{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T20:09:02Z","timestamp":1778962142832,"version":"3.51.4"},"reference-count":229,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Virtual Reality & Intelligent Hardware"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.vrih.2026.03.001","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:36:09Z","timestamp":1778762169000},"page":"131-171","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["From embodied AI to cobodied AI: Foundations and frontiers"],"prefix":"10.1016","volume":"8","author":[{"given":"Feng","family":"LU","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruijia","family":"PANG","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bosong","family":"QI","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinping","family":"ZHAO","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.vrih.2026.03.001_bib1","first-page":"444","article-title":"Towards cobodied\/symbodied AI: concept and eight scientific and technical problems","volume":"55","author":"Lu","year":"2025","journal-title":"SCIENTIA SINICA Infrmationis (SSI)"},{"issue":"1","key":"10.1016\/j.vrih.2026.03.001_bib2","article-title":"Towards cobodied\/symbodied AI: concept and eight scientific and technical problems","volume":"69","author":"Lu","year":"2026","journal-title":"SCIENCE CHINA Information Sciences (SCIS)"},{"key":"10.1016\/j.vrih.2026.03.001_bib3","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"3992","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib4","series-title":"Towards interactive intelligence for digital humans","author":"Cai","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib5","series-title":"Gs-slam: dense visual slam with 3D Gaussian splatting","author":"Yan","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib6","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"13442","article-title":"AutoNeRF: training implicit scene representations with autonomous agents","author":"Marza","year":"2024"},{"issue":"6","key":"10.1016\/j.vrih.2026.03.001_bib7","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Communications of the ACM"},{"key":"10.1016\/j.vrih.2026.03.001_bib8","series-title":"2016 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"1957","article-title":"Dex-Net 1.0: a cloud-based network of 3D objects for robust grasp planning using a multi-armed bandit model with correlated rewards","author":"Mahler","year":"2016"},{"key":"10.1016\/j.vrih.2026.03.001_bib9","series-title":"Dex-net 2.0: deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics","author":"Mahler","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.001_bib10","series-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"5620","article-title":"Dex-net 3.0: computing robust vacuum suction grasp targets in point clouds using a new analytic model and deep learning","author":"Mahler","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib11","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7272","article-title":"Cognitive mapping and planning for visual navigation","author":"Gupta","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.001_bib12","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib13","series-title":"Palm-e: an embodied multimodal language model","author":"Driess","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib14","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"2798","article-title":"DINOBot: robot manipulation via retrieval and alignment with vision foundation models","author":"Di Palo","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib15","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"9630","article-title":"Emerging properties in self-supervised Vision Transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib16","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12689","article-title":"PointPillars: fast encoders for object detection from point clouds","author":"Lang","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.001_bib17","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6526","article-title":"Multi-view 3D object detection network for autonomous driving","author":"Chen","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.001_bib18","series-title":"2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"922","article-title":"VoxNet: a 3D convolutional neural network for real-time object recognition","author":"Maturana","year":"2015"},{"key":"10.1016\/j.vrih.2026.03.001_bib19","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"190","article-title":"Semantic scene completion from a single depth image","author":"Song","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.001_bib20","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3070","article-title":"4D spatio-temporal ConvNets: minkowski convolutional neural networks","author":"Choy","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.001_bib21","series-title":"PointNet++: deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.001_bib22","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4840","article-title":"Point Transformer V3: simpler, faster, stronger","author":"Wu","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib23","series-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"3619","article-title":"PointNet++ grasping: learning an end-to-end spatial grasp generation algorithm from sparse point clouds","author":"Ni","year":"2020"},{"issue":"1","key":"10.1016\/j.vrih.2026.03.001_bib24","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3503250","article-title":"NeRF: representing scenes as neural radiance fields for view synthesis","volume":"65","author":"Mildenhall","year":"2021","journal-title":"Communications of the ACM"},{"issue":"4","key":"10.1016\/j.vrih.2026.03.001_bib25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3528223.3530127","article-title":"Instant neural graphics primitives with a multiresolution hash encoding","volume":"41","author":"M\u00fcller","year":"2022","journal-title":"ACM Transactions on Graphics"},{"issue":"4","key":"10.1016\/j.vrih.2026.03.001_bib26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592433","article-title":"3D Gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Transactions on