On-line data-driven fuzzy clustering with applications to real-time robotic tracking

Robotic target tracking has been used in a variety of applications. Due to limited sampling rate, sensory characteristics and processing delays, an important issue in such systems is thus to extrapolate ahead the trajectory (position, orientation, velocity and/or acceleration) of moving targets based on past observations. This paper introduces a novel on-tine datadriven fuzzy clustering algorithm that is based on the Maximum Entropy Principle for this particular task. In this algorithm, the fuzzy inference mechanism is extracted automatically from observed data without any human help, which thus eliminates the necessity of expert knowledge and a priori information on moving targets, as required by most traditional techniques. This algorithm does not require training, which enables it to work in a completely on-line fashion. Another important and distinct advantage of the algorithm exists in the fact that it is very fast and efficient in terms of computational cost and thus can be implemented in real time. In the mean time, the introduced algorithm has the ability to adapt quickly to the dynamics of moving targets. All these features make it especially suitable for the task to predict the trajectory of moving targets in robotic tracking. Simulation results show the effectiveness and efficiency of the presented algorithm.