Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning
It is challenging for a mobile robot to navigate through human crowds. Existing approaches usually assume that pedestrians follow a predefined collision avoidance strategy, like social force model (SFM) or optimal reciprocal collision avoidance (ORCA). However, their performances commonly need to be...
Main Authors: | , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2109.02541 https://arxiv.org/abs/2109.02541 |
id |
ftdatacite:10.48550/arxiv.2109.02541 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2109.02541 2023-05-15T17:53:50+02:00 Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning Yao1, Shunyi Chen, Guangda Qiu, Quecheng Ma, Jun Chen, Xiaoping Ji, Jianmin 2021 https://dx.doi.org/10.48550/arxiv.2109.02541 https://arxiv.org/abs/2109.02541 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Robotics cs.RO FOS Computer and information sciences Article CreativeWork article Preprint 2021 ftdatacite https://doi.org/10.48550/arxiv.2109.02541 2022-03-10T13:41:35Z It is challenging for a mobile robot to navigate through human crowds. Existing approaches usually assume that pedestrians follow a predefined collision avoidance strategy, like social force model (SFM) or optimal reciprocal collision avoidance (ORCA). However, their performances commonly need to be further improved for practical applications, where pedestrians follow multiple different collision avoidance strategies. In this paper, we propose a map-based deep reinforcement learning approach for crowd-aware robot navigation with various pedestrians. We use the sensor map to represent the environmental information around the robot, including its shape and observable appearances of obstacles. We also introduce the pedestrian map that specifies the movements of pedestrians around the robot. By applying both maps as inputs of the neural network, we show that a navigation policy can be trained to better interact with pedestrians following different collision avoidance strategies. We evaluate our approach under multiple scenarios both in the simulator and on an actual robot. The results show that our approach allows the robot to successfully interact with various pedestrians and outperforms compared methods in terms of the success rate. : 7 page Article in Journal/Newspaper Orca DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Robotics cs.RO FOS Computer and information sciences |
spellingShingle |
Robotics cs.RO FOS Computer and information sciences Yao1, Shunyi Chen, Guangda Qiu, Quecheng Ma, Jun Chen, Xiaoping Ji, Jianmin Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning |
topic_facet |
Robotics cs.RO FOS Computer and information sciences |
description |
It is challenging for a mobile robot to navigate through human crowds. Existing approaches usually assume that pedestrians follow a predefined collision avoidance strategy, like social force model (SFM) or optimal reciprocal collision avoidance (ORCA). However, their performances commonly need to be further improved for practical applications, where pedestrians follow multiple different collision avoidance strategies. In this paper, we propose a map-based deep reinforcement learning approach for crowd-aware robot navigation with various pedestrians. We use the sensor map to represent the environmental information around the robot, including its shape and observable appearances of obstacles. We also introduce the pedestrian map that specifies the movements of pedestrians around the robot. By applying both maps as inputs of the neural network, we show that a navigation policy can be trained to better interact with pedestrians following different collision avoidance strategies. We evaluate our approach under multiple scenarios both in the simulator and on an actual robot. The results show that our approach allows the robot to successfully interact with various pedestrians and outperforms compared methods in terms of the success rate. : 7 page |
format |
Article in Journal/Newspaper |
author |
Yao1, Shunyi Chen, Guangda Qiu, Quecheng Ma, Jun Chen, Xiaoping Ji, Jianmin |
author_facet |
Yao1, Shunyi Chen, Guangda Qiu, Quecheng Ma, Jun Chen, Xiaoping Ji, Jianmin |
author_sort |
Yao1, Shunyi |
title |
Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning |
title_short |
Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning |
title_full |
Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning |
title_fullStr |
Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning |
title_full_unstemmed |
Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning |
title_sort |
crowd-aware robot navigation for pedestrians with multiple collision avoidance strategies via map-based deep reinforcement learning |
publisher |
arXiv |
publishDate |
2021 |
url |
https://dx.doi.org/10.48550/arxiv.2109.02541 https://arxiv.org/abs/2109.02541 |
genre |
Orca |
genre_facet |
Orca |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2109.02541 |
_version_ |
1766161532566110208 |