Path planning of virtual human by using reinforcement learning

Yue Sheng He; Yuan Yan Tang

doi:10.1109/ICMLC.2008.4620548

Path planning of virtual human by using reinforcement learning

Yue Sheng He^*
, Yuan Yan Tang

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

3 Citations (Scopus)

Abstract

Virtual Human can hold the possibility of performing a variety of assistive and analysis tasks in 3D virtual environments. However, widespread use of avatars assistants in these environments requires ease of use by individuals who are generally not skilled on designing operators. In this paper we present a method of training virtual human that bridges the gap between designing and building of a virtual human's action as well as its autonomous learning ability to adapt a certain task. With our approach, we integrate reinforcement learning to the action of virtual human's path planning to achieve fast policy acquisition. The result of the approach is illustrated in the case of successfully instructing virtual human to cross a terrain with pyramid and a number of obstacles to reach a certain target.

Original language	English
Title of host publication	Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC
Publisher	IEEE
Pages	987-992
Number of pages	6
Volume	2
ISBN (Electronic)	9781424420964
ISBN (Print)	9781424420957
DOIs	https://doi.org/10.1109/ICMLC.2008.4620548
Publication status	Published - 12 Jul 2008
Event	7th International Conference on Machine Learning and Cybernetics, ICMLC 2008 - Kunming, China Duration: 12 Jul 2008 → 15 Jul 2008

Publication series

Name	Proceedings of the International Conference on Machine Learning and Cybernetics, ICMLC
Publisher	IEEE
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	7th International Conference on Machine Learning and Cybernetics, ICMLC 2008
Country/Territory	China
City	Kunming
Period	12/07/08 → 15/07/08

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

User-Defined Keywords

Behavioral model
Character animation
Intelligent animation
Machine learning
Path plan
Reinforcement learning
Virtual human

Access to Document

10.1109/ICMLC.2008.4620548

Cite this

@inproceedings{6bb2c7c7100c4c4cbcfd9be45efafdbc,

title = "Path planning of virtual human by using reinforcement learning",

abstract = "Virtual Human can hold the possibility of performing a variety of assistive and analysis tasks in 3D virtual environments. However, widespread use of avatars assistants in these environments requires ease of use by individuals who are generally not skilled on designing operators. In this paper we present a method of training virtual human that bridges the gap between designing and building of a virtual human's action as well as its autonomous learning ability to adapt a certain task. With our approach, we integrate reinforcement learning to the action of virtual human's path planning to achieve fast policy acquisition. The result of the approach is illustrated in the case of successfully instructing virtual human to cross a terrain with pyramid and a number of obstacles to reach a certain target.",

keywords = "Behavioral model, Character animation, Intelligent animation, Machine learning, Path plan, Reinforcement learning, Virtual human",

author = "He, \{Yue Sheng\} and Tang, \{Yuan Yan\}",

note = "Publisher copyright: {\textcopyright} 2008 IEEE; 7th International Conference on Machine Learning and Cybernetics, ICMLC 2008 ; Conference date: 12-07-2008 Through 15-07-2008",

year = "2008",

month = jul,

day = "12",

doi = "10.1109/ICMLC.2008.4620548",

language = "English",

isbn = "9781424420957",

volume = "2",

series = "Proceedings of the International Conference on Machine Learning and Cybernetics, ICMLC",

publisher = "IEEE",

pages = "987--992",

booktitle = "Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC",

address = "United States",

}

He, YS & Tang, YY 2008, Path planning of virtual human by using reinforcement learning. in Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC. vol. 2, Proceedings of the International Conference on Machine Learning and Cybernetics, ICMLC, IEEE, pp. 987-992, 7th International Conference on Machine Learning and Cybernetics, ICMLC 2008, Kunming, China, 12/07/08. https://doi.org/10.1109/ICMLC.2008.4620548

Path planning of virtual human by using reinforcement learning. / He, Yue Sheng; Tang, Yuan Yan.
Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC. Vol. 2 IEEE, 2008. p. 987-992 (Proceedings of the International Conference on Machine Learning and Cybernetics, ICMLC).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Path planning of virtual human by using reinforcement learning

AU - He, Yue Sheng

AU - Tang, Yuan Yan

PY - 2008/7/12

Y1 - 2008/7/12

N2 - Virtual Human can hold the possibility of performing a variety of assistive and analysis tasks in 3D virtual environments. However, widespread use of avatars assistants in these environments requires ease of use by individuals who are generally not skilled on designing operators. In this paper we present a method of training virtual human that bridges the gap between designing and building of a virtual human's action as well as its autonomous learning ability to adapt a certain task. With our approach, we integrate reinforcement learning to the action of virtual human's path planning to achieve fast policy acquisition. The result of the approach is illustrated in the case of successfully instructing virtual human to cross a terrain with pyramid and a number of obstacles to reach a certain target.

AB - Virtual Human can hold the possibility of performing a variety of assistive and analysis tasks in 3D virtual environments. However, widespread use of avatars assistants in these environments requires ease of use by individuals who are generally not skilled on designing operators. In this paper we present a method of training virtual human that bridges the gap between designing and building of a virtual human's action as well as its autonomous learning ability to adapt a certain task. With our approach, we integrate reinforcement learning to the action of virtual human's path planning to achieve fast policy acquisition. The result of the approach is illustrated in the case of successfully instructing virtual human to cross a terrain with pyramid and a number of obstacles to reach a certain target.

KW - Behavioral model

KW - Character animation

KW - Intelligent animation

KW - Machine learning

KW - Path plan

KW - Reinforcement learning

KW - Virtual human

UR - https://www.scopus.com/pages/publications/57849146826

U2 - 10.1109/ICMLC.2008.4620548

DO - 10.1109/ICMLC.2008.4620548

M3 - Conference proceeding

AN - SCOPUS:57849146826

SN - 9781424420957

VL - 2

T3 - Proceedings of the International Conference on Machine Learning and Cybernetics, ICMLC

SP - 987

EP - 992

BT - Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC

PB - IEEE

T2 - 7th International Conference on Machine Learning and Cybernetics, ICMLC 2008

Y2 - 12 July 2008 through 15 July 2008

ER -

Path planning of virtual human by using reinforcement learning

Abstract

Publication series

Conference

UN SDGs

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this