{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T03:24:28Z","timestamp":1772940268321,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"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":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341545","type":"proceedings-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:26:48Z","timestamp":1613183208000},"page":"8408-8414","source":"Crossref","is-referenced-by-count":30,"title":["Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter"],"prefix":"10.1109","author":[{"given":"Andrey","family":"Kurenkov","sequence":"first","affiliation":[{"name":"Stanford University"}]},{"given":"Joseph","family":"Taglic","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Rohun","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Marcus","family":"Dominguez-Kuhne","sequence":"additional","affiliation":[{"name":"Caltech"}]},{"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[{"name":"University of Toronto & Vector Institute"}]},{"given":"Roberto","family":"Martin-Martin","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[{"name":"Stanford University"}]}],"member":"263","reference":[{"key":"ref33","author":"coumans","year":"2017","journal-title":"pybullet a python module for physics simulation games robotics and machine learning"},{"key":"ref32","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00346"},{"key":"ref30","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2895878"},{"key":"ref36","article-title":"Benchmarking in manipulation research: The ycb object and model set and benchmarking protocols","author":"calli","year":"2015"},{"key":"ref35","article-title":"Bayesian policy gradients via alpha divergence dropout inference","author":"henderson","year":"2017"},{"key":"ref34","article-title":"Gibson env v2: Embodied simulation environments for interactive navigation","author":"xia","year":"2019","journal-title":"Stanford University Tech Rep"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1109\/TRO.2017.2721939","article-title":"Interactive perception: Leveraging action in perception and perception in action","volume":"33","author":"bohg","year":"2017","journal-title":"IEEE Transactions on Robotics"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487714"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152393"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9407-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2361346"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28619-4_32"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2008.4755944"},{"key":"ref18","first-page":"712","article-title":"Randomized physics-based motion planning for grasping in cluttered and uncertain environments","volume":"3","author":"moll","year":"2017","journal-title":"IEEE l of Robotics and Automation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793494"},{"key":"ref28","article-title":"Decoupling feature extraction from policy learning: Assessing benefits of state representation learning in goal based robotics","author":"raffin","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2970622"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref29","article-title":"Mid-level visual representations improve generalization and sample efficiency for learning visuomotor policies","author":"sax","year":"2018"},{"key":"ref5","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018"},{"key":"ref8","article-title":"Asymmetric actor critic for image-based robot learning","author":"pinto","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385903"},{"key":"ref9","article-title":"Ac-teach: A bayesian actor-critic method for policy learning with an ensemble of suboptimal teachers","author":"kurenkov","year":"2019"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794143"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906922"},{"key":"ref22","article-title":"Object finding in cluttered scenes using interactive perception","author":"novkovic","year":"2019"},{"key":"ref21","first-page":"515","article-title":"Learning deep policies for robot bin picking by simulating robust grasping sequences","author":"mahler","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref24","article-title":"End-to-end learning of semantic grasping","author":"jang","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968042"},{"key":"ref26","first-page":"9605","article-title":"An intriguing failing of convolutional neural networks and the coordconv solution","author":"liu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968114"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341545.pdf?arnumber=9341545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:54:48Z","timestamp":1656453288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341545","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}