End-to-end Decentralized Multi-robot Navigation in Unknown Complex Environments via Deep Reinforcement Learning

TL;DR

This paper introduces a decentralized deep reinforcement learning approach enabling multi-robot teams to navigate unknown complex environments efficiently without prior map construction, maintaining connectivity and avoiding collisions.

Contribution

It presents a novel end-to-end DRL-based method for decentralized multi-robot navigation that operates directly on raw sensor data, validated through simulations and real-world experiments.

Findings

Effective navigation in complex environments demonstrated

Decentralized policies outperform centralized approaches

Successful real-world UGV experiments conducted

Abstract

In this paper, a novel deep reinforcement learning (DRL)-based method is proposed to navigate the robot team through unknown complex environments, where the geometric centroid of the robot team aims to reach the goal position while avoiding collisions and maintaining connectivity. Decentralized robot-level policies are derived using a mechanism of centralized learning and decentralized executing. The proposed method can derive end-to-end policies, which map raw lidar measurements into velocity control commands of robots without the necessity of constructing obstacle maps. Simulation and indoor real-world unmanned ground vehicles (UGVs) experimental results verify the effectiveness of the proposed method.