Lab2Car: A Versatile Wrapper for Deploying Experimental Planners in Complex Real-world Environments
Human-level autonomous driving is an ever-elusive goal, with planning and decision making -- the cognitive functions that determine driving behavior -- posing the greatest challenge. Despite a proliferation of promising approaches, progress is stifled by the difficulty of deploying experimental plan...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
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 | Heim, Marc Suarez-Ruiz, Francisco Bhuiyan, Ishraq Brito, Bruno Tomov, Momchil S |
description | Human-level autonomous driving is an ever-elusive goal, with planning and
decision making -- the cognitive functions that determine driving behavior --
posing the greatest challenge. Despite a proliferation of promising approaches,
progress is stifled by the difficulty of deploying experimental planners in
naturalistic settings. In this work, we propose Lab2Car, an optimization-based
wrapper that can take a trajectory sketch from an arbitrary motion planner and
convert it to a safe, comfortable, dynamically feasible trajectory that the car
can follow. This allows motion planners that do not provide such guarantees to
be safely tested and optimized in real-world environments. We demonstrate the
versatility of Lab2Car by using it to deploy a machine learning (ML) planner
and a search-based planner on self-driving cars in Las Vegas. The resulting
systems handle challenging scenarios, such as cut-ins, overtaking, and
yielding, in complex urban environments like casino pick-up/drop-off areas. Our
work paves the way for quickly deploying and evaluating candidate motion
planners in realistic settings, ensuring rapid iteration and accelerating
progress towards human-level autonomy. |
doi_str_mv | 10.48550/arxiv.2409.09523 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2409_09523</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2409_09523</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2409_095233</originalsourceid><addsrcrecordid>eNqFjr0KwkAQhK-xEPUBrNwXSDzzA8ZOYsTCQkS0DKte5GBzd2xCTN7eROytBoZvhk-I-Ur60TqO5RK51Y0fRDLxZRIH4Vg8jngPUuQNbOGquMJak4Ibo3OKobAMO-XIdtq8IGv7TpfK1EhwIjSmH4A2kNrSkWrhrJC8t2V6QmYazdYMcDUVowKpUrNfTsRin13Sg_fVyV3_idzlg1b-1Qr_Ex_2ZkNy</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Lab2Car: A Versatile Wrapper for Deploying Experimental Planners in Complex Real-world Environments</title><source>arXiv.org</source><creator>Heim, Marc ; Suarez-Ruiz, Francisco ; Bhuiyan, Ishraq ; Brito, Bruno ; Tomov, Momchil S</creator><creatorcontrib>Heim, Marc ; Suarez-Ruiz, Francisco ; Bhuiyan, Ishraq ; Brito, Bruno ; Tomov, Momchil S</creatorcontrib><description>Human-level autonomous driving is an ever-elusive goal, with planning and
decision making -- the cognitive functions that determine driving behavior --
posing the greatest challenge. Despite a proliferation of promising approaches,
progress is stifled by the difficulty of deploying experimental planners in
naturalistic settings. In this work, we propose Lab2Car, an optimization-based
wrapper that can take a trajectory sketch from an arbitrary motion planner and
convert it to a safe, comfortable, dynamically feasible trajectory that the car
can follow. This allows motion planners that do not provide such guarantees to
be safely tested and optimized in real-world environments. We demonstrate the
versatility of Lab2Car by using it to deploy a machine learning (ML) planner
and a search-based planner on self-driving cars in Las Vegas. The resulting
systems handle challenging scenarios, such as cut-ins, overtaking, and
yielding, in complex urban environments like casino pick-up/drop-off areas. Our
work paves the way for quickly deploying and evaluating candidate motion
planners in realistic settings, ensuring rapid iteration and accelerating
progress towards human-level autonomy.</description><identifier>DOI: 10.48550/arxiv.2409.09523</identifier><language>eng</language><subject>Computer Science - Robotics</subject><creationdate>2024-09</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/2409.09523$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2409.09523$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Heim, Marc</creatorcontrib><creatorcontrib>Suarez-Ruiz, Francisco</creatorcontrib><creatorcontrib>Bhuiyan, Ishraq</creatorcontrib><creatorcontrib>Brito, Bruno</creatorcontrib><creatorcontrib>Tomov, Momchil S</creatorcontrib><title>Lab2Car: A Versatile Wrapper for Deploying Experimental Planners in Complex Real-world Environments</title><description>Human-level autonomous driving is an ever-elusive goal, with planning and
