Research on Q-ELM algorithm in robot path planning

Abstract

In view of high dimension, the difficulty of training, the problem of slow learning speed in the application of BP neural network in mobile robot path planning, an algorithm of reinforcement Q learning based on extreme learning machine (Q-ELM algorithm) is proposed in this paper. Firstly, the characteristic of reinforcement learning is combining the dynamic network with supervised learning, and the algorithm obtains the state information of the environment and the robot by the characteristic. After that, it is used to analyze the state to get the rewards and punishments of the current state by extreme learning machine. Secondly, it is used to solve the problem of slow training speed by the characteristic of less parameter settings and better generalization performance; Finally the autonomic learning performance of the learning algorithm is verified. The experimental results show that the Q-ELM learning algorithm not only improves the initiative of machine learning, but also improves the learning rate of 4 times than TD reinforcement learning methods, and verifies the stability and convergence of the algorithm.