Hypotheses based multi-object tracking in the RoboCup MidSize league

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

62 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 languageEnglish
Title of host publicationProceedings 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
EditorsU. Visser, S. Asadi, T. Laue, M. Mayer
Publication statusPublished - 2010
Event9th 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 201014 May 2010
http://www.cse.yorku.ca/AAMAS2010/

Conference

Conference9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), May 10-14, 2010, Toronto, Canada
Abbreviated titleAAMAS 2010
Country/TerritoryCanada
CityToronto
Period10/05/1014/05/10
Internet address

Fingerprint

Dive into the research topics of 'Hypotheses based multi-object tracking in the RoboCup MidSize league'. Together they form a unique fingerprint.

Cite this