Abstract: An inventory verification device (“IVD”) provides automatic inventory verification and detection of inventory discrepancies. The IVD automatically verifies the quantity of items in a container based on weight and/or height measurements obtained for the items in the container using two or more sensors of the IVD. The IVD may also automatically updated tracked inventory of an item based on detected changes to the weight and/or height of the items in the container as a result of a worker adding items to the container or removing items from the container without the working providing confirmation for each addition and/or removal. The IVD autoatmically verifies whether correct items are stored in a container by performing feature matching of various characteristics for items imaged in the container against expected characteristics for items that should be stored in the container.

Abstract: Provided are systems and methods by which robots predictively detect objects that may obstruct robotic tasks prior to the robots performing those tasks. For instance, a robot may receive a task, and may obtain dimensions of a task object based on a first identifier obtained with the task or with a sensor of the robot. The robot may determine a first boundary for moving the task object based on the task object dimensions and an added buffer of space that accounts for imprecise robotic operation. The robot may detect a second identifier of a neighboring object, and may obtain dimensions of the neighboring object using the second identifier. The robot may compute a second boundary of the neighboring object based on the dimensions of the neighboring object and a position of the second identifier, and may detect an obstruction based on the second boundary crossing into the first boundary.

Abstract: An automated robotic depalletizing system includes at least one robot for transferring inventory that arrives on a pallet to different storage locations within a warehouse. The robot may perform the automated depalletizing by moving to the pallet having a stacked arrangement of a plurality of objects, identifying, via a sensor, a topmost object of the plurality of objects, aligning a retriever with the topmost object, engaging the topmost object with the retriever, and transferring the topmost object from the pallet to the robot by actuating the retriever. The automated depalletizing may also be performed via coordinated operations of two or more robots. For instance, a first robot may retrieve objects from the pallet, and a second set of one or more robots may be used to transfer the retrieved objects into storage.

Abstract: Spatiotemporal robotic navigation may include providing a set of robots non-conflicting access to the same shared resources at different times so that the robots may operate without continually accounting for the locations of the other robots and workers operating in the particular site, without continually planning or updating paths after determining an initial path, and without continuously adjusting movements as the robots near one another. The spatiotemporal robotic navigation involves generating spatiotemporal plans. Each plan has a set of objectives that a robot is to execute by different time intervals. Each plan is generated so as to not conflict with the resources being accessed by other robots at time intervals set in the plans of other robots.

Abstract: Provided are systems and methods by which robots predictively detect objects that may obstruct robotic tasks prior to the robots performing those tasks. For instance, a robot may receive a task, and may obtain dimensions of a task object based on a first identifier obtained with the task or with a sensor of the robot. The robot may determine a first boundary for moving the task object based on the task object dimensions and an added buffer of space that accounts for imprecise robotic operation. The robot may detect a second identifier of a neighboring object, and may obtain dimensions of the neighboring object using the second identifier. The robot may compute a second boundary of the neighboring object based on the dimensions of the neighboring object and a position of the second identifier, and may detect an obstruction based on the second boundary crossing into the first boundary.

Abstract: Provided are robots that autonomously detect and correct individualized anomalies resulting from deviations in the sensors and/or actuators of individual robots, and environmental anomalies resulting from deviations in the environment elements that the robots rely on or use in the execution of different tasks. To do so, a robot may receive a task, may determine expected kinematics that include expected activations of a set of sensors and actuators by which the robot executes the task, may activate the set of sensors and actuators according to the expected kinematics, may track the actual kinematics resulting from activating the set of sensors and actuators according to the expected kinematics and continuing the activations until detecting one or more environment elements signaling completion of the task, and may adjust one or more sensors, actuators, or environment elements in response to the actual kinematics deviating from the expected kinematics.

