.32.395

    CiNii Article

    CiNii Books

    J-GLOBAL

  40. 2A1-I02 Development of A Personal Mobility Robot to Collect Magnetic Data in Large-scale Environment(Demonstration experiments of personal mobility robots in Mobility Robot Special Zone of Tsukuba-city)

    Akai Naoki, MATSUDA Takuya, INOUE Kazumichi, UNAI Ryutaro, YAMAUCHI Kenji, YAMAMOTO Jotaro, OZAKI Koichi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2014 ( 0 ) page: _2A1 - I02_1-_2A1-I02_2   2014

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    Many studies on autonomous mobile robots field have been worked. However, mobile robots which work in actual environments are not developed yet. We have developed a personal mobility robot which supports persons in civil environment. The robot can also collect magnetic data during driving. It is permitted that we conduct experiments with use of the robot in Tsukuba Mobility Robot Special District. In the report, the specification of the robot is described. Moreover, the possibility is indicated that a constructed magnetic map by the robot can be shared by other robots. Finally, we discuss about the knowledge obtained by developing the robot.

    DOI: 10.1299/jsmermd.2014._2A1-I02_1

    CiNii Article

    J-GLOBAL

  41. 2P1-R07 Development of Magnetic Navigation based on Cooperative Behavior by Multiple Agents as Moving Method : Verification Experimentation of Guidance Demonstration for Persons in ROBOMEC 2013(Wheeled Robot/Tracked Vehicle (3))

    AKAI Naoki, OZAKI Koichi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2013 ( 0 ) page: _2P1 - R07_1-_2P1-R07_4   2013

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    This report describes performance of a guidance robot that leads persons in public space. The robot has a unique navigation system consisting of multiple agents as moving method. One of the moving methods is the magnetic navigation method, which was proposed by the authors, and mainly executed in the navigation system. The other methods are for supporting the magnetic navigation to induce the robot to the target path. Flexible and stable behavior is spontaneously generated by cooperation of processes of every method, which are independently executed. By the navigation system, a robot enables guidance navigation in the public space with pedestrians and bicycles. In ROBOMEC 2013, demonstration guiding participants to the venue will be planed, and it is assumed that many obstacles surrounding the robot. In this report, it is shown performance of the navigation system by experimental results that the robot accomplishes stable guiding navigation in the assumed situation.

    DOI: 10.1299/jsmermd.2013._2P1-R07_1

    CiNii Article

    J-GLOBAL

  42. Implementation of a long-distance navigation method of low cost structure that combines a localization using magnetic information and a lateral position compensation

    Naoki Akai, Rahok Sam Ann, Kazumichi Inoue, Koichi Ozaki

    Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C   Vol. 79 ( 799 ) page: 681 - 690   2013

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    We have proposed a navigation method using magnetic information that occurs in the environment. This paper proposes a improve navigation method that combines a localization using magnetic information and a lateral error compensation based on external geometric information. In our previous method, it is required to adjust parameters used for the robot navigation. This adjustment is needed excluding unreliable magnetic information. On the other hand, our proposed method enables a robot to travel long distance without adjustment parameters even if the unreliable magnetic information is included. The robot is able to identify its position with the particle filter on a topological map using magnetic information. Furthermore, the robot uses external geometric information for only compensate the lateral error. As a result, the localization accuracy is increased and is not depend on geometric information. In addition, these methods are applicable to the robot using simple algorithm, computational and memory costs are low. Through the navigation experiments, we show that the robot achieved over 2 km navigation in real world. Moreover, the proposed method is compared to other two methods. Finally, the usefulness and advantage of the proposed method are presented. © 2013 The Japan Society of Mechanical Engineers.

