{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:41:47Z","timestamp":1773772907440,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,5]],"date-time":"2024-10-05T00:00:00Z","timestamp":1728086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation (NSF)","award":["NSF Cooper- ative Agreement EEC-2133516"],"award-info":[{"award-number":["NSF Cooper- ative Agreement EEC-2133516"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,5]]},"DOI":"10.1145\/3675094.3677588","type":"proceedings-article","created":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:31:48Z","timestamp":1726965108000},"page":"76-80","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-0164","authenticated-orcid":false,"given":"Yuan","family":"Sun","sequence":"first","affiliation":[{"name":"Rutgers University, WINLAB, Rutgers University, Piscataway, New Jersey, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7295-5813","authenticated-orcid":false,"given":"Navid","family":"Salami Pargoo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rutgers University, New Brunswick, New Jersey, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7688-3730","authenticated-orcid":false,"given":"Peter","family":"Jin","sequence":"additional","affiliation":[{"name":"Civil and Environmental Engineering, Rutgers, The State University of New Jersey, Piscataway, New Jersey, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3325-1298","authenticated-orcid":false,"given":"Jorge","family":"Ortiz","sequence":"additional","affiliation":[{"name":"Electrical Computer Engineering, Rutgers University, Piscataway, New Jersey, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,10,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"DriveLLM: Charting the path toward full autonomous driving with large language models","author":"Cui Yaodong","year":"2023","unstructured":"Yaodong Cui, Shucheng Huang, Jiaming Zhong, Zhenan Liu, YutongWang, Chen Sun, Bai Li, XiaoWang, and Amir Khajepour. 2023. DriveLLM: Charting the path toward full autonomous driving with large language models. IEEE Transactions on Intelligent Vehicles (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Prompting Multi-Modal Tokens to Enhance End-to-End Autonomous Driving Imitation Learning with LLMs. arXiv preprint arXiv:2404.04869","author":"Duan Yiqun","year":"2024","unstructured":"Yiqun Duan, Qiang Zhang, and Renjing Xu. 2024. Prompting Multi-Modal Tokens to Enhance End-to-End Autonomous Driving Imitation Learning with LLMs. arXiv preprint arXiv:2404.04869 (2024)."},{"key":"e_1_3_2_1_3_1","unstructured":"Center for Advanced Infrastructure and Transportation. 2024. DataCity Smart Mobility Testing Ground. https:\/\/cait.rutgers.edu\/datacity\/ Accessed: 2024-05--26."},{"key":"e_1_3_2_1_4_1","volume-title":"LimSim: A Closed-Loop Platform for Deploying Multimodal LLMs in Autonomous Driving. arXiv preprint arXiv:2402.01246","author":"Fu Daocheng","year":"2024","unstructured":"Daocheng Fu,Wenjie Lei, LichengWen, Pinlong Cai, Song Mao, Min Dou, Botian Shi, and Yu Qiao. 2024. LimSim: A Closed-Loop Platform for Deploying Multimodal LLMs in Autonomous Driving. arXiv preprint arXiv:2402.01246 (2024)."},{"key":"e_1_3_2_1_5_1","unstructured":"Christopher Galias Adam Jakubowski Henryk Michalewski. 2019. Simulation-based reinforcement learning for autonomous driving. (2019)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569568"},{"key":"e_1_3_2_1_7_1","volume-title":"Understanding the effects of rlhf on llm generalisation and diversity. arXiv preprint arXiv:2310.06452","author":"Kirk Robert","year":"2023","unstructured":"Robert Kirk, Ishita Mediratta, Christoforos Nalmpantis, Jelena Luketina, Eric Hambro, Edward Grefenstette, and Roberta Raileanu. 2023. Understanding the effects of rlhf on llm generalisation and diversity. arXiv preprint arXiv:2310.06452 (2023)."},{"key":"e_1_3_2_1_8_1","unstructured":"COSMOS Lab. 2024. COSMOS Lab. https:\/\/cosmos-lab.org\/ Accessed: 2024-05--26."},{"key":"e_1_3_2_1_9_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap Timothy P","year":"2015","unstructured":"Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)."},{"key":"e_1_3_2_1_10_1","unstructured":"Jimuyang Zhang Zanming Huang Arijit Ray and Eshed Ohn-Bar. [n. d.]. Feedback- Guided Autonomous Driving. ([n. d.])."},{"key":"e_1_3_2_1_11_1","unstructured":"Stuart J Russell and Peter Norvig. 