Cross-OEM Federated Learning for Autonomous Driving
Keywords:
Autonomous Vehicle Technology, Collaborative Artificial Intelligence, Federated Learning Frameworks, Privacy-Preserving Machine Learning, Distributed Model Training, Collaborative Autonomous Driving, Multi-Manufacturer Vehicular Networks, Limited-Visibility Driving Scenarios, Safe Intersection Navigation, Communication-Efficient Learning, Vehicle Resource Constraints, Proprietary Data Formats, Decentralized Data Governance, Local Model Training, Agent-Specific Knowledge, Perception Gap Mitigation, Federated Data Flow Design, Secure Model Aggregation, Intelligent Transportation Systems, Privacy-Aware Autonomous Systems.Abstract
The growing interest in autonomous vehicle technology presents opportunities for manufacturers to pursue plans based on machine learning to develop their own self-driving solutions while maintaining their competitive edge. Collaborative artificial intelligence presents manufacturers with the possibility of cooperation without sharing private user data. Federated learning is a distributed machine-learning framework that enables multiple parties to cooperate on a common model while training locally on their own private data. Despite the similarities in the underlying technology, the application of federated learning for autonomous driving has attracted limited interest. Numerous challenges arise and need to be addressed: Different autonomous driving systems develop independently, and hence their models differ significantly. Vehicle manufacturers may use proprietary data formats that ensure the privacy of user data, and the necessary training data remain in the manufacturer domain. Communication efficiency is critical, as the resources of vehicles are constrained compared with fixed servers. Training data remain local, and agent-specific knowledge cannot be transferred directly.
Collaborative autonomous driving powered by federated learning could fill the perceptual gaps during periods of limited visibility and ensure the safe crossing of busy intersections. A federated-learning framework has been developed that integrates several key components and techniques for training across a multi-manufacture federated vehicular network. It transmits only key information that preserves the privacy of the drivers while enabling safe autonomous driving in a limited-visibility environment. Powers and constraints differ across manufacturers, so establishing a top-level data flow is also necessary.
References
1. Abad, G., Picek, S., Ramírez-Durán, V. J., & Urbieta, A. (2021). On the security & privacy in federated learning. In Proceedings of the 2021 IEEE International Conference on Cyber Security and Resilience (CSR).
2. Chellapandi, V. P., Yuan, L., Brinton, C. G., Żak, S. H., & Wang, Z. (2024). Federated learning for connected and automated vehicles: A survey of existing approaches and challenges. IEEE Transactions on Intelligent Vehicles, 9(1), 119–137.
3. Inala, R. (2023). Big Data Architectures for Modernizing Customer Master Systems in Group Insurance and Retirement Planning. Educational Administration: Theory and Practice, 29(4), 5493-5505.
4. Chellapandi, V. P., Yuan, L., Żak, S. H., & Wang, Z. (2023). A survey of federated learning for connected and automated vehicles. In 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC).
5. Cui, Y., Zhu, J., & Li, J. (2024). FLAV: Federated learning for autonomous vehicle privacy protection. Ad Hoc Networks.
6. Dai, R., Shen, L., He, F., Tian, X., & Tao, D. (2022). DisPFL: Towards communication-efficient personalized federated learning via decentralized sparse training. Proceedings of the 39th International Conference on Machine Learning, 162, 4587–4604.
7. Donevski, I., Nielsen, J. J., & Popovski, P. (2021). On addressing heterogeneity in federated learning for autonomous vehicles connected to a drone orchestrator. Frontiers in Communications and Networks, 2, Article 709946.
8. Fu, Y., Tang, X., Li, C., Yu, F. R., & others. (2024). A secure personalized federated learning algorithm for autonomous driving. IEEE Transactions on Intelligent Transportation Systems, 25(12), 20378–20389.
9. Hu, X., Li, R., Ning, Y., Ota, K., & Wang, L. (2023). A data sharing scheme based on federated learning in IoV. IEEE Transactions on Vehicular Technology.
10. Lee, J., Ko, H., & Pack, S. (2022). Adaptive deadline determination for mobile device selection in federated learning. IEEE Transactions on Vehicular Technology, 71(3), 3367–3371.
