Occlusion-Aware Search for Object Retrieval in Clutter
This addresses the manipulation task for robots in cluttered environments, representing an incremental improvement with specific domain application.
The paper tackles the problem of retrieving a target object from a cluttered shelf when it is hidden, using a data-driven hybrid planner that generates occlusion-aware actions in closed loop. The approach successfully searches and retrieves objects in near real time in real-world settings, trained only in simulation.
We address the manipulation task of retrieving a target object from a cluttered shelf. When the target object is hidden, the robot must search through the clutter for retrieving it. Solving this task requires reasoning over the likely locations of the target object. It also requires physics reasoning over multi-object interactions and future occlusions. In this work, we present a data-driven hybrid planner for generating occlusion-aware actions in closed-loop. The hybrid planner explores likely locations of the occluded target object as predicted by a learned distribution from the observation stream. The search is guided by a heuristic trained with reinforcement learning to act on observations with occlusions. We evaluate our approach in different simulation and real-world settings (video available on https://youtu.be/dY7YQ3LUVQg). The results validate that our approach can search and retrieve a target object in near real time in the real world while only being trained in simulation.