An Adaptive Behavior Navigation Method for Mobile Robots
Reinforcement learning has been one of the methods used to adapt robotics control systems to changing environments. Because it does not need priori knowledge and behaviors to complete given tasks are obtained automatically by repeating trial and error. However, the generalization ability and learning efficiency of RL-based navigation systems have to be improved to satisfy the requirements of the continuous sensory information of mobile robots. This paper proposes an adaptive behavior navigation method for mobile robots which is based on a competitive neural network model and uses reinforcement learning with adaptive state space construction strategy. The method can divide the state space gradually according to the task complexity and progress of learning, and overcome the difficulty of dimensionality cruse. The simulation results are provided to show the validity of the proposed method in solving mobile robot navigation.
Guizhi Li Yaoguang Wei
Computer Center Beijing Information Science and Technology University Beijing 100085 Institute of Information China Agriculture University Beijing 100083
国际会议
南宁
英文
2007-07-20（万方平台首次上网日期，不代表论文的发表时间）