Abstract: A controller is provided to orchestrate operations of two or more different actors or resources in completing a task. The controller orchestrates the operations based on a dependency graph that the controller generates for each received task. The dependency graph has a linked list of nodes. Each node includes a different set of operations for completing a different part of a task represented by that dependency graph. Each set of operations associated with a node may be dependent on the successful completion of a prior set of operations associated with a prior linked node in the same dependency graph. The controller may allocate different sets of operations from different nodes of the dependency graph to different human or robotic resources, and may track the status of multiple tasks in parallel based on the progression through different nodes of the corresponding dependency graphs.

Abstract: A virtual put wall system includes a storage apparatus with multiple containers, and different container identifiers attached to the containers. The system includes databases storing a first mapping that maps each customer order of a plurality of customer orders to a different container, a second mapping that maps each container to a different container identifier attached to that container, and a different visual identifier of each container. The system also includes a display device and a coordinating device that detects retrieval of an object, determines that the object belongs to a particular customer order, selects, based on the second mapping, a particular container that is used to store objects of the particular customer order, and directs the transfer of the object to the particular container by modifying the display device to present a particular visual identifier of the particular container.

Abstract: A magnetically-displacing charging station includes a front wall with an opening about its center, and a charging interface with a back wall, at least one support extension, a magnet, and a charging plug. The back wall is disposed behind the front wall and is larger than the opening. The at least one support extension extends through the opening with a proximal end connected to the back wall, and a distal end that extends out in front of the front wall and that retains the magnet and charging plug. The charging station further includes springs connected to the front wall at one end, and to the back wall at an opposite end. The springs provide a default position for the charging interface within the opening, and further provide for a displacement of the charging interface about the opening in response to magnetic or other forces.

Abstract: An automated robotic depalletizing system includes at least one robot for transferring inventory that arrives on a pallet to different storage locations within a warehouse. The robot may perform the automated depalletizing by moving to the pallet having a stacked arrangement of a plurality of objects, identifying, via a sensor, a topmost object of the plurality of objects, aligning a retriever with the topmost object, engaging the topmost object with the retriever, and transferring the topmost object from the pallet to the robot by actuating the retriever. The automated depalletizing may also be performed via coordinated operations of two or more robots. For instance, a first robot may retrieve objects from the pallet, and a second set of one or more robots may be used to transfer the retrieved objects into storage.

Abstract: Spatiotemporal robotic navigation may include providing a set of robots non-conflicting access to the same shared resources at different times so that the robots may operate without continually accounting for the locations of the other robots and workers operating in the particular site, without continually planning or updating paths after determining an initial path, and without continuously adjusting movements as the robots near one another. The spatiotemporal robotic navigation involves generating spatiotemporal plans. Each plan has a set of objectives that a robot is to execute by different time intervals. Each plan is generated so as to not conflict with the resources being accessed by other robots at time intervals set in the plans of other robots.

Abstract: Coordinated operation of two or more autonomous robots is based on a clustered partitioning of a collective set of operations and/or tasks that the robots perform simultaneously. The clustered partitioning may include generating a set of clusters with each cluster of the set of clusters allocating a different subset of the collective set of operations and/or tasks to a different robot such that the set of clusters results in a least amount of cumulative distance that the robots traverse in performing each operation and/or task of the collective set, and a maximum amount of distance separating the robots when performing each operation and/or task. Each cluster may be assigned to a different robot with the collective set of assigned clusters causing the robots to operate and move in a coordinated efficient and nonconflicting manner.

Abstract: A virtual put wall system includes a storage apparatus with multiple containers, and different container identifiers attached to the containers. The system includes databases storing a first mapping that maps each customer order of a plurality of customer orders to a different container, a second mapping that maps each container to a different container identifier attached to that container, and a different visual identifier of each container. The system also includes a display device and a coordinating device that detects retrieval of an object, determines that the object belongs to a particular customer order, selects, based on the second mapping, a particular container that is used to store objects of the particular customer order, and directs the transfer of the object to the particular container by modifying the display device to present a particular visual identifier of the particular container.

