Behavioral Analysis of Mobile Robot Trajectories Using a Point Distribution Model

In recent years, the advent of robust tracking systems has enabled behavioral analysis of individuals based on their trajectories. An analysis method based on a Point Distribution Model (PDM) is presented here. It is an unsupervised modeling of the trajectories in order to extract behavioral features. The applicability of this method has been demonstrated on trajectories of a realistically simulated mobile robot endowed with various controllers that lead to different patterns of motion. Results show that this analysis method is able to clearly classify controllers in the PDM-transformed space, an operation extremely difficult in the original space. The analysis also provides a link between the behaviors and trajectory differences.

Published in:
Lecture Notes in Artificial Intelligence, 4095, 819--830
Presented at:
Ninth Int. Conference on the Simulation of Adaptive Behavior, Roma, 25-29 september
Other identifiers:

Note: The status of this file is: Involved Laboratories Only

 Record created 2006-06-02, last modified 2020-10-28

Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
(Not yet reviewed)