    DOI: 10.1299/kikaic.79.681

    Scopus

    CiNii Article

  43. Implementation of a Long-Distance Navigation Method of Low Cost Structure That Combines a Localization Using Magnetic Information and a Lateral Position Compensation

    赤井直紀, SAM ANN Rahok, 井上一道, 尾崎功一

    日本機械学会論文集 C編(Web)   Vol. 79 ( 799 )   2013

     More details

  44. 磁気および幾何情報を用いたマルチナビゲータによる自律移動ロボットのナビゲーション法の実装

    赤井直紀, 尾崎功一

    日本ロボット学会学術講演会予稿集(CD-ROM)   Vol. 31st   2013

     More details

  45. 撮影画像による三次元形状認識を用いた原子炉内調査への適用性検討

    上地優, 伊藤主税, 日野竜太郎, 赤井直紀, 尾崎功一

    日本原子力学会秋の大会予稿集(CD-ROM)   Vol. 2013   2013

     More details

  46. Development of 3D Reconstruction Technology using Captured Images-Study of Matching Method and Preliminary Examination-

    上地優, 赤井直紀, 赤井直紀, 尾崎功一, 尾崎功一, 伊藤主税

    日本原子力研究開発機構JAEA-Research(Web)   Vol. 2013 ( 2013-018 ) page: 巻頭1 - 2,1-18   2013

     More details

  47. 1P1-G07 Development of 3D-measurement technology with fiber scope images(IBARAKI Robot Technology)

    KAMIJI Yu, AKAI Naoki, OZAKI Koichi, ITO Chikara, HINO Ryutaro

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2013 ( 0 ) page: _1P1 - G07_1-_1P1-G07_2   2013

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    Preliminary examination of image processing was conducted using existing reactor inside images through a fiber scope in order to confirm applicability of 3D-mapping in a reactor as a part of development of 3D-measurement technology. The Upright SURF (Speeded Up Robust Features) was used to find corresponding points between two captured images. In case of images showing many similar textures or lack of texture, it was difficult to find corresponding points using SURF only. By coupling with a canny algorithm to detect edges of the inside structure, it was found that 3-D structure could be measured for rectilinear objects.

    DOI: 10.1299/jsmermd.2013._1P1-G07_1

    CiNii Article

    J-GLOBAL

  48. 1P1-A06 Conceptual Design of Personal Mobility and Challenge of Development for Special Zone of Experiment by Mobility Robots in Tsukuba(Demonstration experiments of personal mobility robots in Mobility Robot Special Zone of Tsukuba-city)

    MATSUDA Takuya, INOUE Kazumichi, AKAI Naoki, NAKADA Mio, OZAKI Koichi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2013 ( 0 ) page: _1P1 - A06_1-_1P1-A06_3   2013

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    In order to entry the Special zone of experiment by mobility robots, it is required to obey the inspection of District Land Transport Bureaus in development of mobility robots. This report describes a challenge of development for a personal mobility robot that makes fun to ride. The mobility robot has two front driving and one rear free wheels, and the center of rider's body is placed on upper of the rear wheel. Therefore, the rider has fun since feels like rotating its body when the robot moves on curve. Furthermore, for fun, the shape of the robot is designed to be stylish since it is considered that its looks are important. As the results of developing the robot, this report shows the basic design for the inspection, assemble the chassis by using general parts, and molding the exterior body for stylish and safety.

    DOI: 10.1299/jsmermd.2013._1P1-A06_1

    CiNii Article

    J-GLOBAL

  49. 1A2-I09 Long-Distance Navigation Method using Environmental Magnetic Field based on Topological Map(Wheeled Robot/Tracked Vehicle(2))

    AKAI Naoki, SHINOHARA Masatoshi, SHIMADA Ryo, KATAYOSE Kohei, AMM RAHOK Sam, OZAKI Koichi

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   Vol. 2012 ( 0 ) page: _1A2 - I09_1-_1A2-I09_3   2012

     More details

    Language:Japanese   Publisher:The Japan Society of Mechanical Engineers  

    This paper describes a navigation method using environmental magnetic field called magnetic navigation based on topological map. The mobile robot that navigates with the magnetic navigation, estimates its position using change of environmental magnetic intensity. However, the magnetic navigation produces lateral error. Therefore, it is necessary to compensate that error. This paper proposes a method using Laser Scanner (LS) to compensate the lateral error occurred during the navigation. Since only two data of LS (one on the left and one on the right) are used in the proposed method, the mobile robot is able to navigate on a distance of 2km with a low computational cost in comparison to scan matching.

