AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Prediction

arXiv:2402.08698v1 Announce Type: cross
Abstract: Accurate prediction of pedestrians' future motions is critical for intelligent driving systems. Developing models for this task requires rich datasets containing diverse sets of samples. However, the existing naturalistic trajectory prediction datasets are generally imbalanced in favor of simpler samples and lack challenging scenarios. Such a long-tail effect causes prediction models to underperform on the tail portion of the data distribution containing safety-critical scenarios. Previous methods tackle the long-tail problem using methods such as contrastive …

abstract arxiv cs.cv cs.lg cs.ro datasets diverse driving experts framework future intelligent mixture of experts pedestrians prediction samples systems trajectory type