Traffic-Aware Autonomous Driving with Differentiable Traffic Simulation

While there have been advancements in autonomous driving control and traffic simulation, there have been little to no works exploring their unification with deep learning. Works in both areas seem to focus on entirely different exclusive problems, yet traffic and driving are inherently related in th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zheng, Laura, Son, Sanghyun, Lin, Ming C
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 Zheng, Laura
Son, Sanghyun
Lin, Ming C
description While there have been advancements in autonomous driving control and traffic simulation, there have been little to no works exploring their unification with deep learning. Works in both areas seem to focus on entirely different exclusive problems, yet traffic and driving are inherently related in the real world. In this paper, we present Traffic-Aware Autonomous Driving (TrAAD), a generalizable distillation-style method for traffic-informed imitation learning that directly optimizes for faster traffic flow and lower energy consumption. TrAAD focuses on the supervision of speed control in imitation learning systems, as most driving research focuses on perception and steering. Moreover, our method addresses the lack of co-simulation between traffic and driving simulators and provides a basis for directly involving traffic simulation with autonomous driving in future work. Our results show that, with information from traffic simulation involved in the supervision of imitation learning methods, an autonomous vehicle can learn how to accelerate in a fashion that is beneficial for traffic flow and overall energy consumption for all nearby vehicles.
doi_str_mv 10.48550/arxiv.2210.03772
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_03772</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_03772</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-8eeb63e970ee7ca514cc9b7c2679d7df03314b8ea88e772374ec2024c4e77cba3</originalsourceid><addsrcrecordid>eNotj8tuwjAURL3poqJ8QFf1D4Q6thM7ywhaWgmJRbOPrs01XCmPyiQ8_p6UshrNSDOaw9hrKhbaZpl4h3ih00LKKRDKGPnM1lWEEMgn5Rki8nIc-q5v-_HIV5FO1O35mYYDX1EIGLEbCFyD_FHiP9SODQzUdy_sKUBzxPlDZ6z6_KiWX8lmu_5elpsEciMTi-hyhYURiMZDlmrvC2e8zE2xM7sglEq1swjW4nRPGY1eCqm9nqx3oGbs7X_2TlL_RmohXus_ovpOpG6nNEcO</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Traffic-Aware Autonomous Driving with Differentiable Traffic Simulation</title><source>arXiv.org</source><creator>Zheng, Laura ; Son, Sanghyun ; Lin, Ming C</creator><creatorcontrib>Zheng, Laura ; Son, Sanghyun ; Lin, Ming C</creatorcontrib><description>While there have been advancements in autonomous driving control and traffic simulation, there have been little to no works exploring their unification with deep learning. Works in both areas seem to focus on entirely different exclusive problems, yet traffic and driving are inherently related in the real world. In this paper, we present Traffic-Aware Autonomous Driving (TrAAD), a generalizable distillation-style method for traffic-informed imitation learning that directly optimizes for faster traffic flow and lower energy consumption. TrAAD focuses on the supervision of speed control in imitation learning systems, as most driving research focuses on perception and steering. Moreover, our method addresses the lack of co-simulation between traffic and driving simulators and provides a basis for directly involving traffic simulation with autonomous driving in future work. Our results show that, with information from traffic simulation involved in the supervision of imitation learning methods, an autonomous vehicle can learn how to accelerate in a fashion that is beneficial for traffic flow and overall energy consumption for all nearby vehicles.