Variable Time Delays in Visual Servoing and Task Execution Control

In English We study an image-based visual servoing system implemented on a non-dedicatednetwork with non-deterministic computationalnodes. A problem is thattime delays aretypically non-deterministic and variable and may causesignificant degradation of control system performance, stability androbustness if not compensated for.Another problem is thepresence of noise due to information loss and measurement errors inthe image and vision processing part of the loop also resultingin decreased control performance.This paper focuses on an image plane linear predictionstrategy implemented using time-stamped data and a nonuniformly updating Kalman filter tocompensate for time delays and noise. Control performance isexperimentally verified by presenting prediction errormeasurements from an image-based visual servoing experiment ofgripping a moving object using a 6-DOF industrial robot anduncalibrated cameras.