Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans

TL;DR

This paper introduces a reinforcement learning-based method for mapless collision avoidance in dynamic environments with pedestrians, emphasizing social safety and ego-safety, and demonstrating successful transfer from simulation to real robots.

Contribution

The paper presents a novel social-safety-aware reinforcement learning approach for mapless navigation that effectively transfers from simulation to real-world robots without fine-tuning.

Findings

High success rate in dynamic crowd navigation

Smooth transfer from simulation to real robots

Demonstrates cooperative and socially-aware robot behavior

Abstract

We propose a method to tackle the problem of mapless collision-avoidance navigation where humans are present using 2D laser scans. Our proposed method uses ego-safety to measure collision from the robot's perspective while social-safety to measure the impact of our robot's actions on surrounding pedestrians. Specifically, the social-safety part predicts the intrusion impact of our robot's action into the interaction area with surrounding humans. We train the policy using reinforcement learning on a simple simulator and directly evaluate the learned policy in Gazebo and real robot tests. Experiments show the learned policy can be smoothly transferred without any fine tuning. We observe that our method demonstrates time-efficient path planning behavior with high success rate in mapless navigation tasks. Furthermore, we test our method in a navigation among dynamic crowds task considering both low and high volume traffic. Our learned policy demonstrates cooperative behavior that actively drives our robot into traffic flows while showing respect to nearby pedestrians. Evaluation videos are at https://sites.google.com/view/ssw-batman