{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:33:14Z","timestamp":1780637594016,"version":"3.54.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812019","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"8298-8304","source":"Crossref","is-referenced-by-count":31,"title":["Visuotactile-RL: Learning Multimodal Manipulation Policies with Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Johanna","family":"Hansen","sequence":"first","affiliation":[{"name":"Samsung AI Research Center Montreal,Montreal,QC,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francois","family":"Hogan","sequence":"additional","affiliation":[{"name":"Samsung AI Research Center Montreal,Montreal,QC,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitriy","family":"Rivkin","sequence":"additional","affiliation":[{"name":"Samsung AI Research Center Montreal,Montreal,QC,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Meger","sequence":"additional","affiliation":[{"name":"Samsung AI Research Center Montreal,Montreal,QC,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Jenkin","sequence":"additional","affiliation":[{"name":"Samsung AI Research Center Montreal,Montreal,QC,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory","family":"Dudek","sequence":"additional","affiliation":[{"name":"Samsung AI Research Center Montreal,Montreal,QC,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JRA.1987.1087068","article-title":"A unified approach for motion and force control of robot manipulators: The operational space formulation","volume":"3","author":"khatib","year":"1987","journal-title":"IEEE J Robotics Autom"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref31","article-title":"Highway networks","author":"srivastava","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref36","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref35","article-title":"Tactile object pose estimation from the first touch with geometric contact rendering","author":"bauza","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"Tacto: A fast, flexible and open-source simulator for high-resolution vision-based tactile sensors","author":"wang","year":"2020","journal-title":"ArXiv"},{"key":"ref10","article-title":"Feedback control of the pusher-slider system: A story of hybrid and underactuated contact dynamics","author":"hogan","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.044"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561646"},{"key":"ref13","article-title":"Robosuite: A modular simulation framework and benchmark for robot learning","author":"zhu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.sna.2012.02.051"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s18040948"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593661"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794219"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196976"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341006"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"2762","DOI":"10.3390\/s17122762","article-title":"Gelsight: High-resolution robot tactile sensors for estimating geometry and force","volume":"17","author":"yuan","year":"2017","journal-title":"SENSORS"},{"key":"ref28","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"yarats","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref27","article-title":"Dream to control: Learning behaviors by latent imagination","author":"hafner","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"OmniTact: A multi-dimensional high resolution touch sensor","author":"padmanabha","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref5","author":"taylor","year":"2021","journal-title":"GelSlim3 0 High-resolution measurement of shape force and slip in a compact tactile-sensing finger"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.06.001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00126"},{"key":"ref2","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","author":"yarats","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref1","first-page":"3189","article-title":"Effect of visual and haptic feedback on grasping movements","author":"bazzacchi","year":"2104","journal-title":"J Neurophysiol"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913506757"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561646"},{"key":"ref22","author":"church","year":"2021","journal-title":"Optical tactile sim-to-real policy transfer via real-to-sim tactile image translation"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.29007\/25x3"},{"key":"ref23","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref26","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Improving sample efficiency in model-free reinforcement learning from images","author":"yarats","year":"2019","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812019.pdf?arnumber=9812019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:08:51Z","timestamp":1667516931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812019","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}