Graphics"},{"key":"10.1016\/j.vrih.2026.03.001_bib27","series-title":"Dex-NeRF: using a neural radiance field to grasp transparent objects","author":"Ichnowski","year":"2021"},{"issue":"9","key":"10.1016\/j.vrih.2026.03.001_bib28","doi-asserted-by":"crossref","first-page":"7827","DOI":"10.1109\/LRA.2024.3432348","article-title":"GaussianGrasper: 3D language Gaussian splatting for open-vocabulary robotic grasping","volume":"9","author":"Zheng","year":"2024","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.vrih.2026.03.001_bib29","series-title":"Advances in Neural Information Processing Systems 35. New Orleans, Louisiana, USA, Neural Information Processing Systems Foundation, Inc","first-page":"665","article-title":"VLMbench: a compositional benchmark for vision-and-language manipulation","author":"Chen","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib30","series-title":"Computer Vision \u2013 ECCV 2020","first-page":"17","article-title":"SoundSpaces: audio-visual navigation in 3D environments","author":"Chen","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib31","series-title":"Soundspaces 2.0: a simulation platform for visual-acoustic learning","author":"Chen","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib32","series-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"1581","article-title":"BatVision: learning to see 3D spatial layout with two ears","author":"Christensen","year":"2020"},{"issue":"12","key":"10.1016\/j.vrih.2026.03.001_bib33","doi-asserted-by":"crossref","first-page":"2762","DOI":"10.3390\/s17122762","article-title":"GelSight: high-resolution robot tactile sensors for estimating geometry and force","volume":"17","author":"Yuan","year":"2017","journal-title":"Sensors"},{"issue":"3","key":"10.1016\/j.vrih.2026.03.001_bib34","doi-asserted-by":"crossref","first-page":"3838","DOI":"10.1109\/LRA.2020.2977257","article-title":"DIGIT: a novel design for a low-cost compact high-resolution tactile sensor with application to in-hand manipulation","volume":"5","author":"Lambeta","year":"2020","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.vrih.2026.03.001_bib35","series-title":"Tactile beyond pixels: multisensory touch representations for robot manipulation","author":"Higuera","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib36","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6896","article-title":"Suppressing uncertainties for large-scale facial expression recognition","author":"Wang","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib37","series-title":"2024 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1","article-title":"CLIPER: a unified vision-language framework for in-the-wild facial expression recognition","author":"Li","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib38","series-title":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","first-page":"1","article-title":"EmoCLIP: a vision-language method for zero-shot video facial expression recognition","author":"Foteinopoulou","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib39","series-title":"GoEmotions: a dataset of fine-grained emotions","author":"Demszky","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib40","series-title":"DialogueGCN: a graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.001_bib41","series-title":"Is ChatGPT a good sentiment analyzer? A preliminary study","author":"Wang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib42","series-title":"Reasoning implicit sentiment with chain-of-thought prompting","author":"Fei","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib43","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103198","article-title":"Exploring embodied multimodal large models: development, datasets, and future directions","volume":"122","author":"Chen","year":"2025","journal-title":"Information Fusion"},{"issue":"5","key":"10.1016\/j.vrih.2026.03.001_bib44","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","article-title":"ORB-SLAM: a versatile and accurate monocular SLAM system","volume":"31","author":"Mur-Artal","year":"2015","journal-title":"IEEE Transactions on Robotics"},{"key":"10.1016\/j.vrih.2026.03.001_bib45","series-title":"DROID-SLAM: deep visual SLAM for monocular, stereo, and RGB-D cameras","author":"Teed","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib46","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6209","article-title":"iMAP: implicit mapping and positioning in real-time","author":"Sucar","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib47","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12776","article-title":"NICE-SLAM: neural implicit scalable encoding for SLAM","author":"Zhu","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib48","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1238","article-title":"Learning to look around: intelligently exploring unseen environments for unknown tasks","author":"Jayaraman","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib49","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16351","article-title":"Evidential active recognition: intelligent and prudent open-world embodied perception","author":"Fan","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib50","series-title":"AutoNeRF: training implicit scene representations with autonomous agents","author":"Marza","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib51","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"11305","article-title":"NeU-NBV: next best view planning using uncertainty estimation in image-based neural rendering","author":"Jin","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib52","series-title":"Do as I can, not as I say: grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib53","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"5543","article-title":"HM3D-OVON: a dataset and benchmark for open-vocabulary object goal navigation","author":"Yokoyama","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib54","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"8664","article-title":"CoPAL: corrective planning of robot actions with large language models","author":"Joublin","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib55","series-title":"Computer Vision \u2013 ECCV 2020","first-page":"202","article-title":"Scanrefer: 