Dynamic Obstacle Avoidance by Distributed Algorithm based on Reinforcement Learning

In this paper we focus on the application of reinforcement learning to obstacle avoidance in dynamic Environments in wireless sensor networks. A distributed algorithm based on reinforcement learning is developed for sensor networks to guide mobile robot through the dynamic obstacles. The sensor network models the danger of the area under coverage as obstacles, and has the property of adoption of itself against possible changes. The proposed protocol can integrate the reward computation of the sensors with information of the intended place of robot so that it guides the robot step by step through the sensor network by choosing the safest path in dangerous zones. Simulation results show that the mobile robot can get to the target point without colliding with any obstacle after a period of learning.Also we discussed about time propagation between obstacle, goal, and mobile robot information. Experimental results show that our proposed method has the ability of fast adoption in real applications in wireless sensor networks