Learning real-time stereo vergence control

Piater, J. H. ; Grupen, R. A. ; Ramamritham, K. (1999) Learning real-time stereo vergence control Proceedings of the 1999 IEEE International Symposium on Intelligent Control/Intelligent Systems and Semiotics . pp. 272-277.

Full text not available from this repository.

Official URL: http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnum...

Related URL: http://dx.doi.org/10.1109/ISIC.1999.796667


Online learning robotic systems have many desirable properties. This work contributes a reinforcement learning framework for learning a time-constrained closed-loop control policy. The task is to verge the two cameras of a stereo vision system to foveate on the same world feature, within a limited number of perception-action cycles. Online learning is beneficial in at least the following ways: 1) the control parameters are optimized with respect to the characteristics of the environment actually encountered during operation; 2) visual feedback contributes to the choice of the best control action at every step in a multi-step control policy; 3) no initial calibration or explicit modeling of system parameters is required; and 4) the system can be made to adapt to non-stationary environments. Our vergence system provides a running estimate of the resulting verge quality that can be exploited by a real-time scheduler. It is shown to perform superior to two hand-calibrated vergence policies.

Item Type:Article
Source:Copyright of this article belongs to IEEE Press.
ID Code:94292
Deposited On:23 Aug 2012 11:39
Last Modified:23 Aug 2012 11:39

Repository Staff Only: item control page