{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:40:12Z","timestamp":1735198812524,"version":"3.32.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802712","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"5195-5202","source":"Crossref","is-referenced-by-count":0,"title":["Learning Temporally Composable Task Segmentations with Language"],"prefix":"10.1109","author":[{"given":"Divyanshu","family":"Raj","sequence":"first","affiliation":[{"name":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"}]},{"given":"Omkar","family":"Patil","sequence":"additional","affiliation":[{"name":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"}]},{"given":"Weiwei","family":"Gu","sequence":"additional","affiliation":[{"name":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"}]},{"given":"Chitta","family":"Baral","sequence":"additional","affiliation":[{"name":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"}]},{"given":"Nakul","family":"Gopalan","sequence":"additional","affiliation":[{"name":"Arizona State University,School of Computing and Augmented Intelligence,Tempe,Arizona,United States"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref2"},{"article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","year":"2023","author":"Padalkar","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref5","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on robot learning","author":"Kalashnikov"},{"key":"ref6","article-title":"Constructing skill trees for reinforcement learning agents from demonstration trajectories","volume-title":"Advances in Neural Information Processing Systems","volume":"23","author":"Konidaris","year":"2010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914554471"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2020.XVI.102","article-title":"Simultaneously learning transferable symbols and language groundings from perceptual data for instruction following","volume-title":"RSS","author":"Gopalan","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911428653"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref12","article-title":"Qvhighlights: Detecting moments and highlights in videos via natural language queries","author":"Lei","year":"2021","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353414"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-009-9163-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOAS395"},{"article-title":"Walk the talk: Connecting language, knowledge, and action in route instructions","year":"2006","author":"MacMahon","key":"ref17"},{"key":"ref18","article-title":"Weakly supervised learning of semantic parsers for mapping instructions to actions","volume-title":"TACL","volume":"1","author":"Artzi","year":"2013"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2015.XI.018","article-title":"Grounding english commands to reward functions","volume-title":"RSS","author":"MacGlashan","year":"2015"},{"article-title":"Grounded language learning in a simulated 3d world","year":"2017","author":"Hermann","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11832"},{"key":"ref22","article-title":"Guiding pretraining in reinforcement learning with large language models","author":"Du","year":"2023","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.773"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350879"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00150"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"issue":"5","key":"ref32","first-page":"469","article-title":"A survey of robot learning from demonstration","volume-title":"Robotics and Autonomous Systems","volume":"57","author":"Argall","year":"2009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.01075","article-title":"Alfred: A benchmark for interpreting grounded instructions for everyday tasks","volume-title":"CVPR","author":"Shridhar","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01281"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611293"},{"article-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"ref37"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802712.pdf?arnumber=10802712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:01:59Z","timestamp":1735196519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802712","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}