decision making -- the cognitive functions that determine driving behavior --
posing the greatest challenge. Despite a proliferation of promising approaches,
progress is stifled by the difficulty of deploying experimental planners in
naturalistic settings. In this work, we propose Lab2Car, an optimization-based
wrapper that can take a trajectory sketch from an arbitrary motion planner and
convert it to a safe, comfortable, dynamically feasible trajectory that the car
can follow. This allows motion planners that do not provide such guarantees to
be safely tested and optimized in real-world environments. We demonstrate the
versatility of Lab2Car by using it to deploy a machine learning (ML) planner
and a search-based planner on self-driving cars in Las Vegas. The resulting
systems handle challenging scenarios, such as cut-ins, overtaking, and
yielding, in complex urban environments like casino pick-up/drop-off areas. Our
work paves the way for quickly deploying and evaluating candidate motion
planners in realistic settings, ensuring rapid iteration and accelerating
progress towards human-level autonomy.</description><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjr0KwkAQhK-xEPUBrNwXSDzzA8ZOYsTCQkS0DKte5GBzd2xCTN7eROytBoZvhk-I-Ur60TqO5RK51Y0fRDLxZRIH4Vg8jngPUuQNbOGquMJak4Ibo3OKobAMO-XIdtq8IGv7TpfK1EhwIjSmH4A2kNrSkWrhrJC8t2V6QmYazdYMcDUVowKpUrNfTsRin13Sg_fVyV3_idzlg1b-1Qr_Ex_2ZkNy</recordid><startdate>20240914</startdate><enddate>20240914</enddate><creator>Heim, Marc</creator><creator>Suarez-Ruiz, Francisco</creator><creator>Bhuiyan, Ishraq</creator><creator>Brito, Bruno</creator><creator>Tomov, Momchil S</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240914</creationdate><title>Lab2Car: A Versatile Wrapper for Deploying Experimental Planners in Complex Real-world Environments</title><author>Heim, Marc ; Suarez-Ruiz, Francisco ; Bhuiyan, Ishraq ; Brito, Bruno ; Tomov, Momchil S</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2409_095233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Heim, Marc</creatorcontrib><creatorcontrib>Suarez-Ruiz, Francisco</creatorcontrib><creatorcontrib>Bhuiyan, Ishraq</creatorcontrib><creatorcontrib>Brito, Bruno</creatorcontrib><creatorcontrib>Tomov, Momchil S</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Heim, Marc</au><au>Suarez-Ruiz, Francisco</au><au>Bhuiyan, Ishraq</au><au>Brito, Bruno</au><au>Tomov, Momchil S</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Lab2Car: A Versatile Wrapper for Deploying Experimental Planners in Complex Real-world Environments</atitle><date>2024-09-14</date><risdate>2024</risdate><abstract>Human-level autonomous driving is an ever-elusive goal, with planning and
decision making -- the cognitive functions that determine driving behavior --
posing the greatest challenge. Despite a proliferation of promising approaches,
progress is stifled by the difficulty of deploying experimental planners in
naturalistic settings. In this work, we propose Lab2Car, an optimization-based
wrapper that can take a trajectory sketch from an arbitrary motion planner and
convert it to a safe, comfortable, dynamically feasible trajectory that the car
can follow. This allows motion planners that do not provide such guarantees to
be safely tested and optimized in real-world environments. We demonstrate the
versatility of Lab2Car by using it to deploy a machine learning (ML) planner
and a search-based planner on self-driving cars in Las Vegas. The resulting
systems handle challenging scenarios, such as cut-ins, overtaking, and
yielding, in complex urban environments like casino pick-up/drop-off areas. Our
work paves the way for quickly deploying and evaluating candidate motion
planners in realistic settings, ensuring rapid iteration and accelerating
progress towards human-level autonomy.</abstract><doi>10.48550/arxiv.2409.09523</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2409.09523 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2409_09523 |
source | arXiv.org |
subjects | Computer Science - Robotics |
title | Lab2Car: A Versatile Wrapper for Deploying Experimental Planners in Complex Real-world Environments |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T15%3A26%3A26IST&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=Lab2Car:%20A%20Versatile%20Wrapper%20for%20Deploying%20Experimental%20Planners%20in%20Complex%20Real-world%20Environments&rft.au=Heim,%20Marc&rft.date=2024-09-14&rft_id=info:doi/10.48550/arxiv.2409.09523&rft_dat=%3Carxiv_GOX%3E2409_09523%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 |