{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:31:43Z","timestamp":1772040703291,"version":"3.50.1"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Automat. Mag."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/mra.2021.3129448","type":"journal-article","created":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T20:52:29Z","timestamp":1641847949000},"page":"75-84","source":"Crossref","is-referenced-by-count":2,"title":["Learning Fast and Precise Pixel-to-Torque Control: A Platform for Reproducible Research of Learning on Hardware"],"prefix":"10.1109","volume":"29","author":[{"given":"Steffen","family":"Bleher","sequence":"first","affiliation":[{"name":"Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Heim","sequence":"additional","affiliation":[{"name":"Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Trimpe","sequence":"additional","affiliation":[{"name":"Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"refS1","doi-asserted-by":"publisher","DOI":"10.1155\/2011\/528341"},{"key":"refS3","doi-asserted-by":"publisher","DOI":"10.1109\/ETCM.2017.8247510"},{"key":"ref10","first-page":"66","article-title":"Learning by cheating","volume":"100","author":"chen","year":"0","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"refS2","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00140-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3016929"},{"key":"refS5","article-title":"Blue river controls: A toolkit for reinforcement learning control systems on hardware","author":"polzounov","year":"2019"},{"key":"ref12","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"refS4","year":"2020","journal-title":"Another batch of Furuta pendulums"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068639"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"refS6","year":"0","journal-title":"Quanser qube servo 2 manual"},{"key":"ref15","article-title":"Flingbot: The unreasonable effectiveness of dynamic manipulation for cloth unfolding","author":"ha","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2930489"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34500-5_16"},{"key":"ref18","first-page":"133","article-title":"Deep drone racing: Learning agile flight in dynamic environments","volume":"87","author":"kaufmann","year":"0","journal-title":"Proc 2nd Conf Robot Learn (CoRL)"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref4","article-title":"Solving Rubik’s cube with a robot hand","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref8","first-page":"293","author":"roberts","year":"2010","journal-title":"Motor Learning at Intermediate Reynolds Number Experiments with Policy Gradient on the Flapping Flight of A Rigid Wing"},{"key":"ref7","first-page":"317","article-title":"Learning locomotion skills for cassie: Iterative design and sim-to-real","volume":"100","author":"xie","year":"0","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21587"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594092"},{"key":"ref20","article-title":"The effectiveness of data augmentation in image classification using deep learning","author":"perez","year":"2017"},{"key":"ref22","first-page":"19,884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"laskin","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref21","first-page":"627","article-title":"A learnable safety measure","volume":"100","author":"heim","year":"0","journal-title":"Proc 3rd Conf Robot Learn (CoRL)"}],"container-title":["IEEE Robotics & Automation Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/100\/9794949\/09675140.pdf?arnumber=9675140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T19:47:28Z","timestamp":1656964048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9675140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":28,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/mra.2021.3129448","relation":{},"ISSN":["1070-9932","1558-223X"],"issn-type":[{"value":"1070-9932","type":"print"},{"value":"1558-223X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}