Redundancy resolution in tasks with parameterizable uncertainty

Redundant robots motion planning and control in uncertain task is addressed by model-based approach. Instead of controlling and adapting the environment to the robot or applying a complex visual servoing system, we model the redundancy resolution on the parameter spaces that quantify uncertainties of the task. The modeling tool is a successive approximation (SA). It provides very advantageous properties: small computational effort and small model size, accurate output, extrapolation, and generalization across the parameter set obtained by random addressing of the model. The task discussed is press loading with typical two-dimensional uncertainties in pick-up and unloading locations. The robot used is a 4-DOF planar robot. The SA-based models of redundancy resolution in a 2D parameter spaces are highly efficient: for more than 30 times less computational efforts resulted in a zero end-point errors, regardless of the task uncertainty.