Integrated fuzzy logic and genetic algorithmic approach for simultaneous localization and mapping of mobile robots

This paper presents a novel method of integrating fuzzy logic (FL) and genetic algorithm (GA) to solve the simultaneous localization and mapping (SLAM) problem of mobile robots. The core of the proposed SLAM algorithm is based on an island model GA (IGA) which searches for the most probable map(s) such that the associated pose(s) provides the robot with the best localization information. Prior knowledge about the problem domain is transferred to GA in order to speed up the convergence. Fuzzy logic is employed to serve this purpose and allows the IGA to conduct the search starting from a potential region of the pose space. The underlying fuzzy mapping rules infer the uncertainty in the robot's location after executing a motion command and generate a sample-based prediction of its current position. This sample set is used as the initial population for the proposed IGA. Thus the GA-based search starts with adequate knowledge on the problem domain. The correspondence problem in SLAM is solved by exploiting the property of natural selection, which supports better performing individuals to survive in the competition. The proposed algorithm follows essentially no assumption about the environment and has the capacity to resolve the loop closure problem without maintaining explicit loop closure heuristics. The algorithm processes sensor data incrementally and therefore, has the capability of real time map generation. Experimental results in different indoor environments are presented to validate robustness of the algorithm.