Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments

In autonomous navigation of mobile robots, sensors suffer from massive occlusion in cluttered environments, leaving significant amount of space unknown during planning. In practice, treating the unknown space in optimistic or pessimistic ways both set limitations on planning performance, thus aggres...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Lizi, Ye, Hongkai, Wang, Qianhao, Gao, Yuman, Xu, Chao, Gao, Fei
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Wang, Lizi
Ye, Hongkai
Wang, Qianhao
Gao, Yuman
Xu, Chao
Gao, Fei
description In autonomous navigation of mobile robots, sensors suffer from massive occlusion in cluttered environments, leaving significant amount of space unknown during planning. In practice, treating the unknown space in optimistic or pessimistic ways both set limitations on planning performance, thus aggressiveness and safety cannot be satisfied at the same time. However, humans can infer the exact shape of the obstacles from only partial observation and generate non-conservative trajectories that avoid possible collisions in occluded space. Mimicking human behavior, in this paper, we propose a method based on deep neural network to predict occupancy distribution of unknown space reliably. Specifically, the proposed method utilizes contextual information of environments and learns from prior knowledge to predict obstacle distributions in occluded space. We use unlabeled and no-ground-truth data to train our network and successfully apply it to real-time navigation in unseen environments without any refinement. Results show that our method leverages the performance of a kinodynamic planner by improving security with no reduction of speed in clustered environments.
doi_str_mv 10.48550/arxiv.2011.03981
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2011_03981</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2011_03981</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-ebf79f7189ee89c06d8baeae64907c995a103a2fa75ff99d1b5516d146699b793</originalsourceid><addsrcrecordid>eNotj7tOwzAYRr0woMIDMOEXSLDr2M4_VqVcpIgydGGK_vhSWWrsyrmIvj00MH3Dp3OkQ8gDZ2VVS8meMH-HuVwzzksmoOa35KtxmGOIx6LDwVkqnunemOmM0VzoZ3Y2mDGkSH3KdDONKaY-TQP9wDkccXlCvBKnyf7SuziHnGLv4jjckRuPp8Hd_--KHF52h-1b0exf37ebpkCleeE6r8FrXoNzNRimbN2hQ6cqYNoASORM4Nqjlt4DWN5JyZXllVIAnQaxIo9_2qWtPefQY76018Z2aRQ_j9NNQQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments</title><source>arXiv.org</source><creator>Wang, Lizi ; Ye, Hongkai ; Wang, Qianhao ; Gao, Yuman ; Xu, Chao ; Gao, Fei</creator><creatorcontrib>Wang, Lizi ; Ye, Hongkai ; Wang, Qianhao ; Gao, Yuman ; Xu, Chao ; Gao, Fei</creatorcontrib><description>In autonomous navigation of mobile robots, sensors suffer from massive occlusion in cluttered environments, leaving significant amount of space unknown during planning. In practice, treating the unknown space in optimistic or pessimistic ways both set limitations on planning performance, thus aggressiveness and safety cannot be satisfied at the same time. However, humans can infer the exact shape of the obstacles from only partial observation and generate non-conservative trajectories that avoid possible collisions in occluded space. Mimicking human behavior, in this paper, we propose a method based on deep neural network to predict occupancy distribution of unknown space reliably. Specifically, the proposed method utilizes contextual information of environments and learns from prior knowledge to predict obstacle distributions in occluded space. We use unlabeled and no-ground-truth data to train our network and successfully apply it to real-time navigation in unseen environments without any refinement. Results show that our method leverages the performance of a kinodynamic planner by improving security with no reduction of speed in clustered environments.