{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T20:29:59Z","timestamp":1770496199223,"version":"3.49.0"},"reference-count":47,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangxi Science and Technology Major Project","award":["AA22068057"],"award-info":[{"award-number":["AA22068057"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62262009"],"award-info":[{"award-number":["62262009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62495083"],"award-info":[{"award-number":["62495083"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>In mixed traffic scenarios involving both motorized and non-motorized participants, accurately predicting future trajectories of surrounding vehicles remains a major challenge for autonomous driving. Predicting the motion of powered two-wheelers (PTWs) is particularly difficult due to their abrupt behavioral changes and stochastic interaction patterns. To address this issue, this paper proposes an enhanced Social-GAT model with a multi-module architecture for PTW trajectory prediction. The model consists of a dual-channel LSTM encoder that separately processes position and motion features; a temporal attention mechanism to weight key historical states; and a residual-connected two-layer GAT structure to model social relationships within the interaction range, capturing interactive features between PTWs and surrounding vehicles through dynamic adjacency matrices. Finally, an LSTM decoder integrates spatiotemporal features and outputs the predicted trajectory. Experimental results on the rounD dataset demonstrate that our model achieves an outstanding ADE of 0.28, surpassing Trajectron++ by 9.68% and Social-GAN by 69.2%. It also attains the lowest RMSE values across 0.4\u20132.0s prediction horizons, confirming its superior accuracy and stability for PTW trajectory prediction in mixed traffic environments.<\/jats:p>","DOI":"10.3390\/systems13111036","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T11:17:27Z","timestamp":1763551047000},"page":"1036","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Trajectory Prediction for Powered Two-Wheelers in Mixed Traffic Scenes: An Enhanced Social-GAT Approach"],"prefix":"10.3390","volume":"13","author":[{"given":"Longxin","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin 541000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8606-3648","authenticated-orcid":false,"given":"Fujian","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin 541000, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0256-1382","authenticated-orcid":false,"given":"Jiangfeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin 541000, China"}]},{"given":"Haiquan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin 541000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5801-4937","authenticated-orcid":false,"given":"Yujie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin 541000, China"}]},{"given":"Zhongyi","family":"Zhai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541000, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TIV.2022.3167103","article-title":"A survey on trajectory-prediction methods for autonomous driving","volume":"7","author":"Huang","year":"2022","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"9127062","DOI":"10.1155\/2019\/9127062","article-title":"Modeling and simulation of nonmotorized vehicles\u2019 dispersion at mixed flow intersections","volume":"2019","author":"Liu","year":"2019","journal-title":"J. Adv. Transp."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104304","DOI":"10.1016\/j.trc.2023.104304","article-title":"A Two-layer integrated model for cyclist trajectory prediction considering multiple interactions with the environment","volume":"155","author":"Li","year":"2023","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"100077","DOI":"10.1016\/j.jcmr.2025.100077","article-title":"Cycling speed profiles from GPS data: Insights for conventional and electrified bicycles in Switzerland","volume":"5","author":"Maurer","year":"2025","journal-title":"J. Cycl. Micromobil. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"109997","DOI":"10.1016\/j.patcog.2023.109997","article-title":"MFAN: Mixing feature attention network for trajectory prediction","volume":"146","author":"Li","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"109513","DOI":"10.1016\/j.comnet.2022.109513","article-title":"A networked multi-agent reinforcement learning approach for cooperative FemtoCaching assisted wireless heterogeneous networks","volume":"220","author":"Yan","year":"2023","journal-title":"Comput. Netw."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Leigh, A., Pineau, J., Olmedo, N., and Zhang, H. (2015, January 26\u201330). Person tracking and following with 2D laser scanners. Proceedings of the International Conference on Robotics and Automation, Seattle, WA, USA.","DOI":"10.1109\/ICRA.2015.7139259"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1696","DOI":"10.1109\/LRA.2020.2969925","article-title":"What the constant velocity model can teach us about pedestrian motion prediction","volume":"5","author":"Aravantinos","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_11","first-page":"933","article-title":"Dynamic modeling and trajectory tracking of intelligent vehicles in off-road terrain","volume":"39","author":"Liu","year":"2019","journal-title":"J. Beijing Inst. Technol."},{"key":"ref_12","unstructured":"Liao, J.H. (2020). Research on LiDAR\/IMU Integrated Navigation and Positioning Method. [Ph.D. Theis, Nanchang University]."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/LRA.2020.3032079","article-title":"Interaction-aware motion prediction for autonomous driving: A multiple model Kalman filtering scheme","volume":"6","author":"Lefkopoulos","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3459","DOI":"10.1109\/LRA.2021.3062807","article-title":"Vehicle trajectory prediction using generative adversarial network with temporal logic syntax tree features","volume":"6","author":"Li","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"30210","DOI":"10.1109\/ACCESS.2020.2971705","article-title":"Research on traffic vehicle behavior prediction method based on game theory and HMM","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1109\/TII.2016.2597744","article-title":"Cyclist social force model at unsignalized intersections with heterogeneous traffic","volume":"13","author":"Huang","year":"2017","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"120753","DOI":"10.1016\/j.eswa.2023.120753","article-title":"High-resolution reconstruction of non-motorized trajectory in shared space: A new approach integrating the social force model and particle filtering","volume":"233","author":"Yan","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"107800","DOI":"10.1016\/j.patcog.2020.107800","article-title":"LSTM based trajectory prediction model for cyclist utilizing multiple interactions with environment","volume":"112","author":"Huang","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1016\/j.oceaneng.2019.04.024","article-title":"Ship trajectory uncertainty prediction based on a Gaussian process model","volume":"182","author":"Rong","year":"2019","journal-title":"Ocean Eng."