能動推論による物体中心シーン表現
Object-Centric Scene Representations using Active Inference
能動推論を用いた階層的物体中心生成モデルで、エージェントが物体カテゴリと姿勢を推論し、目標視点探索タスクで教師あり・強化学習を上回る性能を示した。
著者: Toon Van de Maele, Tim Verbelen, Pietro Mazzaglia, Stefano Ferraro, Bart Dhoedt
分類: cs.RO, cs.AI
原文アブストラクト
Representing a scene and its constituent objects from raw sensory data is a core ability for enabling robots to interact with their environment. In this paper, we propose a novel approach for scene understanding, leveraging a hierarchical object-centric generative model that enables an agent to infer object category and pose in an allocentric reference frame using active inference, a neuro-inspired framework for action and perception. For evaluating the behavior of an active vision agent, we also propose a new benchmark where, given a target viewpoint of a particular object, the agent needs to find the best matching viewpoint given a workspace with randomly positioned objects in 3D. We demonstrate that our active inference agent is able to balance epistemic foraging and goal-driven behavior, and outperforms both supervised and reinforcement learning baselines by a large margin.
