Learning to Efficiently Plan Robust Frictional Multi-Object Grasps

Agboh, W.C., Sharma, S., Srinivas, K. et al. (7 more authors) (2023) Learning to Efficiently Plan Robust Frictional Multi-Object Grasps. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 01-05 Oct 2023, Detroit, USA. IEEE , pp. 10660-10667. ISBN 978-1-6654-9191-4

Abstract

We consider a decluttering problem where multiple rigid convex polygonal objects rest in randomly placed positions and orientations on a planar surface and must be efficiently transported to a packing box using both single and multi-object grasps. Prior work considered frictionless multi-object grasping. In this paper, we introduce friction to increase the number of potential grasps for a given group of objects, and thus increase picks per hour. We train a neural network using real examples to plan robust multi-object grasps. In physical experiments, we find a 13.7% increase in success rate, a 1.6x increase in picks per hour, and a 6.3x decrease in grasp planning time compared to prior work on multi-object grasping. Compared to single-object grasping, we find a 3.1x increase in picks per hour.

Metadata

Authors/Creators:

Agboh, W.C.
Sharma, S.
Srinivas, K.
Parulekar, M.
Datta, G.
Qiu, T.
Ichnowski, J.
Solowjow, E.
Dogar, M. https://orcid.org/0000-0002-6896-5461
Goldberg, K.

This is an author produced version of a conference paper accepted for publication in Proceedings of the 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), made available under the terms of the Creative Commons Attribution License (CC-BY), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited.

Dates: