{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:14:22Z","timestamp":1778530462383,"version":"3.51.4"},"reference-count":138,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CHANAKYA Fellowship Program of TIH Foundation for IoT & IoE","award":["CFP\/2022\/027"],"award-info":[{"award-number":["CFP\/2022\/027"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,5,15]]},"DOI":"10.1109\/jiot.2026.3671268","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:02:54Z","timestamp":1772830974000},"page":"20452-20476","source":"Crossref","is-referenced-by-count":0,"title":["A Comprehensive Review of Generative Physical Artificial Intelligence"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3259-0383","authenticated-orcid":false,"given":"Satyam","family":"Gaba","sequence":"first","affiliation":[{"name":"Qualcomm Research, San Diego, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4571-2649","authenticated-orcid":false,"given":"Krutiksinh","family":"Rana","sequence":"additional","affiliation":[{"name":"Department of Electronics and Instrumentation, Birla Institute of Technology and Science, Pilani (BITS Pilani), K K Birla Goa Campus, Pilani, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0927-9370","authenticated-orcid":false,"given":"Siva","family":"Sai","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6730-3060","authenticated-orcid":false,"given":"Vinay","family":"Chamola","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, BITS Pilani, Pilani Campus, Pilani, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"210","article-title":"On three-layer architectures","volume":"195","author":"Gat","year":"1998","journal-title":"Artif. Intell. Mobile Robots"},{"key":"ref2","volume-title":"The Rise of AI Robots","year":"2025"},{"key":"ref3","volume-title":"The Global Market for Humanoid Robots Could Reach $38 Billion by 2035","year":"2025"},{"key":"ref4","volume-title":"The Rise of AI-Powered Robotics, and the Future of Work","author":"Kelly","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/systems13050361"},{"key":"ref6","volume-title":"Robotics and Physical AI: Intelligence in Motion"},{"key":"ref7","article-title":"Generative artificial intelligence in robotic manipulation: A survey","author":"Zhang","year":"2025","journal-title":"arXiv:2503.03464"},{"key":"ref8","article-title":"Generative physical AI in vision: A survey","author":"Liu","year":"2025","journal-title":"arXiv:2501.10928"},{"key":"ref9","article-title":"A survey on robotics with foundation models: Toward embodied AI","author":"Xu","year":"2024","journal-title":"arXiv:2402.02385"},{"key":"ref10","article-title":"A comprehensive survey on world models for embodied AI","author":"Li","year":"2025","journal-title":"arXiv:2510.16732"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129963"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.26599\/AIR.2024.9150042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aad9398"},{"key":"ref14","article-title":"Industry 6.0: New generation of industry driven by generative AI and swarm of heterogeneous robots","author":"Lykov","year":"2024","journal-title":"arXiv:2409.10106"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/smb2.12008"},{"key":"ref16","article-title":"Vision-language-action (VLA) models: Concepts, progress, applications and challenges","author":"Sapkota","year":"2025","journal-title":"arXiv:2505.04769"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app13169255"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2025.3585028"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-024-00988-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2024.1427786"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01005-x"},{"key":"ref22","article-title":"REASSEMBLE: A multimodal dataset for contact-rich robotic assembly and disassembly","author":"Sliwowski","year":"2025","journal-title":"arXiv:2502.05086"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2024.12.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.799893"},{"key":"ref26","article-title":"Cosmos world foundation model platform for physical AI","author":"Agarwal","year":"2025","journal-title":"arXiv:2501.03575"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00465"},{"key":"ref28","article-title":"Robots pre-train robots: Manipulation-centric robotic representation from large-scale robot datasets","author":"Jiang","year":"2024","journal-title":"arXiv:2410.22325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02495-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/17298814211007305"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2300548"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref34","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref35","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kulkarni"},{"key":"ref36","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Christiano"},{"key":"ref37","article-title":"RLAIF vs. RLHF: Scaling reinforcement learning from human feedback with AI feedback","volume-title":"arXiv:2309.00267","author":"Lee","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.23919\/ECC55457.2022.9838102"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref44","first-page":"1411","article-title":"ROS-PyBullet Interface: A framework for reliable contact simulation and human\u2013robot interaction","volume-title":"Proc. Conf. Robot Learn.","author":"Mower"},{"key":"ref45","article-title":"Isaac gym: High performance GPU-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv:2108.10470"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2022.3197811"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref51","article-title":"REALM: A real-to-sim validated benchmark for generalization in robotic manipulation","author":"Sedlacek","year":"2025","journal-title":"arXiv:2512.19562"},{"key":"ref52","article-title":"Defining and evaluating physical safety for large language models","author":"Tang","year":"2024","journal-title":"arXiv:2411.02317"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241281508"},{"key":"ref55","article-title":"Zero-shot whole-body humanoid control via behavioral foundation models","author":"Tirinzoni","year":"2025","journal-title":"arXiv:2504.11054"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3601045"},{"key":"ref59","article-title":"Unified vision-language-action model","author":"Wang","year":"2025","journal-title":"arXiv:2506.19850"},{"key":"ref60","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Driess"},{"key":"ref61","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich"},{"key":"ref62","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"arXiv:2205.06175"},{"key":"ref63","article-title":"Exploring GPT-4 for robotic agent strategy with real-time state feedback and a reactive behaviour framework","author":"O\u2019Brien","year":"2025","journal-title":"arXiv:2503.23601"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2025.3590165"},{"key":"ref65","article-title":"Universal sentence encoder","author":"Cer","year":"2018","journal-title":"arXiv:1803.11175"},{"key":"ref66","article-title":"OpenVLA: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv:2406.09246"},{"key":"ref67","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref69","article-title":"Gemini robotics: