Neural networks based reinforcement learning for mobile robots obstacle avoidance

作者：

Highlights：

• We propose a new path planning algorithm based on the use of Q-learning and artificial neural networks.

• We analyze and model in VR the mobile robot PowerBot.

• We implement and test the proposed algorithm in both VR and real workspaces.

• The solution converges to collision-free trajectories in dynamic environments.

摘要

•We propose a new path planning algorithm based on the use of Q-learning and artificial neural networks.•We analyze and model in VR the mobile robot PowerBot.•We implement and test the proposed algorithm in both VR and real workspaces.•The solution converges to collision-free trajectories in dynamic environments.

论文关键词：Obstacle avoidance,Neural networks,Q-learning,Virtual reality

论文评审过程：Received 29 October 2015, Revised 9 June 2016, Accepted 9 June 2016, Available online 11 June 2016, Version of Record 16 June 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.06.021