From Perception to End-To-End: A Comprehensive Exploration of Intelligent Driving Technology, Scenarios, and Industrialization Challenges
DOI:
https://doi.org/10.54097/zzpnbg94Keywords:
Intelligent driving; BEV perception; sensor fusion; end-to-end learning; occupancy prediction.Abstract
Intelligent driving technology is evolving from traditional modular architectures toward end-to-end learning and shifting from 3D detection-based perception solutions to occupancy prediction and world models. This paper surveys the current mainstream intelligent driving technology solutions, including pure visual BEV (Bird's-Eye-View) solutions, radar-vision fusion solutions, and LiDAR-dominated solutions, while analyzing the advantages and disadvantages of each solution in L2/L3-level intelligent driving on urban roads. Research indicates that under the trade-off between cost and stability, different scenarios require distinct technical routes: radar-vision fusion solutions are suitable for low-speed urban scenarios, pure visual solutions can be applied in highway scenarios, and multi-sensor redundancy is necessary under adverse weather conditions. Future intelligent driving will move toward a more integrated and end-to-end direction, with occupancy prediction and world models emerging as key technologies.
Downloads
References
[1] Chen, L., Li, Y., Huang, C., Li, B., Zhang, B., Nie, L., Zhang, A., Xue, Z., & Wang, F. Y. (2022). Milestones in autonomous driving and intelligent vehicles: Survey of surveys. IEEE Transactions on Intelligent Vehicles, 8(2), 1046-1056.
[2] Chen, L., Wu, P., Chitta, K., Jaeger, B., Geiger, A., & Li, H. (2024). End-to-End autonomous driving: Challenges and frontiers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 10164-10183.
[3] Hu, Y., Yang, J., Chen, L., Li, K., Sima, C., Zhu, X., Chai, S., Du, S., Lin, T., Wang, W., Lu, L., Jia, X., Liu, P., Wang, D., Chen, Y., Wang, H., & Li, H. (2023). Planning-oriented autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 17853-17862).
[4] Muhammad, K., Ullah, A., Lloret, J., Del Ser, J., & de Albuquerque, V. H. C. (2020). Deep learning for safe autonomous driving: Current challenges and future directions. IEEE Transactions on Intelligent Transportation Systems, 22(7), 4316-4336.
[5] 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. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(3), 2020-2036.
[6] Wei, Y., Zhao, L., Zheng, W., Zhu, Z., Zhou, J., & Lu, J. (2023). SurroundOcc: Multi-camera 3D occupancy prediction for autonomous driving. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 21729-21740).
[7] Nabati, R., & Qi, H. (2021). CenterFusion: Center-based radar and camera fusion for 3D object detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 1527-1536).
[8] 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. arXiv preprint arXiv:2205.13542. https://arxiv.org/abs/2205.13542
[9] Xu, W., Cai, Y., He, D., Lin, J., & Zhang, F. (2022). FAST-LIO2: Fast direct LiDAR-inertial odometry. IEEE Transactions on Robotics, 38(4), 2053-2073.
[10] Teed, Z., & Deng, J. (2021). DROID-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras. Advances in Neural Information Processing Systems, 34, 16558-16569.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
