自動運転のための歩行者行動予測:要件・評価指標・有効な特徴量
Pedestrian Behavior Prediction for Automated Driving: Requirements, Metrics, and Relevant Features
実世界の歩行者と車両のインタラクションを分析し、自動運転車が取るべき反応パターンから歩行者予測の要件を導出。システムレベル視点の新評価指標を提案し、大規模データで検証した論文。
著者: Michael Herman, Jörg Wagner, Vishnu Prabhakaran, Nicolas Möser, Hanna Ziesche, Waleed Ahmed, Lutz Bürkle, Ernst Kloppenburg, Claudius Gläser
分類: cs.RO, cs.LG
原文アブストラクト
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.
