SafePicking: learning safe object extraction via object-level mapping

Publication available at:
Title: SafePicking: learning safe object extraction via object-level mapping
Authors: Wada, K
James, S
Davison, AJ
Item Type: Conference Paper
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.
Issue Date: 12-Jul-2022
Date of Acceptance: 1-Jul-2022
DOI: 10.1109/icra46639.2022.9812009
Publisher: IEEE
Journal / Book Title: 2022 International Conference on Robotics and Automation (ICRA)
Copyright Statement: © 20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Dyson Technology Limited
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: PO 4500501004
Conference Name: 2022 IEEE International Conference on Robotics and Automation (ICRA)
Publication Status: Published
Start Date: 2022-05-23
Finish Date: 2022-05-27
Open Access location:
Appears in Collections:Computing