Skip to main content

Learning Synergies between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning

Author(s): Zeng, A; Song, S; Welker, S; Lee, J; Rodriguez, A; et al

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1fz5w
Abstract: © 2018 IEEE. Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile (e.g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help displace objects to make pushing movements more precise and collision-free. In this work, we demonstrate that it is possible to discover and learn these synergies from scratch through model-free deep reinforcement learning. Our method involves training two fully convolutional networks that map from visual observations to actions: one infers the utility of pushes for a dense pixel-wise sampling of end-effector orientations and locations, while the other does the same for grasping. Both networks are trained jointly in a Q-learning framework and are entirely self-supervised by trial and error, where rewards are provided from successful grasps. In this way, our policy learns pushing motions that enable future grasps, while learning grasps that can leverage past pushes. During picking experiments in both simulation and real-world scenarios, we find that our system quickly learns complex behaviors even amid challenging cases of tightly packed clutter, and achieves better grasping success rates and picking efficiencies than baseline alternatives after a few hours of training. We further demonstrate that our method is capable of generalizing to novel objects. Qualitative results (videos), code, pre-trained models, and simulation environments are available at http://vpg.cs.princeton.edu .
Publication Date: 27-Dec-2018
Citation: Zeng, A, Song, S, Welker, S, Lee, J, Rodriguez, A, Funkhouser, T. (2018). Learning Synergies between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning. IEEE International Conference on Intelligent Robots and Systems, 4238 - 4245. doi:10.1109/IROS.2018.8593986
DOI: doi:10.1109/IROS.2018.8593986
ISSN: 2153-0858
EISSN: 2153-0866
Pages: 4238 - 4245
Type of Material: Conference Article
Journal/Proceeding Title: IEEE International Conference on Intelligent Robots and Systems
Version: Author's manuscript



Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.