TrACT: A Training Dynamics Aware Contrastive Learning Framework for Long-tail Trajectory Prediction

arXiv:2404.12538v1 Announce Type: cross
Abstract: As a safety critical task, autonomous driving requires accurate predictions of road users' future trajectories for safe motion planning, particularly under challenging conditions. Yet, many recent deep learning methods suffer from a degraded performance on the challenging scenarios, mainly because these scenarios appear less frequently in the training data. To address such a long-tail issue, existing methods force challenging scenarios closer together in the feature space during training to trigger information sharing among them for …

abstract arxiv autonomous autonomous driving cs.cv cs.lg deep learning driving dynamics framework future motion planning performance planning prediction predictions safe safety training trajectory type