event

PhD Proposal by Man Xie

Primary tabs

Title: Learning Motion Policies for Dexterous Manipulation with Geometric Fabrics

 

Date: Wednesday, May 4th, 2022

Time: 4:00 PM – 6:00 PM EST

Location: Zoom Meeting (https://gatech.zoom.us/j/96014725301?pwd=SlpXbUhMNFptbzUvRng4RzYvVHhjUT09)

 

Man Xie

Ph.D. Student in Computer Science 

School of Interactive Computing

Georgia Institute of Technology

 

Committee:

Dr. Frank Dellaert (Advisor) – School of Interactive Computing, Georgia Institute of Technology

Dr. Harish Ravichandar (Co-advisor) – School of Interactive Computing, Georgia Institute of Technology

Dr. Seth Hutchinson – School of Interactive Computing, Georgia Institute of Technology

Dr. Byron Boots – School of Computer Science & Engineering, University of Washington

Dr. Nathan Ratliff – Seattle Robotics Lab, Nvidia

 

Summary:

Given that our world is designed by and for humans with impressive dexterity, it is natural to posit that robots with dexterous manipulation skills can effectively operate in a variety of human environments. However, dexterous manipulation in multi-fingered robots has been a long-standing challenge in robotics due to the fact that dexterity requires complex skills, such as coordinating numerous degrees of freedom, balancing contact forces, and breaking and reestablishing contacts with objects. Existing methods are often limited to simulation, or rely on extensive interactions with the environment and incur considerable computational burden. This thesis makes contributions that will help robots efficiently learn and reliably execute dexterous manipulation skills. First, we develop and investigate a new class of behavioral dynamical systems, we call Geometric Fabrics, that can encode complex behaviors in high dimensions by introducing strong structural inductive biases while retaining expressivity. Second, to circumvent the need for painstaking human effort required to manually design these models, we introduce Neural Geometric Fabrics (NGF) that can be used to efficiently learn generalizable manipulation skills. Third, we propose a policy learning architecture that can encode nominal behaviors that are shared across a wide variety of dexterous manipulation tasks into a NGF model and expose a high-level action space to enable efficient policy learning for a novel task with commonly used RL methods.

Status

  • Workflow Status:Published
  • Created By:Tatianna Richardson
  • Created:04/25/2022
  • Modified By:Tatianna Richardson
  • Modified:04/25/2022

Categories

Keywords