Paper Details: Downloads: 449
Serial Number: P1120906633
Title: Using Self Organizing Networks for Moving Object Trajectory Prediction
Authors: Vijay S Rajpurohit and Manohara Pai M. M.
Abstract: Trajectory prediction for moving objects in a Robotic navigational environment is a challenging problem. The trajectory prediction techniques operate in two stages i. Learning stage: Observe the moving objects in the workspace in order to determine the typical motion patterns.ii. Prediction stage: Use the learned typical motion patterns to predict the future motion of a given object. In the proposed work trajectory prediction is done using Fuzzy based Self Organizing Map(FSOM).The navigational environment under observation is fuzzy based, representing the object’s position (Range and Direction) from the Robot in the form of Fuzzy values. Results are tested for Real Life data sets.
Keywords: Long Term motion Prediction, Fuzzy based Self Organizing Map, Trajectory clustering,Neuro Fuzzy Learning algorithm, Partial Trajectory.
Journal/Conference: International Journal of Artificial Intelligence and Machine Learning
Volume: 9
Issue: 1
Submission Date: 2/4/2009 12:00:00 AM
Review Date: 2/13/2009 12:00:00 AM
Publishing Date: 3/3/2009 12:00:00 AM
Article Downloads: 449
Download:

Facebook