Sense4FL: Vehicular Crowdsensing Enhanced Federated Learning for Autonomous Driving

2025-03-22

AI Summary

In federated learning (FL)-driven autonomous driving perception, conventional vehicle selection strategies ignore vehicular motion trajectories, leading to severe data distribution shifts across clients. Method: We propose a trajectory-aware vehicular crowdsourcing-enhanced FL framework that jointly models vehicle trajectories and spatial distributions of perception data. We introduce an Earth Mover’s Distance (EMD)-based metric to quantify data representativeness and theoretically derive a convergence upper bound for the FL process. To address the resulting NP-hard vehicle selection problem, we design an efficient approximation algorithm with provable approximation ratio guarantees. Contribution/Results: Extensive experiments on regional object detection demonstrate that our method improves mean Average Precision (mAP) by 12.7% over state-of-the-art baselines, validating the critical impact of trajectory-aware client selection on global model performance.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

To accommodate constantly changing road conditions, real-time model training is essential for autonomous driving (AD). Federated learning (FL) serves as a promising paradigm to enable autonomous vehicles to train models collaboratively with their onboard computing resources. However, existing vehicle selection schemes for FL all assume predetermined and location-independent vehicles' datasets, neglecting the fact that vehicles collect training data along their routes, thereby resulting in suboptimal vehicle selection. To improve the perception quality in AD for a region, we propose Sense4FL, a vehicular crowdsensing-enhanced FL framework featuring trajectory-dependent vehicular training data collection. To this end, we first derive the convergence bound of FL by considering the impact of both vehicles' uncertain trajectories and uploading probabilities, from which we discover that minimizing the training loss is equivalent to minimizing a weighted sum of local and global earth mover's distance (EMD) between vehicles' collected data distribution and global data distribution. Based on this observation, we formulate the trajectory-dependent vehicle selection and data collection problem for FL in AD. Given that the problem is NP-hard, we develop an efficient algorithm to find the solution with an approximation guarantee. Extensive simulation results have demonstrated the effectiveness of our approach in improving object detection performance compared with existing benchmarks.

Problem

• Improving autonomous driving perception via trajectory-aware federated learning
• Optimizing vehicle selection by minimizing data distribution discrepancies
• Enhancing real-time model training with crowdsourced vehicular data collection

Innovation

• Trajectory-dependent vehicular training data collection
• Minimizing local and global earth mover's distance
• Efficient algorithm with approximation guarantee