Conformable variable friction manipulator

    公开(公告)号:US10343290B2

    公开(公告)日:2019-07-09

    申请号:US15452956

    申请日:2017-03-08

    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).

    Packing locations for inventory items

    公开(公告)号:US10235653B1

    公开(公告)日:2019-03-19

    申请号:US14963075

    申请日:2015-12-08

    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.

    Variable compliance EOAT for optimization of GCU

    公开(公告)号:US10207868B1

    公开(公告)日:2019-02-19

    申请号:US15371077

    申请日:2016-12-06

    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.

    Robotic device control optimization using spring lattice deformation model

    公开(公告)号:US10919151B1

    公开(公告)日:2021-02-16

    申请号:US15934568

    申请日:2018-03-23

    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.

Patent Agency Ranking