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

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 prec...

Full description

Bibliographic Details
Main Authors: Zeng, Andy (Author), Song, Shuran (Author), Welker, Stefan (Author), Lee, Johnny (Author), Rodriguez Garcia, Alberto (Author), Funkhouser, Thomas (Author)
Other Authors: Massachusetts Institute of Technology. Department of Mechanical Engineering (Contributor)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE), 2021-02-26T16:49:08Z.
Subjects:
Online Access:Get fulltext