Visual based SLAM using modified PSO

Simultaneous Localization and Mapping (SLAM) addresses the problem of a robot navigating and acquiring spatial models of initially unknown environments, without an absolute localization means. To solve this problem, we propose a mapping system that builds feature-based geometrical maps by applying a modified Particle Swarm Optimization (PSO) algorithm. Particles are defined as the location of individual features in the environment where the size of the swarm increases as the features are re-observed at different positions. PSO adjusts the velocity and location of particles towards a target (feature location) as the particles move around the constrained 2-dimensional search space. Finally, the particles will converge around an optimum feature location. The mobile robot is also localized with respect to this map simultaneously. It is demonstrated that accurate feature locations can be obtained using the proposed technique.