Object-Centric Scene Representations using Active Inference
This addresses scene representation for robots, enabling better interaction with environments, but appears incremental as it builds on existing active inference frameworks.
The paper tackles the problem of scene understanding for robots by proposing an object-centric generative model using active inference to infer object category and pose, and demonstrates that their agent outperforms supervised and reinforcement learning baselines by a large margin on a new benchmark.
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.