{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:44:38Z","timestamp":1730270678441,"version":"3.28.0"},"reference-count":41,"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:\/\/2.zoppoz.workers.dev:443\/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:\/\/2.zoppoz.workers.dev:443\/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\/iros47612.2022.9981223","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T14:38:15Z","timestamp":1672065495000},"page":"7635-7642","source":"Crossref","is-referenced-by-count":0,"title":["Risk-sensitive MPCs with Deep Distributional Inverse RL for Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Keuntaek","family":"Lee","sequence":"first","affiliation":[{"name":"Amazon Robotics AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Isele","sequence":"additional","affiliation":[{"name":"Honda Research Institute USA, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evangelos A.","family":"Theodorou","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangjae","family":"Bae","sequence":"additional","affiliation":[{"name":"Honda Research Institute USA, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICRA40945.2020.9197132"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/IVS.2015.7225830"},{"key":"ref12","article-title":"Model-predictive policy learning with uncertainty regularization for driving in dense traffic","author":"henaff","year":"0","journal-title":"International Conference on Learning Representations 2019"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/ICRA48506.2021.9560916"},{"key":"ref15","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"0","journal-title":"Proc AAAI"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1103\/PhysRevE.62.1805"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.23919\/ACC45564.2020.9147837"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref31","article-title":"Perceptual attention-based predictive control","author":"lee","year":"2019","journal-title":"3rd Conference on Robot Learning (CoRL)"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/ICMLA.2019.00145"},{"key":"ref11","article-title":"Imitation learning for agile autonomous driving","author":"pan","year":"2019","journal-title":"International Journal of Robotics Research (IJRR)"},{"key":"ref33","article-title":"Aggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control","author":"drews","year":"2017","journal-title":"1st Conference on Robot Learning"},{"key":"ref10","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/ICRA.2019.8794189"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1145\/1015330.1015430"},{"key":"ref1","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proceedings of the 17th International Conference on Machine Learning 06"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1177\/0278364917722396"},{"key":"ref39","first-page":"7","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"2015","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"year":"2016","author":"wulfmeier","journal-title":"Watch this Scalable cost-function learning for path planning in urban environments","key":"ref16"},{"key":"ref38","article-title":"Intelligence Laboratory","author":"artificial","year":"0","journal-title":"The Robot Operating System"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/LRA.2021.3059628"},{"key":"ref18","first-page":"894","article-title":"Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories","author":"zhang","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref24","first-page":"510","article-title":"Adaptive risk sensitive model predictive control with stochastic search","volume":"144","author":"wang","year":"0","journal-title":"Proceedings of the 3rd Conference on Learning for Dynamics and Control"},{"key":"ref23","first-page":"958","article-title":"Improving robustness via risk averse distributional reinforcement learning","volume":"120","author":"singh","year":"0","journal-title":"Proceedings of the 2nd Conference on Learning for Dynamics and Control"},{"key":"ref26","article-title":"Weight uncertainty in neural networks","volume":"37","author":"blundell","year":"2015","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1103\/PhysRev.106.620"},{"key":"ref20","article-title":"Scaling up robust mdps using function approximation","volume":"32","author":"tamar","year":"2014","journal-title":"Proceedings of the"},{"key":"ref41","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref22","article-title":"Worst cases policy gradients","author":"tang","year":"2019","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref21","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"chow","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref28","article-title":"Simple and scalable predic-tive uncertainty estimation using deep ensembles","author":"lakshminarayanan","year":"0","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems 2017"},{"key":"ref27","first-page":"1050","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"0","journal-title":"Proceedings of the 33rd International Conference on Machine Learning - Volume"},{"key":"ref29","first-page":"5580","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","author":"kendall","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/LRA.2022.3146635"},{"key":"ref7","article-title":"Maximum entropy deep inverse reinforement learning","author":"wulfmeier","year":"0","journal-title":"Neural Information Processing Systems Conference Deep Reinforcement Learning Workshop"},{"key":"ref9","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning - Volume 70"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICRA.2019.8793721"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref6","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"Proceedings of the 1st Annual Conference on Robot Learning"},{"key":"ref5","first-page":"66","article-title":"Learning by cheating","author":"chen","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref40","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2014","journal-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR)"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981223.pdf?arnumber=9981223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T17:36:18Z","timestamp":1701279378000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/9981223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":41,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/iros47612.2022.9981223","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}