3D object localization in RGB-D scans using natural language","author":"Chen","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib56","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2899","article-title":"3D-VisTA: pre-trained Transformer for 3D vision and text alignment","author":"Zhu","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib57","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10737","article-title":"ALFRED: a benchmark for interpreting grounded instructions for everyday tasks","author":"Shridhar","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib58","series-title":"A persistent spatial semantic representation for high-level natural language instruction execution","author":"Blukis","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib59","series-title":"ProgPrompt: generating situated robot task plans using large language models","author":"Singh","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib60","series-title":"SayPlan: grounding large language models using 3D scene graphs for scalable robot task planning","author":"Rana","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib61","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3674","article-title":"Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments","author":"Anderson","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib62","series-title":"Speaker-follower models for vision-and-language navigation","author":"Fried","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib63","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"8451","article-title":"Structured scene memory for vision-language navigation","author":"Wang","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib64","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16516","article-title":"Think global, act local: dual-scale graph Transformer for vision-and-language navigation","author":"Chen","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib65","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12872","article-title":"Neural topological SLAM for visual navigation","author":"Singh Chaplot","year":"2020"},{"issue":"7","key":"10.1016\/j.vrih.2026.03.001_bib66","doi-asserted-by":"crossref","first-page":"7641","DOI":"10.1609\/aaai.v38i7.28597","article-title":"NavGPT: explicit reasoning in vision-and-language navigation with large language models","volume":"38","author":"Zhou","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.vrih.2026.03.001_bib67","series-title":"Embodied navigation foundation model","author":"Zhang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib68","series-title":"Language models as zero-shot planners: extracting actionable knowledge for embodied agents","author":"Huang","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib69","series-title":"React: synergizing reasoning and acting in language models","author":"Yao","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib70","series-title":"Inner monologue: embodied reasoning through planning with language models","author":"Huang","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib71","series-title":"EmbodiedGPT: vision-language pre-training via embodied chain of thought","author":"Mu","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib72","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2986","article-title":"LLM-planner: few-shot grounded planning for embodied agents with large language models","author":"Song","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib73","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"284","article-title":"Long-term feature banks for detailed video understanding","author":"Wu","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.001_bib74","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13577","article-title":"MeMViT: memory-augmented multiscale Vision Transformer for efficient long-term video recognition","author":"Wu","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib75","series-title":"Long short-term Transformer for online action detection","author":"Xu","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib76","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"18221","article-title":"MovieChat: from dense token to sparse memory for long video understanding","author":"Song","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib77","series-title":"VideoAgent: long-form video understanding with large language model as agent","author":"Wang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib78","series-title":"PoseGPT: quantization-based 3D human motion generation and forecasting","author":"Lucas","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib79","series-title":"Human-agent joint learning for efficient robot manipulation skill acquisition","author":"Luo","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib80","series-title":"AnyTeleop: a general vision-based dexterous robot arm-hand teleoperation system","author":"Qin","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib81","series-title":"Closing the loop for robotic grasping: a real-time, generative grasp synthesis approach","author":"Morrison","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib82","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16865","article-title":"L2G: a simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation","author":"Jiang","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib83","series-title":"Transporter networks: rearranging the visual world for robotic manipulation","author":"Zeng","year":"2020"},{"issue":"5","key":"10.1016\/j.vrih.2026.03.001_bib84","doi-asserted-by":"crossref","first-page":"3522","DOI":"10.1109\/TMECH.2023.3347785","article-title":"Multifingered grasp planning based on Gaussian process implicit surface and its partial differentials","volume":"29","author":"Liu","year":"2024","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"key":"10.1016\/j.vrih.2026.03.001_bib85","series-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"Rajeswaran","year":"2017"},{"issue":"1","key":"10.1016\/j.vrih.2026.03.001_bib86","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/0278364919887447","article-title":"Learning dexterous in-hand manipulation","volume":"39","author":"Andrychowicz","year":"2020","journal-title":"The