Abstract: Vision based systems may select actions based on analysis of images to redistribute objects. Actions may include action type, action axis and/or action direction. Analysis may determine whether an object is accessible by a robot, whether an upper surface of a collection of objects meet a defined criteria and/or whether clusters of objects preclude access.

Abstract: Briefly described, one embodiment determines pose of an object of interest at a run time by capturing a first image of a first structured light pattern projected onto a first local surface of the object of interest; determining a first run-time data set from the captured first image, wherein the first run-time data set corresponds to information determined from the first structured light pattern projected onto the first local surface; comparing the determined first run-time data set and a corresponding first reference data set, the first reference data set corresponding to an ideal pose of the first local surface on an ideally posed reference object; and determining at least one first degree of constraint that defines a first partial pose of the first local surface, the at least one first degree of constraint based upon the comparison of the first run-time data set with the corresponding first reference data set.

Abstract: A method of three-dimensional object location and guidance to allow robotic manipulation of an object with variable position and orientation using a sensor array which is a collection of one or more sensors capable of forming a single image.

Abstract: A system and method for identifying objects using a machine-vision based system are disclosed. Briefly described, one embodiment is a method that captures a first image of at least one object with an image capture device, processes the first captured image to find an object region based on a reference two-dimensional model and determines a three-dimensional pose estimation based on a reference three-dimensional model that corresponds to the reference two-dimensional model and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known. Thus, two-dimensional information or data is used to segment an image and three-dimensional information or data used to perform three-dimensional pose estimation on a segment of the image.