Novel SLAM algorithm for UGVs based BBO-CEPF

Localization is one of the important topics for autonomous driving of unmanned ground vehicle(UGV). Most problems in localization are due to uncertainties in the modeling and sensors. Therefore, various filters method are developed to estimate the states with noise. Recently, particle filter is widely used because it can be applied to the system with nonlinear model and non-Gaussian noise. In this paper a adaptive particle filter based cross entropy and Biogeography Based Optimization is proposed, whose basic idea is to generate the new proposal density using optimization method. For comparison, we test a conventional particle filter method and our proposed method, experimental results show that the proposed method has better localization performance.