Deep Reinforcement Learning for Mobile Robot Path Planning

TL;DR

This paper introduces a novel deep reinforcement learning approach combined with a hybrid A* algorithm for efficient and high-quality path planning in mobile robots, optimized for embedded systems.

Contribution

It presents a new DRL-based path planning method with tailored reward functions and a hybrid A* algorithm, optimized for mobile robot deployment.

Findings

DRL-based algorithm achieves better planning results

Consumes less computing resources on embedded systems

Improves local path quality with hybrid A*

Abstract

Path planning is an important problem with the the applications in many aspects, such as video games, robotics etc. This paper proposes a novel method to address the problem of Deep Reinforcement Learning (DRL) based path planning for a mobile robot. We design DRL-based algorithms, including reward functions, and parameter optimization, to avoid time-consuming work in a 2D environment. We also designed an Two-way search hybrid A* algorithm to improve the quality of local path planning. We transferred the designed algorithm to a simple embedded environment to test the computational load of the algorithm when running on a mobile robot. Experiments show that when deployed on a robot platform, the DRL-based algorithm in this article can achieve better planning results and consume less computing resources.