Motion planning of wheeled mobile robots based on heuristic dynamic programming for WCICA 2014 proceedings published by IEEE

Abstract

This paper presents a novel motion planning method, based on heuristic dynamic programming (HDP), applicable to the control of wheeled mobile robots (WMRs). First, a new architecture of motion planning system is proposed, where the motion planner is designed based on the HDP algorithm. Second, we devise a reward function, which is beneficial for improving the planning efficiency. Then, back propagation (BP) neural networks (NNs) are utilized to implement the HDP algorithm for constructing the motion planner. At last, simulation and experimental results demonstrate the validity of the proposed scheme.