FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems

Bird's eye view (BEV) perception is becoming increasingly important in the field of autonomous driving. It uses multi-view camera data to learn a transformer model that directly projects the perception of the road environment onto the BEV perspective. However, training a transformer model often requires a large amount of data, and as camera data for road traffic is often private, it is typically not shared. Federated learning offers a solution that enables clients to collaborate and train models without exchanging data. In this paper, we propose FedBEVT, a federated transformer learning approach for BEV perception. We address two common data heterogeneity issues in FedBEVT: (i) diverse sensor poses and (ii) varying sensor numbers in perception systems. We present federated learning with camera-attentive personalization~(FedCaP) and adaptive multi-camera masking~(AMCM) to enhance the performance in real-world scenarios. To evaluate our method in real-world settings, we create a dataset consisting of four typical federated use cases. Our findings suggest that FedBEVT outperforms the baseline approaches in all four use cases, demonstrating the potential of our approach for improving BEV perception in autonomous driving. We will make all codes and data publicly available.