Trajectory Prediction with Observations of Variable-Length for Motion Planning in Highway Merging scenarios

TL;DR

This paper introduces a transformer-based trajectory prediction method capable of handling variable-length observations, improving safety and efficiency in highway merging scenarios for automated vehicles.

Contribution

It presents a novel prediction approach that works with any observation length over one frame, enabling faster reactions and better integration with motion planning.

Findings

Achieves state-of-the-art performance on highD dataset.

Maintains lower prediction error than constant velocity model across all observation lengths.

Enhances safety, comfort, and efficiency in dense traffic scenarios.

Abstract

Accurate trajectory prediction of nearby vehicles is crucial for the safe motion planning of automated vehicles in dynamic driving scenarios such as highway merging. Existing methods cannot initiate prediction for a vehicle unless observed for a fixed duration of two or more seconds. This prevents a fast reaction by the ego vehicle to vehicles that enter its perception range, thus creating safety concerns. Therefore, this paper proposes a novel transformer-based trajectory prediction approach, specifically trained to handle any observation length larger than one frame. We perform a comprehensive evaluation of the proposed method using two large-scale highway trajectory datasets, namely the highD and exiD. In addition, we study the impact of the proposed prediction approach on motion planning and control tasks using extensive merging scenarios from the exiD dataset. To the best of our knowledge, this marks the first instance where such a large-scale highway merging dataset has been employed for this purpose. The results demonstrate that the prediction model achieves state-of-the-art performance on highD dataset and maintains lower prediction error w.r.t. the constant velocity across all observation lengths in exiD. Moreover, it significantly enhances safety, comfort, and efficiency in dense traffic scenarios, as compared to the constant velocity model.