Inferring Pedestrian Motions at Urban Crosswalks

Abstract

Robust prediction of pedestrian behavior is one of the most challenging problems for autonomous driving. Particularly, predicting pedestrian crossings at crosswalks is of considerable importance for avoiding accidents on the one hand and not unnecessarily slowing down traffic on the other hand. Traditional model-based motion tracking and prediction approaches have difficulties in capturing abrupt changes in motions, as humans can perform. In this paper, an approach for predicting pedestrian motions that combines established motion tracking algorithms with data-driven methods is presented. The approach is built upon a hierarchical structure, where, first, the intent of each pedestrian is classified. Then, the approach computes several qualitative metrics, such as time-to-cross, for the pedestrians classified as crossing. The approach is evaluated on a challenging urban dataset collected for different types of crosswalks such as roundabouts and straight roads. The evaluation also provides a thorough analysis of the generalization performance of the proposed approach.

Toronto Intelligent Systems Lab Co-authors