Handling uncertainties of robot manipulators and active vision by constraint propagation

Joint errors are inevitable in robot manipulation. These uncertainties propagate to give rise to translationaland orientational errors in the position and orientation of the robot end‐effector. The displacement ofthe active vision head mounted on the robot end‐effector produces distortion of the projected object onthe image. Upon active visual inspection, the observed dimension of a mechanical part is given dimension by themeasurement on the projected edge segment on the image. The difference between the observed dimension and theactual dimension is the displacement error in active vision. For different motion of the active vision head, theresulting displacement errors are different. Given the uncertainties of the robot manipulator's jointerrors, constraint propagation can be employed to assign the motion of the active sensor in order to satisfy thetolerance of the displacement errors for inspection. In this article, we define the constraint consistency andnetwork satisfaction in the constraint network for the problem of displacement errors in active vision. Aconstraint network is a network where the nodes represent variables, or constraints, and the arcs represent therelationships between the output variables and the input variables of the constraints. In the displacement errorsproblem, the tolerance of the displacement errors and the translational and orientational errors of robotmanipulators have interval values while the sensor motion has real values. Constraint propagation is developed topropagate the tolerance of displacement errors in the hierarchical interval constraint network in order to findthe feasible robot motion. © 2002 Wiley Periodicals, Inc.