Bringing AI into the physical world","author":"Robotics Team","year":"2025","journal-title":"arXiv:2503.20020"},{"key":"ref70","article-title":"Large content and behavior models to understand, simulate, and optimize content and behavior","author":"Khandelwal","year":"2023","journal-title":"arXiv:2309.00359"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127493"},{"key":"ref72","article-title":"Diffusion transformer policy","author":"Hou","year":"2024","journal-title":"arXiv:2410.15959"},{"key":"ref73","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Proc. Conf. Robot Learning","author":"Florence"},{"key":"ref74","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021","journal-title":"arXiv:2108.03298"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2025.07.011"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2025.103076"},{"key":"ref78","article-title":"Octo: An open-source generalist robot policy","author":"Model Team","year":"2024","journal-title":"arXiv:2405.12213"},{"key":"ref79","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ho"},{"key":"ref80","article-title":"A survey: Learning embodied intelligence from physical simulators and world models","author":"Long","year":"2025","journal-title":"arXiv:2507.00917"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e26503"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29075"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560935"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.04.181"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.153"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-025-02641-1"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02573"},{"key":"ref88","article-title":"WorldModelBench: Judging video generation models as world models","author":"Li","year":"2025","journal-title":"arXiv:2502.20694"},{"key":"ref89","article-title":"WorldSimBench: Towards video generation models as world simulators","author":"Qin","year":"2024","journal-title":"arXiv:2410.18072"},{"key":"ref90","article-title":"GAIA-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv:2309.17080"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.4324\/9780367262051-8"},{"key":"ref92","article-title":"End-to-end planning of autonomous driving in industry and academia: 2022\u20132023","author":"Lan","year":"2023","journal-title":"arXiv:2401.08658"},{"key":"ref93","volume-title":"NVIDIA DRIVE Full-Stack Autonomous Vehicle Software Rolls Out","author":"Wu","year":"2025"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102360"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3400161"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1111\/mice.70107"},{"key":"ref97","volume-title":"Dual-Arm YuMi\u00ae\u2014IRB 14000 (Collaborative Robot, ABB)","year":"2025"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/SII55687.2023.10039308"},{"key":"ref99","article-title":"Surgical scene understanding in the era of foundation AI models: A comprehensive review","author":"Khan","year":"2025","journal-title":"arXiv:2502.14886"},{"key":"ref100","article-title":"Surgical-LVLM: Learning to adapt large vision-language model for grounded visual question answering in robotic surgery","author":"Wang","year":"2024","journal-title":"arXiv:2405.10948"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/s00464-024-11126-w"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.3349\/ymj.2018.59.8.975"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.3390\/jpm13081233"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-021-01928-9"},{"key":"ref105","article-title":"GR00T n1: An open foundation model for generalist humanoid robots","author":"NVIDIA","year":"2025","journal-title":"arXiv:2503.14734"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9479-3"},{"key":"ref107","article-title":"Amazon announces 2 new ways it\u2019s using robots to assist employees and deliver for customers","author":"Dresser","year":"2023"},{"key":"ref108","volume-title":"Tesla Bot\u2019s New Human-Level Learning Milestone","author":"Kalil","year":"2025"},{"key":"ref109","article-title":"Dynamic AGV task allocation in intelligent warehouses","author":"Dehghan","year":"2023","journal-title":"arXiv:2312.16026"},{"key":"ref110","volume-title":"Amazon Has More Than 750,000 Robots That Sort, Lift, and Carry Packages\u2014See Them in Action","author":"Greenawalt","year":"2025"},{"key":"ref111","volume-title":"Walmart Commerce Technologies Launches Ai-powered Logistics Product"},{"key":"ref112","volume-title":"BMW Group Scales Virtual Factory","author":"Schmerbeck","year":"2025"},{"key":"ref113","volume-title":"Artificial Intelligence As a Quality Booster","author":"Graser","year":"2025"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.3390\/robotics15030055"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00832-8"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.30919\/esg1183"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2021.08.006"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-59958-9"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197326"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3411008"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-025-10457-7"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/j.modpat.2024.100686"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1017\/ilm.2024.46"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2138611"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2943405"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2024.3518761"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.3390\/computers12030060"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.3390\/technologies12060081"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-88714-7_29"},{"key":"ref130","article-title":"Open-endedness is essential for artificial superhuman intelligence","author":"Hughes","year":"2024","journal-title":"arXiv:2406.04268"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS64960.2025.00013"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2025.1668910"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/3806048"},{"key":"ref134","first-page":"708","article-title":"Learning for safety-critical control with control barrier functions","volume-title":"Proc. Learn. Dyn. control","author":"Taylor"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10916-x"},{"key":"ref136","article-title":"How hungry is AI? Benchmarking energy, water, and carbon footprint of LLM inference","author":"Jegham","year":"2025","journal-title":"arXiv:2505.09598"},{"key":"ref137","volume-title":"The Future of AI: Trends Shaping the Next 10 Years","author":"Mucci","year":"2024"},{"key":"ref138","article-title":"Toward general-purpose robots via foundation models: A survey and meta-analysis","author":"Hu","year":"2023","journal-title":"arXiv:2312.08782"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11513275\/11422915.pdf?arnumber=11422915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:48:57Z","timestamp":1778528937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11422915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,15]]},"references-count":138,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3671268","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,15]]}}}