Faculty Profiles - HASEGAWA, Yasuhisa

Presentations -

Division display 481 - 494 of about 494 ／ All the affair displays >>

Behaviour adaption on behavior-based controller for brachiation robot

Y Hasegawa, Y Ito, T Fukuda

ADVANCES IN ARTIFICIAL LIFE, PROCEEDINGS 1999 SPRINGER-VERLAG BERLIN

Event date： 1999

Language：English Presentation type：Oral presentation (general)

This paper proposes novel adaptation method for a behavior-based locomotion robot. Utilization of hierarchical behavior controller makes the controller designing process easier and shorter, because the designer can deal with behavior controllers for simple behaviors independently, and coordinate those behavior controllers in order for a robot to perform the objective behavior after finishing the design of the fundamental behavior controllers. Some problems are still remaining. One is how to adjust the behavior coordinator when the objective behavior or robot parameters are slightly changed. We propose the novel method to adjust the behavior coordinator against some changes. This method measures the effects of the fundamental behavior controllers to the total behavior, and changes the activation values for them in less trials. This proposed method is applied to the real brachiation robot control. This brachiation robot has redundant mechanism to locomote from branch to branch with 14 actuators like a long-armed ape.

researchmap

Learning method for hierarchical behavior controller

Y Hasegawa, T Fukuda

ICRA '99: IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-4, PROCEEDINGS 1999 IEEE

Event date： 1999

Language：English Presentation type：Oral presentation (general)

Complex behavior is hardly obtained using an; unsupervised leaning methods, because of enormous searching space. In order to reduce the searching space, a hierarchical behavior structure is effective. In this paper, we proposed the hierarchical behavior controller, which consists of three types of modules, behavior coordinator, behavior controller and feedback controller. We also propose a new learning algorithm for the behavior coordinator and the behavior controller that consists of some sub-coordinators and some sub-controllers, respectively. This algorithm selects a deficient one by evaluating each sub-coordinator or sub-controller using multiple regression analysis based on previously obtained evaluation values. This can reduce the searching area and the learning rimes by avoiding the necessary of trying to tune good sub-coordinators or sub-controllers. The hierarchical behavior controller is applied to the problem of controlling a seven-link brachiation robot, which moves dynamically from branch to branch like gibbon swinging its body.

researchmap

Robot hand manipulation by evolutionary programming

T Fukuda, K Mase, Y Hasegawa

ICRA '99: IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-4, PROCEEDINGS 1999 IEEE

Event date： 1999

Language：English Presentation type：Oral presentation (general)

In this paper, we propose a searching method of the grasping and manipulating an object in the three-dimensional space by using a four-fingered robot hand which is applicable to the real robot hand. Recently there are many researches about multi-fingered robot hand. To manipulate some object, it is need to teach contact points and forces of fingertip. But it is difficult to optimize each parameter for natural grasping. So this paper shows the manipulation using EP (Evolutionary Programming) to optimize the motion of the fingers. In this case, EP determines not only when and where the fingers are molted but also which finger is operated to the next contact point as the grasping attitude is changed Moreover the coding of individual is unique, which makes easy to optimize the parameter: The result examines the effective in computer simulation in this paper but it would be applicable to a real robot hand.

researchmap

Hierarchical control system based on unsupervised fuzzy-neuro system

Koji Shimojima, Toshio Fukuda, Yasuhisa Hasegawa

IEEE International Conference on Neural Networks - Conference Proceedings 1995.12.1

Event date： 1995.12

Language：English Presentation type：Oral presentation (general)

Recently, fuzzy systems are applied to various systems. However, lack of learning ability, the determination of most fuzzy rules and membership function was made by human experts. In this paper, we propose a hierarchical control system based on the unsupervised RBF Fuzzy system. The learning algorithm of the fuzzy system is based on Genetic Algorithms. This hierarchical control system has the skill database, which manages the some of the fuzzy controllers acquired through the unsupervised learning process. Thus, the proposed system can use the acquired fuzzy controller effectively and it leads to reduce the iteration time for a new object. The effectiveness of the proposed method is shown through the simulations of the cart-pole problem.

researchmap

Reinforcement learning method for generating fuzzy controller

Toshio Fukuda, Yasuhisa Hasegawa, Koji Shimojima, Fuminori Saito

Proceedings of the IEEE Conference on Evolutionary Computation 1995.12.1

Event date： 1995.12

Language：English Presentation type：Oral presentation (general)

