TossingBot: Learning to Throw Arbitrary Objects With Residual Physics
Name
TossingBot_Learning_to_Throw_Arbitrary_Objects_With_Residual_Physics.pdf
Description
Published version
Size
4.31 MB
Format
Unknown
Checksum (MD5)
dec6aa9963ea4090080a812c9c09f3fa
Author(s)
Zeng, Andy
Song, Shuran
Lee, Johnny
Rodriguez Garcia, Alberto
Funkhouser, Thomas
Date Issued
2020
Journal
IEEE Transactions on Robotics
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Zeng, Andy, Song, Shuran, Lee, Johnny, Rodriguez, Alberto and Funkhouser, Thomas. 2020. "TossingBot: Learning to Throw Arbitrary Objects With Residual Physics." IEEE Transactions on Robotics, 36 (4).
Version
Final published version
Abstract
© 2004-2012 IEEE. We investigate whether a robot arm can learn to pick and throw arbitrary rigid objects into selected boxes quickly and accurately. Throwing has the potential to increase the physical reachability and picking speed of a robot arm. However, precisely throwing arbitrary objects in unstructured settings presents many challenges: from acquiring objects in grasps suitable for reliable throwing, to handling varying object-centric properties (e.g., mass distribution, friction, shape) and complex aerodynamics. In this work, we propose an end-to-end formulation that jointly learns to infer control parameters for grasping and throwing motion primitives from visual observations (RGB-D images of arbitrary objects in a bin) through trial and error. Within this formulation, we investigate the synergies between grasping and throwing (i.e., learning grasps that enable more accurate throws) and between simulation and deep learning (i.e., using deep networks to predict residuals on top of control parameters predicted by a physics simulator). The resulting system, TossingBot, is able to grasp and successfully throw arbitrary objects into boxes located outside its maximum reach range at 500+ mean picks per hour (600+ grasps per hour with 85% throwing accuracy); and generalizes to new objects and target locations.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/TRO.2020.2988642
