Pedestrian Behavior Prediction for Automated Driving: Requirements, Metrics, and Relevant Features
This work addresses the critical problem of pedestrian behavior prediction for automated driving systems by proposing a system-level approach and a new metric, which is an incremental improvement for the autonomous vehicle domain.
This paper analyzes the requirements for pedestrian behavior prediction in automated driving by studying real-world pedestrian-vehicle interactions with human drivers. It derives appropriate reaction patterns for automated vehicles and proposes a novel system-level metric for prediction performance, which is evaluated on a large-scale dataset.
Automated vehicles require a comprehensive understanding of traffic situations to ensure safe and anticipatory driving. In this context, the prediction of pedestrians is particularly challenging as pedestrian behavior can be influenced by multiple factors. In this paper, we thoroughly analyze the requirements on pedestrian behavior prediction for automated driving via a system-level approach. To this end we investigate real-world pedestrian-vehicle interactions with human drivers. Based on human driving behavior we then derive appropriate reaction patterns of an automated vehicle and determine requirements for the prediction of pedestrians. This includes a novel metric tailored to measure prediction performance from a system-level perspective. The proposed metric is evaluated on a large-scale dataset comprising thousands of real-world pedestrian-vehicle interactions. We furthermore conduct an ablation study to evaluate the importance of different contextual cues and compare these results to ones obtained using established performance metrics for pedestrian prediction. Our results highlight the importance of a system-level approach to pedestrian behavior prediction.