- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Faculty Research and Publications /
- Guided learning of control graphs for physics-based...
Open Collections
UBC Faculty Research and Publications
Guided learning of control graphs for physics-based characters Liu, Libin; van de Panne, Michiel; Yin, KangKang
Abstract
The difficulty of developing control strategies has been a primary bottleneck in the adoption of physics-based simulations of human motion. We present a method for learning robust feedback strategies around given motion capture clips as well as the transition paths between clips. The output is a control graph that supports real-time physics-based simulation of multiple characters, each capable of a diverse range of robust movement skills, such as walking, running, sharp turns, cartwheels, spin-kicks, and flips. The control fragments which comprise the control graph are developed using guided learning. This leverages the results of open-loop sampling-based reconstruction in order to produce state-action pairs which are then transformed into a linear feedback policy for each control fragment using linear regression. Our synthesis framework allows for the development of robust controllers with a minimal amount of prior knowledge.
Item Metadata
Title |
Guided learning of control graphs for physics-based characters
|
Creator | |
Date Issued |
2015-11-30
|
Description |
The difficulty of developing control strategies has been a primary bottleneck in the adoption of physics-based simulations of human motion. We present a method for learning robust feedback
strategies around given motion capture clips as well as the transition paths between clips. The
output is a control graph that supports real-time physics-based simulation of multiple characters,
each capable of a diverse range of robust movement skills, such as walking, running, sharp turns,
cartwheels, spin-kicks, and flips. The control fragments which comprise the control graph are
developed using guided learning. This leverages the results of open-loop sampling-based
reconstruction in order to produce state-action pairs which are then transformed into a linear
feedback policy for each control fragment using linear regression. Our synthesis framework allows
for the development of robust controllers with a minimal amount of prior knowledge.
|
Genre | |
Type | |
Language |
eng
|
Date Available |
2015-12-04
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution-NonCommercial-NoDerivs 2.5 Canada
|
DOI |
10.14288/1.0220787
|
URI | |
Affiliation | |
Peer Review Status |
Unreviewed
|
Scholarly Level |
Faculty
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivs 2.5 Canada