In this paper, we propose a new reinforcement learning algorithm for generating a fuzzy controller. The algorithm generates a range of continuous real-valued actions, and reinforcement signal is self-scaled. This prevents the weights from overshooting when the system gets a very large reinforcement value. The proposed method is applied to the problem of controlling the brachiation robot, which moves dynamically from branch to branch like a gibbon swinging its body in a pendulum fashion(Fig. 1).

researchmap

RBF-fuzzy system with GA based unsupervised/supervised learning method

Koji Shimojima, Toshio Fukuda, Yasuhisa Hasegawa

IEEE International Conference on Fuzzy Systems 1995.1.1

Event date： 1995.1

Language：English Presentation type：Oral presentation (general)

Fuzzy systems are used in many fields and places so far. In order to apply the fuzzy systems to the various fields and places, the tuning and optimizing method of the fuzzy system is the key issue. And the optimization of structure of fuzzy system (the number of membership function, the number of rules) is also very important to simplify the fuzzy systems. Some self-tuning methods have been proposed so far. However these conventional self-tuning methods do not have sufficient capability of learning. In this paper, we propose new unsupervised/supervised self-tuning fuzzy system, which consists of some membership functions expressed by the radial basis function with insensitive region. Learning are based on the genetic algorithms. The descent method is also utilized for tuning the shapes of membership function and consequent parts in case of supervised learning. The effectiveness of the proposed methods is shown by some numerical examples and simulations.

researchmap

STRUCTURE ORGANIZATION OF HIERARCHICAL FUZZY MODEL USING BY GENETIC ALGORITHM

T FUKUDA, Y HASEGAWA, K SHIMOJIMA

PROCEEDINGS OF 1995 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS I-IV 1995 I E E E

Hierarchical fuzzy reasoning - adaptive structure and rule by genetic algorithms

Toshio Fukuda, Yasuhisa Hasegawa, Koji Shimojima

IEEE Conference on Evolutionary Computation - Proceedings 1994.12.1

Event date： 1994.12

Language：English Presentation type：Oral presentation (general)

This paper proposes a self-tuning hierarchical fuzzy reasoning that uses the Genetic Algorithm and back-propagation method. If a fuzzy system has a number of inputs, the number of membership functions and rules will be exploded. Therefore, it is necessary to reduce the number of membership functions. One method to do so is to make a hierarchical structure of fuzzy inference units that have a few inputs. However the hierarchical structure cannot be made without considering the relationship among inputs. The proposed method is based on the Genetic Algorithm with a strategy that favors systems with fewer rules and membership functions, and obtains the optimal structure. The proposed method is applied to multi-dimentional function approximation problems in order to show the effectiveness.

researchmap

Advantage of variable stiffness of human fingers for key insertion task

Yasuhisa HASEGAWA, Ojiro KITAMURA

2014 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM) 2014.7.8

Bio-Fabrication of Ca-Alginate Cell Sheets with the Electrodeposition Method for Hepatic Lobule Tissue Reconstracts

Zeyang Liu, Masaru Takeuchi, Yasuhisa Hasegawa, Toshio Fukuda, Qiang Huang

The 21st International Conference on Miniaturized Systems for Chemistry and Life Sciences (MicroTAS 2017) 2017.10.24

Auricularis Muscles based Control Interface for Robotic Extra Thumb

Noel Segura Meraz, Yasuhisa Hasegawa, Hiroshi Shikida

2017 International Symposium on Micro-NanoMechatronics and Human Science (MHS 2017), 2017.12.4

Assembly of Hepatic Lobule-like Microtissue with Repetitive Single-Step Contact Manipulation

Zeyang Liu, Masaru Takeuchi, Masahiro Nakajima, Toshio Fukuda, Yasuhisa Hasegawa, Qiang Huang

2016 International Symposium on Micro-NanoMechatronics and Human Science (MHS 2016) 2016.11.28

HMD表示可能な視野拡張型顕微鏡システムの観察可能範囲の評価 International conference

竹野更宇, 青山忠義, 竹内大, 長谷川泰久, 石井抱

第24回ロボティクスシンポジア 2019.3.14

Peripheral Nerve Stimulation Device Enabling Adjusment of Stimulation Voltage

Takahiro Miyamoto, Masaru Takeuchi, Tadayoshi Aoyama, Yasuhisa Hasegawa, Tomonori Nakano, Shigeru Kurimoto, Hitoshi Hirata

2018 International Symposium on Micro-NanoMechatronics and Human Science (MHS 2018) 2018.12.10

　 PREV - NEXT 　

<HASEGAWA, Yasuhisa>

Presentations -