A Dempster-Shafer Reasoning Theory Approach

One of the problems usually discussed in autonomous mobile robot navigation is how to build a map of the environment where the robot is navigating. In the case of indoor navigation, a suitable method to do this mapping is the fusion of the data that are gathered from the several sensors, which are mounted on the robot. Here, a mobile robot equipped just with range finding sensors has been supposed to do path planning autonomously. The environment map that is built by the robot has the same structure as an occupancy grids map, but with some differences and beneficial extensions. A new method has been proposed to fuse the ranges that are provided by the sensors. This method is based on the Dempster 's Rule of Combination in Dempster-Shafer theory of reasoning. Simulation results show that the new method results a map, which is safer for path planning, compared to the map deduced from the Bayesian fusion method.