Obtaining Robust Control and Navigation Policies for Multi-Robot Navigation via Deep Reinforcement Learning

TL;DR

This paper presents a deep reinforcement learning approach to develop decentralized control policies for multi-robot navigation, enabling robots to navigate complex environments and recover from dead ends.

Contribution

It introduces a novel DRL-based decentralized policy that generalizes across environments for multi-robot navigation tasks.

Findings

The learned policy effectively navigates complex scenarios.

Robust recovery from dead ends demonstrated.

Generalization across different environments achieved.

Abstract

Multi-robot navigation is a challenging task in which multiple robots must be coordinated simultaneously within dynamic environments. We apply deep reinforcement learning (DRL) to learn a decentralized end-to-end policy which maps raw sensor data to the command velocities of the agent. In order to enable the policy to generalize, the training is performed in different environments and scenarios. The learned policy is tested and evaluated in common multi-robot scenarios like switching a place, an intersection and a bottleneck situation. This policy allows the agent to recover from dead ends and to navigate through complex environments.