Abstract: To automate a pricing strategy for an otherwise unpriced service or item, prices may be generated through a plurality of different pricing models, via a pricing engine passing input data to a plurality of discrete pricing models. Those pricing models may pass data back to the pricing engine, which then adjudicates the results of the pricing models to identify a most-relevant pricing model for the particular unpriced service or item.

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: 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: To automate a pricing strategy for an otherwise unpriced service or item, prices may be generated through a plurality of different pricing models, via a pricing engine passing input data to a plurality of discrete pricing models. Those pricing models may pass data back to the pricing engine, which then adjudicates the results of the pricing models to identify a most-relevant pricing model for the particular unpriced service or item.

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: 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: 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: 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: In one example embodiment, a robotic vacuum sorting system comprises: a suction gripper mechanism mounted to a sorting robot; a vacuum system coupled to the suction gripper mechanism; robot control logic and electronics coupled to the sorting robot and the vacuum system; and an imaging device coupled to the robot control logic and electronics. In response to an image signal from the imaging device, the robot control logic and electronics outputs robot control signals to control the sorting robot, and outputs one or more airflow control signals to the vacuum system to execute a capture action on a target object using the suction gripper. During the capture action, the robot control logic and electronics outputs control signals such that the vacuum system pulls a vacuum at the gripping port of the suction gripper mechanism as the suction gripper mechanism is applied to capture and hold the target object.

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: 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: In one example embodiment, a robotic vacuum sorting system comprises: a suction gripper mechanism mounted to a sorting robot; a vacuum system coupled to the suction gripper mechanism; robot control logic and electronics coupled to the sorting robot and the vacuum system; and an imaging device coupled to the robot control logic and electronics. In response to an image signal from the imaging device, the robot control logic and electronics outputs robot control signals to control the sorting robot, and outputs one or more airflow control signals to the vacuum system to execute a capture action on a target object using the suction gripper. During the capture action, the robot control logic and electronics outputs control signals such that the vacuum system pulls a vacuum at the gripping port of the suction gripper mechanism as the suction gripper mechanism is applied to capture and hold the target object.

Abstract: In one example embodiment, a robotic vacuum sorting system comprises: a suction gripper mechanism mounted to a sorting robot; a vacuum system coupled to the suction gripper mechanism; robot control logic and electronics coupled to the sorting robot and the vacuum system; and an imaging device coupled to the robot control logic and electronics. In response to an image signal from the imaging device, the robot control logic and electronics outputs robot control signals to control the sorting robot, and outputs one or more airflow control signals to the vacuum system to execute a capture action on a target object using the suction gripper. During the capture action, the robot control logic and electronics outputs control signals such that the vacuum system pulls a vacuum at the gripping port of the suction gripper mechanism as the suction gripper mechanism is applied to capture and hold the target object.

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: 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: In one example embodiment, a robotic vacuum sorting system comprises: a suction gripper mechanism mounted to a sorting robot; a vacuum system coupled to the suction gripper mechanism; robot control logic and electronics coupled to the sorting robot and the vacuum system; and an imaging device coupled to the robot control logic and electronics. In response to an image signal from the imaging device, the robot control logic and electronics outputs robot control signals to control the sorting robot, and outputs one or more airflow control signals to the vacuum system to execute a capture action on a target object using the suction gripper. During the capture action, the robot control logic and electronics outputs control signals such that the vacuum system pulls a vacuum at the gripping port of the suction gripper mechanism as the suction gripper mechanism is applied to capture and hold the target object.

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: Various embodiments of the present invention provide systems and methods for data filter tuning. As an example, a method for filter tuning is disclosed that includes: providing a tunable filter having an operation filter and a calibration filter; applying a low frequency test input to the operation filter in place of an input signal to yield a first filter output; calculating a low frequency magnitude value corresponding to the first filter output; applying a high frequency test input to the operation filter in place of an input signal to yield a second filter output; calculating a high frequency magnitude value corresponding to the second filter output; modifying a tuning factor of the calibration filter when a ratio of the high frequency magnitude value and the low frequency magnitude value is outside of a defined range; and storing the tuning factor of the calibration filter when the ratio of the high frequency magnitude value and the low frequency magnitude value is within the defined range.

Abstract: Various embodiments of the present invention provide tunable filter circuits and methods for using such. As an example, a tunable biquad filter is disclosed that includes a tunable biquad circuit, a mixer circuit and a low pass filter. The tunable biquad circuit exhibits a cutoff frequency corresponding to an adjustment value, and is operable to receive an filter input and to provide a filter output. The mixer circuit is operable to provide a product of the filter input and the filter output. The product includes a time dependent component and a static component. The low pass filter is operable to receive the product and to provide the static component.