Abstract: Techniques for controlling a robotic picking arm using estimated seal quality metrics. A plurality of candidate contact points for holding an item using a suction device of the robotic picking arm, based on captured images of the item and an n-dimensional surface model of the item. An expected seal quality metric for a first one of the candidate contact points, by processing the n-dimensional surface model of the item and physical properties of the suction device of the robotic picking arm. Based on the expected seal quality metric, embodiments can determine whether to retrieve the item from the storage container by holding the item at the first candidate contact point using the suction device of the robotic picking arm.

Abstract: Systems, methods, and computer-readable media are disclosed for toroidal suction grippers. In one embodiment, an example device may include a first annular elastic membrane configured to form an orifice having a toroid geometry, and a first vacuum suction device disposed in the first annular elastic membrane. The first annular elastic membrane may be configured to be actuated to grasp an object.

Abstract: Method and apparatus for training a machine learning model for controlling a robotic picking device having a suction device end effector. A robotic control operation and a candidate contact point for holding a first item using a suction device of a robotic picking arm are determined, by processing information describing the first item as an input to a machine learning model. A seal quality metric is estimated for the candidate contact point, based on a predicted deformed n-dimensional shape of the suction device and a n-dimensional shape associated with the first item. One or more weights within the machine learning model are refined based on the estimated seal quality metric.

Abstract: Techniques for controlling a robotic picking arm using estimated seal quality metrics. A plurality of candidate contact points for holding an item using a suction device of the robotic picking arm, based on captured images of the item and an n-dimensional surface model of the item. An expected seal quality metric for a first one of the candidate contact points, by processing the n-dimensional surface model of the item and physical properties of the suction device of the robotic picking arm. Based on the expected seal quality metric, embodiments can determine whether to retrieve the item from the storage container by holding the item at the first candidate contact point using the suction device of the robotic picking arm.

Abstract: Techniques for controlling a robotic picking arm using estimated seal quality metrics. A plurality of candidate contact points for holding an item using a suction device of the robotic picking arm, based on captured images of the item and an n-dimensional surface model of the item. An expected seal quality metric for a first one of the candidate contact points, by processing the n-dimensional surface model of the item and physical properties of the suction device of the robotic picking arm. Based on the expected seal quality metric, embodiments can determine whether to retrieve the item from the storage container by holding the item at the first candidate contact point using the suction device of the robotic picking arm.

Abstract: Techniques for controlling a robotic picking arm using estimated seal quality metrics. A plurality of candidate contact points for holding an item using a suction device of the robotic picking arm, based on captured images of the item and an n-dimensional surface model of the item. An expected seal quality metric for a first one of the candidate contact points, by processing the n-dimensional surface model of the item and physical properties of the suction device of the robotic picking arm. Based on the expected seal quality metric, embodiments can determine whether to retrieve the item from the storage container by holding the item at the first candidate contact point using the suction device of the robotic picking arm.

Abstract: Laser scanners are used for determining deformation in vehicle bodies and the like, using a laser scanning apparatus in conjunction with a plurality of coded targets suspended from (or in known relationship to) known reference points on the vehicle to calculate three dimensional spatial coordinates defining the actual positions of the targets, and to compare such calculated positions with manufacturer-provided specification values. The present invention provides improved signal collection through the use of an independent synchronization circuit that uses a fiber optic cable for signal collection; improved component isolation through the use of a mounting plate and isolation mounts; improved component alignment through the use of easier and more reliable alignment mechanisms; and improved data collection and processing through the use of onboard data averaging and filtering.

Abstract: An athletic implement swing training and correction system includes a computer controlled mechanical manipulation mechanism for controlling the position and orientation of the athletic implement within a predetermined swing path geometry. The predetermined athletic implement swing path position and orientation is tailored to the physiology of the individual athlete from a collection of swing path geometries. A system of computer controlled position control actuators guide the swing of the student athlete through a tailored swing path geometry. Deviations from the tailored swing path geometry result in force feedback to the student athlete in direct relation to the amount of deviation from the tailored swing path position and implement orientation.