By Topic

Learning implicit models during target pursuit

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Gaskett, C. ; Dept. of Humanoid Robotics & Comput. Neurosci., ATR Comput. Neurosci. Lab., Kyoto, Japan ; Brown, P. ; Cheng, G. ; Zelinsky, A.

Smooth control using an active vision head's verge-axis joint is performed through continuous state and action reinforcement learning. The system learns to perform visual servoing based on rewards given relative to tracking performance. The learned controller compensates for the velocity of the target and performs lag-free pursuit of a swinging target. By comparing controllers exposed to different environments we show that the controller is predicting the motion of the target by forming an implicit model of the target's motion. Experimental results are presented that demonstrate the advantages and disadvantages of implicit modelling.

Published in:

Robotics and Automation, 2003. Proceedings. ICRA '03. IEEE International Conference on  (Volume:3 )

Date of Conference:

14-19 Sept. 2003