Socially-Aware Multi-Agent Following with 2D Laser Scans via Deep Reinforcement Learning and Potential Field

TL;DR

This paper introduces a multi-robot system that uses deep reinforcement learning and potential fields to enable socially-aware target following in crowded environments using only 2D laser scans, effectively avoiding static and dynamic obstacles.

Contribution

It presents a novel multi-agent approach combining reinforcement learning and potential fields for socially-aware target following with 2D laser scans, handling arbitrary robot numbers and dynamic obstacles.

Findings

Successful in unseen dynamic environments

Robots follow targets socially-aware with only laser scans

Effective collision avoidance with static and dynamic obstacles

Abstract

Target following in dynamic pedestrian environments is an important task for mobile robots. However, it is challenging to keep tracking the target while avoiding collisions in crowded environments, especially with only one robot. In this paper, we propose a multi-agent method for an arbitrary number of robots to follow the target in a socially-aware manner using only 2D laser scans. The multi-agent following problem is tackled by utilizing the complementary strengths of both reinforcement learning and potential field, in which the reinforcement learning part handles local interactions while navigating to the goals assigned by the potential field. Specifically, with the help of laser scans in obstacle map representation, the learning-based policy can help the robots avoid collisions with both static obstacles and dynamic obstacles like pedestrians in advance, namely socially aware. While the formation control and goal assignment for each robot is obtained from a target-centered potential field constructed using aggregated state information from all the following robots. Experiments are conducted in multiple settings, including random obstacle distributions and different numbers of robots. Results show that our method works successfully in unseen dynamic environments. The robots can follow the target in a socially compliant manner with only 2D laser scans.