A Federated Multi-Task Meta-Learning Framework for Collaborative Perception and Adaptation in Connected and Automated Vehicles
Article Sidebar
Main Article Content
Abstract
Connected and Automated Vehicles (CAVs) operate in dynamic environments influenced by traffic patterns and pedestrian behaviour, which complicates the development of real-time navigation algorithms with voluminous data communicated by CAVs, raising privacy concerns. To address these challenges, we propose Federated Learning (FL) for concurrent and collaborative learning across fleets to generate privacy-preserving personalised models that adapt to diverse environments. Combining graph neural networks (GNNs) enables the real-time modelling of vehicle interactions and captures spatial and temporal dependencies. Utilising a message-passing paradigm, GNNs facilitate dynamic communication among vehicles. By aggregating information from neighbouring nodes, GNNs learn meaningful feature representations that enhance perception in CAVs, improving their responsiveness and enabling route optimisation and traffic flow enhancement. In this work, Model Predictive Control (MPC) influences GNNs to improve vehicle state prediction. It optimises control actions that minimise a cost function, such as travel time, fuel consumption, or collision risk, while adhering to constraints. GNNs enable the system to adapt its predictive model based on evolving vehicle relationships. At the same time, MPCs re-optimise control actions in response to these changes, allowing the CAVs to manage trajectories and make informed decisions adaptively in dynamic environments. The Federated Multi-Task Meta-Learning Framework for Collaborative Perception and Adaptation in Connected and Automated Vehicles (FedCAV) model is deployed across Edge, Fog, and Cloud layers to optimise performance, with a total estimated latency of 210 ms for 10 vehicles, influenced by local model training. Its low first-byte latency of 25 to 34 ms enhances communication efficiency, facilitating real-time decision-making and adaptive interactions.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access). As soon as the paper is accepted, finally submitted and edited, the paper will appear in the "OnlineFirst" page of the journal, thus from this point no other internet-based publication is necessary.
References
Acar, B., Sterling, M. (2023). Ensuring Federated Learning Reliability for Infrastructure-Enhanced Autonomous Driving. Journal of Intelligent and Connected Vehicles. 6(3), 125–135. DOI: http://doi.org/10.26599/JICV.2023.9210009
Avianto, D., Harjoko, A., Afiahayati (2022). CNN-Based Classification for Highly Similar Vehicle Model Using Multi-Task Learning. Journal of Imaging. 8(11), 293. DOI: http://doi.org/10.3390/jimaging8110293
Barrachina, D. G., Boldizsár, A., Zoldy, M., Torok, A. (2019). Can Neural Network Solve Everything? Case Study of Contradiction in Logistic Processes with Neural Network Optimisation. 2019 Modern Safety Technologies in Transportation (MOSATT). Kosice, Slovakia. 21–24, DOI: http://doi.org/10.1109/MOSATT48908.2019.8944120
Bas, J., Zou, Z., Cirillo, C. (2021). An interpretable machine learning approach to understanding the impacts of attitudinal and ridesourcing factors on electric vehicle adoption. Transportation Letters. 15(1), 30–41. DOI: http://doi.org/10.1080/19427867.2021.2009098
Basnet, M., Ali, M. H. (2021). A Deep Learning Perspective on Connected Automated Vehicle (CAV) Cybersecurity and Threat Intelligence. ArXiv. abs/2109.10763. DOI: http://doi.org/10.48550/arXiv.2109.10763
Cao, H., Zoldy, M. (2021). MPC Tracking Controller Parameters Impacts in Roundabouts. Mathematics. 9(12), 1394. DOI: http://doi.org/10.3390/math9121394
Chai, H., Leng, S., Chen, Y., Zhang, K. (2021). A Hierarchical Blockchain-Enabled Federated Learning Algorithm for Knowledge Sharing in Internet of Vehicles. IEEE Transactions on Intelligent Transportation Systems. 22(7), 3975–3986. DOI: http://doi.org/10.1109/TITS.2020.3002712
Chellapandi, V. P., Yuan, L., Brinton, C. G., Żak, S. H., Wang, Z. (2023). Federated Learning for Connected and Automated Vehicles: A Survey of Existing Approaches and Challenges. IEEE Transactions on Intelligent Vehicles. 9(1), 119–137. DOI: http://doi.org/10.1109/TIV.2023.3332675
