The evolved Gaussian mixture Bayes´ technique using sensor selection task integrated with sensor fusion scheme in mobile robot position estimation

Modelling and reducing uncertainty are two essential problems with mobile robot localisation. Previously we developed a robot localisation system, namely the Gaussian Mixture of Bayes with Regularised Expectation Maximisation (GMB-REM), which introduced sensor selection task. GMB-REM allows a robot´s position to be modelled as a probability distribution, and uses Bayes´ theorem to reduce the uncertainty of its location. In this paper, a new sensor selection task incorporated with sensor fusion is proposed, namely an evolved form of GMB-REM. Empirical results show the new sensor selection method outperforms GMB-REM with the previous sensor selection. Especially, in this paper, we illustrate that the new system is able to significantly constrain the error of a robot´s position