Autonomous mobile target tracking system based on grey-fuzzy control algorithm

Abstract

This paper presents a new position-based tracking system for autonomous mobile target tracking task. A grey-fuzzy controller (GFC) is developed for motion control of the tracker, in which dynamics models of the target and tracker are not required a priori. The target detection is based on the adaptive visual detector (AVD), which can online adjust the histogram model based on the change of surrounding conditions, such as light variation, in a natural environment. The AVD and GFC are integrated together for mobile target-tracking applications. There are several advantages of the integrated system, in particular: (1) it can rapidly learn the target appearance model for the detection involved with the tracking task; (2) the temporal dynamics model of the target motion can be approximated for the predictive localization of the moving target; and (3) the system can deal with the uncertain environmental conditions to ensure the tracking performance by GFC. Three mobile robots in the authors' laboratory have been used to demonstrate the success of this integrated system experimentally. They also conduct target tracking experiments, in which Chung Cheng-I tracks various moving targets. The results demonstrate the robustness and flexibility of the overall system in dealing with mobile target-tracking problems under varied natural environment conditions.