{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:21:35Z","timestamp":1776183695729,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610272","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"18355-18361","source":"Crossref","is-referenced-by-count":3,"title":["Uncertainty-aware Reinforcement Learning for Autonomous Driving with Multimodal Digital Driver Guidance"],"prefix":"10.1109","author":[{"given":"Wenhui","family":"Huang","sequence":"first","affiliation":[{"name":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zitong","family":"Shan","sequence":"additional","affiliation":[{"name":"Jilin University,State Key Laboratory of Automotive Simulation and Control,Changchun,China,130022"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanhe","family":"Lou","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Lv","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2023.10.005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3312453"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref5","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref6","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref8","author":"Abel","year":"2017","journal-title":"Agent-agnostic human-in-the-loop reinforcement learning"},{"key":"ref9","first-page":"2067","article-title":"Trial without error: Towards safe reinforcement learning via human intervention","volume-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","author":"Saunders"},{"key":"ref10","first-page":"410","article-title":"Intervention aided reinforcement learning for safe and practical policy optimization in navigation","volume-title":"Conference on Robot Learning","author":"Wang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060404"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2019.00220"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.055"},{"key":"ref14","article-title":"Efficient learning of safe driving policy via human-ai copilot optimization","volume-title":"International Conference on Learning Representations","author":"Li"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3177685"},{"key":"ref16","first-page":"1554","article-title":"Safe driving via expert guided policy optimization","volume-title":"Conference on Robot Learning","author":"Peng"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2019-97884"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322426"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462978"},{"key":"ref21","author":"Michelmore","year":"2018","journal-title":"Evaluating uncertainty quantification in end-to-end autonomous driving control"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968307"},{"key":"ref23","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy"},{"key":"ref24","article-title":"Uncertainty-aware model-based reinforcement learning: methodology and application in autonomous driving","author":"Wu","year":"2022","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"ref25","volume-title":"Reinforcement learning: An introduction.","author":"Sutton","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3134702"},{"key":"ref27","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref28","article-title":"Understanding the relation between maximum-entropy inverse reinforcement learning and behaviour cloning","author":"Ghasemipour","year":"2019"},{"key":"ref29","article-title":"Reverse kl-divergence training of prior networks: Improved uncertainty and adversarial robustness","volume":"32","author":"Malinin","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66723-8_19"},{"key":"ref31","first-page":"1183","article-title":"Deep bayesian active learning with image data","volume-title":"International conference on machine learning","author":"Gal"},{"key":"ref32","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"Lakshminarayanan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3317628"},{"key":"ref34","article-title":"Multi-task learning as multi-objective optimization","volume":"31","author":"Sener","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref35","author":"Ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref36","article-title":"Towards stabilizing batch statistics in backward propagation of batch normalization","volume-title":"International Conference on Learning Representations","author":"Yan"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref38","author":"Zhou","year":"2020","journal-title":"Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving"},{"key":"ref39","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Wang"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610272.pdf?arnumber=10610272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:46:44Z","timestamp":1723268804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610272","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}