A Transferable Pedestrian Motion Prediction Model for Intersections with Different Geometries
This addresses the problem of pedestrian safety in autonomous driving by enabling accurate intent prediction across varied intersection layouts, though it is incremental as it builds on existing ASNSC methods.
The paper tackles pedestrian trajectory prediction at intersections by introducing a transferable framework that uses contravariant components in curbside coordinates to handle different geometries, achieving a 7.2% improvement in accuracy when trained and tested on the same intersection and comparable performance when transferred to new intersections.
This paper presents a novel framework for accurate pedestrian intent prediction at intersections. Given some prior knowledge of the curbside geometry, the presented framework can accurately predict pedestrian trajectories, even in new intersections that it has not been trained on. This is achieved by making use of the contravariant components of trajectories in the curbside coordinate system, which ensures that the transformation of trajectories across intersections is affine, regardless of the curbside geometry. Our method is based on the Augmented Semi Nonnegative Sparse Coding (ASNSC) formulation and we use that as a baseline to show improvement in prediction performance on real pedestrian datasets collected at two intersections in Cambridge, with distinctly different curbside and crosswalk geometries. We demonstrate a 7.2% improvement in prediction accuracy in the case of same train and test intersections. Furthermore, we show a comparable prediction performance of TASNSC when trained and tested in different intersections with the baseline, trained and tested on the same intersection.