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: An example apparatus of the present disclosure may include an end effector. The end effector may include a pair of actuator-driven fingers that each include a compliant tip. The compliant tips may be used to scoop underneath items as part of item manipulation.

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: Finger assemblies at the end of a robotic arm end effector includes talon that are retractable. Retraction may be accomplished by a vertical or horizontal barrel cam, a paddle and spin assembly, and/or a resilient plate. A method includes contacting a portion of a finger body against a datum.

Abstract: Finger assemblies at the end of a robotic arm end effector includes talon that are retractable. Retraction may be accomplished by a vertical or horizontal barrel cam, a paddle and spin assembly, and/or a resilient plate.

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: Finger assemblies at the end of a robotic arm end effector includes talon that are retractable. Retraction may be accomplished by a vertical or horizontal barrel cam, a paddle and spin assembly, and/or a resilient plate.

Abstract: Finger assemblies at the end of a robotic arm end effector includes talon that are retractable. Retraction may be accomplished by a vertical or horizontal barrel cam, a paddle and spin assembly, and/or a resilient plate.

Abstract: A grasp management system and corresponding methods are described. In some examples, information about a set of grasps of a robotic manipulator is accessed. The information is used by the robotic manipulator to attempt to grasp an item using the set of grasps associated with a first grasping orientation. An orientation of the robotic manipulator can be adjusted into a second grasping orientation and the robotic manipulator can attempt to grasp the item using the set of grasps associated with the second grasping orientation. Information about the attempts can be recorded and used to determine a richness measure that may represent a richness of the set of grasps for the item.

Abstract: Apparatuses including compliant tips and methods of manipulating items using the compliant tips are described herein. An example apparatus may include a robotic manipulator and a pair of end effectors. One end effector may include a pair of actuator-driven fingers that each include a compliant tip. The compliant tips may be used to scoop underneath items as part of item manipulation.

Abstract: Described herein are techniques for optimizing gross cubic utilization of inventory space by compressing items into closer proximity. In some embodiments, the inventory system selects an initial force limit to which an item to be stored may be subjected. The inventory system may cause a robotic arm to grasp the item and to push that item into a determined storage location. The inventory system then pushes the item into the storage location while applying a force up to the initial force limit to the item. While monitoring the position of the item, the inventory system may detect that the changes in position of the item are decreasing or stopping and determine that the item is approaching its force limit. The inventory system then updates database records with the force limit associated with the item.

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: An example system includes a moveable arm, a pick tool connected to the arm, and a controller. The pick tool includes a first finger, a second finger disposed opposite the first finger, a first handler disposed at a first end of the first finger, and a second handler disposed at a first end of the second finger. Rotation of the first and second handlers while first and second forces are applied to an item by the first and second handlers, respectively, causes movement of the item.

Abstract: A system, apparatus, and method is configured to retrieve items and particularly items that are stored in high-density storage solutions. The system can include one or two-piece manipulators with retractable grippers. The manipulators can be relatively low profile and/or low friction to facilitate their placement between a target item and adjacent items on densely packed shelves or trays. In a retracted position, the grippers can be stowed beneath the surface of the manipulators to further facilitate the placement of the manipulators. In a deployed position, the grippers can extend above the surface of the manipulators to increase the contact area, coefficient of friction, and/or surface pressure of the manipulators on the target item. The grippers can enable the manipulators to be thinner than would otherwise be possible to enable retrieval of items from tightly packed storage solutions—e.g., warehouses with higher gross cubic utilization (GCU).

Abstract: Finger assemblies at the end of a robotic arm end effector includes talon that are retractable. Retraction may be accomplished by a vertical or horizontal barrel cam, a paddle and spin assembly, and/or a resilient plate.

Abstract: Finger assemblies at the end of a robotic arm end effector includes talon that are retractable. Retraction may be accomplished by a vertical or horizontal barrel cam, a paddle and spin assembly, and/or a resilient plate.

Abstract: An inventory packing system and method are described. In some examples, a plurality of items having various dimensions may be accessed. A plurality of trays having various height dimensions into which the plurality of items can be packed may be identified. The plurality of items may be grouped into one or more groups based on height. Allocated inventory trays may be searched to locate free space that can function as a packing location for a first item. If free space is not found in the allocated inventory trays, other inventory trays can be allocated, searched, and free space identified in one of the other inventory trays.

Abstract: Described herein is an inventory management system and methods of operating a robotic arm assembly in which the level of compliance of the robotic arm assembly is altered in order to achieve a high gross cubic utilization. In at least some embodiments, a robotic arm assembly may adopt a low level of compliance when grasping an item. The inventory management system may identify an appropriate storage location for the item and move the item to that storage location. Upon reaching the storage location, the robotic arm assembly may adopt a higher level of compliance. The robotic arm assembly may then push the item against one or more other items in order to insert the item into the determined storage location.

Abstract: A system, apparatus, and method is configured to retrieve items and particularly items that are stored in high-density storage solutions. The system can include one or two-piece manipulators with retractable grippers. The manipulators can be relatively low profile and/or low friction to facilitate their placement between a target item and adjacent items on densely packed shelves or trays. In a retracted position, the grippers can be stowed beneath the surface of the manipulators to further facilitate the placement of the manipulators. In a deployed position, the grippers can extend above the surface of the manipulators to increase the contact area, coefficient of friction, and/or surface pressure of the manipulators on the target item. The grippers can enable the manipulators to be thinner than would otherwise be possible to enable retrieval of items from tightly packed storage solutions—e.g., warehouses with higher gross cubic utilization (GCU).