2024-03-29T13:39:38Z
https://u-ryukyu.repo.nii.ac.jp/oai
oai:u-ryukyu.repo.nii.ac.jp:02000772
2023-08-03T05:39:28Z
1642838163960:1642838338003
1642838403551:1642838406845
非厳密な評価規準をもつGAによる自転車のニューロ制御
Neurocontrol of Bicycle using GA with Rough Evaluations
山本, 哲彦
吐合, 隆拡
中園, 邦彦
金城, 寛
玉城, 史朗
Yamamoto, Tetsuhiko
Haki-ai, Takahiro
Nakazono, Kunihiko
Kinjo, Hiroshi
Tamaki, Shiro
open access
Copyright (c) 1996 日本機械学会
Neural Networks
Robot
Learning
Direct Control
Genetic Algorithms
Rough Evaluation
Bicycle
Environment Adaptation
Genetic algorithms (GAs) with rough evaluations can prompt the evolution of neural networks that are able to control unstable dynamic systems. The proposed control method exploits the advantage of GAs that time-varying evaluations can be easily incorporated. First an easy evaluation in GAs induces the appearance of neural networks with controllability. Second, an evaluation of settling time prompts the evolution of neural networks that show high performance. The method is applied to the stable control of a bicycle. Neurocontrol of the steering at direction change causes reverse response like that of a human cyclist.
論文
日本機械学会
1996-09-25
jpn
journal article
VoR
http://hdl.handle.net/20.500.12000/64
http://hdl.handle.net/20.500.12000/64
https://u-ryukyu.repo.nii.ac.jp/records/2000772
03875024
AN00187463
日本機械学会論文集. C編
Transactions of the Japan Society of Mechanical Engineers. C
62
601
108
113
https://u-ryukyu.repo.nii.ac.jp/record/2000772/files/kinzyou_h02.pdf