A method for operating a robotic system includes determining a discretized object model based on source sensor data; comparing the discretized object model to a packing plan or to master data; determining a discretized platform model based on destination sensor data; determining height measures based on the destination sensor data; comparing the discretized platform model and/or the height measures to an expected platform model and/or expected height measures; and determining one or more errors by (i) determining at least one source matching error by identifying one or more disparities between (a) the discretized object model and (b) the packing plan or the master data or (ii) determining at least one destination matching error by identifying one or more disparities between (a) the discretized platform model or the height measures and (b) the expected platform model or the expected height measures, respectively.

A system for singulating objects includes a bin for receiving a collection of objects, a robotic manipulator for grasping objects from the bin, a scale for measuring a weight of the grasped objects, and a computer system for comparing measured weights to acceptable weight ranges to detect double picks. Methods include determining acceptable weight ranges by weighing a plurality of objects.

A system and method for automatically moving one or more items between a structure at a source location and a destination using a robot is provided. The system includes first and second vision systems to identify an item and to determine the precise location and orientation of the item at the source location and the precise location and orientation of the destination, which may or may not be in a fixed location. A controller plans the best path for the robot to follow in moving the item between the source location and the destination. An end effector on the robot picks the item from the source location, holds it as the robot moves, and places the item at the destination. The system may also check the item for quality by one or both of the vision systems. An example of loading and unloading baskets from a machine is provided.

An order-picking method includes autonomously routing a plurality of mobile robotic units in an order fulfillment facility and picking articles to or putting articles from the robotic units in the order fulfillment facility. A material-handling robotic unit that is adapted for use in an order fulfillment facility includes an autonomous mobile vehicle base and a plurality of article receptacles positioned on the base. A visual indicator associated with the receptacle facilitates picking articles to or putting articles from the robotic unit.

A method for operating a robotic system includes determining a discretized object model based on source sensor data; comparing the discretized object model to a packing plan or to master data; determining a discretized platform model based on destination sensor data; determining height measures based on the destination sensor data; comparing the discretized platform model and/or the height measures to an expected platform model and/or expected height measures; and determining one or more errors by (i) determining at least one source matching error by identifying one or more disparities between (a) the discretized object model and (b) the packing plan or the master data or (ii) determining at least one destination matching error by identifying one or more disparities between (a) the discretized platform model or the height measures and (b) the expected platform model or the expected height measures, respectively.

A trajectory information generating unit is included, the trajectory information generating unit generating trajectory information that defines a trajectory for which a picking hand picks one of one or more works stored in one supply container included in one or more supply containers and arranges the work in one arrangement container included in one or more arrangement containers. After performing a process of generating trajectory information representing a first work included in the one or more works and before a movement of the first work is completed, the trajectory information generating unit may generate trajectory information representing a second work included in the one or more work and different from the first work by using an operation result in the process of generating the trajectory information regarding the first work.

A three-dimensional information acquiring unit for acquiring three-dimensional information of a target object, a gripping information acquiring unit for acquiring gripping information that defines a method of gripping the target object by using a picking hand, and an information management unit for storing, in a storage apparatus in association with each other, (i) three-dimensional information of the target object acquired by the three-dimensional information acquiring unit and (ii) gripping information acquired by the gripping information acquiring unit are included. The three-dimensional information of the target object may include at least one of origin position information and the coordinate axis information. A two-dimensional information acquiring unit for acquiring two-dimensional information of the target object may be further included.

An automated modular plant growing system includes a rack structure with primary guiding tracks and secondary guiding tracks transverse to each other, and upper guiding tracks in parallel and above the primary guiding tracks. The automated modular plant growing system also includes a plurality of mobile modules detachably connected to the upper guiding tracks and to a nutrient solution supply system.

Various embodiments of the present technology generally relate to robotic devices and artificial intelligence. More specifically, some embodiments relate to an artificial neural network training method that does not require extensive training data or time expenditure. The few-shot training model disclosed herein includes attempting to pick up items and, in response to a failed pick up attempt, transferring and generalizing information to similar regions to improve probability of success in future attempts. In some implementations, the training method is used to robotic device for picking items from a bin and perturbing items in a bin. When no picking strategies with high probability of success exist, the robotic device may perturb the contents of the bin to create new available pick-up points. In some implementations, the device may include one or more Computer-vision systems.

Various embodiments of the present technology generally relate to robotic devices and artificial intelligence. More specifically, some embodiments relate to a robotic device for picking items from a bin and perturbing items in a bin. The robotic device may include one or more picking elements and one or more perturbation elements for disturbing a present arrangement of items in the bin. In an exemplary embodiment, a perturbation element comprises a compressed air valve. In some implementations, the robotic device may also include one or more computer-vision systems. Based on image data from the one or more computer-vision systems, a strategy for picking up items from the bin is determined. When no strategies with high probability of success exist, the robotic device may perturb the contents of the bin to create new available pick-up points.