{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:39:11Z","timestamp":1782409151279,"version":"3.54.5"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342194","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"8487-8494","source":"Crossref","is-referenced-by-count":10,"title":["End-to-End Learning of Deep Visuomotor Policy for Needle Picking"],"prefix":"10.1109","author":[{"given":"Hongbin","family":"Lin","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Chu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and En-gineering,Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhui","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwok Wai","family":"Samuel Au","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering,Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139594"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2515161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461200"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2019.8843089"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561673"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635867"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812393"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2913082"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.3029114"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref11","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on Robot Learning","author":"Kalashnikov","year":"2018"},{"key":"ref12","article-title":"Mastering atari with discrete world models","author":"Hafner","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref14","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"International Conference on Machine Learning","author":"Hafner","year":"2019"},{"key":"ref16","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Daydreamer: World models for physical robot learning","author":"Wu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref19","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","year":"2018"},{"key":"ref20","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","volume-title":"Proceedings of the 28th International Conference on machine learning (ICML-11)","author":"Deisenroth","year":"2011"},{"issue":"34","key":"ref21","first-page":"25","article-title":"Improving pilco with bayesian neural network dynamics models","volume":"4","author":"Gal","year":"2016","journal-title":"Data-efficient machine learning workshop, ICML"},{"key":"ref22","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"Chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref25","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","author":"Goecks","year":"2019","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"Ebert","year":"2018","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Dream and search to control: Latent space planning for continuous control","author":"Koul","year":"2020","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3227873"},{"key":"ref30","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146900"},{"key":"ref33","article-title":"Open-source High-precision Autonomous Suturing Framework With Visual Guidance","volume-title":"IEEE Int. Conf. Intell. Robots and Syst. (IROS) Workshop on \u201cA Panacea Or An Alchemy? Benefits And Risks Of Robot Learning In Medical Applications\u201d","author":"Lin","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342194.pdf?arnumber=10342194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:32:22Z","timestamp":1705023142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342194","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}