International Journal of Robotics Research"},{"key":"10.1016\/j.vrih.2026.03.001_bib87","series-title":"DexMachina: functional retargeting for bimanual dexterous manipulation","author":"Zhao","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib88","series-title":"Deep dynamics models for learning dexterous manipulation","author":"Nagabandi","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.001_bib89","series-title":"DEFT: dexterous fine-tuning for real-world hand policies","author":"Kannan","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib90","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"109","article-title":"SemGrasp: semantic grasp generation via language aligned discretization","author":"Li","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib91","series-title":"Structure-aware human-action generation","author":"Yu","year":"2020"},{"issue":"1","key":"10.1016\/j.vrih.2026.03.001_bib92","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1609\/aaai.v37i1.25206","article-title":"MultiAct: long-term 3D human motion generation from multiple action labels","volume":"37","author":"Lee","year":"2023","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.vrih.2026.03.001_bib93","series-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"5915","article-title":"Text2Action: generative adversarial synthesis from language to action","author":"Ahn","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib94","series-title":"MotionCLIP: exposing human motion generation to CLIP space","author":"Tevet","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib95","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13253","article-title":"GOAL: generating 4D whole-body motion for hand-object grasping","author":"Taheri","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib96","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"20428","article-title":"Towards diverse and natural scene-aware 3D human motion synthesis","author":"Wang","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib97","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11050","article-title":"Bailando: 3D dance generation by actor-critic GPT with choreographic memory","author":"Li","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib98","series-title":"Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents","first-page":"97","article-title":"Analyzing input and output representations for speech-driven gesture generation","author":"Kucherenko","year":"2019"},{"issue":"8","key":"10.1016\/j.vrih.2026.03.001_bib99","doi-asserted-by":"crossref","first-page":"3052","DOI":"10.1109\/TCYB.2018.2838573","article-title":"Adaptive fuzzy control for coordinated multiple robots with constraint using impedance learning","volume":"49","author":"Kong","year":"2019","journal-title":"IEEE Transactions on Cybernetics"},{"key":"10.1016\/j.vrih.2026.03.001_bib100","doi-asserted-by":"crossref","DOI":"10.1016\/j.robot.2025.104943","article-title":"A task and motion planning framework using iteratively deepened AND\/OR graph networks","volume":"189","author":"Karami","year":"2025","journal-title":"Robotics and Autonomous Systems"},{"issue":"6","key":"10.1016\/j.vrih.2026.03.001_bib101","doi-asserted-by":"crossref","first-page":"3128","DOI":"10.1109\/TMECH.2021.3053562","article-title":"Human\u2013robot cooperation control based on trajectory deformation algorithm for a lower limb rehabilitation robot","volume":"26","author":"Zhou","year":"2021","journal-title":"ASME Transactions on Mechatronics"},{"key":"10.1016\/j.vrih.2026.03.001_bib102","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejcon.2022.100738","article-title":"Comparative study of post-impact motion control of a flexible arm space robot","volume":"69","author":"Kayastha","year":"2023","journal-title":"European Journal of Control"},{"issue":"10","key":"10.1016\/j.vrih.2026.03.001_bib103","doi-asserted-by":"crossref","first-page":"4796","DOI":"10.1109\/TCYB.2020.3021069","article-title":"Adaptive neural-network boundary control for a flexible manipulator with input constraints and model uncertainties","volume":"51","author":"Ren","year":"2021","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"2","key":"10.1016\/j.vrih.2026.03.001_bib104","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1109\/TNNLS.2020.2979600","article-title":"A vibration control method for hybrid-structured flexible manipulator based on sliding mode control and reinforcement learning","volume":"32","author":"Long","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"8","key":"10.1016\/j.vrih.2026.03.001_bib105","first-page":"759","article-title":"Optimum settings for automatic controllers","volume":"64","author":"Ziegler","year":"1942","journal-title":"Journal of Fluids Engineering"},{"issue":"3","key":"10.1016\/j.vrih.2026.03.001_bib106","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1016\/S0019-9958(65)90241-X","article-title":"Fuzzy sets","volume":"8","author":"Zadeh","year":"1965","journal-title":"Information and control"},{"issue":"1","key":"10.1016\/j.vrih.2026.03.001_bib107","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0020-7373(75)80002-2","article-title":"An experiment in linguistic synthesis with a fuzzy logic controller","volume":"7","author":"Mamdani","year":"1975","journal-title":"International Journal of Man-Machine Studies"},{"key":"10.1016\/j.vrih.2026.03.001_bib108","doi-asserted-by":"crossref","first-page":"100467","DOI":"10.1109\/ACCESS.2019.2928572","article-title":"A hybrid position\/force control method for a continuum robot with robotic and environmental compliance","volume":"7","author":"Xu","year":"2019","journal-title":"IEEE Access"},{"issue":"5","key":"10.1016\/j.vrih.2026.03.001_bib109","doi-asserted-by":"crossref","first-page":"1298","DOI":"10.1109\/TRO.2016.2593492","article-title":"Stability considerations for variable impedance control","volume":"32","author":"Kronander","year":"2016","journal-title":"IEEE Transactions on Robotics"},{"issue":"1","key":"10.1016\/j.vrih.2026.03.001_bib110","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1109\/TRO.2017.2765674","article-title":"Hierarchical force and positioning task specification for indirect force controlled robots","volume":"34","author":"Lutscher","year":"2018","journal-title":"IEEE