University of Cambridge > Talks.cam > Machine Learning @ CUED > Quasi-linear Sensor Management

Quasi-linear Sensor Management

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani.

In multimodal sensor systems, such as sensor networks, the main objective of sensor management is to utilize sensors and their sensing modalities in a most informative way. This requires planning decisions over multiple time steps. For computationally constrained sensor systems, the “quasi-linear sensor management” approach allows efficient and meaningful decision making for nonlinear non-Gaussian systems by utilizing open-loop feedback control. In this talk, three key techniques of the quasi-linear sensor management approach are presented: (1) predictive statistical linearization for converting nonlinear non-Gaussian sensor management problems into linear Gaussian ones, (2) optimal branch-and-bound pruning for quickly solving linear Gaussian sensor management problems, and (3) Gaussian mixture reduction for bounding the growth of the number of mixture components when employing Gaussian mixture models for Bayesian filtering. The effectiveness of these techniques is demonstrated by means of simulations including mobile sensor control and sensor scheduling in sensor networks.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity