C-MASS: Combinatorial Mobility-Aware Sensor Scheduling for Collaborative Perception with Second-Order Topology Approximation

Collaborative Perception (CP) has been a promising solution to address occlusions in the traffic environment by sharing sensor data among collaborative vehicles (CoV) via vehicle-to-everything (V2X) network. With limited wireless bandwidth, CP necessitates task-oriented and receiver-aware sensor sch...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jia, Yukuan, Sun, Yuxuan, Mao, Ruiqing, Nan, Zhaojun, Zhou, Sheng, Niu, Zhisheng
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 Jia, Yukuan
Sun, Yuxuan
Mao, Ruiqing
Nan, Zhaojun
Zhou, Sheng
Niu, Zhisheng
description Collaborative Perception (CP) has been a promising solution to address occlusions in the traffic environment by sharing sensor data among collaborative vehicles (CoV) via vehicle-to-everything (V2X) network. With limited wireless bandwidth, CP necessitates task-oriented and receiver-aware sensor scheduling to prioritize important and complementary sensor data. However, due to vehicular mobility, it is challenging and costly to obtain the up-to-date perception topology, i.e., whether a combination of CoVs can jointly detect an object. In this paper, we propose a combinatorial mobility-aware sensor scheduling (C-MASS) framework for CP with minimal communication overhead. Specifically, detections are replayed with sensor data from individual CoVs and pairs of CoVs to maintain an empirical perception topology up to the second order, which approximately represents the complete perception topology. A hybrid greedy algorithm is then proposed to solve a variant of the budgeted maximum coverage problem with a worst-case performance guarantee. The C-MASS scheduling algorithm adapts the greedy algorithm by incorporating the topological uncertainty and the unexplored time of CoVs to balance exploration and exploitation, addressing the mobility challenge. Extensive numerical experiments demonstrate the near-optimality of the proposed C-MASS framework in both edge-assisted and distributed CP configurations. The weighted recall improvements over object-level CP are 5.8% and 4.2%, respectively. Compared to distance-based and area-based greedy heuristics, the gaps to the offline optimal solutions are reduced by up to 75% and 71%, respectively.
doi_str_mv 10.48550/arxiv.2407.00412
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2407_00412</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2407_00412</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2407_004123</originalsourceid><addsrcrecordid>eNqFjrEKwjAURbM4iPoBTr4faI1aUdxKUVxEoe4lbWP7IOaFZ7QW_HiruDtdLpwDR4jxTIbRermUU8VPfITzSK5CKaPZvC9eSXCI03QDCV1ztMoTozJwoBwN-jaIG8UaUm1vxJAWtS7vBm0Fl-4mZIzKiZXHh4aT5kI7j2ShQV93TkG2DI5caoYzOTJUtRA7x_TEq_qAQ9G7KHPTo98OxGS3PSf74NuZOe44brNPb_btXfwn3tb4TQQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>C-MASS: Combinatorial Mobility-Aware Sensor Scheduling for Collaborative Perception with Second-Order Topology Approximation</title><source>arXiv.org</source><creator>Jia, Yukuan ; Sun, Yuxuan ; Mao, Ruiqing ; Nan, Zhaojun ; Zhou, Sheng ; Niu, Zhisheng</creator><creatorcontrib>Jia, Yukuan ; Sun, Yuxuan ; Mao, Ruiqing ; Nan, Zhaojun ; Zhou, Sheng ; Niu, Zhisheng</creatorcontrib><description>Collaborative Perception (CP) has been a promising solution to address occlusions in the traffic environment by sharing sensor data among collaborative vehicles (CoV) via vehicle-to-everything (V2X) network. With limited wireless bandwidth, CP necessitates task-oriented and receiver-aware sensor scheduling to prioritize important and complementary sensor data. However, due to vehicular mobility, it is challenging and costly to obtain the up-to-date perception topology, i.e., whether a combination of CoVs can jointly detect an object. In this paper, we propose a combinatorial mobility-aware sensor scheduling (C-MASS) framework for CP with minimal communication overhead. Specifically, detections are replayed with sensor data from individual CoVs and pairs of CoVs to maintain an empirical perception topology up to the second