Bionic Learning Algorithm Based on Skinners Operant Conditioning and Control of Robot
Aiming at the problem about the movement balance control of two-wheeled self-balancing mobile robot, a learning algorithm that it is made up of BP neural network and eligibility traces based on the operant conditioning theory is put forward as a learning mechanism of the two-wheeled robot. The algorithm utilizes the characters of eligibility traces about quicker learning speed, higher reliability and ability in resolving effect about delay, so that the two-wheeled robot can obtain the movement balance skills of controlling like a human or animal by interacting, studying and training with unknown environmental, and realize the movement balance control of the two-wheeled robot by using the complex learning algorithm. Finally, a simulation experiment is done and the simulation results show that a learning mechanism of the complex learning algorithm can embodies the stronger skills of self-learning and abilities of balance control of the robot, and it also has the higher research significance in theory and the application value in project.
Skinners operation conditioning eligibility traces self-learning balance control two-wheeled robot
Xiaogang Ruan Hongge Ren
School of Electronic & Control Engineering Beijing University of Technology Beijing, China
国际会议
2009 WASE International Conference on Information Engineering(2009年国际信息工程会议)(ICIE 2009)
太原
英文
721-724
2009-07-10（万方平台首次上网日期，不代表论文的发表时间）