关键词: 模糊神经网络；Agent；强化学习；路径规划；自主式地面车辆

Abstract:

By introducing FMQ(frequency maximum Q) heuristic learning algorithm, a hierarchical method of reinforcement learning was improved, through the combination of this method and fuzzy neural-networks, a global path planning Agent was developed. This Agent integrated the human operation experience and the capacity of machine learning, so that it ensured the search direction, reduced the amount of computation, strengthened the adaptive capacity and met the real-time requirements. The simulation results show that the global path planning Agent can find the optimal strategy effective and real-time in the large state space and the dynamic changing environment.

Key words: fuzzy neural-network, Agent, reinforcement learning, path planning, automated land vehicle(ALV)