Snapshot: Towards Application-centered Models for Pedestrian Trajectory Prediction in Urban Traffic Environments
This work addresses the problem of improving real-world applicability and accuracy for autonomous driving systems, though it appears incremental by building on existing datasets and methods.
The paper tackles pedestrian trajectory prediction in urban traffic by introducing Snapshot, a modular feed-forward neural network that reduces Average Displacement Error by 8.8% compared to state-of-the-art methods while using less information.
This paper explores pedestrian trajectory prediction in urban traffic while focusing on both model accuracy and real-world applicability. While promising approaches exist, they often revolve around pedestrian datasets excluding traffic-related information, or resemble architectures that are either not real-time capable or robust. To address these limitations, we first introduce a dedicated benchmark based on Argoverse 2, specifically targeting pedestrians in traffic environments. Following this, we present Snapshot, a modular, feed-forward neural network that outperforms the current state of the art, reducing the Average Displacement Error (ADE) by 8.8% while utilizing significantly less information. Despite its agent-centric encoding scheme, Snapshot demonstrates scalability, real-time performance, and robustness to varying motion histories. Moreover, by integrating Snapshot into a modular autonomous driving software stack, we showcase its real-world applicability.