Robot pose estimation based on visual information and particle swarm optimization

Pose estimation is one of the most important tasks in mobile robotics. The problem consist in estimate the position of the mobile robot using a sensor on the robot. In this work we assume that a vision sensor is mounted on the robot, with the visual information provided by this sensor we estimate the motion of the mobile platform. In the 3D space the problem can be seen as the estimation of the transformation between two consecutive frames. In this paper the authors propose a pose estimation scheme which is based on particle swarm optimization (PSO). The proposed algorithm is designed to estimate the pose in the 3D space, and to be robust to outliers.