Hypotheses based multi-object tracking in the RoboCup MidSize league

R.J.M. Janssen; M.J.G. Molengraft, van de; M. Steinbuch

Hypotheses based multi-object tracking in the RoboCup MidSize league

R.J.M. Janssen, M.J.G. Molengraft, van de, M. Steinbuch

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

86 Downloads (Pure)

Abstract

One of the main challenges in the RoboCupMidSize league is to create a global view, or world model, of peer and opponent players in the game environment. This view is essential for strategic gameplay and global path planning. In this paper the team of TechUnited Eindhoven describes their solution to this issue. Ego and omnivision object measurements are shared amongst peer players. Each peer individually processes the measurements according to an hypotheses based sequential clustering algorithm. For each cluster Kalman observers are initiated from which an estimated position and velocity can be derived. This paper describes the first world model design known in the MidSize league that includes dynamics and labeling of peer and opponent players.

Original language	English
Title of host publication	Proceedings of the Internal Conference on Autonomous Agents And MultiAgent Systems (AAMAS2010) : Workshop on Agents in Real-time and Dynamic Environments, May 10-14, 2010, Toronto, Canada
Editors	U. Visser, S. Asadi, T. Laue, M. Mayer
Publication status	Published - 2010
Event	9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), May 10-14, 2010, Toronto, Canada - Sheraton Centre Toronto Hotel, Toronto, Canada Duration: 10 May 2010 → 14 May 2010 http://www.cse.yorku.ca/AAMAS2010/

Conference

Conference	9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), May 10-14, 2010, Toronto, Canada
Abbreviated title	AAMAS 2010
Country/Territory	Canada
City	Toronto
Period	10/05/10 → 14/05/10
Internet address	http://www.cse.yorku.ca/AAMAS2010/

Access to Document

888783997601417Final author version , 103 KB

Cite this

Janssen, R. J. M., Molengraft, van de, M. J. G., & Steinbuch, M. (2010). Hypotheses based multi-object tracking in the RoboCup MidSize league. In U. Visser, S. Asadi, T. Laue, & M. Mayer (Eds.), Proceedings of the Internal Conference on Autonomous Agents And MultiAgent Systems (AAMAS2010) : Workshop on Agents in Real-time and Dynamic Environments, May 10-14, 2010, Toronto, Canada

Janssen, R.J.M. ; Molengraft, van de, M.J.G. ; Steinbuch, M. / Hypotheses based multi-object tracking in the RoboCup MidSize league. Proceedings of the Internal Conference on Autonomous Agents And MultiAgent Systems (AAMAS2010) : Workshop on Agents in Real-time and Dynamic Environments, May 10-14, 2010, Toronto, Canada. editor / U. Visser ; S. Asadi ; T. Laue ; M. Mayer. 2010.

@inproceedings{10bf91d9263c4621a61d5a0188886f1b,

title = "Hypotheses based multi-object tracking in the RoboCup MidSize league",

abstract = "One of the main challenges in the RoboCupMidSize league is to create a global view, or world model, of peer and opponent players in the game environment. This view is essential for strategic gameplay and global path planning. In this paper the team of TechUnited Eindhoven describes their solution to this issue. Ego and omnivision object measurements are shared amongst peer players. Each peer individually processes the measurements according to an hypotheses based sequential clustering algorithm. For each cluster Kalman observers are initiated from which an estimated position and velocity can be derived. This paper describes the first world model design known in the MidSize league that includes dynamics and labeling of peer and opponent players.",

author = "R.J.M. Janssen and {Molengraft, van de}, M.J.G. and M. Steinbuch",

year = "2010",

language = "English",

editor = "U. Visser and S. Asadi and T. Laue and M. Mayer",

booktitle = "Proceedings of the Internal Conference on Autonomous Agents And MultiAgent Systems (AAMAS2010) : Workshop on Agents in Real-time and Dynamic Environments, May 10-14, 2010, Toronto, Canada",

note = "9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), May 10-14, 2010, Toronto, Canada, AAMAS 2010 ; Conference date: 10-05-2010 Through 14-05-2010",

url = "http://www.cse.yorku.ca/AAMAS2010/",

}

Janssen, RJM, Molengraft, van de, MJG & Steinbuch, M 2010, Hypotheses based multi-object tracking in the RoboCup MidSize league. in U Visser, S Asadi, T Laue & M Mayer (eds), Proceedings of the Internal Conference on Autonomous Agents And MultiAgent Systems (AAMAS2010) : Workshop on Agents in Real-time and Dynamic Environments, May 10-14, 2010, Toronto, Canada. 9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), May 10-14, 2010, Toronto, Canada, Toronto, Canada, 10/05/10.

Hypotheses based multi-object tracking in the RoboCup MidSize league. / Janssen, R.J.M.; Molengraft, van de, M.J.G.; Steinbuch, M.
Proceedings of the Internal Conference on Autonomous Agents And MultiAgent Systems (AAMAS2010) : Workshop on Agents in Real-time and Dynamic Environments, May 10-14, 2010, Toronto, Canada. ed. / U. Visser; S. Asadi; T. Laue; M. Mayer. 2010.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Hypotheses based multi-object tracking in the RoboCup MidSize league

AU - Janssen, R.J.M.

AU - Molengraft, van de, M.J.G.

AU - Steinbuch, M.

PY - 2010

Y1 - 2010

N2 - One of the main challenges in the RoboCupMidSize league is to create a global view, or world model, of peer and opponent players in the game environment. This view is essential for strategic gameplay and global path planning. In this paper the team of TechUnited Eindhoven describes their solution to this issue. Ego and omnivision object measurements are shared amongst peer players. Each peer individually processes the measurements according to an hypotheses based sequential clustering algorithm. For each cluster Kalman observers are initiated from which an estimated position and velocity can be derived. This paper describes the first world model design known in the MidSize league that includes dynamics and labeling of peer and opponent players.

AB - One of the main challenges in the RoboCupMidSize league is to create a global view, or world model, of peer and opponent players in the game environment. This view is essential for strategic gameplay and global path planning. In this paper the team of TechUnited Eindhoven describes their solution to this issue. Ego and omnivision object measurements are shared amongst peer players. Each peer individually processes the measurements according to an hypotheses based sequential clustering algorithm. For each cluster Kalman observers are initiated from which an estimated position and velocity can be derived. This paper describes the first world model design known in the MidSize league that includes dynamics and labeling of peer and opponent players.

M3 - Conference contribution

BT - Proceedings of the Internal Conference on Autonomous Agents And MultiAgent Systems (AAMAS2010) : Workshop on Agents in Real-time and Dynamic Environments, May 10-14, 2010, Toronto, Canada

A2 - Visser, U.

A2 - Asadi, S.

A2 - Laue, T.

A2 - Mayer, M.

T2 - 9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), May 10-14, 2010, Toronto, Canada

Y2 - 10 May 2010 through 14 May 2010

ER -

Hypotheses based multi-object tracking in the RoboCup MidSize league

Abstract

Conference

Access to Document

Fingerprint

Cite this