Abstract: Time-varying control of a controllable air stream is disclosed, including: a set of image sensors configured to capture image data showing a target object being conveyed by a conveyor device along a Y-direction; an array of air jets located along an X-direction, wherein the X-direction crosses the Y-direction; and a processor configured to: receive the image data from the set of image sensors; determine a classification of the target object within the image data; and modify a two-dimensional firing polygon of air to be directed by the array of air jets on the target object based at least in part on the classification of the target object; and wherein the array of air jets is configured to perform a sorting operation on the target object as the target object is translated across the array of air jets based at least in part on the modified two-dimensional firing polygon.

Abstract: Maintaining a data structure corresponding to a target object is disclosed, including: determining that an identified target object from a sensed signal is a new target object, wherein the sensed signal is generated at a sorting facility; generating a new data structure corresponding to the new target object; and updating the new data structure with an attribute associated with the new target object, wherein the attribute is derived from the sensed signal associated with the new target object.

Abstract: A legged robot having a frame with a plurality of links in mechanical communication with plurality of brackets, the frame forming a front, back, top, bottom, and sides, legs in mechanical communication with one or more of the plurality of brackets, each leg having a knee motor, an abduction motor, and a hip motor, a computer module in mechanical communication with one or more of the plurality of brackets and in electrical communication with the legs, and a power module in mechanical communication with one or more of the plurality of brackets and in electrical communication with the legs and the computer module.

Abstract: Sorting biogenic material from a stream of heterogeneous materials is disclosed, including: detecting biogenic material within an input stream of heterogeneous material; sorting the biogenic material based at least in part on a desired biochar formulation; and tracking a composition of a sorted mixture of biogenic material.

Abstract: An efficient material recovery facility is disclosed, including: a first sorting device configured to: process a first instruction to remove a first target item from a set of items; and in response to the first instruction, perform a first sorting action to remove the first target item from the set of items, wherein the set of items excluding at least the first target item is to be transported towards a second sorting device, wherein the second sorting device is associated with a same sorting device type as the first sorting device; and wherein the second sorting device is configured to perform a second sorting action to remove a second target item from the set of items excluding at least the first target item in response to receiving a second instruction to remove the second target item.

Abstract: Systems and methods for vacuum extraction for material sorting applications are provided. In one embodiments, a vacuum object sorting system comprises: a vacuum extraction assembly that includes at least one vacuum extractor device having an inlet and an outlet, wherein the at least one vacuum extractor device is configured to convert a controlled compressed air stream into a channeled vacuum airflow entering the inlet and exiting the outlet; and an object recognition device coupled to sorting control logic and electronics, wherein the controlled compressed air stream is controlled in response to a signal generated by the object recognition device; wherein the at least one vacuum extractor device is configured to capture a target object identified by the sorting control logic and electronics utilizing the channeled vacuum airflow, and further utilizing the channeled vacuum airflow, to pass the target object through the inlet and outlet to a deposit location.

Abstract: Object path planning in a sorting facility is disclosed, including: obtain data describing a trajectory associated with a target object; generate a control signal for a sorting device to perform a sorting operation on the target object based at least in part on the trajectory associated with the target object; and provide the control signal to the sorting device, wherein the sorting device is configured to execute the control signal with respect to the target object.

Abstract: A controllable array sorting device is disclosed, including: an array of diverting mechanisms; and a processor coupled to the array of diverting mechanisms, wherein the processor is configured to: process an instruction to perform a sorting action on a target item, wherein the instruction specifies a selected at least subset of the array of diverting mechanisms to use to perform the sorting action; and in response to the instruction, cause the selected at least subset of the array of diverting mechanisms to perform the sorting action on the target item.

Abstract: Pick quality determination is disclosed, including: using a pressure meter to sense a pressure associated with an airflow through a gripper mechanism of a diverting mechanism over time during a pick operation on a target object; storing the sensed pressure associated with the airflow through the gripper mechanism over time as a pressure sequence associated with the pick operation on the target object; and correlating the pressure sequence with representative pressure sequences associated with corresponding pick quality types to determine whether the pick operation on the target object was successful or not.

Abstract: Using machine learning to recognize variant objects is disclosed, including: identifying an object as a variant of an object type by inputting sensed data associated with the object into a modified machine learning model corresponding to the variant of the object type, wherein the modified machine learning model corresponding to the variant of the object type is generated using a machine learning model corresponding to the object type; and generating a control signal to provide to a sorting device that is configured to perform a sorting operation on the object, wherein the sorting operation on the object is determined based at least in part on the variant of the object type associated with the object.

Abstract: Systems and methods for optical material characterization of waste materials using machine learning are provided. In one embodiment, a system comprises: an imaging device configured to generate image frames an area and target objects within the area; an object characterization processor coupled to the imaging device and comprising Neural Processing Units and a Neural Network Parameter Set. The Neural Network Parameter Set stores learned parameters utilized by the one or more Neural Processing Units for characterizing the one or more target objects. The Neural Processing Units are configured by the Neural Network Parameter Set to detect a presence of a plurality of different materials within the image frames based on a plurality of different features. For a first image frame of the plurality of image frames, the Neural Processing Units outputs material characterization data that identifies which of the plurality of different materials are detected in the first image frame.

