Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Shuijing, Chang, Peixin, Liang, Weihang, Chakraborty, Neeloy, Driggs-Campbell, Katherine
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916585647636480
author Liu, Shuijing
Chang, Peixin
Liang, Weihang
Chakraborty, Neeloy
Driggs-Campbell, Katherine
author_facet Liu, Shuijing
Chang, Peixin
Liang, Weihang
Chakraborty, Neeloy
Driggs-Campbell, Katherine
contents Safe and efficient navigation through human crowds is an essential capability for mobile robots. Previous work on robot crowd navigation assumes that the dynamics of all agents are known and well-defined. In addition, the performance of previous methods deteriorates in partially observable environments and environments with dense crowds. To tackle these problems, we propose decentralized structural-Recurrent Neural Network (DS-RNN), a novel network that reasons about spatial and temporal relationships for robot decision making in crowd navigation. We train our network with model-free deep reinforcement learning without any expert supervision. We demonstrate that our model outperforms previous methods in challenging crowd navigation scenarios. We successfully transfer the policy learned in the simulator to a real-world TurtleBot 2i. For more information, please visit the project website at https://sites.google.com/view/crowdnav-ds-rnn/home.
format Preprint
id arxiv_https___arxiv_org_abs_2011_04820
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning
Liu, Shuijing
Chang, Peixin
Liang, Weihang
Chakraborty, Neeloy
Driggs-Campbell, Katherine
Robotics
Artificial Intelligence
Machine Learning
Safe and efficient navigation through human crowds is an essential capability for mobile robots. Previous work on robot crowd navigation assumes that the dynamics of all agents are known and well-defined. In addition, the performance of previous methods deteriorates in partially observable environments and environments with dense crowds. To tackle these problems, we propose decentralized structural-Recurrent Neural Network (DS-RNN), a novel network that reasons about spatial and temporal relationships for robot decision making in crowd navigation. We train our network with model-free deep reinforcement learning without any expert supervision. We demonstrate that our model outperforms previous methods in challenging crowd navigation scenarios. We successfully transfer the policy learned in the simulator to a real-world TurtleBot 2i. For more information, please visit the project website at https://sites.google.com/view/crowdnav-ds-rnn/home.
title Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2011.04820