Full Text PDF
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Vol 10 No 6 (2026): Volume 10, Issue 6, June 2026 | Pages: 1-25
International Research Journal of Innovations in Engineering and Technology
OPEN ACCESS | Research Article | Published Date: 05-06-2026
Agent Trajectory Prediction (ATP) predicts future motion of an agent (vehicle/individual) given the surrounding environment (pathways, pedestrians, vehicles) and the agent’s previous motion history. This study aims to create a lightweight vehicle trajectory model that integrates driving lane information and physics-guided sparsification (i.e., inclusion of only the critical interacting nearby agents by selecting the select few based on physics-based neural network processing). The trajectory and other information was gathered using the nuScenes dataset and trained using different models to check the feasibility of both hard sparsification and physics-based gated learning using multi-layer perceptron (MLP) network. In this study, five models were created with different known architectures, among which the proposed model in this study implemented both physics-based gated learning using MLP and hard sparsification through selection of the top five critical neighboring agents based on the criticality score for interaction input. The models were compared on the basis of different evaluation metrics for accuracy, stability and safety. Qualitative analysis based on trajectory results and quantitative analysis based on robustness tests for missing or corrupt input was also performed to evaluate the models. Based on the results, the proposed model provided the most accurate and stable results for different scenarios, proving the effectiveness of combining gated learning with hard sparsification in creating an accurate and efficient ego trajectory model.
Trajectory Prediction, Sparsification, Ego Vehicle, nuScenes, Physics-guided.
Abhishek Silwal, & Anku Jaiswal. (2026). Physics-Guided Interaction Sparsification for Efficient Ego Trajectory Prediction. International Research Journal of Innovations in Engineering and Technology - IRJIET, 10(6), 1-25. Article DOI https://doi.org/10.47001/IRJIET/2026.106001
This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
Zhang, J., & Cho, Y., "Deep Trajectory Prediction: A Deep Learning Approach." Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2017.
Gupta, A., & Khan, M., "Predicting Future Trajectories with Generative Adversarial Networks." Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2018.
A. Alahi, K. Goel, V. Ramanathan, A. Robicquet, L. Fei-Fei, and S. Savarese, “Social LSTM: Human Trajectory Prediction in Crowded Spaces,” Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 961–971.
Z. Sheng, Z. Huang, and S. Chen, “EPG-MGCN: Ego-Planning Guided Multi-Graph Convolutional Network for Heterogeneous Agent Trajectory Prediction,” arXiv preprint arXiv:2303.17027, 2023.
M. Zhang, Z. Cai, L. Pan, F. Hong, X. Guo, L. Yang, and Z. Liu, "MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 6, pp. 4115–4128, 2024.
Z. Zhao, C. Hua, F. Berto, K. Lee, Z. Ma, J. Li, and J. Park, "Trajevo: Designing Trajectory Prediction Heuristics via LLM-Driven Evolution," arXiv preprint arXiv:2505.04480, 2025.
C. Liu, S. He, H. Liu, and J. Chen, "Intention-Aware Denoising Diffusion Model for Trajectory Prediction," arXiv preprint arXiv:2403.09190, 2024.
Y. Tang, H. He, Y. Wang, and Y. Wu, "Using a Diffusion Model for Pedestrian Trajectory Prediction in Semi-Open Autonomous Driving Environments," IEEE Sensors Journal, vol. 24, no. 10, pp. 17208–17218, 2024.
H. Sun, Z. Zhao, and Z. He, "Reciprocal Learning Networks for Human Trajectory Prediction," in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), pp. 7416–7425, 2020.
K. Saleh, “Pedestrian Trajectory Prediction for Real-Time Autonomous Systems via Context-Augmented Transformer Networks,” Sensors, vol. 22, no. 19, Art. no. 7495, Oct. 2022. doi:10.3390/s22197495
X., et al., “Context CVGN: A conditional multimodal trajectory prediction network based on scene semantic modeling,” Information Sciences, vol. 666, May 2024, Art. no. 120433.
B. Dong, H. Liu, Y. Bai, J. Lin, Z. Xu, X. Xu, and Q. Kong, “Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network,” NeurIPS Workshop: Machine Learning for Autonomous Driving, Vancouver, Canada, 2020. arXiv:2103.16273
C. Ji, Q. Li, “TrajSceneLLM: A Multimodal Perspective on Semantic GPS Trajectory Analysis,” arXiv preprint, Jun. 2025. arXiv:2506.16401
Z. Sun, Z. Wang, L. Halilaj, and J. Luettin, “SemanticFormer: Holistic and semantic traffic scene representation for trajectory prediction using knowledge graphs,” IEEE Robotics and Automation Letters, vol. 9, pp. 7381–7388, 2024.
H. Zhang et al., “Probabilistic semantic mapping for autonomous driving in urban environments,” Sensors, vol. 23, no. 14, Art. no. 6504, 2023. doi: 10.3390/s23146504.
Z. Li and H. Yu, “Trajectory prediction for autonomous driving using a transformer network,” arXiv preprint, 2024. arXiv:2402.16501
X. Wang et al., “IAtraj: Multi-modal trajectory prediction through contextual information spatio-temporal interaction and awareness,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 9, no. 5, pp. 17–28, 2024. doi: 10.9781/ijimai.2024.09.001.
J. Zhang, Y. Fan, F. Hui, E. Tan, and X. Zhou, “Interaction-aware trajectory prediction for heterogeneous agents in shared spaces,” Physica A: Statistical Mechanics and its Applications, 2025. Art. no. 131054.
J. Li, H. Ma, Z. Zhang, and M. Tomizuka, “Social-WaGDAT: Interaction-aware trajectory prediction via Wasserstein graph double-attention network,” arXiv preprint, 2020.arXiv:2002.06241
S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
J. L. Elman, “Finding Structure in Time,” Cognitive Science, vol. 14, no. 2, pp. 179–211, 1990, doi: 10.1207/s15516709cog1402_1.
K. Cho et al., “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 2014, pp. 1724–1734, doi: 10.3115/v1/D14-1179.
A. Vaswani et al., “Attention Is All You Need,” in Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA, 2017, pp. 6000–6010, doi: 10.48550/arXiv.1706.03762.
J. Ho, A. Jain, and P. Abbeel, “Denoising Diffusion Probabilistic Models,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 6840–6851, 2020, doi: 10.48550/arXiv.2006.11239.
X. Mo, Y. Xing, and C. Lv, “Interaction-Aware Trajectory Prediction of Connected Vehicles using CNN-LSTM Networks,” 2020.
Y. Peng, G. Zhang, J. Shi, B. Xu, and L. Zheng, “SRAI-LSTM: A Social Relation Attention-based Interaction-aware LSTM for Human Trajectory Prediction,” Neurocomputing, vol. 490, pp. 258–268, 2022.