Reputation-Driven Asynchronous Federated Learning for Enhanced Trajectory Prediction With Blockchain

Federated learning (FL), when integrated with blockchain, facilitates secure data sharing in autonomous driving applications. As vehicle-generated data becomes more granular and complex, the absence of data quality audits raises concerns about multiparty mistrust in trajectory prediction tasks. However, most of the existing research on trajectory prediction focuses on how to improve the model to enhance the prediction accuracy, and lacks the consideration of the privacy and security issues of data sharing in real-world scenarios. To address this, we propose an asynchronous FL data-sharing method, incorporating an interpretable reputation quantization mechanism based on graph convolutional networks. Data providers share data structures under differential privacy constraints, ensuring security while minimizing redundancy. We utilize deep reinforcement learning to classify vehicles by reputation level, optimizing FL aggregation efficiency. Experimental results show that the proposed scheme not only strengthens the security of trajectory prediction but also improves prediction accuracy.

I. Introduction

The rapid advancements in computational and communication technologies, particularly within the 5G network, have revolutionized modern vehicular services and applications, significantly enhancing the driving experience [1]. Autonomous vehicles are complex systems that integrate various technologies, including perception algorithms [2], path planning [3], control theory [4], and positioning [5]. Among the key research areas, trajectory prediction [6] is pivotal to the decision-making processes of intelligent vehicles. A precise and reliable trajectory prediction algorithm can anticipate potential traffic accidents, thereby enhancing overall vehicular safety through timely preventive measures.