Dexterity

The present application discloses a system, a method, and a computer system for moving items deemed to be too heavy to be picked up by a robotic arm. The method includes (i) receiving sensor data from one or more sensors associated with a source conveyor configured to convey items to a pick location, (ii) determining, based at least in part on the sensor data, that an item that is too heavy to be lifted by a robotic arm controlled by the one or more processors has entered the source conveyor, and (iii) providing an output indicating that the item too heavy to be lifted by the robotic arm has been detected.

Abstract A robotic system is disclosed to control multiple robots to cooperatively load/unload a truck or other container. In various embodiments, image data is received and used to control a first robotic arm and a second robotic arm to load or unload objects into or from the truck or other container, including by loading or unloading one or more of the objects using the first robotic arm and the second robotic arm together to cooperatively to grasp and move each of one or more of the objects along a corresponding trajectory.

Abstract The present application discloses a method, system, and computer system for arranging a set of objects for loading to a transport container. The method includes (i) receiving an indication of the set of objects to be loaded into the transport container for transport from a source location to a destination location, (ii) determining, based at least in part on object information corresponding to the set of objects and resources available to load the set of objects, an arrangement of the set of objects loaded into the transport container that satisfies a weight distribution criteria, and (iii) providing the arrangement as an output to be used in connection with loading the set of objects to the transport container.

A robotic system is disclosed. The system includes a communication interface configured to receive, from one or more sensors deployed in a workspace, sensor data indicative of a current state of the workspace, the workspace comprising a pallet or other receptacle and a plurality of items stacked on or in the receptacle. The system includes one or more processors that use a geometric model based at least in part on past item placements in combination with the sensor data to estimate a state of the pallet or other receptacle and one or more items stacked on or in the pallet or other receptacle, and use the estimated state to generate or update a plan to control a robotic arm to place a next item on or in, or remove a next item from, the pallet or other receptacle in a manner that avoids having the next item collide with any other item stacked on or in the pallet or other receptacle.

Abstract A kitting system is disclosed. In various embodiments, the kitting system includes a conveyance structure configured to impart to an item a first net resultant force substantially in a first direction, wherein the first direction is associated with a direction of flow from a source end of the conveyance structure to a destination end opposite the source end and associated with a pick-up zone from which the item is to be retrieved; a sensor configured to provide a sensor output associated with the pick-up zone; and a processor configured to provide a control input to one or both of the conveyance structure and a disrupter device associated with the conveyance structure based at least in part on the sensor output.

Abstract A robotic system is disclosed. The system includes a memory that stores a machine learning-based model to provide a scoring function value for a candidate item placement on a pallet on which are plurality of items are to be stacked given a current state value of the pallet and a set of zero or more items placed previously. The system includes one or more processors that use the model to determine a corresponding score for each of a plurality of candidate placements for a next item to be placed and the current state value associated with the current state of the pallet and a set of zero or more items placed previously, select a selected placement based at least in part on the respective scores, control a robotic arm to place the next item according to the selected placement.

Abstract A robotic system is disclosed. The system includes a communication interface, and one or more processors coupled to the communication interface and configured to: receive, via the communication interface, data associated with a plurality of items within a workspace, determine to control a flow of items on a chute based at least in part on the data associated with the plurality of items within the workspace, and in response to determining to control the flow of items, implement to control the flow of items at least by controlling a flow disrupter move in a manner that causes the flow of items to change, wherein the flow disrupter is flush with the chute when the flow disrupter is not deployed to impede the flow of items.

Abstract A robotic system is disclosed. The system includes a communication interface, and one or more processors coupled to the communication interface and configured to: generate based at least in part on the received data a plan to stack the items on or in the destination location. For each item, the generating the plan includes determining the destination location based at least in part on a characteristic associated with the item, and at least one of (i) a characteristic of a platform or receptacle on which one or more items are to be stacked, and (ii) an existing stack of one or more items on the platform or receptacle. The destination location is determined from among a plurality of zones in which platforms or receptacles are disposed, and each of the plurality of zones are within a range of a robotic arm. A robotic arm is controlled to implement the plan.