Privacy-preserving and Uncertainty-aware Federated Trajectory Prediction for Connected Autonomous Vehicles
This work addresses privacy and uncertainty issues in safety-critical autonomous vehicle systems, but it is incremental as it builds on existing federated and active learning techniques.
The paper tackles the problem of privacy leakage and lack of uncertainty-awareness in trajectory prediction for autonomous vehicles by proposing a federated learning algorithm (FLTP) and an active learning-enhanced version (ALFLTP), which outperforms local training and shows improved convergence and performance metrics like NLL, minADE, and MR on the Argoverse dataset.
Deep learning is the method of choice for trajectory prediction for autonomous vehicles. Unfortunately, its data-hungry nature implicitly requires the availability of sufficiently rich and high-quality centralized datasets, which easily leads to privacy leakage. Besides, uncertainty-awareness becomes increasingly important for safety-crucial cyber physical systems whose prediction module heavily relies on machine learning tools. In this paper, we relax the data collection requirement and enhance uncertainty-awareness by using Federated Learning on Connected Autonomous Vehicles with an uncertainty-aware global objective. We name our algorithm as FLTP. We further introduce ALFLTP which boosts FLTP via using active learning techniques in adaptatively selecting participating clients. We consider both negative log-likelihood (NLL) and aleatoric uncertainty (AU) as client selection metrics. Experiments on Argoverse dataset show that FLTP significantly outperforms the model trained on local data. In addition, ALFLTP-AU converges faster in training regression loss and performs better in terms of NLL, minADE and MR than FLTP in most rounds, and has more stable round-wise performance than ALFLTP-NLL.