Abstract: Robots and/or a robot coordinator are provided to execute an overall task by partitioning the task into subtasks and by coalescing results and/or output of the subtasks. The robot coordinator may coordinate, control, and/or program a set of robots to operate within different sections of a site and to execute subtasks associated with different tasks that fall within their respective sections in parallel. The robot coordinator may coordinate, control, and/or program the same or different set of robots to coalesce results and/or output for subtasks for a particular task from the different sections to complete the overall task. For instance, a first set of robots may retrieve objects that are stored at storage locations within the sections in which each robot operates, and a second set of robots may rotate moveable storage apparatus across the sections so that each storage apparatus stores all objects of a particular order.

Abstract: Provided is a robot for retrieving objects with different sizes, shapes, weights, placements, configurations, and/or other characteristics from a floor or raised height. The robot may include a motorized base, a lift that raises to a plurality of heights from the base, an upper platform attached over the lift, a vertical extension extending downwards from a frontside of the upper platform and in front of the lift, a lower platform with a proximal end coupled to the vertical extension and a distal end extending in front of the robot and directly over a ground surface on which the motorized base moves when the lift is in a lowered position, and a retriever for retrieving an object onto the lower platform.

Abstract: A robot may include a spatiotemporal controller for controlling the kinematics or movements of the robot via continuous and/or granular adjustments to the actuators that perform the physical operations of the robot. The spatiotemporal controller may continuously and/or granularly adjust the actuators to align completion or execution of different objectives or waypoints from a spatiotemporal plan within time intervals allotted for each objective by the spatiotemporal plan. The spatiotemporal controller may also continuously and/or granularly adjust the actuators to workaround unexpected conflicts that may arise during the execution of an objective and delays that result from a workaround while still completing the objective within the allotted time interval. By completing objectives within the allotted time intervals, the spatiotemporal controller may ensure that conflicts do not arise as the robots simultaneously operate in the site using some of the same shared resource.

Abstract: A workflow management system (WMS) coordinates, controls, and monitors item picking assets, item retrieval assets, and order packaging assets in performance of different workflows. The WMS optimizes the different workflows by assigning tasks to the different assets in a manner that minimizes overall execution time, cost, and resource utilization. Some optimizations include maximizing or prioritizing item pick rate, item packaging rate, or both. Assets integrated with the WMS and under WMS control include human workers, autonomous robots, and resources used in performance of the workflows.

Abstract: Provided is an automated vertical transfer system for a site that includes one or more mezzanines or other structures that create different operational vertical planes. The system may include a robot controller and one or more robots that operate exclusively on one of the different operational vertical planes. The robot controller may synchronize and/or coordinate the operations of the robots and/or other devices so that objects may be transferred across planes while each robot remains and continues operations on one plane.

Abstract: Local caches are provided for last-mile item distribution. Each local cache stores items belonging to different customers. A management server tracks customer locations relative to a local cache. The management server instructs at least one robot within the local cache to ready for pickup items belonging to a particular customer as the particular customer nears the local cache. The robot retrieves and queues the items for pickup prior to the particular customer arriving at the local cache. The item is transferred once the particular customer arrives at the local cache. The management server monitors the position through a front-end application running on a mobile device of the particular customer. The application can also be used to contact delivery drivers to deliver items on behalf of customers that do not wish to pickup items from the local cache.

Abstract: Provided are robots for managing inventory of arbitrary size, shape, weighted, or other distinct featured items. The robots dynamically and adaptively manage inventory for items stacked atop one another, items stacked behind one another, items that are horizontally arranged, items that are dispensed from a gravity flow dispenser, items that are dispensed from a back-to-front push dispenser, and items that are loosely contained within a bin. The robots have a sensory array from which dimensions of a particular arrangement and dimensions of a particular item in the particular arrangement can be calculated. The calculated dimensions can include length, width, or height of a particular arrangement and a particular item or force imposed by the particular arrangement and mass of the particular item. Based on these dimensions, the robots can dynamically track different item inventories without counting each individual item.