SafePicking: Learning Safe Object Extraction via Object-Level Mapping

TL;DR

SafePicking is a system that combines object-level scene understanding and learning-based motion planning to enable robots to safely extract occluded objects from cluttered piles, improving safety and robustness.

Contribution

It introduces a novel integration of object-level mapping with deep Q-network-based motion planning for safe object extraction.

Findings

Enhanced safety in object extraction from cluttered piles.

Improved robustness through observation fusion of poses and depth data.

Successful real-world and simulation experiments with YCB objects.

Abstract

Robots need object-level scene understanding to manipulate objects while reasoning about contact, support, and occlusion among objects. Given a pile of objects, object recognition and reconstruction can identify the boundary of object instances, giving important cues as to how the objects form and support the pile. In this work, we present a system, SafePicking, that integrates object-level mapping and learning-based motion planning to generate a motion that safely extracts occluded target objects from a pile. Planning is done by learning a deep Q-network that receives observations of predicted poses and a depth-based heightmap to output a motion trajectory, trained to maximize a safety metric reward. Our results show that the observation fusion of poses and depth-sensing gives both better performance and robustness to the model. We evaluate our methods using the YCB objects in both simulation and the real world, achieving safe object extraction from piles.