Distilling Knowledge for Short-to-Long Term Trajectory Prediction

TL;DR

This paper introduces Di-Long, a knowledge distillation approach where a teacher model guides a student model to improve long-term trajectory prediction by leveraging short-term forecasts, achieving state-of-the-art results.

Contribution

The paper proposes a novel distillation framework that uses a teacher-student setup to enhance long-term trajectory forecasting accuracy.

Findings

Di-Long outperforms existing methods on inD and SDD datasets.

Knowledge distillation reduces uncertainty in long-term predictions.

The approach achieves state-of-the-art performance in long-term trajectory forecasting.

Abstract

Long-term trajectory forecasting is an important and challenging problem in the fields of computer vision, machine learning, and robotics. One fundamental difficulty stands in the evolution of the trajectory that becomes more and more uncertain and unpredictable as the time horizon grows, subsequently increasing the complexity of the problem. To overcome this issue, in this paper, we propose Di-Long, a new method that employs the distillation of a short-term trajectory model forecaster that guides a student network for long-term trajectory prediction during the training process. Given a total sequence length that comprehends the allowed observation for the student network and the complementary target sequence, we let the student and the teacher solve two different related tasks defined over the same full trajectory: the student observes a short sequence and predicts a long trajectory, whereas the teacher observes a longer sequence and predicts the remaining short target trajectory. The teacher's task is less uncertain, and we use its accurate predictions to guide the student through our knowledge distillation framework, reducing long-term future uncertainty. Our experiments show that our proposed Di-Long method is effective for long-term forecasting and achieves state-of-the-art performance on the Intersection Drone Dataset (inD) and the Stanford Drone Dataset (SDD).