2016. Artificial intelligence: a modern approach. Pearson."},{"key":"e_1_3_2_1_12_1","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon Nisan","year":"2020","unstructured":"Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learning to summarize with human feedback. Advances in Neural Information Processing Systems 33 (2020), 3008--3021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","volume-title":"Reinforcement learning in the era of llms: What is essential? what is needed? an rl perspective on rlhf, prompting, and beyond. arXiv preprint arXiv:2310.06147","author":"Sun Hao","year":"2023","unstructured":"Hao Sun. 2023. Reinforcement learning in the era of llms: What is essential? what is needed? an rl perspective on rlhf, prompting, and beyond. arXiv preprint arXiv:2310.06147 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Language conditioned traffic generation. arXiv preprint arXiv:2307.07947","author":"Tan Shuhan","year":"2023","unstructured":"Shuhan Tan, Boris Ivanovic, Xinshuo Weng, Marco Pavone, and Philipp Kraehenbuehl. 2023. Language conditioned traffic generation. arXiv preprint arXiv:2307.07947 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Efficient reinforcement learning for autonomous driving with parameterized skills and priors. arXiv preprint arXiv:2305.04412","author":"Wang Letian","year":"2023","unstructured":"Letian Wang, Jie Liu, Hao Shao, Wenshuo Wang, Ruobing Chen, Yu Liu, and Steven L Waslander. 2023. Efficient reinforcement learning for autonomous driving with parameterized skills and priors. arXiv preprint arXiv:2305.04412 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering. 1--4.","author":"Sheng Zhuheng","year":"2022","unstructured":"SenWang, Zhuheng Sheng, Jingwei Xu, Taolue Chen, Junjun Zhu, Shuhui Zhang, Yuan Yao, and Xiaoxing Ma. 2022. ADEPT: A testing platform for simulated autonomous driving. In Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering. 1--4."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 22nd International Conference on Information Processing in Sensor Networks. 332--333","author":"Wu Tong","year":"2023","unstructured":"Tong Wu, Navid Salami Pargoo, and Jorge Ortiz. 2023. Multi-sensor Fusion for In-cabin Vehicular Sensing Applications. In Proceedings of the 22nd International Conference on Information Processing in Sensor Networks. 332--333."},{"key":"e_1_3_2_1_18_1","volume-title":"Enhancing Conversational LLMs with Direct RLHF. arXiv preprint arXiv:2403.02513","author":"Zheng Chen","year":"2024","unstructured":"Chen Zheng, Ke Sun, Hang Wu, Chenguang Xi, and Xun Zhou. 2024. Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF. arXiv preprint arXiv:2403.02513 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Machine Learning. PMLR, 43037--43067","author":"Zhu Banghua","year":"2023","unstructured":"Banghua Zhu, Michael Jordan, and Jiantao Jiao. 2023. Principled reinforcement learning with human feedback from pairwise or k-wise comparisons. In International Conference on Machine Learning. PMLR, 43037--43067."},{"key":"e_1_3_2_1_20_1","volume-title":"Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593","author":"Ziegler Daniel M","year":"2019","unstructured":"Daniel M Ziegler, Nisan Stiennon, JeffreyWu, Tom B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2019. Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593 (2019)."}],"event":{"name":"UbiComp '24: The 2024 ACM International Joint Conference on Pervasive and Ubiquitous Computing","location":"Melbourne VIC Australia","acronym":"UbiComp '24","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGSPATIAL ACM Special Interest Group on Spatial Information"]},"container-title":["Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3675094.3677588","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3675094.3677588","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:03:48Z","timestamp":1755839028000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3675094.3677588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,5]]},"references-count":20,"alternative-id":["10.1145\/3675094.3677588","10.1145\/3675094"],"URL":"https:\/\/doi.org\/10.1145\/3675094.3677588","relation":{},"subject":[],"published":{"date-parts":[[2024,10,5]]},"assertion":[{"value":"2024-10-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}