{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T12:08:31Z","timestamp":1779192511596,"version":"3.51.4"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["P0058204"],"award-info":[{"award-number":["P0058204"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.inffus.2026.104372","type":"journal-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T05:06:08Z","timestamp":1776143168000},"page":"104372","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Generative AI-augmented intention recognition and hierarchical multimodal policy learning for indoor navigation"],"prefix":"10.1016","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7858-7847","authenticated-orcid":false,"given":"Weizhi","family":"Tao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4202-3377","authenticated-orcid":false,"given":"Xinhao","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2667-6423","authenticated-orcid":false,"given":"Hailong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104372_bib0001","doi-asserted-by":"crossref","first-page":"141981","DOI":"10.1109\/ACCESS.2021.3120618","article-title":"Assistive delivery robot application for real-world postal services","volume":"9","author":"Lee","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.inffus.2026.104372_bib0002","doi-asserted-by":"crossref","first-page":"793","DOI":"10.3390\/electronics10070793","article-title":"On the gap between domestic robotic applications and computational intelligence","volume":"10","author":"Zhong","year":"2021","journal-title":"Electronics"},{"key":"10.1016\/j.inffus.2026.104372_bib0003","series-title":"Universal Access in Human-Computer Interaction. Interaction Techniques and Environments (UAHCI 2016)","first-page":"414","article-title":"Human aware robot navigation in semantically annotated domestic environments","volume":"9738","author":"Kostavelis","year":"2016"},{"key":"10.1016\/j.inffus.2026.104372_bib0004","series-title":"Robot Operating System (ROS)","first-page":"121","article-title":"ROS navigation: concepts and tutorial","volume":"625","author":"aes","year":"2020"},{"key":"10.1016\/j.inffus.2026.104372_bib0005","series-title":"2009 IEEE\/RSJ International Conference on Intelligent Robots and Systems, St Louis, MO, USA","first-page":"5573","article-title":"Generalized velocity obstacles","author":"Wilkie","year":"2009"},{"key":"10.1016\/j.inffus.2026.104372_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102532","article-title":"Embodied navigation with multi-modal information: a survey from tasks to methodology","volume":"112","author":"Wu","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104372_bib0007","doi-asserted-by":"crossref","first-page":"439","DOI":"10.23919\/JSEE.2023.000051","article-title":"A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures","volume":"34","author":"Dong","year":"2023","journal-title":"J. Syst. Eng. Electron."},{"key":"10.1016\/j.inffus.2026.104372_bib0008","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1177\/0278364920916531","article-title":"Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios","volume":"39","author":"Fan","year":"2020","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.inffus.2026.104372_bib0009","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada","first-page":"1343","article-title":"Socially aware motion planning with deep reinforcement learning","author":"Chen","year":"2017"},{"key":"10.1016\/j.inffus.2026.104372_bib0010","series-title":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No. 00TH8512), La Jolla, CA, USA","first-page":"256","article-title":"Evolutionary artificial potential fields and their application in real time robot path planning","volume":"1","author":"Vadakkepat","year":"2000"},{"key":"10.1016\/j.inffus.2026.104372_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2023.102440","article-title":"Multimodal fusion for autonomous navigation via deep reinforcement learning with sparse rewards and hindsight experience replay","volume":"78","author":"Xiao","year":"2023","journal-title":"Displays"},{"key":"10.1016\/j.inffus.2026.104372_bib0012","doi-asserted-by":"crossref","first-page":"6886","DOI":"10.1109\/LRA.2022.3178791","article-title":"Deep reinforcement learning for robot collision avoidance with self-state-attention and sensor fusion","volume":"7","author":"Han","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"10.1016\/j.inffus.2026.104372_bib0013","doi-asserted-by":"crossref","first-page":"4986","DOI":"10.1109\/LRA.2021.3064461","article-title":"Towards multi-modal perception-based navigation: a deep reinforcement learning method","volume":"6","author":"Huang","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104372_bib0014","doi-asserted-by":"crossref","first-page":"3668","DOI":"10.1109\/LRA.2025.3546069","article-title":"NavRL: learning safe flight in dynamic environments","volume":"10","author":"Xu","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104372_bib0015","first-page":"6","article-title":"Ethical decision making in autonomous vehicles: challenges and research progress","volume":"14","author":"Wang","year":"2022","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"10.1016\/j.inffus.2026.104372_bib0016","unstructured":"OpenAI, ChatGPT, 2022. [Online]. Available: https:\/\/openai.com."