空間整列時間エンコーディングによる画像を用いたデータ駆動型確率的動作評価と最適化
Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding
画像から初期状態を観測し、タスクを達成する長期的な動作を確率的に予測する手法を提案。画像と動作を空間整列時間エンコーディングで統合し、自己教師ありのDeep Motion Optimizerで最適化する。
著者: Takeru Oba, Norimichi Ukita
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
This paper proposes a probabilistic motion prediction method for long motions. The motion is predicted so that it accomplishes a task from the initial state observed in the given image. While our method evaluates the task achievability by the Energy-Based Model (EBM), previous EBMs are not designed for evaluating the consistency between different domains (i.e., image and motion in our method). Our method seamlessly integrates the image and motion data into the image feature domain by spatially-aligned temporal encoding so that features are extracted along the motion trajectory projected onto the image. Furthermore, this paper also proposes a data-driven motion optimization method, Deep Motion Optimizer (DMO), that works with EBM for motion prediction. Different from previous gradient-based optimizers, our self-supervised DMO alleviates the difficulty of hyper-parameter tuning to avoid local minima. The effectiveness of the proposed method is demonstrated with a variety of experiments with similar SOTA methods.