order, which approximately represents the complete perception topology. A hybrid greedy algorithm is then proposed to solve a variant of the budgeted maximum coverage problem with a worst-case performance guarantee. The C-MASS scheduling algorithm adapts the greedy algorithm by incorporating the topological uncertainty and the unexplored time of CoVs to balance exploration and exploitation, addressing the mobility challenge. Extensive numerical experiments demonstrate the near-optimality of the proposed C-MASS framework in both edge-assisted and distributed CP configurations. The weighted recall improvements over object-level CP are 5.8% and 4.2%, respectively. Compared to distance-based and area-based greedy heuristics, the gaps to the offline optimal solutions are reduced by up to 75% and 71%, respectively.</description><identifier>DOI: 10.48550/arxiv.2407.00412</identifier><language>eng</language><subject>Computer Science - Information Theory ; Computer Science - Multiagent Systems ; Computer Science - Networking and Internet Architecture ; Computer Science - Robotics ; Mathematics - Information Theory</subject><creationdate>2024-06</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2407.00412$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2407.00412$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Jia, Yukuan</creatorcontrib><creatorcontrib>Sun, Yuxuan</creatorcontrib><creatorcontrib>Mao, Ruiqing</creatorcontrib><creatorcontrib>Nan, Zhaojun</creatorcontrib><creatorcontrib>Zhou, Sheng</creatorcontrib><creatorcontrib>Niu, Zhisheng</creatorcontrib><title>C-MASS: Combinatorial Mobility-Aware Sensor Scheduling for Collaborative Perception with Second-Order Topology Approximation</title><description>Collaborative Perception (CP) has been a promising solution to address occlusions in the traffic environment by sharing sensor data among collaborative vehicles (CoV) via vehicle-to-everything (V2X) network. With limited wireless bandwidth, CP necessitates task-oriented and receiver-aware sensor scheduling to prioritize important and complementary sensor data. However, due to vehicular mobility, it is challenging and costly to obtain the up-to-date perception topology, i.e., whether a combination of CoVs can jointly detect an object. In this paper, we propose a combinatorial mobility-aware sensor scheduling (C-MASS) framework for CP with minimal communication overhead. Specifically, detections are replayed with sensor data from individual CoVs and pairs of CoVs to maintain an empirical perception topology up to the second order, which approximately represents the complete perception topology. A hybrid greedy algorithm is then proposed to solve a variant of the budgeted maximum coverage problem with a worst-case performance guarantee. The C-MASS scheduling algorithm adapts the greedy algorithm by incorporating the topological uncertainty and the unexplored time of CoVs to balance exploration and exploitation, addressing the mobility challenge. Extensive numerical experiments demonstrate the near-optimality of the proposed C-MASS framework in both edge-assisted and distributed CP configurations. The weighted recall improvements over object-level CP are 5.8% and 4.2%, respectively. Compared to distance-based and area-based greedy heuristics, the gaps to the offline optimal solutions are reduced by up to 75% and 71%, respectively.</description><subject>Computer Science - Information Theory</subject><subject>Computer Science - Multiagent Systems</subject><subject>Computer Science - Networking and Internet Architecture</subject><subject>Computer Science - Robotics</subject><subject>Mathematics - Information Theory</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjrEKwjAURbM4iPoBTr4faI1aUdxKUVxEoe4lbWP7IOaFZ7QW_HiruDtdLpwDR4jxTIbRermUU8VPfITzSK5CKaPZvC9eSXCI03QDCV1ztMoTozJwoBwN-jaIG8UaUm1vxJAWtS7vBm0Fl-4mZIzKiZXHh4aT5kI7j2ShQV93TkG2DI5caoYzOTJUtRA7x_TEq_qAQ9G7KHPTo98OxGS3PSf74NuZOe44brNPb_btXfwn3tb4TQQ</recordid><startdate>20240629</startdate><enddate>20240629</enddate><creator>Jia, Yukuan</creator><creator>Sun, Yuxuan</creator><creator>Mao, Ruiqing</creator><creator>Nan, Zhaojun</creator><creator>Zhou, Sheng</creator><creator>Niu, Zhisheng</creator><scope>AKY</scope><scope>AKZ</scope><scope>GOX</scope></search><sort><creationdate>20240629</creationdate><title>C-MASS: