{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:11:53Z","timestamp":1772554313449,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Robotics Institute Germany","award":["16ME0997K"],"award-info":[{"award-number":["16ME0997K"]}]},{"name":"European Union's Horizon Europe Research and Innovation","award":["101155035"],"award-info":[{"award-number":["101155035"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/lra.2025.3553046","type":"journal-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T19:30:23Z","timestamp":1742585423000},"page":"4810-4817","source":"Crossref","is-referenced-by-count":7,"title":["Semantically Safe Robot Manipulation: From Semantic Scene Understanding to Motion Safeguards"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9893-9889","authenticated-orcid":false,"given":"Lukas","family":"Brunke","sequence":"first","affiliation":[{"name":"Learning Systems and Robotics Lab, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5075-3441","authenticated-orcid":false,"given":"Yanni","family":"Zhang","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2283-3161","authenticated-orcid":false,"given":"Ralf","family":"R\u00f6mer","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, Technical University of Munich, Munich, Germany"}]},{"given":"Jack","family":"Naimer","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1929-654X","authenticated-orcid":false,"given":"Nikola","family":"Staykov","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7240-546X","authenticated-orcid":false,"given":"Siqi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4012-4668","authenticated-orcid":false,"given":"Angela P.","family":"Schoellig","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, Technical University of Munich, Munich, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-071723-102940"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2023.3291885"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Info. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref6","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref8","first-page":"68367","article-title":"OpenMask3D: Open-vocabulary 3D instance segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Takmaz","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161068"},{"key":"ref10","first-page":"4005","article-title":"RoboPoint: A vision-language model for spatial affordance prediction for robotics","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Yuan","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-094829"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812280"},{"key":"ref13","article-title":"Riemannian motion policies","author":"Ratliff","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192634"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263977"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app10020497"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196885"},{"key":"ref19","article-title":"OKVIS2: Realtime scalable visual-inertial SLAM with loop closure","author":"Leutenegger","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref22","article-title":"GPT4Scene: Understand 3D scenes from videos with vision-language models","author":"Qi","year":"2025"},{"key":"ref23","first-page":"4573","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Huang","year":"2025"},{"key":"ref24","article-title":"Updating robot safety representations online from natural language feedback","volume-title":"Proc. 2025 IEEE Int. Conf. Robot. Autom.","author":"Santos","year":"2025"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref27","first-page":"178","article-title":"Language embedded radiance fields for zero-shot task-oriented grasping","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Rashid","year":"2023"},{"key":"ref28","first-page":"3384","article-title":"Language-conditioned path planning","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Xie","year":"2023"},{"key":"ref29","first-page":"749","article-title":"Language-guided manipulator motion planning with bounded task space","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Oelerich","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref31","first-page":"2120","article-title":"Tag map: A text-based map for spatial reasoning and navigation with large language models","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Zhang","year":"2025"},{"key":"ref32","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Huang","year":"2023"},{"key":"ref33","first-page":"23","article-title":"SayPlan: Grounding large language models using 3D scene graphs for scalable robot task planning","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Rana","year":"2023"},{"key":"ref34","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Huang","year":"2023"},{"key":"ref35","first-page":"1590","article-title":"APRICOT: Active preference learning and constraint-aware task planning with LLMs","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Wang","year":"2025"},{"key":"ref36","article-title":"Task success is not enough: Investigating the use of video-language models as behavior critics for catching undesirable agent behaviors","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Guan","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01580-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1017\/9781316661239"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00270"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14601"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1017\/9781009299909"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00036"},{"key":"ref44","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10935293\/10933541.pdf?arnumber=10933541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:09:25Z","timestamp":1744063765000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10933541\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":45,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3553046","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}