</description><identifier>DOI: 10.48550/arxiv.2011.03981</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Computer Science - Robotics</subject><creationdate>2020-11</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2011.03981$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2011.03981$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Wang, Lizi</creatorcontrib><creatorcontrib>Ye, Hongkai</creatorcontrib><creatorcontrib>Wang, Qianhao</creatorcontrib><creatorcontrib>Gao, Yuman</creatorcontrib><creatorcontrib>Xu, Chao</creatorcontrib><creatorcontrib>Gao, Fei</creatorcontrib><title>Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments</title><description>In autonomous navigation of mobile robots, sensors suffer from massive occlusion in cluttered environments, leaving significant amount of space unknown during planning. In practice, treating the unknown space in optimistic or pessimistic ways both set limitations on planning performance, thus aggressiveness and safety cannot be satisfied at the same time. However, humans can infer the exact shape of the obstacles from only partial observation and generate non-conservative trajectories that avoid possible collisions in occluded space. Mimicking human behavior, in this paper, we propose a method based on deep neural network to predict occupancy distribution of unknown space reliably. Specifically, the proposed method utilizes contextual information of environments and learns from prior knowledge to predict obstacle distributions in occluded space. We use unlabeled and no-ground-truth data to train our network and successfully apply it to real-time navigation in unseen environments without any refinement. Results show that our method leverages the performance of a kinodynamic planner by improving security with no reduction of speed in clustered environments.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7tOwzAYRr0woMIDMOEXSLDr2M4_VqVcpIgydGGK_vhSWWrsyrmIvj00MH3Dp3OkQ8gDZ2VVS8meMH-HuVwzzksmoOa35KtxmGOIx6LDwVkqnunemOmM0VzoZ3Y2mDGkSH3KdDONKaY-TQP9wDkccXlCvBKnyf7SuziHnGLv4jjckRuPp8Hd_--KHF52h-1b0exf37ebpkCleeE6r8FrXoNzNRimbN2hQ6cqYNoASORM4Nqjlt4DWN5JyZXllVIAnQaxIo9_2qWtPefQY76018Z2aRQ_j9NNQQ</recordid><startdate>20201108</startdate><enddate>20201108</enddate><creator>Wang, Lizi</creator><creator>Ye, Hongkai</creator><creator>Wang, Qianhao</creator><creator>Gao, Yuman</creator><creator>Xu, Chao</creator><creator>Gao, Fei</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20201108</creationdate><title>Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments</title><author>Wang, Lizi ; Ye, Hongkai ; Wang, Qianhao ; Gao, Yuman ; Xu, Chao ; Gao, Fei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-ebf79f7189ee89c06d8baeae64907c995a103a2fa75ff99d1b5516d146699b793</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Lizi</creatorcontrib><creatorcontrib>Ye, Hongkai</creatorcontrib><creatorcontrib>Wang, Qianhao</creatorcontrib><creatorcontrib>Gao, Yuman</creatorcontrib><creatorcontrib>Xu, Chao</creatorcontrib><creatorcontrib>Gao, Fei</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wang, Lizi</au><au>Ye, Hongkai</au><au>Wang, Qianhao</au><au>Gao, Yuman</au><au>Xu, Chao</au><au>Gao, Fei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments</atitle><date>2020-11-08</date><risdate>2020</risdate><abstract>In autonomous navigation of mobile robots, sensors suffer from massive occlusion in cluttered environments, leaving significant amount of space unknown during planning. In practice, treating the unknown space in optimistic or pessimistic ways both set limitations on planning performance, thus aggressiveness and safety cannot be satisfied at the same time. However, humans can infer the exact shape of the obstacles from only partial observation and generate non-conservative trajectories that avoid possible collisions in occluded space. Mimicking human behavior, in this paper, we propose a method based on deep neural network to predict occupancy distribution of unknown space reliably. Specifically, the proposed method utilizes contextual information of environments and learns from prior knowledge to predict obstacle distributions in occluded space. We use unlabeled and no-ground-truth data to train our network and successfully apply it to real-time navigation in unseen environments without any refinement. Results show that our method leverages the performance of a kinodynamic planner by improving security with no reduction of speed in clustered environments.</abstract><doi>10.48550/arxiv.2011.03981</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2011.03981
ispartof
issn
language eng
recordid cdi_arxiv_primary_2011_03981
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Computer Science - Robotics
title Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T00%3A50%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Learning-based%203D%20Occupancy%20Prediction%20for%20Autonomous%20Navigation%20in%20Occluded%20Environments&rft.au=Wang,%20Lizi&rft.date=2020-11-08&rft_id=info:doi/10.48550/arxiv.2011.03981&rft_dat=%3Carxiv_GOX%3E2011_03981%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true