Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty

TL;DR

This paper introduces a model for long-term prediction of people trajectories in traffic scenes, incorporating uncertainty estimation to improve safety in autonomous driving scenarios.

Contribution

It presents a novel approach that jointly predicts ego motion and pedestrian trajectories over a 1-second horizon, emphasizing uncertainty modeling in dynamic traffic environments.

Findings

Successful long-term trajectory prediction at 1-second horizon

Uncertainty estimates correlate with prediction errors

Sequence modeling and odometry prediction are crucial for performance

Abstract

Progress towards advanced systems for assisted and autonomous driving is leveraging recent advances in recognition and segmentation methods. Yet, we are still facing challenges in bringing reliable driving to inner cities, as those are composed of highly dynamic scenes observed from a moving platform at considerable speeds. Anticipation becomes a key element in order to react timely and prevent accidents. In this paper we argue that it is necessary to predict at least 1 second and we thus propose a new model that jointly predicts ego motion and people trajectories over such large time horizons. We pay particular attention to modeling the uncertainty of our estimates arising from the non-deterministic nature of natural traffic scenes. Our experimental results show that it is indeed possible to predict people trajectories at the desired time horizons and that our uncertainty estimates are informative of the prediction error. We also show that both sequence modeling of trajectories as well as our novel method of long term odometry prediction are essential for best performance.