Transactions on Robotics"},{"issue":"5","key":"10.1016\/j.vrih.2026.03.001_bib111","doi-asserted-by":"crossref","first-page":"2342","DOI":"10.1109\/TMECH.2019.2961478","article-title":"Passivity preservation for variable impedance control of compliant robots","volume":"25","author":"Spyrakos-Papastavridis","year":"2020","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"issue":"2","key":"10.1016\/j.vrih.2026.03.001_bib112","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1109\/TMECH.2022.3212707","article-title":"Dynamic skill learning from human demonstration based on the human arm stiffness estimation model and Riemannian DMP","volume":"28","author":"Liao","year":"2023","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"issue":"12","key":"10.1016\/j.vrih.2026.03.001_bib113","doi-asserted-by":"crossref","first-page":"7957","DOI":"10.1109\/TCYB.2023.3240502","article-title":"Trajectory tracking of variable centroid objects based on fusion of vision and force perception","volume":"53","author":"Gao","year":"2023","journal-title":"IEEE Transactions on Cybernetics"},{"key":"10.1016\/j.vrih.2026.03.001_bib114","series-title":"Dual control reference generation for optimal pick-and-place execution under payload uncertainty","author":"Vantilborgh","year":"2025"},{"issue":"5","key":"10.1016\/j.vrih.2026.03.001_bib115","doi-asserted-by":"crossref","first-page":"2752","DOI":"10.1109\/TMECH.2021.3112722","article-title":"An offline-merge-online robot teaching method based on natural human-robot interaction and visual-aid algorithm","volume":"27","author":"Du","year":"2022","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"key":"10.1016\/j.vrih.2026.03.001_bib116","series-title":"A survey on vision-language-action models for embodied AI","author":"Ma","year":"2024"},{"issue":"8059","key":"10.1016\/j.vrih.2026.03.001_bib117","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1038\/s41586-025-08744-2","article-title":"Mastering diverse control tasks through world models","volume":"640","author":"Hafner","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.vrih.2026.03.001_bib118","series-title":"RynnVLA-002: a unified vision-language-action and world model","author":"Cen","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib119","series-title":"WorldVLA: towards autoregressive action world model","author":"Cen","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib120","series-title":"Cliport: what and where pathways for robotic manipulation","author":"Shridhar","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib121","series-title":"RT-1: robotics Transformer for real-world control at scale","author":"Brohan","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib122","series-title":"RT-2: vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib123","series-title":"CogACT: a foundational vision-language-action model for synergizing cognition and action in robotic manipulation","author":"Li","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib124","series-title":"Octo: an open-source generalist robot policy","author":"Ghosh","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib125","series-title":"OpenVLA: an open-source vision-language-action model","author":"Kim","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib126","series-title":"\u03c00: a vision-language-action flow model for general robot control","author":"Black","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib127","series-title":"MoLe-VLA: dynamic layer-skipping vision language action model via mixture-of-layers for efficient robot manipulation","author":"Zhang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib128","series-title":"SimpleVLA-RL: scaling VLA training via reinforcement learning","author":"Li","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib129","series-title":"GR-3 technical report","author":"Cheang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib130","series-title":"V-JEPA 2: self-supervised video models enable understanding, prediction and planning","author":"Assran","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib131","series-title":"Findings of the Association for Computational Linguistics: ACL 2025","first-page":"26043","article-title":"Text2World: benchmarking large language models for symbolic world model generation","author":"Hu","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib132","series-title":"Aether: geometric-aware unified world modeling","author":"Zhu","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib133","series-title":"RoboScape: physics-informed embodied world model","author":"Shang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib134","series-title":"AgentSociety: large-scale simulation of LLM-driven generative agents advances understanding of human behaviors and society","author":"Piao","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib135","series-title":"Wan: open and advanced large-scale video generative models","author":"Wang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib136","series-title":"Cosmos world foundation model platform for physical AI","author":"NVIDIA","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib137","series-title":"Genie 3: A new frontier for world models","author":"DeepMind","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib138","series-title":"Genie envisioner: a unified world foundation platform for robotic manipulation","author":"Liao","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib139","series-title":"DreamGen: unlocking generalization in robot learning through video world models","author":"Jang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib140","series-title":"MineWorld: a real-time and open-source interactive world model on minecraft","author":"Guo","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib141","series-title":"Matrix-game: interactive world foundation model","author":"Zhang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib142","series-title":"GWM: towards scalable Gaussian world models for robotic manipulation","author":"Lu","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib143","series-title":"HunyuanWorld 1.0: generating immersive, explorable, and interactive 3D worlds from words