{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:48:22Z","timestamp":1762508902708,"version":"3.37.3"},"reference-count":45,"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"}],"funder":[{"DOI":"10.13039\/100010663","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004063","name":"Knut and Alice Wallenberg Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981540","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"13392-13399","source":"Crossref","is-referenced-by-count":3,"title":["Embedding Koopman Optimal Control in Robot Policy Learning"],"prefix":"10.1109","author":[{"given":"Hang","family":"Yin","sequence":"first","affiliation":[{"name":"CAS\/RPL, KTH Royal Institute of Technology,Stockholm,Sweden"}]},{"given":"Michael C.","family":"Welle","sequence":"additional","affiliation":[{"name":"CAS\/RPL, KTH Royal Institute of Technology,Stockholm,Sweden"}]},{"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[{"name":"CAS\/RPL, KTH Royal Institute of Technology,Stockholm,Sweden"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911402527"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011379"},{"key":"ref4","article-title":"Plenary lecture: Embedded convex optimization for control","volume-title":"Conference on Decision and Control (CDC)","author":"Boyd","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2012.00097"},{"key":"ref6","article-title":"Path integral networks: End-to-end differentiable optimal control","volume":"abs\/1706.09597","author":"Okada","year":"2017","journal-title":"CoRR"},{"key":"ref7","first-page":"4739","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","volume":"80","author":"Srinivas","year":"2018"},{"key":"ref8","article-title":"Differentiable MPC for End-to-end Planning and Control","author":"Amos","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"361","article-title":"Learning convex optimization control policies","volume-title":"Proceedings of the 2nd Conference on Learning for Dynamics and Control","volume":"120","author":"Agrawal","year":"Jun 2020"},{"key":"ref10","first-page":"7979","article-title":"Pontryagin differentiable programming: An end-to-end learning and control framework","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Jin","year":"2020"},{"key":"ref11","article-title":"Differentiable convex optimization layers","author":"Agrawal","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.17.5.315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3076581"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3038693"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353496"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3028529"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562071"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3111962"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264429"},{"key":"ref20","article-title":"Differentiable robust LQR layers","volume":"abs\/2106.05535","author":"Vien","year":"2021","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561083"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/16M1062296"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.03.046"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2978039"},{"key":"ref25","article-title":"Learning data-driven stable koopman operators","volume-title":"Advances in Neural Information Processing Systems","author":"Mamakoukas","year":"2020"},{"key":"ref26","article-title":"A recurrent latent variable model for sequential data","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Chung","year":"2015"},{"key":"ref27","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Watter","year":"2015"},{"article-title":"Deep variational bayes filters: Unsupervised learning of state space models from raw data","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"Karl","key":"ref28"},{"key":"ref29","article-title":"Predictive coding for locally-linear control","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Shu","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00443"},{"key":"ref31","article-title":"Learning koopman invariant subspaces for dynamic mode decomposition","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Takeishi","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-07210-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815339"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/440"},{"key":"ref35","article-title":"Learning compositional koopman operators for model-based control","volume-title":"International Conference on Learning Representations","author":"Li","year":"2020"},{"key":"ref36","article-title":"Deep lagrangian networks: Using physics as model prior for deep learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lutter","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref38","article-title":"Openai gym","volume":"abs\/1606.01540","author":"Brockman","year":"2016","journal-title":"CoRR"},{"volume-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","year":"2016\u20132021","author":"Coumans","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref41","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"abs\/1801.01290","author":"Haarnoja","year":"2018","journal-title":"CoRR"},{"volume-title":"Garage: A toolkit for reproducible reinforcement learning research","year":"2019","key":"ref42"},{"key":"ref43","article-title":"Dynamic environments with deformable objects","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Antonova","year":"2021"},{"key":"ref44","article-title":"Reinforcement learning for pivoting task","author":"Antonova","year":"2017","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Gradients are not all you need","author":"Metz","year":"2021","journal-title":"arXiv preprint"}],"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":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981540.pdf?arnumber=9981540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:43:48Z","timestamp":1706759028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981540","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}