Conformal Trajectory Prediction with Multi-View Data Integration in Cooperative Driving

TL;DR

This paper introduces V2INet, an end-to-end multi-view trajectory prediction framework for cooperative driving that integrates V2V and V2I data, calibrated with conformal prediction for reliable confidence regions.

Contribution

The paper presents V2INet, a novel end-to-end model for multi-view trajectory prediction that seamlessly fuses V2V and V2I data, improving accuracy and confidence calibration.

Findings

Outperforms existing methods in FDE and Miss Rate

Supports end-to-end training with multi-view data

Achieves superior results using a single GPU

Abstract

Current research on trajectory prediction primarily relies on data collected by onboard sensors of an ego vehicle. With the rapid advancement in connected technologies, such as vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, valuable information from alternate views becomes accessible via wireless networks. The integration of information from alternative views has the potential to overcome the inherent limitations associated with a single viewpoint, such as occlusions and limited field of view. In this work, we introduce V2INet, a novel trajectory prediction framework designed to model multi-view data by extending existing single-view models. Unlike previous approaches where the multi-view data is manually fused or formulated as a separate training stage, our model supports end-to-end training, enhancing both flexibility and performance. Moreover, the predicted multimodal trajectories are calibrated by a post-hoc conformal prediction module to get valid and efficient confidence regions. We evaluated the entire framework using the real-world V2I dataset V2X-Seq. Our results demonstrate superior performance in terms of Final Displacement Error (FDE) and Miss Rate (MR) using a single GPU. The code is publicly available at: https://github.com/xichennn/V2I_trajectory_prediction.