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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Shuijing, Hong, Kaiwen, Chakraborty, Neeloy, Driggs-Campbell, Katherine
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914814158176256
author Liu, Shuijing
Hong, Kaiwen
Chakraborty, Neeloy
Driggs-Campbell, Katherine
author_facet Liu, Shuijing
Hong, Kaiwen
Chakraborty, Neeloy
Driggs-Campbell, Katherine
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16830
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Structured Graph Network for Constrained Robot Crowd Navigation with Low Fidelity Simulation
Liu, Shuijing
Hong, Kaiwen
Chakraborty, Neeloy
Driggs-Campbell, Katherine
Robotics
Artificial Intelligence
Machine Learning
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.
title Structured Graph Network for Constrained Robot Crowd Navigation with Low Fidelity Simulation
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.16830