Evidence Reasoning Machine based on DSmT for mobile robot mapping in unknown dynamic environment

In this paper a new method of information fusion, Dezert-Smarandache theory (DSmT) is introduced to deal with high conflicting and uncertain information. And then the evidence reasoning machine (ERM) based on DSmT is presented for mobile robot mapping in unknown dynamic environment. Considering the characteristics of sonar sensors, the grid map method is adopted and a sonar sensor mathematical model is constructed based on DSmT. Meanwhile a few of general basic belief assignment functions (gbbaf) are constructed for fusion. Finally, map building experiment is carried out with Pioneer 2-DXe mobile robot. The experiment results testify the validity of ERM with DSmT for fusing imprecise information during map building in unknown dynamic environment.