{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:24:38Z","timestamp":1773246278891,"version":"3.50.1"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981695","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"8652-8659","source":"Crossref","is-referenced-by-count":39,"title":["Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Eli","family":"Bronstein","sequence":"first","affiliation":[{"name":"Waymo Research"}]},{"given":"Mark","family":"Palatucci","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Dominik","family":"Notz","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Brandyn","family":"White","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Alex","family":"Kuefler","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Yiren","family":"Lu","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Supratik","family":"Paul","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Payam","family":"Nikdel","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Paul","family":"Mougin","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Hongge","family":"Chen","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Justin","family":"Fu","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Austin","family":"Abrams","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Punit","family":"Shah","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Evan","family":"Racah","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Benjamin","family":"Frenkel","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Shimon","family":"Whiteson","sequence":"additional","affiliation":[{"name":"Waymo Research"}]},{"given":"Dragomir","family":"Anguelov","sequence":"additional","affiliation":[{"name":"Waymo Research"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Reward (mis)design for autonomous driving","volume-title":"CoRR","volume":"abs\/2104.13906","author":"Knox","year":"2021"},{"key":"ref2","article-title":"ALVINN: an autonomous land vehicle in a neural network","author":"Pomerleau","year":"1989","journal-title":"Advances in neural information processing systems 1"},{"key":"ref3","article-title":"End to end learning for self-driving cars","volume-title":"CoRR","author":"Bojarski","year":"2016"},{"key":"ref4","volume-title":"Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst","author":"Bansal","year":"2018"},{"key":"ref5","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"Ross","year":"2011","journal-title":"AI Stats"},{"key":"ref6","author":"Levine","year":"2020","journal-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems"},{"key":"ref7","first-page":"390","article-title":"End-to-end differentiable adversarial imitation learning","volume-title":"International Conference on Machine Learning. PMLR","author":"Baram","year":"2017"},{"key":"ref8","author":"Swamy","year":"2021","journal-title":"Of moments and matching: A game-theoretic framework for closing the imitation gap"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811990"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196935"},{"key":"ref12","author":"Ding","year":"2019","journal-title":"Goal-conditioned imitation learning"},{"key":"ref13","author":"de Haan","year":"2019","journal-title":"Causal confusion in imitation learning"},{"key":"ref14","author":"Jain","year":"2021","journal-title":"Autonomy 2.0: Why is self-driving always 5 years away?"},{"key":"ref15","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"in Proc. 17th International Conf. on Machine Learning","author":"Ng","year":"2000"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794412"},{"key":"ref18","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"Ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref19","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"International Conference on Machine Learning","author":"Finn","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref23","author":"Ortega","year":"2021","journal-title":"Shaking the foundations: delusions in sequence models for interaction and control"},{"key":"ref24","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","author":"Fu","year":"2017","journal-title":"Learning robust rewards with adversarial inverse reinforcement learning."},{"key":"ref26","first-page":"3812","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","author":"Li","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811576"},{"key":"ref29","author":"Chen","year":"2019","journal-title":"Learning by cheating"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812107"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00291"},{"key":"ref34","author":"Rhinehart","year":"2019","journal-title":"Deep imitative models for flexible inference, planning, and control"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561123"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01417"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref39","author":"Ngiam","year":"2021","journal-title":"Scene transformer: A unified architecture for predicting multiple agent trajectories"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01026"},{"key":"ref41","volume-title":"nuplan: A closed-loop ml-based planning benchmark for autonomous vehicles","author":"Caesar","year":"2021"},{"key":"ref42","article-title":"Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving","author":"Zhou","year":"2020","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"CARLA: An open urban driving simulator","author":"Dosovitskiy","year":"2017","journal-title":"arXiv preprint"},{"key":"ref44","author":"OKelly","year":"2019","journal-title":"Scalable end-to-end autonomous vehicle testing via rare-event simulation"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref46","author":"M\u00fcller","year":"2018","journal-title":"Driving policy transfer via modularity and abstraction"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00749"},{"key":"ref48","article-title":"Perceiver: General perception with iterative attention","author":"Jaegle","year":"2021","journal-title":"ICML"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref50","first-page":"71","article-title":"Cognitive models from subcognitive skills","volume":"44","author":"Michie","year":"1990","journal-title":"IEE control engineering series"},{"key":"ref51","article-title":"Variance reduction properties of the reparameterization trick","author":"Xu","year":"2019","journal-title":"AI Stats"},{"key":"ref52","volume-title":"Computing the shortest path: A* search meets graph theory","author":"Goldberg","year":"2003"},{"key":"ref53","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197340"},{"key":"ref55","article-title":"Set transformer: A framework for attention-based permutation- invariant neural networks","author":"Lee","year":"2019","journal-title":"ICML"},{"key":"ref56","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref58","article-title":"Generative adversarial imitation from observation","author":"Torabi","year":"2018","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","volume-title":"3rd International Conference on Learning Representations, ICLR 2015","author":"Kingma","year":"2015"},{"key":"ref60","author":"Amodei","year":"2016","journal-title":"Concrete problems in ai safety"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981695.pdf?arnumber=9981695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:09:44Z","timestamp":1706767784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981695\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981695","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}