{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:17:26Z","timestamp":1778113046267,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127407","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1481-1487","source":"Crossref","is-referenced-by-count":3,"title":["Towards Autonomous Wood-Log Grasping with a Forestry Crane: Simulator and Benchmarking"],"prefix":"10.1109","author":[{"given":"M.N.","family":"Vu","sequence":"first","affiliation":[{"name":"Automation & Control Institute (ACIN), TU Wien,Vienna,Austria,1040"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Wachter","sequence":"additional","affiliation":[{"name":"Automation & Control Institute (ACIN), TU Wien,Vienna,Austria,1040"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G.","family":"Ebmer","sequence":"additional","affiliation":[{"name":"Automation & Control Institute (ACIN), TU Wien,Vienna,Austria,1040"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Ecker","sequence":"additional","affiliation":[{"name":"Automation & Control Institute (ACIN), TU Wien,Vienna,Austria,1040"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Gl\u00fcck","sequence":"additional","affiliation":[{"name":"AIT Austrian Institute of Technology GmbH,Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W.","family":"Kemmetm\u00fcller","sequence":"additional","affiliation":[{"name":"Automation & Control Institute (ACIN), TU Wien,Vienna,Austria,1040"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Kugi","sequence":"additional","affiliation":[{"name":"Automation & Control Institute (ACIN), TU Wien,Vienna,Austria,1040"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21496"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2016.12.013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref5","first-page":"44323","article-title":"Robohive: A unified framework for robot learning","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Kumar","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13205"},{"key":"ref8","first-page":"241","article-title":"Hacman: Learning hybrid actor-critic maps for 6d non-prehensile manipulation","volume-title":"Proceedings of The 7th Conference on Robot Learning, ser. Proceedings of Machine Learning Research","volume":"229","author":"Zhou","year":"2023"},{"key":"ref9","article-title":"Maniskill: Generalizable manipulation skill benchmark with large-scale demonstrations","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","volume":"1","author":"Mu","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636219"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161562"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2014.09.006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/256951"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981425"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref16","volume-title":"AGX Dynamics","year":"2024"},{"key":"ref17","volume-title":"Iterative linear quadratic regulator for collision-free trajectory optimization and model predictive control of a timber crane","author":"Ecker","year":"2022"},{"key":"ref18","volume-title":"Robot modeling and control","author":"Spong","year":"2006"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2011.03.010"},{"key":"ref21","article-title":"Understanding domain randomization for sim-to-real transfer","volume-title":"International Conference on Learning Representations","author":"Chen","year":"2022"},{"key":"ref22","article-title":"How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?","author":"Vuong","year":"2019","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611277"},{"key":"ref25","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","volume-title":"International conference on machine learning","author":"Chou","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/2309786"},{"key":"ref27","article-title":"Policy gradient algorithms","author":"Weng","year":"2018","journal-title":"lilianweng. github. io\/lil-log"},{"issue":"274","key":"ref28","first-page":"1","article-title":"Cleanrl: High-quality single-file implementations of deep reinforcement learning algorithms","volume":"23","author":"Huang","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/wics.13"},{"issue":"1","key":"ref30","first-page":"12348","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"The Journal of Machine Learning Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref32","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman","year":"2015"},{"key":"ref33","article-title":"The 37 implementation details of proximal policy optimization","author":"Huang","year":"2023","journal-title":"The ICLR Blog Track 2023"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127407.pdf?arnumber=11127407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:55:23Z","timestamp":1756882523000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127407","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}