Language：Japanese   Publisher：IEEE Internet of Things Journal  

The Internet of Things plays an indispensable role in the development of connected vehicles, which will pave the way for road safety applications. In recent years, the concept of a cooperative collision warning system (CCWS) has been introduced and developed to enhance road safety, and it has been seen as a typical Internet-of-Vehicles application. In most CCWSs, it is vital to have a detection mechanism based on trajectory predictions where the uncertainties associated with vehicular state and motion are complex. However, most available approaches in this regard did not consider these uncertainties. Hence, this article proposes a new collision risk assessment (CRA) method where sigma trajectories that include multiple possible trajectories considering multiple aspects of vehicular motion are designed to cope with vehicular uncertainties. Our method is implemented in a novel server-based architecture, which is different from the commonly used vehicle-based controlled CCWSs. The CRA is provided as a service by a cloud server. The proposed method and architecture are validated and evaluated through extensive real-world experiments. Experimental results show that our method outperforms a referenced method in terms of CRA and achieves better robustness in tolerating communication delays and dropouts. Latencies in CRA service were analyzed, and it was found that powerful computing resources provided by cloud servers can significantly decrease computational cost, which will indirectly compensate for communication costs in the future. Based on our high-performance CRA method, the proposed architecture can be regarded as a novel option for CCWS design.

DOI： 10.1109/JIOT.2021.3059222

Web of Science

Scopus

Language：Japanese   Publisher：International Journal of Mechatronics and Automation  

Pedestrian detection sensors in road infrastructure and smartphone's built-in sensors have been used to detect and track pedestrians for road safety. Nevertheless, although pedestrian detection sensors in road infrastructure can detect pedestrians' high-precision position, they cannot acquire the accurate attribute information of pedestrians. On the other hand, smartphone sensors can send location information, user identifier, and the attribute information of a user, but it has a significant margin of error in GPS data. The defects of LiDAR and smartphone render acquiring a pedestrian's high-precision location and attribute information simultaneously impossible. Currently, few studies on the simultaneous acquisition of pedestrian high-precision position and attribute information have been conducted. In this paper, the authors propose a pedestrian position and attribute information detecting system to extract both pedestrian high-precision position and attribute information in real-time based on LiDAR and smartphone sensor fusion. Moreover, an experiment is carried out to evaluate the system.

DOI： 10.1504/IJMA.2021.120380

Scopus

Language：Japanese   Publisher：2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021  

Pedestrian detection sensors in road infrastructure and GPS sensors mounted in smartphones have been used in driving safety support systems for detecting pedestrians. However, although pedestrian detection sensors in road infrastructure can detect pedestrians' high-precision position, they cannot acquire the attribute information of pedestrians. Conversely, a smartphone's built-in sensor can send GPS location information, user identifier, and the attribute information of a user, but it has a margin of error from meters to more than tens of meters in GPS location information. This renders acquiring a pedestrian's high-precision location and attribute information simultaneously impossible. To date, no research on the simultaneous acquisition of pedestrian high-precision position and attribute information has been conducted. To fill this gap, this paper proposes an approach to extract both pedestrian high-precision position and attribute information in real-time based on multi-sensor fusion. Moreover, an experiment is conducted to evaluate the proposed approach.

DOI： 10.1109/ICMA52036.2021.9512649

Web of Science

Scopus

Language：Japanese   Publisher：The Robotics Society of Japan  

<p>In order for autonomous vehicles to drive safely and comfortably, environmental information detected by sensors need to be gathered from wider area and to be more accurate. We can improve data accuracy by fusions of sensor data from not only vehicles but also road infrastructures. Fusion processing is usually performed in a high-performance server (centralized system). However, when the number of sensors is enormous, processing time and communication time for fusions become unacceptable due to high-load and limited capacity of network. And, waiting data-arrivals from all sensors is impractical in such situations. Thus, fusions should be distributed and incrementally updated on each data-arrival. In this paper, we propose a distributed environmental information management system using edge computing and a sensor fusion method.Since the system is composed of geographically distributed edges and a centralized cloud, it can distribute processing costs and communication costs of fusions to the edges and the cloud. The proposal sensor fusion method can incrementally compute intermediate results without waiting for receiving all the environmental information. In comparison experiments with the centralized system, the proposed system improved the efficiency of data processing and reduced the amount of communication data. </p>

DOI： 10.7210/jrsj.38.199

CiNii Research

Language：Japanese   Publisher：The Robotics Society of Japan  

<p>A wide range of accurate environmental information is needed in order for autonomous mobile robots to move safely. An intelligent space, which contains multiple sensors attached to the environment, is useful for information provision. Many optical sensors such as Laser Range Finders (LRFs) are placed to monitor fixed areas. But, LRFs occasionally miss objects due to distance attenuation of lasers, irregular reflection of lasers, and gaps between lasers. Thus, possibility of these detection failures of LRFs should be considered. In this paper, a novel measurement model with properties of the two-dimensional LRFs is constructed, and the empty probability distribution created by the model are proposed. We set two-dimensional LRFs up on a roadside, and calculated an empty probability distribution to evaluate the utility of the proposed model. In addition, since intelligent spaces often contain multiple LRFs, data measured from different viewpoints can be fused to improve data accuracy. We also evaluated sensor-fusion of multiple empty probability distributions obtained from individual LRFs. The fusion result grasps a location at which a detection failure of LRF has occurred. The usefulness of the proposed method was confirmed in our experimental evaluation. </p>

DOI： 10.7210/jrsj.38.379

CiNii Research

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

Language：Japanese  

Web of Science

Event date： 2023.9

Event date： 2023.9 - 2923.9

Language：Japanese   Presentation type：Oral presentation (general)  

Venue：仙台国際センター  

Event date： 2022.9

Event date： 2021.12

Event date： 2021.9

Event date： 2021.1

Event date： 2020.9

Event date： 2019.9

Event date： 2018.9