},{"key":"10.1016\/j.inffus.2026.104372_bib0017","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"Devlin","year":"2019"},{"key":"10.1016\/j.inffus.2026.104372_bib0018","series-title":"Proceedings of the 40th International Conference on Machine Learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume":"202","author":"Radford","year":"2023"},{"key":"10.1016\/j.inffus.2026.104372_bib0019","series-title":"Proc. of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021)","doi-asserted-by":"crossref","first-page":"3","DOI":"10.65109\/DPRS3876","article-title":"Simulating realistic pedestrian behaviors in the context of autonomous vehicles in shared spaces: doctoral consortium","author":"Pr\u00e9dhumeau","year":"2021"},{"key":"10.1016\/j.inffus.2026.104372_bib0020","series-title":"Advances in Artificial Intelligence, Canadian AI 2017","first-page":"260","article-title":"Speech intention classification with multimodal deep learning","volume":"10233","author":"Gu","year":"2017"},{"key":"10.1016\/j.inffus.2026.104372_bib0021","series-title":"Advances in Neural Information Processing Systems","first-page":"12449","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020"},{"key":"10.1016\/j.inffus.2026.104372_bib0022","series-title":"2019 International Engineering Conference (IEC), Erbil, Iraq","first-page":"200","article-title":"An overview of bag of words: importance, implementation, applications, and challenges","author":"Qader","year":"2019"},{"key":"10.1016\/j.inffus.2026.104372_bib0023","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3439726","article-title":"Deep learning\u2013based text classification: a comprehensive review","volume":"54","author":"Minaee","year":"2021","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"10.1016\/j.inffus.2026.104372_bib0024","first-page":"1097","article-title":"Exploring algorithmic efficiency of A-star and Dijkstra for optimal route planning in green transportation","volume":"23","author":"Elshaer","year":"2025","journal-title":"Int. J. Intell. Transp. Syst. Res."},{"key":"10.1016\/j.inffus.2026.104372_bib0025","series-title":"2011 IEEE International Conference on Robotics and Automation","first-page":"1478","article-title":"Anytime motion planning using the RRT*","author":"Karaman","year":"2011"},{"key":"10.1016\/j.inffus.2026.104372_bib0026","series-title":"2016 IEEE International Conference on Real-time Computing and Robotics (RCAR), Angkor Wat, Cambodia","first-page":"227","article-title":"A human-friendly robot navigation algorithm using the risk-RRT approach","author":"Chi","year":"2016"},{"key":"10.1016\/j.inffus.2026.104372_bib0027","series-title":"2017 18th International Conference on Advanced Robotics (ICAR), Hong Kong, China","first-page":"583","article-title":"Risk-RRT*: a robot motion planning algorithm for the human robot coexisting environment","author":"Chi","year":"2017"},{"key":"10.1016\/j.inffus.2026.104372_bib0028","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/100.580977","article-title":"The dynamic window approach to collision avoidance","volume":"4","author":"Fox","year":"1997","journal-title":"IEEE Robot. Autom. Mag."},{"key":"10.1016\/j.inffus.2026.104372_bib0029","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1080\/01441647.2017.1396265","article-title":"Social force models for pedestrian traffic \u2013 state of the art","volume":"38","author":"Chen","year":"2017","journal-title":"Transp. Rev."},{"key":"10.1016\/j.inffus.2026.104372_bib0030","doi-asserted-by":"crossref","first-page":"221743","DOI":"10.1109\/ACCESS.2020.3043333","article-title":"HPPRM: hybrid potential based probabilistic roadmap algorithm for improved dynamic path planning of mobile robots","volume":"8","author":"Ravankar","year":"2020","journal-title":"IEEE Access"},{"issue":"8","key":"10.1016\/j.inffus.2026.104372_bib0031","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1177\/00202940241291282","article-title":"Path planning of mobile robot based on improved PRM and APF","volume":"58","author":"Xi","year":"2024","journal-title":"Meas. Control"},{"key":"10.1016\/j.inffus.2026.104372_bib0032","doi-asserted-by":"crossref","first-page":"4946","DOI":"10.1109\/LRA.2025.3555937","article-title":"Intent prediction-driven model predictive control for UAV planning and navigation in dynamic environments","volume":"10","author":"Xu","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104372_bib0033","doi-asserted-by":"crossref","first-page":"66031","DOI":"10.1109\/ACCESS.2024.3394869","article-title":"A comprehensive review on deep learning-based motion planning and end-to-end learning for self-driving vehicle","volume":"12","author":"Ganesan","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.inffus.2026.104372_bib0034","doi-asserted-by":"crossref","first-page":"13087","DOI":"10.1109\/TASE.2025.3551464","article-title":"NAMR-RRT: neural adaptive motion planning for mobile robots in dynamic environments","volume":"22","author":"Sun","year":"2024","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.inffus.2026.104372_bib0035","series-title":"Advances in Neural Information Processing Systems","article-title":"PointNet++: deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017"},{"key":"10.1016\/j.inffus.2026.104372_bib0036","doi-asserted-by":"crossref","first-page":"96733","DOI":"10.1109\/ACCESS.2023.3311023","article-title":"Local path planning: dynamic window approach with Q-learning considering congestion environments for mobile robot","volume":"11","author":"Kobayashi","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.inffus.2026.104372_bib0037","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/s10514-020-09947-4","article-title":"Reinforcement based mobile robot path planning with improved dynamic window approach in