介入的行動予測：過信した予測を避けるインタラクティブ予測
Interventional Behavior Prediction: Avoiding Overly Confident Anticipation in Interactive Prediction
自動運転のインタラクティブ予測において、計画軌道を介入として扱う介入的行動予測（IBP）を提案し、時間的独立性を検証するShapley値ベースの評価指標を導入した論文。
著者: Chen Tang, Wei Zhan, Masayoshi Tomizuka
分類: cs.RO, cs.AI
原文アブストラクト
Conditional behavior prediction (CBP) builds up the foundation for a coherent interactive prediction and planning framework that can enable more efficient and less conservative maneuvers in interactive scenarios. In CBP task, we train a prediction model approximating the posterior distribution of target agents' future trajectories conditioned on the future trajectory of an assigned ego agent. However, we argue that CBP may provide overly confident anticipation on how the autonomous agent may influence the target agents' behavior. Consequently, it is risky for the planner to query a CBP model. Instead, we should treat the planned trajectory as an intervention and let the model learn the trajectory distribution under intervention. We refer to it as the interventional behavior prediction (IBP) task. Moreover, to properly evaluate an IBP model with offline datasets, we propose a Shapley-value-based metric to verify if the prediction model satisfies the inherent temporal independence of an interventional distribution. We show that the proposed metric can effectively identify a CBP model violating the temporal independence, which plays an important role when establishing IBP benchmarks.