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mandalia, H., and Salvucci, D. (2005, January 26\u201330). Using support vector machines for lane-change detection. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Orlando, FL, USA.","DOI":"10.1037\/e577512012-017"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"He, G., Li, X., Lv, Y., Gao, B., and Chen, H. (2019, January 22\u201324). Probabilistic intention prediction and trajectory generation based on dynamic Bayesian networks. Proceedings of the 2019 Chinese Automation Congress (CAC), Hangzhou, China.","DOI":"10.1109\/CAC48633.2019.8996494"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"111804","DOI":"10.1016\/j.engappai.2025.111804","article-title":"Vehicle trajectory prediction model based on graph attention Kolmogorov-Arnold networks and multiple attention","volume":"159","author":"Yang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_23","unstructured":"Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"10187","DOI":"10.1109\/TVT.2025.3548019","article-title":"DSTAnet: A trajectory distribution-aware spatio-temporal attention network for vehicle trajectory prediction","volume":"74","author":"Li","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Pool, E.A.I., Kooij, J.F.P., and Gavrila, D.M. (2019, January 9\u201312). Context-based cyclist path prediction using recurrent neural networks. Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Paris, France.","DOI":"10.1109\/IVS.2019.8813889"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Scheel, O., Nagaraja, N.S., Schwarz, L., Navab, N., and Tombari, F. (2019, January 20\u201324). Attention-based lane change prediction. Proceedings of the International Conference on Robotics and Automation, Montreal, QC, Canada.","DOI":"10.1109\/ICRA.2019.8793648"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3674","DOI":"10.1109\/TITS.2019.2931701","article-title":"Vehicle turning behavior modeling at conflicting areas of mixed-flow intersections based on deep learning","volume":"21","author":"Sun","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1016\/j.neucom.2021.11.089","article-title":"SRAI-LSTM: A social relation attention-based interaction-aware LSTM for human trajectory prediction","volume":"490","author":"Peng","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_29","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":"Phys. Rev. E"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Li, F.F., and Savarese, S. (2016, January 27\u201330). Social LSTM: Human trajectory prediction in crowded spaces. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chandra, R., Bhattacharya, U., Bera, A., and Manocha, D. (2019, January 15\u201320). TraPHic: Trajectory prediction in dense and heterogeneous traffic using weighted interactions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00868"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"13860","DOI":"10.1109\/TPAMI.2023.3298301","article-title":"HDGT: Heterogeneous driving graph transformer for multi-agent trajectory prediction via scene encoding","volume":"45","author":"Jia","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_33","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Ye, L., Wang, J., Wu, K., and Lu, K. (2022, January 18\u201324). HiVT: Hierarchical vector transformer for multi-agent motion prediction. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00862"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1286977","DOI":"10.1155\/2023\/1286977","article-title":"TCN-SA: A Social attention network based on temporal convolutional network for vehicle trajectory prediction","volume":"2023","author":"Li","year":"2023","journal-title":"J. Adv. Transp."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhan, T., Zhang, Q., Chen, G., and Cheng, J. (2023). VRR-Net: Learning vehicle-road relationships for vehicle trajectory prediction on highways. Mathematics, 11.","DOI":"10.3390\/math11061293"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.patrec.2023.03.006","article-title":"AMGB: Trajectory prediction using attention-based mechanism GCN-BiLSTM in IOV","volume":"169","author":"Li","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"867","DOI":"10.7307\/ptt.v36i5.600","article-title":"Vehicle trajectory prediction based on GAT and LSTM networks in urban environments","volume":"36","author":"Zheng","year":"2024","journal-title":"Promet-Traffic Transp."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"125510","DOI":"10.1016\/j.eswa.2024.125510","article-title":"A dual-level graph attention network and transformer for enhanced trajectory prediction under road network constraints","volume":"261","author":"Zhang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"3955","DOI":"10.1109\/TPAMI.2024.3352811","article-title":"MTR++: Multi-agent motion prediction with symmetric scene modeling and guided intention querying","volume":"46","author":"Shi","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Jo, E., Sunwoo, M., and Lee, M. (2021). Vehicle trajectory prediction using hierarchical graph neural network for considering interaction among multimodal maneuvers. Sensors, 21.","DOI":"10.3390\/s21165354"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Salzmann, T. (2020, January 23\u201328). Trajectron++: Dynamically-feasible trajectory forecasting with heterogeneous data. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58523-5_40"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Krajewski, R., Moers, T., Bock, J., Vater, L., and Eckstein, L. (2020, January 20\u201323). The round dataset: A drone dataset of road user trajectories at roundabouts in Germany. Proceedings of the 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Rhodes, Greece.","DOI":"10.1109\/ITSC45102.2020.9294728"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Saleh, K., Hossny, M., and Nahavandi, S. (2018, January 11\u201314). Cyclist trajectory prediction using bidirectional recurrent neural networks. Proceedings of the Australasian Joint Conference on Artificial Intelligence, Wellington, New Zealand.","DOI":"10.1007\/978-3-030-03991-2_28"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Li, F.F., Savarese, S., and Alahi, A. (2018, January 18\u201322). Social GAN: Socially acceptable trajectories with generative adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00240"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"110477","DOI":"10.1016\/j.comnet.2024.110477","article-title":"LSTM-based graph attention network for vehicle trajectory prediction","volume":"248","author":"Wang","year":"2024","journal-title":"Comput. Netw."},{"key":"ref_47","unstructured":"Liao, H., Li, Z., Shen, H., Zeng, W., Liao, D., Li, G., and Xu, C. (March, January 25). BAT: Behavior-aware human-like trajectory prediction for autonomous driving. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/11\/1036\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T11:51:38Z","timestamp":1763553098000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/11\/1036"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":47,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["systems13111036"],"URL":"https:\/\/doi.org\/10.3390\/systems13111036","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,19]]}}}