All-terrain vehicle robot with controllable auxiliary mass
This paper presents a control strategy by learning for an all-terrain vehicle robot,which has been developed by the authors to assist urban search and rescue.This robot consists of two modules:a normal vehicle with wheels or tracks,and a controllable auxiliary mass which is a feature of this vehicle robot.Motion of the auxiliary mass can be controlled by motors with parallel link mechanism in order to improve the vehicle mobility.That is,the auxiliary mass can be seen as a rider of motorcycle and utilized to change the center of gravity,the moment of inertia,adaptively corresponding to the environmental.The reinforcement learning is employed for the controller in which the trajectory of the mass is a control input.It is demonstrated that the reinforcement learning has a possibility to realize an effective controller.
Vehicle robot Motion control Reinforcement learning Nonlinear control
M. Yokoyama R. Adachi
Niigata University,Niigata,Japan
国际会议
The World Forum on Smart Materials and Smart Structures Technology(SMSST07)(2007年世界智能材料与智能结构技术论坛)
重庆·南京
英文
2007-05-01（万方平台首次上网日期，不代表论文的发表时间）