{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:24:02Z","timestamp":1781533442460,"version":"3.54.5"},"reference-count":25,"publisher":"ASME International","issue":"5","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2026276"],"award-info":[{"award-number":["2026276"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Human\u2013robot collaboration (HRC) has become an integral element of many manufacturing and service industries. A fundamental requirement for safe HRC is understanding and predicting human trajectories and intentions, especially when humans and robots operate nearby. Although existing research emphasizes predicting human motions or intentions, a key challenge is predicting both human trajectories and intentions simultaneously. This paper addresses this gap by developing a multi-task learning framework consisting of a bi-long short-term memory-based encoder\u2013decoder architecture that obtains the motion data from both human and robot trajectories as inputs and performs two main tasks simultaneously: human trajectory prediction and human intention prediction. The first task predicts human trajectories by reconstructing the motion sequences, while the second task tests two main approaches for intention prediction: supervised learning, specifically a support vector machine, to predict human intention based on the latent representation, and, an unsupervised learning method, the hidden Markov model, that decodes the latent features for human intention prediction. Four encoder designs are evaluated for feature extraction, including interaction-attention, interaction-pooling, interaction-seq2seq, and seq2seq. The framework is validated through a case study of a desktop disassembly task with robots operating at different speeds. The results include evaluating different encoder designs, analyzing the impact of incorporating robot motion into the encoder, and detailed visualizations. The findings show that the proposed framework can accurately predict human trajectories and intentions.<\/jats:p>","DOI":"10.1115\/1.4067157","type":"journal-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:15:50Z","timestamp":1731564950000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Task Learning for Intention and Trajectory Prediction in Human\u2013Robot Collaborative Disassembly Tasks"],"prefix":"10.1115","volume":"25","author":[{"given":"Xinyao","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Florida Environmental Engineering Sciences, , , \u00a0","place":["Gainesville, FL, 32611"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sibo","family":"Tian","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01f5ytq51","id-type":"ROR","asserted-by":"publisher"}],"name":"Texas A&M University Department of Mechanical Engineering, , , \u00a0","place":["College Station, TX, 77840"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Liang","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01f5ytq51","id-type":"ROR","asserted-by":"publisher"}],"name":"Texas A&M University Department of Civil & Environmental Engineering, , , \u00a0","place":["College Station, TX, 77840"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghui","family":"Zheng","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01f5ytq51","id-type":"ROR","asserted-by":"publisher"}],"name":"Texas A&M University Department of Mechanical Engineering, , , \u00a0","place":["College Station, TX, 77840"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Behdad","sequence":"additional","affiliation":[{"name":"University of Florida Environmental Engineering Sciences, , , \u00a0","place":["Gainesville, FL, 32611"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"33","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"issue":"12","key":"2026031018413125200_CIT0001","doi-asserted-by":"publisher","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","article-title":"A Survey on Multi-Task Learning","volume":"34","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Knowl. Data. Eng."},{"issue":"12","key":"2026031018413125200_CIT0002","doi-asserted-by":"publisher","first-page":"121002","DOI":"10.1115\/1.4062430","article-title":"A Vision-Based Human Digital Twin Modeling Approach for Adaptive Human-Robot Collaboration","volume":"145","author":"Fan","year":"2023","journal-title":"ASME J. Manuf. Sci. Eng."},{"key":"2026031018413125200_CIT0003","doi-asserted-by":"publisher","first-page":"101846","DOI":"10.1016\/j.rcim.2019.101846","article-title":"Human-Robot Coexistence and Interaction in Open Industrial Cells","volume":"61","author":"Magrini","year":"2020","journal-title":"Rob. Comput.-Integr. Manuf."},{"issue":"7","key":"2026031018413125200_CIT0004","doi-asserted-by":"publisher","first-page":"3053","DOI":"10.1007\/s10845-022-01989-y","article-title":"Combining Human Guidance and Structured Task Execution During Physical Human-Robot Collaboration","volume":"34","author":"Cacace","year":"2023","journal-title":"J. Intell. Manuf."},{"key":"2026031018413125200_CIT0005","doi-asserted-by":"publisher","first-page":"102714","DOI":"10.1016\/j.rcim.2023.102714","article-title":"Virtual Data Generation for Human Intention Prediction Based on Digital Modeling of Human-Robot Collaboration","volume":"87","author":"Yao","year":"2024","journal-title":"Rob. Comput.-Integr. Manuf."