    DOI: 10.1299/jsmermd.2012._1A2-I09_1

    CiNii Article

    J-GLOBAL

  50. 環境磁場を用いた自律移動ロボットのナビゲーション手法

    赤井直紀, RAHOK Sam Ann, 尾崎功一

    日本ロボット学会学術講演会予稿集(CD-ROM)   Vol. 30th   2012

     More details

▼display all

Research Project for Joint Research, Competitive Funding, etc. 3

  1. 著作物

  2. ノウハウ

  3. 著作物

KAKENHI (Grants-in-Aid for Scientific Research) 2

  1. 薄暮時・夜間における歩行者と移動体の視覚的インタラクションの基盤技術

    Grant number:19K12080  2019.4 - 2022.3

    日本学術振興会  科学研究費助成事業 基盤研究(C)  基盤研究(C)

    平山 高嗣, MORALES・S Luis・Y, 赤井 直紀, 劉 海龍

      More details

    Authorship:Coinvestigator(s) 

    クルマ(運転知能)が急速に高度化しているが対歩行者事故はほとんど減っていない。薄暮時と夜間の視界不良状況において、クルマはもとより運転者でさえも、受動的な観測によって歩行者の行動予測を行うことが困難なためである。歩行者の顕著性や視認性を向上させる技術が必要であり、歩行者側への支援も重要である。そこで、①次世代ヘッドライト技術を想定した適切なパターンでの光照射により顕著性と視認性を向上させることで、運転者の視覚認知および車載される歩行者認識システムの視覚処理を支援する技術を構築し、②歩行者に自車の接近を気づかせ、安心感を与える光照射による視覚的インタラクションの基礎研究に取り組む。検知、認識、意図伝達の3つのフェーズで構成される視覚的インタラクションを設計する。
    2019年度は主に、検知フェーズにおける歩行者への点滅光照射によるインタラクションの設計と評価を行い、ドライビングシミュレータ上で複数の周辺光条件を設定して模擬した交通環境における実験により、点滅光照射による歩行者の見つけやすさの向上と、周辺光条件に応じて効果的な点滅周波数が異なることを確認した。夜間において周囲に明かりがない環境では3Hz、街灯が存在する環境および前方に信号機が存在する環境では5Hz、薄暮時において街灯が存在する環境では3Hz、前方に信号機が存在する環境では2Hzが効果的な照射光パターンであった。実環境においても、設定することができた周辺光条件は限定的であるが、同様の結果を得ている。また、運転者の視行動の分析とモデル化等の基盤研究やヘッドアップディスプレイの利用を想定した視認性評価の研究も推進した。

  2. Study on the use of machine learning approaches for enabling to guarantee safety of model-based autonomous navigation

    Grant number:18K13727  2018.4 - 2022.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research Grant-in-Aid for Early-Career Scientists  Grant-in-Aid for Early-Career Scientists

      More details

    Authorship:Principal investigator 

    Grant amount:\4160000 ( Direct Cost: \3200000 、 Indirect Cost:\960000 )

Industrial property rights 1

  1. 自己位置推定装置

    赤井直紀

     More details

    Applicant:トヨタ自動車株式会社

    Application no:2018-103111  Date applied:2018.5

    Announcement no:2019-207177  Date announced:2019.12

 

Teaching Experience (On-campus) 1

  1. 機械システム研修Ⅱ

    2020

Teaching Experience (Off-campus) 1

  1. 状況理解特論

    2020.4 - 2020.9 Aichi Prefectural University)

 

Academic Activities 1

  1. ICRA2020査読

    Role(s):Peer review