unknown environment","volume":"45","author":"Chang","year":"2021","journal-title":"Auton. Robot"},{"key":"10.1016\/j.inffus.2026.104372_bib0038","series-title":"2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore","first-page":"1527","article-title":"From perception to decision: a data-driven approach to end-to-end motion planning for autonomous ground robots","author":"Pfeiffer","year":"2017"},{"key":"10.1016\/j.inffus.2026.104372_bib0039","series-title":"2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan","first-page":"1","article-title":"Sensor fusion and motion planning with unified bird\u2019s-eye view representation for end-to-end autonomous driving","author":"Lyu","year":"2024"},{"issue":"3","key":"10.1016\/j.inffus.2026.104372_bib0040","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1109\/MRA.2024.3427891","article-title":"Autonomous ground navigation in highly constrained spaces: lessons learned from the third BARN challenge at ICRA 2024 [Competitions]","volume":"31","author":"Xiao","year":"2024","journal-title":"IEEE Robot. Autom. Mag."},{"issue":"1","key":"10.1016\/j.inffus.2026.104372_bib0041","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1007\/s41315-024-00387-2","article-title":"Local planner selection for autonomous robots using machine learning","volume":"9","author":"\u00d6ner","year":"2025","journal-title":"Int. J. Intell. Robot. Appl."},{"key":"10.1016\/j.inffus.2026.104372_bib0042","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1109\/LRA.2021.3133591","article-title":"Goal-driven autonomous exploration through deep reinforcement learning","volume":"7","author":"Cimurs","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104372_bib0043","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"7568","article-title":"Learn to navigate in dynamic environments with normalized LiDAR scans","author":"Zhu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104372_bib0044","series-title":"Robotics: Science and Systems Proceedings","article-title":"Agile but safe: learning collision-free high-speed legged locomotion","author":"He","year":"2024"},{"key":"10.1016\/j.inffus.2026.104372_bib0045","series-title":"2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada","first-page":"3475","article-title":"A deep reinforcement learning approach to audio-based navigation in a multi-speaker environment","author":"Giannakopoulos","year":"2021"},{"key":"10.1016\/j.inffus.2026.104372_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101834","article-title":"Multi-modal policy fusion for end-to-end autonomous driving","volume":"98","author":"Huang","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104372_bib0047","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain","first-page":"1555","article-title":"Deep reinforcement learning for audio-visual gaze control","author":"Lathuiliere","year":"2018"},{"key":"10.1016\/j.inffus.2026.104372_bib0048","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"5580","article-title":"Robot sound interpretation: combining sight and sound in learning-based control","author":"Chang","year":"2020"},{"key":"10.1016\/j.inffus.2026.104372_bib0049","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1109\/TASE.2025.3646588","article-title":"HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environments","volume":"23","author":"Liu","year":"2026","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.inffus.2026.104372_bib0050","doi-asserted-by":"crossref","first-page":"2700","DOI":"10.1109\/TRO.2023.3257549","article-title":"DRL-VO: learning to navigate through crowded dynamic scenes using velocity obstacles","volume":"39","author":"Xie","year":"2023","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.inffus.2026.104372_bib0051","series-title":"2023 IEEE International Conference on Robotics and Automation (ICRA), London, United Kingdom","first-page":"12015","article-title":"Intention aware robot crowd navigation with attention-based interaction graph","author":"Liu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104372_bib0052","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1007\/s40747-023-01216-y","article-title":"Dynamic warning zone and a short-distance goal for autonomous robot navigation using deep reinforcement learning","volume":"10","author":"Montero","year":"2024","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.inffus.2026.104372_bib0053","unstructured":"J. Schulman, F. Wolski, P. Dhariwal, A. Radford, O. Klimov, Proximal Policy Optimization Algorithms, 2017, (arXiv). https:\/\/arxiv.org\/abs\/1707.06347."},{"key":"10.1016\/j.inffus.2026.104372_bib0054","unstructured":"Z. Xu, H. Shen, X. Han, H. Jin, K. Ye, K. Shimada, LV-DOT: LiDAR-visual dynamic obstacle detection and tracking for autonomous robot navigation, 2025. http:\/\/arxiv.org\/abs\/\/2502.20607."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002514?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002514?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:44:37Z","timestamp":1779191077000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526002514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":54,"alternative-id":["S1566253526002514"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104372","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Generative AI-augmented intention recognition and hierarchical multimodal policy learning for indoor navigation","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104372","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104372"}}