event

Ph.D. Thesis Proposal by Yunfei Bai

Primary tabs

Ph.D. Thesis Proposal Announcement

Title: Simulating Human Motion for Object Manipulation

Yunfei Bai
Ph.D. Student
School of Interactive Computing
College of Computing
Georgia Institute of Technology
http://www.cc.gatech.edu/~ybai30/

Date: Tuesday, April 7, 2015
Time: 9:30am – 11:00am EDT
Location: TSRB 222

Committee
Dr. C.Karen Liu (Advisor), School of Interactive Computing, Georgia Institute of Technology
Dr. Greg Turk, School of Interactive Computing, Georgia Institute of Technology
Dr. Jarek Rossignac, School of Interactive Computing, Georgia Institute of Technology
Dr. Andrea Thomaz, School of Interactive Computing, Georgia Institute of Technology
Dr. Paul G. Kry, School of Computer Science, McGill University

Abstract:
Performing object manipulation with full-body and dexterous hand is an essential human activity in everyday environment. Robotics and computer animation research have made tremendous progress in addressing object manipulation problems. However, it is still a challenge for robots or virtual characters to imitate human motion of object manipulation. First of all, the existing control algorithms for both full-body and dexterous hand manipulation only utilize designated parts of robots constrained by hardware design, which does not have the same level of versatility that humans exhibit. Secondly, the current simulation and control techniques cannot achieve the fidelity requirement for motion in deformable object manipulation.
 
We propose physics-based method to synthesize the human motion of full-body and dexterous hand manipulation, and address the above mentioned challenges. Our proposed three research problems are: synthesizing human activities involving concurrent full-body manipulation of multiple objects; synthesizing in-hand manipulation of a polygonal object with integrated control techniques for both palm and fingers; and synthesizing realistic dexterous manipulation of cloth from sparse cloth configuration. This thesis proposal focuses on the third research problem, where we propose a method to optimize cloth motion under the constraints of hands and the dynamics of cloth to achieve the specifications from artist, and control hands to realize the optimized cloth motion. We plan to demonstrate our algorithm on a variety of cloth manipulation scenarios including folding laundry, wringing a towel, and putting on a scarf.

Status

  • Workflow Status:Published
  • Created By:Tatianna Richardson
  • Created:03/31/2015
  • Modified By:Fletcher Moore
  • Modified:10/07/2016

Categories

Target Audience