11. Lee, J., Ko, H., Seo, S., & Pack, S. (2023). Data distribution-aware online client selection algorithm for federated learning in heterogeneous networks. IEEE Transactions on Vehicular Technology, 72(1), 1127–1136.
12. Li, X., Jiang, M., Zhang, X., Kamp, M., & Dou, Q. (2021). FedBN: Federated learning on non-IID features via local batch normalization. In International Conference on Learning Representations.
13. Li, Y., Tao, X., Zhang, X., Liu, J., & Xu, J. (2022). Privacy-preserved federated learning for autonomous driving. IEEE Transactions on Intelligent Transportation Systems, 23(7), 8423–8434.
14. Li, Y., Li, H., Xu, G., Xiang, T., & Lu, R. (2022). Practical privacy-preserving federated learning in vehicular fog computing. IEEE Transactions on Vehicular Technology, 71(5), 4692–4706.
15. Liu, J., Yin, Z., Nie, L., & Zhao, X. (2024). Federated learning enable training of perception model for autonomous driving. SAE Technical Paper, 2024-01-2873.
16. Segireddy, A. R. (2024). Machine Learning-Driven Anomaly Detection in CI/CD Pipelines for Financial Applications. Journal of Computational Analysis and Applications, 33(8).
17. Liu, S., Yu, G., Yin, R., & Yuan, J. (2023). Communication and computation efficient federated learning for Internet of Vehicles with a constrained latency. IEEE Transactions on Vehicular Technology.
18. Ma, L., Liao, Y., Zhou, B., & Xi, W. (2023). PerHeFed: A general framework of personalized federated learning for heterogeneous convolutional neural networks. World Wide Web, 26, 2027–2049.
19. Ma, X., Zhang, J., Guo, S., & Xu, W. (2022). Layer-wised model aggregation for personalized federated learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10092–10101.
20. Marfoq, O., Neglia, G., Vidal, R., & Kameni, L. (2022). Personalized federated learning through local memorization. Proceedings of the 39th International Conference on Machine Learning, 162, 15070–15092.
21. Montazeri, M., Kebriaei, H., Araabi, B. N., Kang, J., & Niyato, D. (2023). Distributed mechanism design in continuous space for federated learning over vehicular networks. IEEE Transactions on Vehicular Technology, 72(4), 4196–4206.
22. Nguyen, A., Do, T., Tran, M., Nguyen, B. X., Duong, C., Phan, T., Tjiputra, E., & Tran, Q. D. (2021). Deep federated learning for autonomous driving.
23. Parekh, R. D., Patel, N., Gupta, R., Jadav, N. K., & others. (2023). GeFL: Gradient encryption-aided privacy preserved federated learning for autonomous vehicles. IEEE Access, 11, 1825–1839.
24. Kumar, K. M., Parasar, A., Walia, A., Inala, R., & Thulasimani, T. (2025, August). Enhancing Risk Management Strategies in Financial Institutions Using CNN and Support Vector Regression. In 2025 5th Asian Conference on Innovation in Technology (ASIANCON) (pp. 1-6). IEEE.
25. Shinde, S. S., Bozorgchenani, A., Tarchi, D., & Ni, Q. (2022). On the design of federated learning in latency and energy constrained computation offloading operations in vehicular edge computing systems. IEEE Transactions on Vehicular Technology, 71(2), 2041–2057.
26. Wang, S., Li, C., Ng, D. W. K., Eldar, Y. C., Poor, H. V., Hao, Q., & Xu, C. (2023). Federated deep learning meets autonomous vehicle perception: Design and verification. IEEE Network, 37(3), 16–25.
27. Wang, S., Hong, Y., Wang, R., Hao, Q., Wu, Y.-C., & Ng, D. W. K. (2022). Edge federated learning via unit-modulus over-the-air computation. IEEE Transactions on Communications, 70(5), 3141–3156.
28. Zeng, T., Semiari, O., Chen, M., Saad, W., & Bennis, M. (2022). Federated learning on the road: Autonomous controller design for connected and autonomous vehicles. IEEE Transactions on Wireless Communications, 21(12), 10407–10423.
