Weighted and robust incremental method for subspace learning

In this paper we present an appearance-based approach to mobile robot localization based on Canonical Correlation Analysis. The main idea is to learn the relation between the appearances of the environment from a number of training locations and coordinates of these locations using CCA and then to use this knowledge to estimate the position of the robot in the localization stage. We present results of several experiments, which show that this approach is faster and less demanding in terms of space than traditional PCA-based approach, however in its standard form it yields in general inferior localization results.