or pixels","author":"Wang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib144","series-title":"EnerVerse: envisioning embodied future space for robotics manipulation","author":"Huang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib145","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia. Dublin Ireland","first-page":"12519","article-title":"AirScape: an aerial generative world model with motion controllability","author":"Zhao","year":"2025"},{"issue":"13","key":"10.1016\/j.vrih.2026.03.001_bib146","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"10.1016\/j.vrih.2026.03.001_bib147","series-title":"Computer Vision \u2013 ECCV 2018","first-page":"144","article-title":"Memory aware synapses: learning what (not) to forget","author":"Aljundi","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib148","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5533","article-title":"iCaRL: incremental classifier and representation learning","author":"Rebuffi","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.001_bib149","series-title":"Voyager: an open-ended embodied agent with large language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib150","series-title":"Machine Intelligence 15","first-page":"103","article-title":"A framework for behavioural cloning","author":"Bain","year":"2000"},{"key":"10.1016\/j.vrih.2026.03.001_bib151","series-title":"Diffusion policy: visuomotor policy learning via action diffusion","author":"Chi","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib152","series-title":"Generative adversarial imitation learning","author":"Ho","year":"2016"},{"key":"10.1016\/j.vrih.2026.03.001_bib153","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.001_bib154","series-title":"Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib155","series-title":"Conservative Q-learning for offline reinforcement learning","author":"Kumar","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib156","series-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib157","series-title":"Bridge data: boosting generalization of robotic skills with cross-domain datasets","author":"Ebert","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib158","series-title":"Open X-embodiment: robotic learning datasets and RT-X models","author":"O\u2019Neill","year":"2023"},{"issue":"2","key":"10.1016\/j.vrih.2026.03.001_bib159","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1063\/1674-0068\/cjcp1902036","article-title":"Structural evolution and electronic properties of Au2Gen-\/ 0 (n=1-8) clusters: anion photoelectron spectroscopy and theoretical calculations","volume":"32","author":"Lu","year":"2019","journal-title":"Chinese Journal of Chemical Physics"},{"key":"10.1016\/j.vrih.2026.03.001_bib160","series-title":"CLIP-RT: learning language-conditioned robotic policies from natural language supervision","author":"Kang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib161","series-title":"2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1321","article-title":"V-REP: a versatile and scalable robot simulation framework","author":"Rohmer","year":"2013"},{"key":"10.1016\/j.vrih.2026.03.001_bib162","series-title":"2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems. Vilamoura-Algarve","first-page":"5026","article-title":"MuJoCo: a physics engine for model-based control","author":"Todorov","year":"2012"},{"key":"10.1016\/j.vrih.2026.03.001_bib163","series-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2016"},{"key":"10.1016\/j.vrih.2026.03.001_bib164","series-title":"Unity: a general platform for intelligent agents","author":"Juliani","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib165","series-title":"AI2-THOR: an interactive 3D environment for visual AI","author":"Kolve","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.001_bib166","series-title":"Matterport3D: learning from RGB-D data in indoor environments","author":"Chang","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.001_bib167","series-title":"Sapien: a simulated part-based interactive environment","author":"Xiang","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib168","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3161","article-title":"RoboTHOR: an open simulation-to-real embodied AI platform","author":"Deitke","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib169","series-title":"ThreeDWorld: a platform for interactive multi-modal physical simulation","author":"Gan","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib170","series-title":"Habitat 2.0: training home assistants to rearrange their habitat","author":"Szot","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.001_bib171","series-title":"NVIDIA Isaac Sim","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib172","series-title":"ProcTHOR: large-scale embodied AI using procedural generation","author":"Deitke","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib173","series-title":"Proceedings of The 6th Conference on Robot Learning","first-page":"80","article-title":"Behavior-1K: a benchmark for embodied AI with 1,000 everyday activities and realistic simulation","author":"Li","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib174","series-title":"Habitat 3.0: a Co-habitat for humans, avatars and robots","author":"Puig","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib175","series-title":"ManiSkill3: GPU parallelized robotics simulation and rendering for generalizable embodied AI","author":"Tao","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib176","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16277","article-title":"Holodeck: language guided generation of 3D embodied AI environments","author":"Yang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib177","series-title":"RoboCasa: large-scale simulation of everyday tasks for generalist robots","author":"Nasiriany","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib178","series-title":"GRUtopia: dream general robots in a city at scale","author":"Wang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib179","series-title":"MetaUrban: a simulation platform for embodied AI in urban spaces","author":"Wu","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib180","series-title":"Genesis: A generative and