Structured Graph Network for Constrained Robot Crowd Navigation with Low Fidelity Simulation

TL;DR

This paper presents a novel approach for constrained robot crowd navigation using low-fidelity simulation, leveraging a spatio-temporal graph and attention mechanisms to improve real-world deployment.

Contribution

It introduces a new environment representation and a spatio-temporal graph model with attention mechanisms to enhance RL-based crowd navigation in low-fidelity simulations.

Findings

Improved navigation performance in simulation and real-world

Reduced sim2real gap for RL policies

Effective modeling of agent interactions with attention mechanisms

Abstract

We investigate the feasibility of deploying reinforcement learning (RL) policies for constrained crowd navigation using a low-fidelity simulator. We introduce a representation of the dynamic environment, separating human and obstacle representations. Humans are represented through detected states, while obstacles are represented as computed point clouds based on maps and robot localization. This representation enables RL policies trained in a low-fidelity simulator to deploy in real world with a reduced sim2real gap. Additionally, we propose a spatio-temporal graph to model the interactions between agents and obstacles. Based on the graph, we use attention mechanisms to capture the robot-human, human-human, and human-obstacle interactions. Our method significantly improves navigation performance in both simulated and real-world environments. Video demonstrations can be found at https://sites.google.com/view/constrained-crowdnav/home.