Fuzzy Control for Active Perceptual Docking

摘要

The robot is engaged in a docking manœuvre guided by an active perceptual behaviour. In order to dock with an object, the robot must control its heading direction to move directly towards the object. In previous work, we developed a technique in which the robot fixates on the desired target, and corrects its heading direction based on information derived from optical flow data from a log-polar camera. However, the optical flow data derived is noisy. Thus, when the robot direction control is based directly on the optical flow data the resulting path is erratic (see Figure 8.4 in the results section of this chapter). A smooth path is desirable as it reduces strain on motors and simplifies fixation. Furthermore, constant change in direction can result in wheel-slippage, leading to errors in odometry. High quality odometric information is of great advantage for position estimation in mobile robot navigation. Traditional control techniques are not effective in such situations, as it is almost impossible to establish precise models for optical flow data.