ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving Article Swipe
Yongming Chen
,
Miner Chen
,
Lei Liao
,
Mingyang Jiang
,
Xiang Zuo
,
Hengrui Zhang
,
Yuchen Xi
,
Songan Zhang
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2505.24317
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2505.24317
Reinforcement learning (RL) in autonomous driving employs a trial-and-error mechanism, enhancing robustness in unpredictable environments. However, crafting effective reward functions remains challenging, as conventional approaches rely heavily on manual design and demonstrate limited efficacy in complex scenarios. To address this issue, this study introduces a responsibility-oriented reward function that explicitly incorporates traffic regulations into the RL framework. Specifically, we introduced a Traffic Regulation Knowledge Graph and leveraged Vision-Language Models alongside Retrieval-Augmented Generation techniques to automate reward assignment. This integration guides agents to adhere strictly to traffic laws, thus minimizing rule violations and optimizing decision-making performance in diverse driving conditions. Experimental validations demonstrate that the proposed methodology significantly improves the accuracy of assigning accident responsibilities and effectively reduces the agent's liability in traffic incidents.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2505.24317
- https://arxiv.org/pdf/2505.24317
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4414856909
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414856909Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2505.24317Digital Object Identifier
- Title
-
ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous DrivingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-05-30Full publication date if available
- Authors
-
Yongming Chen, Miner Chen, Lei Liao, Mingyang Jiang, Xiang Zuo, Hengrui Zhang, Yuchen Xi, Songan ZhangList of authors in order
- Landing page
-
https://arxiv.org/abs/2505.24317Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2505.24317Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2505.24317Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4414856909 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2505.24317 |
| ids.doi | https://doi.org/10.48550/arxiv.2505.24317 |
| ids.openalex | https://openalex.org/W4414856909 |
| fwci | |
| type | preprint |
| title | ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11099 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9502999782562256 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2203 |
| topics[0].subfield.display_name | Automotive Engineering |
| topics[0].display_name | Autonomous Vehicle Technology and Safety |
| topics[1].id | https://openalex.org/T11942 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9059000015258789 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2203 |
| topics[1].subfield.display_name | Automotive Engineering |
| topics[1].display_name | Transportation and Mobility Innovations |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2505.24317 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2505.24317 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2505.24317 |
| locations[1].id | doi:10.48550/arxiv.2505.24317 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2505.24317 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5067072385 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-4929-8157 |
| authorships[0].author.display_name | Yongming Chen |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Chen, Yongming |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5085539385 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Miner Chen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chen, Miner |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5036022527 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1325-2410 |
| authorships[2].author.display_name | Lei Liao |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Liao, Liewen |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5049630943 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-1127-4838 |
| authorships[3].author.display_name | Mingyang Jiang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jiang, Mingyang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5101154793 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Xiang Zuo |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zuo, Xiang |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5002532818 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Hengrui Zhang |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zhang, Hengrui |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5102837064 |
| authorships[6].author.orcid | https://orcid.org/0009-0003-2982-955X |
| authorships[6].author.display_name | Yuchen Xi |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Xi, Yuchen |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5045427668 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-3238-5406 |
| authorships[7].author.display_name | Songan Zhang |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Zhang, Songan |
