Open Access Open Access  Restricted Access Subscription Access

DriveIntent

Sajith. J, Sanjay Nithin S, Sudhan Sanjay V P, Vignesh K, Ms. Sini Prabhakar

Abstract


Efficient perception and predictive intelligence are critical components of modern autonomous driving systems. DriveIntent: AI-Powered Trajectory Prediction System is designed to enhance road safety by accurately forecasting the future movements of vulnerable road users using advanced artificial intelligence techniques. The system employs transformer- based trajectory prediction combined with multi-sensor fusion to generate context-aware and multimodal future paths, overcoming the limitations of traditional reactive approaches. It further improves prediction reliability by modelling social interactions between agents and leveraging kinematic motion features. To ensure robustness, data from cameras, LiDAR, and radar are integrated, enabling consistent performance under occlusion and challenging environmental conditions. A real-time backend supports efficient inference, while an interactive dashboard provides intuitive visualization of predicted trajectories. Developed using modern deep learning frameworks and scalable system architecture, DriveIntent demonstrates the potential of AI-driven prediction systems to transform safety and decision- making in autonomous mobility.

 


Full Text:

PDF

References


Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser Ł. & Polosukhin I. (2017). Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS), 30, 5998–6008.

Salzmann T., Ivanovic B., Chakravarty P. & Pavone M. (2020). Trajectron++: Dynamically- feasible probabilistic trajectory forecasting with heterogeneous data. Proceedings of the European Conference on Computer Vision (ECCV), 12363, 683–700.

Alahi A., Goel K., Ramanathan V., Robicquet A., Fei-Fei L. & Savarese S. (2016). Social LSTM: Human trajectory prediction in crowded spaces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 961–971.

Giuliari F., Hasan I., Cristani M. & Galasso F. (2021). Transformer networks for trajectory forecasting. Proceedings of the International Conference on Pattern Recognition (ICPR), 10335–10342.

Li Z., Wang W., Li H., Xie E., Sima C., Lu T., Qiao Y. & Dai J. (2022). BEVFormer: Learning bird's-eye-view representation from multi-camera images via spatiotemporal transformers. Proceedings of the European Conference on Computer Vision (ECCV), 1–18.

Liu Z., Tang H., Amini A., Yang X., Mao H., Rus D. & Han S. (2022). BEVFusion: Multi- task multi-sensor fusion with unified bird's-eye view representation. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2774–2781.

Caesar H., Bankiti V., Lang A.H., Vora S., Liong V.E., Xu Q., Krishnan A., Pan Y., Baldan G. & Beijbom O. (2020). nuScenes: A multimodal dataset for autonomous driving. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 11621–11631.

Ren S., He K., Girshick R. & Sun J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems (NeurIPS), 28, 91–99.

Mohamed A., Qian K., Elhoseiny M. & Claudel C. (2020). Social-STGCNN: A social spatio- temporal graph convolutional neural network for human trajectory prediction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 14424–14432.

Zhao H., Gao J., Lan T., Sun C., Sapp B., Varadarajan B., Shen Y., Chai Y., Schmid C., Li C. & Anguelov D. (2021). TNT: Target-driven trajectory prediction. Proceedings of the Conference on Robot Learning (CoRL), 155, 895–904.


Refbacks

  • There are currently no refbacks.