Abstract: A material picker assembly is disclosed, including: a connector configured to be attached to an actuator device; and a plurality of picker mechanisms, wherein each picker mechanism includes a suspension element that is configured to absorb impact on the picker mechanism by one or more objects.

Abstract: Embodiments of the invention provide a power supply control method and a monitor system capable of executing the power supply control method. The monitor system includes a base station, an image capture apparatus, and a processor. The base station includes a charging apparatus including a power supply connector and a power source coupled to the power supply connector and outputting power through the power supply connector. The image capture apparatus shoots the power supply connector to obtain a shot image. The processor determines a foreign object distribution on the power supply connector according to the shot image and sends a warning message according to the foreign object distribution. The foreign object distribution relates to foreign objects formed on the power supply connector. Accordingly, whether a charging mechanism fails can be automatically determined and notification and/or compensation may be performed when the charging mechanism fails.

Abstract: Systems and methods for sorting recyclable items and other materials are provided. In one embodiment, a system for sorting objects comprises: at least one imaging sensor; a controller comprising a processor and memory storage, wherein the controller receives image data captured by the image sensor; and at least one pusher device coupled to the controller, wherein the at least one pusher device is configured to receive an actuation signal from the controller. The processor is configured to detect objects travelling on a conveyor device and recognize at least one target item traveling on a conveyor device by processing the image data and to determine an expected time when the at least one target item will be located within a diversion path of the pusher device. The controller selectively generates the actuation signal based on whether a sensed object detected in the image data comprise the at least one target item.

Abstract: Using a suction gripper cluster device is disclosed, including: causing airflows to be generated by a plurality of airflow generators of a respective plurality of suction gripper mechanisms included in a suction gripper cluster device comprising a plurality of suction gripper mechanisms, wherein the plurality of airflow generators is configured to cause the airflows to enter respective intake ports of the plurality of suction gripper mechanisms and exit respective outlet ports of the respective plurality of suction gripper mechanisms in response to receiving air at a respective air input port of the respective plurality of suction gripper mechanisms; causing a target object to be captured by the suction gripper cluster device using the airflows; activating a positioning actuator mechanism to position the suction gripper cluster device; and causing the target object to be ejected from the suction gripper cluster device.

Abstract: A legged robot having a frame with a plurality of links in mechanical communication with plurality of brackets, the frame forming a front, back, top, bottom, and sides, legs in mechanical communication with one or more of the plurality of brackets, each leg having a knee motor, an abduction motor, and a hip motor, a computer module in mechanical communication with one or more of the plurality of brackets and in electrical communication with the legs, and a power module in mechanical communication with one or more of the plurality of brackets and in electrical communication with the legs and the computer module.

Abstract: Techniques for planning object sorting are disclosed, including: receiving a set of current information associated with target objects on a conveyor device; determining a current state of the sorting system, wherein the sorting system comprises an actuator device that is configured to actuate a picker assembly to capture target objects from the conveyor device; determining a sequence of actions to be performed by the actuator device and the picker assembly with respect to one or more target objects based on the set of current information associated with the target objects and the current state of the sorting system; determining a selected subset of actions with respect to an identified target object from the sequence of actions; and sending an instruction to the actuator device to cause the actuator device to perform the selected subset of actions with respect to the identified target object.

Abstract: A system having components coupled to an aircraft in operation processes sensor-derived data, performs a localization cross-checking procedure, and dynamically generates updated analyses of the position and orientation of the aircraft. Based on the updated analyses, the system can generate instructions for flight control of the aircraft and can update flight control instructions as new data is received and processed. The system functions to reduce the “worst-case” bounds on a localization estimate for the aircraft to a low enough level that is appropriate for completing a flight operation.

Abstract: Grippers, such as robotic grippers, and associated methods and systems are disclosed herein. One disclosed gripper includes a first compliant gripper jaw, a first push-pull assembly having a first distal end fixed on the first compliant gripper jaw, a second compliant gripper jaw, a second push-pull assembly having a second distal end fixed on the second compliant gripper jaw, and an actuator connected to both the first push-pull assembly and the second push-pull assembly.

Abstract: A livestock grazing control robotic system provides a movable livestock enclosure than can travel over uneven terrain allowing livestock to graze over different areas, enabling rotational grazing in a cash crop farmland during non-crop time periods. The system includes an enclosure or pen defined by a fencing mechanism. The fencing mechanism is supported by a movable chassis that includes a drivetrain system. The fencing mechanism includes a ground-clearance portion that flexibly covers the area between the chassis and the uneven ground, preventing animals from entering or exiting the enclosure and that can be raised and lowered on command to enable moving of the enclosure. The fencing mechanism may hold water for watering livestock. The system further includes a control module and a power supply that enable autonomous movement of the enclosure according to a grazing plan. The system may receive water and be towed by a water delivery vehicle.