Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.

  

Measurement Association and Multiple Target Tracking (for the Robocup)

Author(s):

Mathias Bürki
Conference/Journal:

Semester Thesis FS12 (10174)
Abstract:

In order to successfully compete in the Robocup competition, it is important to have precise knowledge about where each robot on the eld is located and to to be able to track individual robots, team-mates as well as opponent robots, over time. Especially high level behavioural control greatly relies on having a accurate estimate of each robot's position, but also for lower level motion control such as trajectory planning and collision avoidance, having access to each robot's location and past trajectory information is essential. This project aims at providing an algorithm that allows tracking each robot on the soccer eld over time. That is, each robot is assigned a distinct label (i.e. "Robot 1" to "Robot 8") and at each time step, the available measurements of robot locations on the eld are associated to the robot labels in an optimal (wrt. maximal likelihood) way and their corresponding position and orientation is updated.

Year:

2012
Type of Publication:

(13)Semester/Bachelor Thesis
Supervisor:

N. Kariotoglou

No Files for download available.
% Autogenerated BibTeX entry
@PhdThesis { Xxx:2012:IFA_4170
}
Permanent link