Model predictive control with a visuomotor system for physics-based character animation = 물리 기반 캐릭터 애니메이션을 위한 시각운동 시스템을 결합한 모델 예측 제어

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 22
  • Download : 0
This paper presents a Model Predictive Control (MPC) framework with a visuomotor system that synthesizes eye and head movements coupled with physics-based full-body motions while placing visual attention on objects of importance in the environment. As the engine of this framework, we propose a visuomotor system based on human visual perception and full-body dynamics with contacts. Relying on partial observations with uncertainty from a simulated visual sensor, an optimal control problem for this system leads to a Partially Observable Markov Decision Process (POMDP), which is difficult to deal with. We approximate it as a deterministic belief MDP for effective control. To obtain a solution for the problem efficiently, we adopt differential dynamic programming (DDP), which is a powerful scheme to find a locally optimal control policy for nonlinear system dynamics. Guided by a reference skeletal motion without any a priori gaze information, our system produces realistic eye and head movements together with full-body motions for various tasks such as catching a thrown ball, walking on stepping stones, balancing after being pushed, and avoiding moving obstacles.
Advisors
Noh, Junyongresearcher노준용researcher
Description
한국과학기술원 :문화기술대학원,
Publisher
한국과학기술원
Issue Date
2020
Identifier
325007
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 문화기술대학원, 2020.2,[ii, 38 p. :]

Keywords

Visuomotor control▼aMotion control▼aPhysics-based simulation▼aPOMDP; 시각운동 제어▼a동작 제어▼a물리 기반 시뮬레이션▼aPOMDP

URI
http://hdl.handle.net/10203/284101
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=908498&flag=dissertation
Appears in Collection
GCT-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0