universal physics engine for robotics and beyond","author":"Zhou","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib181","series-title":"AgentWorld: an interactive simulation platform for scene construction and mobile robotic manipulation","author":"Zhang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib182","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16277","article-title":"Holodeck: language guided generation of 3D embodied AI environments","author":"Yang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib183","series-title":"Stay on the path: instruction fidelity in vision-and-language navigation","author":"Jain","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.001_bib184","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12530","article-title":"Touchdown: natural language navigation and spatial reasoning in visual street environments","author":"Chen","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.001_bib185","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9979","article-title":"Reverie: remote embodied visual referring expression in real indoor environments","author":"Qi","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib186","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12684","article-title":"Soon: scenario oriented object navigation with graph-based exploration","author":"Zhu","year":"2021"},{"issue":"2","key":"10.1016\/j.vrih.2026.03.001_bib187","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1609\/aaai.v36i2.20097","article-title":"TEACh: task-driven embodied agents that chat","volume":"36","author":"Padmakumar","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"4","key":"10.1016\/j.vrih.2026.03.001_bib188","doi-asserted-by":"crossref","first-page":"10049","DOI":"10.1109\/LRA.2022.3193254","article-title":"DialFRED: dialogue-enabled agents for embodied instruction following","volume":"7","author":"Gao","year":"2022","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.vrih.2026.03.001_bib189","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11441","article-title":"GraspNet-1Billion: a large-scale benchmark for general object grasping","author":"Fang","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib190","series-title":"2021 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"6222","article-title":"ACRONYM: a large-scale grasp dataset based on simulation","author":"Eppner","year":"2021"},{"issue":"4\/5","key":"10.1016\/j.vrih.2026.03.001_bib191","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1177\/0278364914549607","article-title":"Deep learning for detecting robotic grasps","volume":"34","author":"Lenz","year":"2015","journal-title":"The International Journal of Robotics Research"},{"key":"10.1016\/j.vrih.2026.03.001_bib192","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"3511","article-title":"Jacquard: a large scale dataset for robotic grasp detection","author":"Depierre","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib193","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1","article-title":"Embodied question answering","author":"Das","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib194","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4089","article-title":"IQA: visual question answering in interactive environments","author":"Gordon","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.001_bib195","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6652","article-title":"Embodied question answering in photorealistic environments with point cloud perception","author":"Wijmans","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.001_bib196","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6302","article-title":"Multi-target embodied question answering","author":"Yu","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.001_bib197","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"19107","article-title":"ScanQA: 3D question answering for spatial scene understanding","author":"Azuma","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.001_bib198","series-title":"SQA3D: situated question answering in 3D scenes","author":"Ma","year":"2022"},{"issue":"10","key":"10.1016\/j.vrih.2026.03.001_bib199","doi-asserted-by":"crossref","first-page":"11948","DOI":"10.1109\/TPAMI.2023.3277206","article-title":"Knowledge-based embodied question answering","volume":"45","author":"Tan","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.vrih.2026.03.001_bib200","series-title":"tackling situational queries in embodied question answering","author":"Dorbala","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib201","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16488","article-title":"OpenEQA: embodied question answering in the era of foundation models","author":"Majumdar","year":"2024"},{"issue":"11","key":"10.1016\/j.vrih.2026.03.001_bib202","doi-asserted-by":"crossref","first-page":"9468","DOI":"10.1109\/TPAMI.2024.3381075","article-title":"Ego4D: around the world in 3, 600 hours of egocentric video","volume":"47","author":"Grauman","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.vrih.2026.03.001_bib203","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"19383","article-title":"Ego-Exo4D: understanding skilled human activity from first- and third-person perspectives","author":"Grauman","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib204","series-title":"The EPIC-KITCHENS dataset: collection, challenges and baselines","author":"Damen","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.001_bib205","series-title":"Computer Vision \u2013 ECCV 2012","first-page":"314","article-title":"Learning to recognize daily actions using gaze","author":"Fathi","year":"2012"},{"key":"10.1016\/j.vrih.2026.03.001_bib206","series-title":"LifelongMemory: leveraging LLMs for answering queries in long-form egocentric videos","author":"Wang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib207","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"92","article-title":"AMEGO: active memory from long EGOcentric videos","author":"Goletto","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib208","series-title":"EgoSchema: a diagnostic benchmark for very long-form video language