</description><identifier>DOI: 10.48550/arxiv.2210.03772</identifier><language>eng</language><subject>Computer Science - Multiagent Systems ; Computer Science - Robotics</subject><creationdate>2022-10</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</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/2210.03772$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.03772$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Zheng, Laura</creatorcontrib><creatorcontrib>Son, Sanghyun</creatorcontrib><creatorcontrib>Lin, Ming C</creatorcontrib><title>Traffic-Aware Autonomous Driving with Differentiable Traffic Simulation</title><description>While there have been advancements in autonomous driving control and traffic simulation, there have been little to no works exploring their unification with deep learning. Works in both areas seem to focus on entirely different exclusive problems, yet traffic and driving are inherently related in the real world. In this paper, we present Traffic-Aware Autonomous Driving (TrAAD), a generalizable distillation-style method for traffic-informed imitation learning that directly optimizes for faster traffic flow and lower energy consumption. TrAAD focuses on the supervision of speed control in imitation learning systems, as most driving research focuses on perception and steering. Moreover, our method addresses the lack of co-simulation between traffic and driving simulators and provides a basis for directly involving traffic simulation with autonomous driving in future work. Our results show that, with information from traffic simulation involved in the supervision of imitation learning methods, an autonomous vehicle can learn how to accelerate in a fashion that is beneficial for traffic flow and overall energy consumption for all nearby vehicles.</description><subject>Computer Science - Multiagent Systems</subject><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tuwjAURL3poqJ8QFf1D4Q6thM7ywhaWgmJRbOPrs01XCmPyiQ8_p6UshrNSDOaw9hrKhbaZpl4h3ih00LKKRDKGPnM1lWEEMgn5Rki8nIc-q5v-_HIV5FO1O35mYYDX1EIGLEbCFyD_FHiP9SODQzUdy_sKUBzxPlDZ6z6_KiWX8lmu_5elpsEciMTi-hyhYURiMZDlmrvC2e8zE2xM7sglEq1swjW4nRPGY1eCqm9nqx3oGbs7X_2TlL_RmohXus_ovpOpG6nNEcO</recordid><startdate>20221007</startdate><enddate>20221007</enddate><creator>Zheng, Laura</creator><creator>Son, Sanghyun</creator><creator>Lin, Ming C</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221007</creationdate><title>Traffic-Aware Autonomous Driving with Differentiable Traffic Simulation</title><author>Zheng, Laura ; Son, Sanghyun ; Lin, Ming C</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-8eeb63e970ee7ca514cc9b7c2679d7df03314b8ea88e772374ec2024c4e77cba3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Multiagent Systems</topic><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Zheng, Laura</creatorcontrib><creatorcontrib>Son, Sanghyun</creatorcontrib><creatorcontrib>Lin, Ming C</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zheng, Laura</au><au>Son, Sanghyun</au><au>Lin, Ming C</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Traffic-Aware Autonomous Driving with Differentiable Traffic Simulation</atitle><date>2022-10-07</date><risdate>2022</risdate><abstract>While there have been advancements in autonomous driving control and traffic simulation, there have been little to no works exploring their unification with deep learning. Works in both areas seem to focus on entirely different exclusive problems, yet traffic and driving are inherently related in the real world. In this paper, we present Traffic-Aware Autonomous Driving (TrAAD), a generalizable distillation-style method for traffic-informed imitation learning that directly optimizes for faster traffic flow and lower energy consumption. TrAAD focuses on the supervision of speed control in imitation learning systems, as most driving research focuses on perception and steering. Moreover, our method addresses the lack of co-simulation between traffic and driving simulators and provides a basis for directly involving traffic simulation with autonomous driving in future work. Our results show that, with information from traffic simulation involved in the supervision of imitation learning methods, an autonomous vehicle can learn how to accelerate in a fashion that is beneficial for traffic flow and overall energy consumption for all nearby vehicles.</abstract><doi>10.48550/arxiv.2210.03772</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.03772
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_03772
source arXiv.org
subjects Computer Science - Multiagent Systems
Computer Science - Robotics
title Traffic-Aware Autonomous Driving with Differentiable Traffic Simulation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T16%3A46%3A39IST&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=Traffic-Aware%20Autonomous%20Driving%20with%20Differentiable%20Traffic%20Simulation&rft.au=Zheng,%20Laura&rft.date=2022-10-07&rft_id=info:doi/10.48550/arxiv.2210.03772&rft_dat=%3Carxiv_GOX%3E2210_03772%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