{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:55Z","timestamp":1757608735902,"version":"3.44.0"},"reference-count":50,"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\/icra55743.2025.11127664","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"2445-2452","source":"Crossref","is-referenced-by-count":0,"title":["CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction"],"prefix":"10.1109","author":[{"given":"Suhwan","family":"Choi","sequence":"first","affiliation":[{"name":"MAUM.AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjun","family":"Cho","sequence":"additional","affiliation":[{"name":"MAUM.AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minchan","family":"Kim","sequence":"additional","affiliation":[{"name":"MAUM.AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaeyoon","family":"Jung","sequence":"additional","affiliation":[{"name":"MAUM.AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Myunchul","family":"Joe","sequence":"additional","affiliation":[{"name":"MAUM.AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubeen","family":"Park","sequence":"additional","affiliation":[{"name":"MAUM.AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minseo","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungwoong","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungjae","family":"Lee","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hwiseong","family":"Park","sequence":"additional","affiliation":[{"name":"MAUM.AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiwan","family":"Chung","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjae","family":"Yu","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3387539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.22107"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793608"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-007-9023-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487453"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611462"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1328934"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197315"},{"key":"ref12","article-title":"Esc: Exploration with soft commonsense constraints for zeroshot object navigation","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Zhou","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref14","article-title":"Commonsense reasoning for legged robot adaptation with vision-language models","volume-title":"arXiv preprint","author":"Chen","year":"2024"},{"key":"ref15","article-title":"Dd-ppo: Learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"International Conference on Learning Representations","author":"Wijmans","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611229"},{"key":"ref17","article-title":"Deep reinforcement learning with enhanced ppo for safe mobile robot navigation","author":"Taheri","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Goal-conditioned imitation learning","author":"Ding","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2925731"},{"volume-title":"Github - ros-planning\/navigation","year":"2023","author":"Robotics","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3182\/20100906-3-it-2019.00010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/23311916.2019.1632046"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA52036.2021.9512584"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref25","article-title":"Vint: A foundation model for visual navigation","volume-title":"Proceedings of The 7 th Conference on Robot Learning","author":"Shah","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460641"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09217-1"},{"key":"ref30","article-title":"BC-z: Zero-shot task generalization with robotic imitation learning","volume-title":"5th Annual Conference on Robot Learning","author":"Jang","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812316"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196602"},{"key":"ref34","article-title":"Behavior transformers: Cloning k modes with one stone","author":"Shafiullah","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Discrete sequential prediction of continuous actions for deep rl","author":"Metz","year":"2017","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Continuous control with action quantization from demonstrations","author":"Dadashi","year":"2021","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Q-transformer: Scalable offline reinforcement learning via autoregressive q-functions","volume-title":"Conference on Robot Learning","author":"Chebotar","year":"2023"},{"key":"ref38","article-title":"Behavior generation with latent actions","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Lee","year":"2024"},{"key":"ref39","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Hydra-mdp: End-to-end multimodal planning with multi-target hydra-distillation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"article-title":"Isaac Sim - Robotics Simulation and Synthetic Data - NVIDIA Developer","volume-title":"NVIDIA","year":"2024","key":"ref41"},{"article-title":"Unreal engine","volume-title":"Epic Games","year":"2024","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/11841036_8"},{"article-title":"Rt-trajectory: Robotic task generalization via hindsight trajectory sketches","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Gu","key":"ref44"},{"key":"ref45","article-title":"What matters when building vision-language models?","author":"Lauren\u00e7on","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref47","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"article-title":"Lora: Low-rank adaptation of large language models","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Hu","key":"ref48"},{"article-title":"Decoupled weight decay regularization","volume-title":"7 th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3141876"}],"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\/11127664.pdf?arnumber=11127664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:14:06Z","timestamp":1756880046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127664","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}