Multi-agent Soft Actor-Critic Based Hybrid Motion Planner for Mobile Robots

TL;DR

This paper introduces a hybrid multi-robot motion planner that leverages multi-agent soft actor-critic algorithms for collaborative waypoint searching and minimal snap trajectory optimization, enabling smooth, safe, and executable paths in decentralized settings.

Contribution

It presents a novel hybrid motion planning framework combining multi-agent reinforcement learning with trajectory optimization for multi-robot systems.

Findings

Effective in non-communication environments

Produces smooth, safe, and feasible trajectories

Validated through multi-group experiments

Abstract

In this paper, a novel hybrid multi-robot motion planner that can be applied under non-communication and local observable conditions is presented. The planner is model-free and can realize the end-to-end mapping of multi-robot state and observation information to final smooth and continuous trajectories. The planner is a front-end and back-end separated architecture. The design of the front-end collaborative waypoints searching module is based on the multi-agent soft actor-critic algorithm under the centralized training with decentralized execution diagram. The design of the back-end trajectory optimization module is based on the minimal snap method with safety zone constraints. This module can output the final dynamic-feasible and executable trajectories. Finally, multi-group experimental results verify the effectiveness of the proposed motion planner.