Preparation Behaviour Synthesis with Reinforcement Learning

Preparation Behaviour Synthesis with Reinforcement Learning

Abstract

When humans perform a series of motions, they prepare for the next motion in advance so as to enhance the response time of their movements. This kind of preparation behaviour results in a natural and smooth transition of the overall movement. In this paper, we propose a new method to synthesize the behaviour using reinforcement learning. To create preparation movements, we propose a customized motion blending algorithm that is governed by a single numerical value, which we called the level of preparation. During the offline process, the system learns the optimal way to approach a target, as well as the realistic behaviour to prepare for interaction considering the level of preparation. At run-time, the trained controller indicates the character to move to a target with the appropriate level of preparation, resulting in human-like movements. We synthesized scenes in which the character has to move in a complex environment and interact with objects, such as a character crawling under and jumping over obstacles while walking. The method is useful not only for computer animation, but also for real-time applications such as computer games, in which the characters need to accomplish a series of tasks in a given environment.

Publication

Hubert P. H. Shum, Ludovic Hoyet, Edmond S. L. Ho, Taku Komura and Franck Multon,
"Preparation Behaviour Synthesis with Reinforcement Learning",
Proceedings of the 2013 International Conference on Computer Animation and Social Agents (CASA)

Citation=1##

## Citation count from Google Scholar as of 2018

Downloads

YouTube

References

BibTeX

@inproceedings{shum13preparation,
 author={Shum, Hubert P. H. and Hoyet, Ludovic and Ho, Edmond S. L. and Komura, Taku and Multon, Franck},
 booktitle={Proceedings of the 2013 International Conference on Computer Animation and Social Agents},
 series={CASA '13},
 title={Preparation Behaviour Synthesis with Reinforcement Learning},
 year={2013},
 month={May},
 numpages={10},
 publisher={John Wiley and Sons Ltd.},
 Address={Chichester, UK},
 location={Turkey, Istanbul},
}

EndNote/RefMan

TY  - CONF
AU  - Shum, Hubert P. H.
AU  - Hoyet, Ludovic
AU  - Ho, Edmond S. L.
AU  - Komura, Taku
AU  - Multon, Franck
T2  - Proceedings of the 2013 International Conference on Computer Animation and Social Agents
TI  - Preparation Behaviour Synthesis with Reinforcement Learning
PY  - 2013
Y1  - May 2013
PB  - John Wiley and Sons Ltd.
ER  - 

Plain Text

Hubert P. H. Shum, Ludovic Hoyet, Edmond S. L. Ho, Taku Komura and Franck Multon, "Preparation Behaviour Synthesis with Reinforcement Learning," in CASA '13: Proceedings of the 2013 International Conference on Computer Animation and Social Agents, Turkey, Istanbul, John Wiley and Sons Ltd., May 2013.

Similar Research

 

         

Last update: 10/03/2019