{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:36:36Z","timestamp":1777570596320,"version":"3.51.4"},"reference-count":54,"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\/iros58592.2024.10801816","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"11879-11886","source":"Crossref","is-referenced-by-count":10,"title":["GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robot"],"prefix":"10.1109","author":[{"given":"Wenxuan","family":"Song","sequence":"first","affiliation":[{"name":"Westlake University,MiLAB,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Zhao","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengxiang","family":"Ding","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Cui","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangke","family":"Lyu","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaning","family":"Fan","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758092"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341908"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184025"},{"key":"ref4","article-title":"Learning quadrupedal locomotion over challenging terrain","volume-title":"Science Robotics","volume":"5","author":"Lee","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ade2256"},{"key":"ref6","article-title":"Learning vision-guided quadrupedal locomotion end-to-end with cross-modal transformers","volume-title":"ArXiv","volume":"abs\/2107.03996","author":"Yang","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3335777"},{"key":"ref8","article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","author":"Kalashnikov","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref11","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref13","article-title":"Bridgedata v2: A dataset for robot learning at scale","author":"Walke","year":"2023"},{"key":"ref14","author":"Chebotar","journal-title":"Q-transformer: Scalable offline reinforcement learning via autoregressive q-functions"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/IROS58592.2024.10801328","article-title":"Llm3:large language model-based task and motion planning with motion failure reasoning","author":"Wang","year":"2024"},{"key":"ref18","article-title":"Mixtures of experts unlock parameter scaling for deep rl","author":"Obando-Ceron","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"ref21","article-title":"Quar-vla: Vision-language-action model for quadruped robots","volume-title":"ArXiv","volume":"abs\/2312.14457","author":"Ding","year":"2023"},{"key":"ref22","article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","author":"Jaques","year":"2019"},{"key":"ref23","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref24","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2021","journal-title":"Cornell University - arXiv,Cornell University - arXiv"},{"key":"ref25","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021"},{"key":"ref26","article-title":"A minimalist approach to offline reinforcement learning","author":"Fujimoto","year":"2021","journal-title":"Neural Information Processing Systems,Neural Information Processing Systems"},{"key":"ref27","article-title":"Bail: Best-action imitation learning for batch deep reinforcement learning","author":"Chen","year":"2019"},{"key":"ref28","article-title":"Generalized decision transformer for offline hindsight information matching","author":"Furuta"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1383-7"},{"key":"ref30","article-title":"Robust imitation learning from corrupted demonstrations","author":"Liu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636633"},{"key":"ref32","article-title":"Conservative q-learning for offline reinforcement learning","author":"Kumar","year":"2020"},{"key":"ref33","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"key":"ref34","article-title":"Deep learning scaling is predictable, empirically","author":"Hestness","year":"2017"},{"key":"ref35","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"Cornell University - arXiv,Cornell University - arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00171"},{"key":"ref37","first-page":"5547","article-title":"Glam: Efficient scaling of language models with mixture-of-experts","volume-title":"International Conference on Machine Learning","author":"Du"},{"key":"ref38","article-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref40","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"ArXiv","volume":"abs\/2109.12098","author":"Shridhar","year":"2021"},{"key":"ref41","article-title":"A generalist agent","author":"Reed","year":"2022"},{"key":"ref42","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"Conference on Robot Learning","author":"Nair"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1109\/IROS58592.2024.10801835","article-title":"Ag2manip: Learning novel manipulation skills with agent-agnostic visual and action representations","author":"Li","year":"2024"},{"key":"ref44","article-title":"Vision-language foundation models as effective robot imitators","volume-title":"ArXiv","volume":"abs\/2311.01378","author":"Li","year":"2023"},{"key":"ref45","article-title":"Large language models as generalizable policies for embodied tasks","author":"Szot","year":"2023"},{"key":"ref46","article-title":"Cobra: Extending mamba to multi-modal large language model for efficient inference","volume-title":"ArXiv","volume":"abs\/2403.14520","author":"Zhao","year":"2024"},{"key":"ref47","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref48","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Conference on Robot Learning","author":"Margolis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","first-page":"7103","article-title":"Mixture-of-experts with expert choice routing","volume":"35","author":"Zhou","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2029"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980145"},{"key":"ref53","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11671","article-title":"Film: Visual reasoning with a general conditioning layer","volume-title":"AAAI Conference on Artificial Intelligence","author":"Perez"},{"key":"ref54","article-title":"Tokenlearner: Adaptive space-time tokenization for videos","author":"Ryoo","year":"2021","journal-title":"Neural Information Processing Systems,Neural Information Processing Systems"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"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\/10801816.pdf?arnumber=10801816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:58:26Z","timestamp":1735196306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801816","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}