November 08, 2016 – Fast Joint Compatibility Branch and Bound for Feature Cloud Matching

Date: November 08, 2016

Presenter: Dr. Xiaotong SHEN

Supervisor: Prof. Daniela RUS (MIT)

 

Robust data association for feature cloud matching is of great importance for autonomous vehicles to build an accurate map. For matching two feature clouds observed at two different poses, we discover that the covariance matrix of the measurement prediction error can be written as the sum of a low rank matrix and a block diagonal matrix, if we assume that the features are observed independently at each pose.

 

Please click on the following icon to find out more about our programme: