目標・経由点・経路から長期人間軌道予測へ
From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting
人間の軌道予測の不確実性を「長期目標による認識的不確実性」と「経由点・経路による偶発的不確実性」に分解し、1分先までの長期予測設定を提案するとともに、その構造を活用するY-netで従来手法を上回った論文。
著者: Karttikeya Mangalam, Yang An, Harshayu Girase, Jitendra Malik
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Human trajectory forecasting is an inherently multi-modal problem. Uncertainty in future trajectories stems from two sources: (a) sources that are known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We propose to factorize this uncertainty into its epistemic & aleatoric sources. We model the epistemic un-certainty through multimodality in long term goals and the aleatoric uncertainty through multimodality in waypoints& paths. To exemplify this dichotomy, we also propose a novel long term trajectory forecasting setting, with prediction horizons upto a minute, an order of magnitude longer than prior works. Finally, we presentY-net, a scene com-pliant trajectory forecasting network that exploits the pro-posed epistemic & aleatoric structure for diverse trajectory predictions across long prediction horizons.Y-net significantly improves previous state-of-the-art performance on both (a) The well studied short prediction horizon settings on the Stanford Drone & ETH/UCY datasets and (b) The proposed long prediction horizon setting on the re-purposed Stanford Drone & Intersection Drone datasets.
