{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:29:58Z","timestamp":1766068198336,"version":"3.44.0"},"reference-count":35,"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\/icra55743.2025.11128700","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"15980-15986","source":"Crossref","is-referenced-by-count":1,"title":["Masked Sensory-Temporal Attention for Sensor Generalization in Quadruped Locomotion"],"prefix":"10.1109","author":[{"given":"Dikai","family":"Liu","sequence":"first","affiliation":[{"name":"NVIDIA AI Technology Centre (NVAITC)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxiong","family":"Yin","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Centre (NVAITC)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"See","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Centre (NVAITC)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref5","first-page":"1893","article-title":"Genloco: Generalized locomotion controllers for quadrupedal robots","volume-title":"Conference on Robot Learning","author":"Feng"},{"key":"ref6","article-title":"Manyquadrupeds: Learning a single locomotion policy for diverse quadruped robots","author":"Shafiee","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00701-w"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref11","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"Padalkar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Barkour: Benchmarking animal-level agility with quadruped robots","author":"Caluwaerts","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160497"},{"key":"ref16","first-page":"2303","article-title":"Learning humanoid locomotion with transformers","author":"Radosavovic","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref17","article-title":"Humanoid locomotion as next token prediction","author":"Radosavovic","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume":"35","author":"Feichtenhofer","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231224053"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cai59869.2024.00257"},{"key":"ref23","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Learning vision-guided quadrupedal locomotion end-to-end with cross-modal transformers","author":"Yang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Saytap: Language to quadrupedal locomotion","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Body transformer: Leveraging robot embodiment for policy learning","author":"Sferrazza","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Better plain vit baselines for imagenet-1k","author":"Beyer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref32","first-page":"597","article-title":"On the computational complexity of self-attention","volume-title":"International Conference on Algorithmic Learning Theory","author":"Keles"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref34","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11128700.pdf?arnumber=11128700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:03:57Z","timestamp":1756879437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128700\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128700","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}