understanding","author":"Mangalam","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.001_bib209","series-title":"Grounded multi-hop videoQA in long-form egocentric videos","author":"Chen","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib210","series-title":"Gazing as visual computing","author":"Lu","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib211","series-title":"In the eye of MLLM: benchmarking egocentric video intent understanding with gaze-guided prompting","author":"Peng","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.001_bib212","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"21978","article-title":"FreeMan: towards benchmarking 3D human pose estimation under real-world conditions","author":"Wang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.001_bib213","series-title":"Fast and slow thinking. Allen Lane and Penguin Books","first-page":"2","author":"Kahneman","year":"2011"},{"key":"10.1016\/j.vrih.2026.03.001_bib214","series-title":"Proceedings of the 2023 AAAI\/ACM Conference on AI, Ethics, and Society","first-page":"913","article-title":"Supporting human-AI collaboration in auditing LLMs with LLMs","author":"Rastogi","year":"2023"},{"issue":"7858","key":"10.1016\/j.vrih.2026.03.001_bib215","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1038\/s41586-021-03506-2","article-title":"High-performance brain-to-text communication via handwriting","volume":"593","author":"Willett","year":"2021","journal-title":"Nature"},{"issue":"2","key":"10.1016\/j.vrih.2026.03.001_bib216","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/nrn2787","article-title":"The free-energy principle: a unified brain theory?","volume":"11","author":"Friston","year":"2010","journal-title":"Nature Reviews Neuroscience"},{"key":"10.1016\/j.vrih.2026.03.001_bib217","doi-asserted-by":"crossref","DOI":"10.1017\/S0140525X16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behavioral and Brain Sciences"},{"key":"10.1016\/j.vrih.2026.03.001_bib218","series-title":"Machine theory of mind","author":"Rabinowitz","year":"2018"},{"issue":"37","key":"10.1016\/j.vrih.2026.03.001_bib219","doi-asserted-by":"crossref","DOI":"10.1126\/scirobotics.aay7120","article-title":"XAI-explainable artificial intelligence","volume":"4","author":"Gunning","year":"2019","journal-title":"Science Robotics"},{"issue":"3","key":"10.1016\/j.vrih.2026.03.001_bib220","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.mechmachtheory.2007.03.003","article-title":"An atlas of physical human\u2013robot interaction","volume":"43","author":"De Santis","year":"2008","journal-title":"Mechanism and Machine Theory"},{"issue":"2","key":"10.1016\/j.vrih.2026.03.001_bib221","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1109\/TRO.2016.2520486","article-title":"Supernumerary robotic limbs for human body support","volume":"32","author":"Parietti","year":"2016","journal-title":"IEEE Transactions on Robotics"},{"issue":"54","key":"10.1016\/j.vrih.2026.03.001_bib222","doi-asserted-by":"crossref","DOI":"10.1126\/scirobotics.abd7935","article-title":"Robotic hand augmentation drives changes in neural body representation","volume":"6","author":"Kieliba","year":"2021","journal-title":"Science Robotics"},{"issue":"9","key":"10.1016\/j.vrih.2026.03.001_bib223","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1016\/j.tics.2016.07.002","article-title":"Cognitive offloading","volume":"20","author":"Risko","year":"2016","journal-title":"Trends in Cognitive Sciences"},{"issue":"3","key":"10.1016\/j.vrih.2026.03.001_bib224","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1177\/0018720810376055","article-title":"Complacency and bias in human use of automation: an attentional integration","volume":"52","author":"Parasuraman","year":"2010","journal-title":"Human Factors"},{"issue":"1","key":"10.1016\/j.vrih.2026.03.001_bib225","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s40504-017-0050-1","article-title":"Towards new human rights in the age of neuroscience and neurotechnology","volume":"13","author":"Ienca","year":"2017","journal-title":"Life Sciences, Society and Policy"},{"issue":"7679","key":"10.1016\/j.vrih.2026.03.001_bib226","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1038\/551159a","article-title":"Four ethical priorities for neurotechnologies and AI","volume":"551","author":"Yuste","year":"2017","journal-title":"Nature"},{"issue":"3","key":"10.1016\/j.vrih.2026.03.001_bib227","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s10676-004-3422-1","article-title":"The responsibility gap: Ascribing responsibility for the actions of learning automata","volume":"6","author":"Matthias","year":"2004","journal-title":"Ethics and Information Technology"},{"issue":"4","key":"10.1016\/j.vrih.2026.03.001_bib228","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1007\/s13347-021-00450-x","article-title":"Four responsibility gaps with artificial intelligence: why they matter and how to address them","volume":"34","author":"Santoni de Sio","year":"2021","journal-title":"Philosophy & Technology"},{"issue":"5","key":"10.1016\/j.vrih.2026.03.001_bib229","doi-asserted-by":"crossref","first-page":"4282","DOI":"10.1103\/PhysRevE.51.4282","article-title":"Social force model for pedestrian dynamics","volume":"51","author":"Helbing","year":"1995","journal-title":"Physical Review E"}],"container-title":["Virtual Reality & Intelligent Hardware"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2096579626000161?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2096579626000161?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T19:45:00Z","timestamp":1778960700000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2096579626000161"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":229,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["S2096579626000161"],"URL":"https:\/\/doi.org\/10.1016\/j.vrih.2026.03.001","relation":{},"ISSN":["2096-5796"],"issn-type":[{"value":"2096-5796","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"From embodied AI to cobodied AI: Foundations and frontiers","name":"articletitle","label":"Article Title"},{"value":"Virtual Reality & Intelligent Hardware","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.vrih.2026.03.001","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"name":"copyright","label":"Copyright"}]}}