身体性AIのための連続的シーン表現
Continuous Scene Representations for Embodied AI
空間を移動するエージェントが物体間の関係を連続値埋め込みで表現し、グラフ構造として動的に構築するシーン表現手法を提案。部屋の再配置タスクで既存手法を上回る。
著者: Samir Yitzhak Gadre, Kiana Ehsani, Shuran Song, Roozbeh Mottaghi
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
We propose Continuous Scene Representations (CSR), a scene representation constructed by an embodied agent navigating within a space, where objects and their relationships are modeled by continuous valued embeddings. Our method captures feature relationships between objects, composes them into a graph structure on-the-fly, and situates an embodied agent within the representation. Our key insight is to embed pair-wise relationships between objects in a latent space. This allows for a richer representation compared to discrete relations (e.g., [support], [next-to]) commonly used for building scene representations. CSR can track objects as the agent moves in a scene, update the representation accordingly, and detect changes in room configurations. Using CSR, we outperform state-of-the-art approaches for the challenging downstream task of visual room rearrangement, without any task specific training. Moreover, we show the learned embeddings capture salient spatial details of the scene and show applicability to real world data. A summery video and code is available at https://prior.allenai.org/projects/csr.
