Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty
This work addresses the challenge of reliable anticipation for assisted and autonomous driving in inner cities, which is incremental in improving safety through better trajectory prediction.
The paper tackles the problem of predicting people trajectories and ego motion over 1-second horizons in dynamic urban traffic scenes, showing that it is possible to achieve such predictions with uncertainty estimates that correlate with prediction error.
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.