Drissi, M. (2023). A state-of-the-art on federated learning for vehicular communications. Vehicular Communications. 45(3), 100709. DOI: http://doi.org/10.1016/j.vehcom.2023.100709
Gregurić, M., Vrbanić, F., Ivanjko, E. (2023). Impact of federated deep learning on vehicle-based speed control in mixed traffic flows. Journal of Parallel and Distributed Computing.186(2), 104812. DOI: http://doi.org/10.1016/j.jpdc.2023.104812
Han, M., Xu, K., Ma, S., Li, A., Jiang, H. (2022). Federated learning‐based trajectory prediction model with privacy preserving for intelligent vehicle. International Journal of Intelligent Systems. 37(1), 10861–10879. DOI: http://doi.org/10.1002/int.22987
Jahn, L. L., Park, S., Lim, Y., An, J., Choi, G. (2024). Enhancing lane detection with a lightweight collaborative late fusion model. Robotics and Autonomous Systems. 175(1),104680. DOI: http://doi.org/10.1016/j.robot.2024.104680
Khoshkangini, R., Mashhadi, P., Tegnered, D., Lundström, J., Rögnvaldsson, T. S. (2022). Predicting Vehicle Behavior Using Multi-task Ensemble Learning. Expert Systems with Applications. 212(6), 118716. DOI: http://doi.org/10.1016/j.eswa.2022.118716
Liu, S., Yu, G., Yin, R., Yuan, J., Qu, F. (2024). Communication and Computation Efficient Federated Learning for Internet of Vehicles with a Constrained Latency. IEEE Transactions on Vehicular Technology. 73(1), 1038–1052. DOI: http://doi.org/10.1109/TVT.2023.3309088
Okegbile, S. D., Cai, J., Zheng, H., Chen, J., Yi, C. (2023). Differentially Private Federated Multi-Task Learning Framework for Enhancing Human-to-Virtual Connectivity in Human Digital Twin. IEEE Journal on Selected Areas in Communications. 41(11), 3533–3547. DOI: http://doi.org/10.1109/JSAC.2023.3310106
Pang, Y., Zhu, X., He, T., Liu, S., Zhang, Z., Lv, Q., Yi, P., Lee, C. (2024). AI-Assisted Self-Powered Vehicle-Road Integrated Electronics for Intelligent Transportation Collaborative Perception. Advanced Materials. 36(36), e2404763. DOI: http://doi.org/10.1002/adma.202404763
Priya, J.C., Nanthakumar, G., Choudhury, T., Karthika, K. (2024). 6G-DeFLI: enhanced quality-of-services using distributed hash table and blockchain-enabled federated learning approach in 6G IoT networks. Wireless Networks. 31(1), 361–375. DOI: http://doi.org/10.1007/s11276-024-03759-5
Qu, Y., Gao, L., Luan, T. H., Xiang, Y., Yu, S., Li, B., Zheng, G. (2020). Decentralised Privacy Using Blockchain-Enabled Federated Learning in Fog Computing. IEEE Internet of Things Journal. 7(6), 5171–5183. DOI: DOI: http://doi.org/10.1109/JIOT.2020.2977383
Qu, K., Zhuang, W., Ye, Q., Wu, W., Shen, X. (2024). Model-Assisted Learning for Adaptive Cooperative Perception of Connected Autonomous Vehicles. IEEE Transactions on Wireless Communications. 23(8), 8820–8835. DOI: http://doi.org/10.1109/TWC.2024.3354507
Shao, Z., Yang, K., Sun, P., Hu, Y., Boukerche, A.F. (2024). The evolution of detection systems and their application for intelligent transportation systems: From solo to symphony. Computer Communications. 225(6), 96–119. DOI: http://doi.org/10.1016/j.comcom.2024.06.015
Tollner, D., Ziyu, W., Zöldy, M., Török, Á. (2024). Demonstrating a new evaluation method on ReLU based Neural Networks for classification problems. Expert Systems with Applications. 250(6), 123905. DOI: http://doi.org/10.1016/j.eswa.2024.123905
Yang, Z., Liu, C. (2023). Unified Perception and Collaborative Mapping for Connected and Autonomous Vehicles. IEEE Network. 37(4), 273–281. DOI: http://doi.org/10.1109/mnet.017.2300121
You, L., Zhu, R., Kwan, M., Chen, M., Zhang, F., Yang, B., Wong, M. S., Qin, Z. (2024). Unraveling adaptive changes in electric vehicle charging behavior toward the postpandemic era by federated meta-learning. The Innovation. 5(2):100587. DOI: http://doi.org/10.1016/j.xinn.2024.100587
Zhang, X., Liu, J., Hu, T., Chang, Z., Zhang, Y., Min, G. (2023). Federated Learning-Assisted Vehicular Edge Computing: Architecture and Research Directions. IEEE Vehicular Technology Magazine. 18(4), 75–84. DOI: http://doi.org/10.1109/MVT.2023.3297793
Zheng, Z., Ruan, T., Wei, Y., Yang, Y., Mei, T. (2020). VehicleNet: Learning Robust Visual Representation for Vehicle Re-Identification. IEEE Transactions on Multimedia. 23, 2683–2693. DOI: http://doi.org/10.1109/TMM.2020.3014488