| authorships[7].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2505.24317 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11099 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9502999782562256 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2203 |
| primary_topic.subfield.display_name | Automotive Engineering |
| primary_topic.display_name | Autonomous Vehicle Technology and Safety |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2505.24317 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2505.24317 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2505.24317 |
| primary_location.id | pmh:oai:arXiv.org:2505.24317 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2505.24317 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2505.24317 |
| publication_date | 2025-05-30 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 7, 44, 60 |
| abstract_inverted_index.RL | 55 |
| abstract_inverted_index.To | 37 |
| abstract_inverted_index.as | 22 |
| abstract_inverted_index.in | 3, 12, 34, 95, 120 |
| abstract_inverted_index.of | 110 |
| abstract_inverted_index.on | 27 |
| abstract_inverted_index.to | 73, 81, 84 |
| abstract_inverted_index.we | 58 |
| abstract_inverted_index.and | 30, 65, 91, 114 |
| abstract_inverted_index.the | 54, 103, 108, 117 |
| abstract_inverted_index.(RL) | 2 |
| abstract_inverted_index.This | 77 |
| abstract_inverted_index.into | 53 |
| abstract_inverted_index.rely | 25 |
| abstract_inverted_index.rule | 89 |
| abstract_inverted_index.that | 48, 102 |
| abstract_inverted_index.this | 39, 41 |
| abstract_inverted_index.thus | 87 |
| abstract_inverted_index.Graph | 64 |
| abstract_inverted_index.laws, | 86 |
| abstract_inverted_index.study | 42 |
| abstract_inverted_index.Models | 68 |
| abstract_inverted_index.adhere | 82 |
| abstract_inverted_index.agents | 80 |
| abstract_inverted_index.design | 29 |
| abstract_inverted_index.guides | 79 |
| abstract_inverted_index.issue, | 40 |
| abstract_inverted_index.manual | 28 |
| abstract_inverted_index.reward | 18, 46, 75 |
| abstract_inverted_index.Traffic | 61 |
| abstract_inverted_index.address | 38 |
| abstract_inverted_index.agent's | 118 |
| abstract_inverted_index.complex | 35 |
| abstract_inverted_index.diverse | 96 |
| abstract_inverted_index.driving | 5, 97 |
| abstract_inverted_index.employs | 6 |
| abstract_inverted_index.heavily | 26 |
| abstract_inverted_index.limited | 32 |
| abstract_inverted_index.reduces | 116 |
| abstract_inverted_index.remains | 20 |
| abstract_inverted_index.traffic | 51, 85, 121 |
| abstract_inverted_index.However, | 15 |
| abstract_inverted_index.accident | 112 |
| abstract_inverted_index.accuracy | 109 |
| abstract_inverted_index.automate | 74 |
| abstract_inverted_index.crafting | 16 |
| abstract_inverted_index.efficacy | 33 |
| abstract_inverted_index.function | 47 |
| abstract_inverted_index.improves | 107 |
| abstract_inverted_index.learning | 1 |
| abstract_inverted_index.proposed | 104 |
| abstract_inverted_index.strictly | 83 |
| abstract_inverted_index.Knowledge | 63 |
| abstract_inverted_index.alongside | 69 |
| abstract_inverted_index.assigning | 111 |
| abstract_inverted_index.effective | 17 |
| abstract_inverted_index.enhancing | 10 |
| abstract_inverted_index.functions | 19 |
| abstract_inverted_index.leveraged | 66 |
| abstract_inverted_index.liability | 119 |
| abstract_inverted_index.Generation | 71 |
| abstract_inverted_index.Regulation | 62 |
| abstract_inverted_index.approaches | 24 |
| abstract_inverted_index.autonomous | 4 |
| abstract_inverted_index.explicitly | 49 |
| abstract_inverted_index.framework. | 56 |
| abstract_inverted_index.incidents. | 122 |
| abstract_inverted_index.introduced | 59 |
| abstract_inverted_index.introduces | 43 |
| abstract_inverted_index.mechanism, | 9 |
| abstract_inverted_index.minimizing | 88 |
| abstract_inverted_index.optimizing | 92 |
| abstract_inverted_index.robustness | 11 |
| abstract_inverted_index.scenarios. | 36 |
| abstract_inverted_index.techniques | 72 |
| abstract_inverted_index.violations | 90 |
| abstract_inverted_index.assignment. | 76 |
| abstract_inverted_index.conditions. | 98 |
| abstract_inverted_index.demonstrate | 31, 101 |
| abstract_inverted_index.effectively | 115 |
| abstract_inverted_index.integration | 78 |
| abstract_inverted_index.methodology | 105 |
| abstract_inverted_index.performance | 94 |
| abstract_inverted_index.regulations | 52 |
| abstract_inverted_index.validations | 100 |
| abstract_inverted_index.Experimental | 99 |
| abstract_inverted_index.challenging, | 21 |
| abstract_inverted_index.conventional | 23 |
| abstract_inverted_index.incorporates | 50 |
| abstract_inverted_index.Reinforcement | 0 |
| abstract_inverted_index.Specifically, | 57 |
| abstract_inverted_index.environments. | 14 |
| abstract_inverted_index.significantly | 106 |
| abstract_inverted_index.unpredictable | 13 |
| abstract_inverted_index.Vision-Language | 67 |
| abstract_inverted_index.decision-making | 93 |
| abstract_inverted_index.trial-and-error | 8 |
| abstract_inverted_index.responsibilities | 113 |
| abstract_inverted_index.Retrieval-Augmented | 70 |
| abstract_inverted_index.responsibility-oriented | 45 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile |