Data based dynamical modeling of vision observed small robots

Abstract

Until recently the control and navigation of mobile robots was mainly performed based on exteroceptive sensoring. Recent investigation on the cooperation of multiple robotic agents with centralized control, has ushered in small and less sophisticated robots that are observed by a global vision system. This paper presents a modeling methodology that enables accurate prediction of such small robot's position and orientation from data measured using the global vision system. Results of several experiments show that the model is both accurate and robust. Another relevant aspect of the work is the ability to determine the limitations likely to be found in centralized control of agents with little or no local "intelligence".