},{"issue":"5","key":"2026031018413125200_CIT0006","doi-asserted-by":"publisher","first-page":"051003","DOI":"10.1115\/1.4064258","article-title":"Early Prediction of Human Intention for Human\u2013Robot Collaboration Using Transformer Network","volume":"24","author":"Zhang","year":"2024","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"4","key":"2026031018413125200_CIT0007","doi-asserted-by":"publisher","first-page":"2056","DOI":"10.1109\/TMECH.2023.3275316","article-title":"Task-Constrained Motion Planning Considering Uncertainty-Informed Human Motion Prediction for Human-Robot Collaborative Disassembly","volume":"28","author":"Liu","year":"2023","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"2026031018413125200_CIT0008","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1016\/j.jmsy.2024.05.015","article-title":"Advancing Human-Robot Collaboration: Predicting Operator Trajectories Through AI and Infrared Imaging","volume":"74","author":"Katsampiris-Salgado","year":"2024","journal-title":"J. Manuf. Syst."},{"issue":"12","key":"2026031018413125200_CIT0009","doi-asserted-by":"publisher","first-page":"121001","DOI":"10.1115\/1.4062235","article-title":"Multi-Agent Reinforcement Learning Method for Disassembly Sequential Task Optimization Based on Human\u2013Robot Collaborative Disassembly in Electric Vehicle Battery Recycling","volume":"145","author":"Xiao","year":"2023","journal-title":"ASME J. Manuf. Sci. Eng."},{"issue":"1","key":"2026031018413125200_CIT0010","doi-asserted-by":"publisher","first-page":"011007","DOI":"10.1115\/1.4044586","article-title":"Prediction of Initial and Final Postures for Motion Planning in Human Manual Manipulation Tasks Based on Cognitive Decision Making","volume":"20","author":"Yang","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2026031018413125200_CIT0011","author":"Abuduweili","year":"2019"},{"key":"2026031018413125200_CIT0012","first-page":"3356","article-title":"An Optimization-Based Human Behavior Modeling and Prediction for Human-Robot Collaborative Disassembly","author":"Tian","year":"2023"},{"key":"2026031018413125200_CIT0013","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.jmsy.2023.01.007","article-title":"An Attention-Based Deep Learning Approach for Inertial Motion Recognition and Estimation in Human-Robot Collaboration","volume":"67","author":"Zhou","year":"2023","journal-title":"J. Manuf. Syst."},{"key":"2026031018413125200_CIT0014","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask Learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn."},{"key":"2026031018413125200_CIT0015","first-page":"579","article-title":"Multi-Task Deep Learning-Based Human Intention Prediction for Human-Robot Collaborative Assembly","author":"Cai","year":"2023"},{"key":"2026031018413125200_CIT0016","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.neucom.2020.10.016","article-title":"Robot Recognizing Humans Intention and Interacting With Humans Based on a Multi-Task Model Combining ST-GCN-LSTM Model and YOLO Model","volume":"430","author":"Liu","year":"2021","journal-title":"Neurocomputing"},{"key":"2026031018413125200_CIT0017","author":"Crawshaw","year":"2020"},{"key":"2026031018413125200_CIT0018","first-page":"9120","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Standley","year":"2020"},{"key":"2026031018413125200_CIT0019","article-title":"Sequence to Sequence Learning With Neural Networks","author":"Sutskever","year":"2014"},{"key":"2026031018413125200_CIT0020","doi-asserted-by":"publisher","first-page":"16283","DOI":"10.1109\/ACCESS.2022.3147519","article-title":"A Deep Learning-Based Approach for Inappropriate Content Detection and Classification of Youtube Videos","volume":"10","author":"Yousaf","year":"2022","journal-title":"IEEE Access"},{"key":"2026031018413125200_CIT0021","article-title":"Attention is All You Need","author":"Vaswani","year":"2017"},{"key":"2026031018413125200_CIT0022","first-page":"316","article-title":"A Comparison of Pooling Methods on LSTM Models for Rare Acoustic Event Classification","author":"Kao","year":"2020"},{"issue":"1","key":"2026031018413125200_CIT0023","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3448074","article-title":"Unsupervised Human Activity Representation Learning With Multi-Task Deep Clustering","volume":"5","author":"Ma","year":"2021","journal-title":"Association for Computing Machinery"},{"issue":"11","key":"2026031018413125200_CIT0024","doi-asserted-by":"publisher","first-page":"6870","DOI":"10.1109\/TCYB.2022.3166545","article-title":"Latent Low-Rank Representation With Weighted Distance Penalty for Clustering","volume":"53","author":"Fu","year":"2023","journal-title":"IEEE Trans. Cybern."},{"issue":"1","key":"2026031018413125200_CIT0025","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1109\/TII.2023.3264284","article-title":"Unsupervised Human Activity Recognition Learning for Disassembly Tasks","volume":"20","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Ind. Inform."}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/25\/5\/051002\/7404131\/jcise-24-1293.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/25\/5\/051002\/7404131\/jcise-24-1293.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T22:41:37Z","timestamp":1773182497000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/25\/5\/051002\/1209208\/Multi-Task-Learning-for-Intention-and-Trajectory"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":25,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4067157","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,10]]},"article-number":"051002"}}