Combinatorial Mobility-Aware Sensor Scheduling for Collaborative Perception with Second-Order Topology Approximation</title><author>Jia, Yukuan ; Sun, Yuxuan ; Mao, Ruiqing ; Nan, Zhaojun ; Zhou, Sheng ; Niu, Zhisheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2407_004123</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Information Theory</topic><topic>Computer Science - Multiagent Systems</topic><topic>Computer Science - Networking and Internet Architecture</topic><topic>Computer Science - Robotics</topic><topic>Mathematics - Information Theory</topic><toplevel>online_resources</toplevel><creatorcontrib>Jia, Yukuan</creatorcontrib><creatorcontrib>Sun, Yuxuan</creatorcontrib><creatorcontrib>Mao, Ruiqing</creatorcontrib><creatorcontrib>Nan, Zhaojun</creatorcontrib><creatorcontrib>Zhou, Sheng</creatorcontrib><creatorcontrib>Niu, Zhisheng</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Mathematics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jia, Yukuan</au><au>Sun, Yuxuan</au><au>Mao, Ruiqing</au><au>Nan, Zhaojun</au><au>Zhou, Sheng</au><au>Niu, Zhisheng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>C-MASS: Combinatorial Mobility-Aware Sensor Scheduling for Collaborative Perception with Second-Order Topology Approximation</atitle><date>2024-06-29</date><risdate>2024</risdate><abstract>Collaborative Perception (CP) has been a promising solution to address occlusions in the traffic environment by sharing sensor data among collaborative vehicles (CoV) via vehicle-to-everything (V2X) network. With limited wireless bandwidth, CP necessitates task-oriented and receiver-aware sensor scheduling to prioritize important and complementary sensor data. However, due to vehicular mobility, it is challenging and costly to obtain the up-to-date perception topology, i.e., whether a combination of CoVs can jointly detect an object. In this paper, we propose a combinatorial mobility-aware sensor scheduling (C-MASS) framework for CP with minimal communication overhead. Specifically, detections are replayed with sensor data from individual CoVs and pairs of CoVs to maintain an empirical perception topology up to the second order, which approximately represents the complete perception topology. A hybrid greedy algorithm is then proposed to solve a variant of the budgeted maximum coverage problem with a worst-case performance guarantee. The C-MASS scheduling algorithm adapts the greedy algorithm by incorporating the topological uncertainty and the unexplored time of CoVs to balance exploration and exploitation, addressing the mobility challenge. Extensive numerical experiments demonstrate the near-optimality of the proposed C-MASS framework in both edge-assisted and distributed CP configurations. The weighted recall improvements over object-level CP are 5.8% and 4.2%, respectively. Compared to distance-based and area-based greedy heuristics, the gaps to the offline optimal solutions are reduced by up to 75% and 71%, respectively.</abstract><doi>10.48550/arxiv.2407.00412</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2407.00412
ispartof
issn
language eng
recordid cdi_arxiv_primary_2407_00412
source arXiv.org
subjects Computer Science - Information Theory
Computer Science - Multiagent Systems
Computer Science - Networking and Internet Architecture
Computer Science - Robotics
Mathematics - Information Theory
title C-MASS: Combinatorial Mobility-Aware Sensor Scheduling for Collaborative Perception with Second-Order Topology Approximation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T20%3A57%3A45IST&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=C-MASS:%20Combinatorial%20Mobility-Aware%20Sensor%20Scheduling%20for%20Collaborative%20Perception%20with%20Second-Order%20Topology%20Approximation&rft.au=Jia,%20Yukuan&rft.date=2024-06-29&rft_id=info:doi/10.48550/arxiv.2407.00412&rft_dat=%3Carxiv_GOX%3E2407_00412%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