Open Access Open Access  Restricted Access Subscription Access

Intelligent All-Terrain Vehicle Robot with Movable Auxiliary Mass

H. Takemi, M. Yokoyama

Abstract


This paper presents a learning control strategy for an all-terrain vehicle robot which consists of two modules: a normal vehicle with wheels or tracks, and a moveable auxiliary mass which is a feature of this vehicle robot. Longitudinal motion of the auxiliary mass can be controlled by a DC motor 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 designing a controller with neural networks. It is  demonstrated that the reinforcement learning is useful to get an effective controller under uncertain environment.

Full Text:

PDF

References


Y. Saitoh and M. Yokoyama, "Traction control of a vehicle robot with variable center of gravity", Proceedings of Joint Conference of Automatic Control in Japan (2010).

Sutton, R. & Barto, A. G. , Reinforcement learning. London: The MIT Press (1998).

Doya, K., "Reinforcement learning in continuous time and space", Neural Computation 12 (1999.): 243-269

J. Morimoto and K. Doya, “Acquisition of stand-up behavior by real robot using hierarchal reinforcement learning”, Robotics and Automation Systems, Vol.36, No.1(2001), pp.37-51

M. Hara, N. Kawabe, N. Sakai, J. Huang, H. Bleuler and T. Yabuta, “Consideration on Robotic Giant-swing Motion Generated by Reinforcement Learning” , Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (2009), pp.4206-4211




DOI: http://dx.doi.org/10.21535%2FProICIUS.2011.v7.347

Refbacks

  • There are currently no refbacks.