A material sorting system sorts materials utilizing a vision system that implements a machine learning system in order to identify or classify each of the materials, which are then sorted into separate groups based on such an identification or classification determining that the materials are composed of either wrought aluminum, extruded aluminum, or cast aluminum.

The present disclosure provides methods and systems for autonomous data collection and system control of a material recovery facility (MRF). A control system receives data from set of sensors that reflect a status of the MRF. The control system determines an operating status of various MRF components (e.g., material handling units (MHUs), sensors, and/or other elements) and/or a composition of a waste stream being processed by the MRF. The control system controls MHU(s) based on the data to optimize the recovery and/or purity of recoverable materials from the waste stream. The control system may rearranging MHUs within the MRF and/or re-tasking individual MHUs to perform different handling functions. Machine learning (ML) and/or artificial intelligence (AI) mechanisms can be used to optimize the operation of the MRF in an autonomous fashion. Other aspects are also disclosed.

Apparatus and method for assigning a material value score to a waste printed circuit board or a portion thereof and system for sorting waste printed circuit boards.

A waste stream is analyzed and sorted to segregate different items for recycling. Certain features of the technology improve the accuracy with which waste stream items are diverted to collection repositories. Other features concern adaptation of neural networks in accordance with context information sensed from the waste. Still other features serve to automate and simplify maintenance of machine vision systems used in waste sorting. Yet other aspects of the technology concern marking 2D machine readable code data on items having complex surfaces (e.g., food containers with integral ribbing for structural strength or juice pooling), to mitigate issues that such surfaces can introduce in code reading. Still other aspects of the technology concern prioritizing certain blocks of conveyor belt imagery for analysis. Yet other aspects of the technology concern joint use of near infrared spectroscopy, artificial intelligence, digital watermarking, and/or other techniques, for waste sorting. A variety of further features and arrangements are also detailed.

A system includes a network interface and a processor coupled to the network interface. The processor is configured to receive an identifier of a waste product via the network interface; determine, based on the identifier, a waste category for the waste product; and provide a report that includes the determined waste category.

A sorting apparatus is provided for sorting selected magnetically attractable articles from a stream of articles including non-selected magnetically attractable articles. The apparatus may include a conveyor for conveying the stream of articles. The conveyor may include a conveyor belt formed in an endless loop including a discharge end configured to launch the stream of articles off the conveyor. A conveyor guide may be located inside of the endless loop adjacent the discharge end. The conveyor guide may be configured to support the conveyor belt such that the conveyor belt slides on the conveyor guide along a downwardly curved path. An array of magnets may be arranged inside of the endless loop for interacting with the stream of articles as the stream of articles passes off the discharge end.

A waste sorting robot comprises: a frame and a manipulator moveably mounted to the frame and comprising a gripper for interacting with one or more waste objects to be sorted within a working area. The waste sorting robot comprises a conveyor for moving the one or more waste objects towards the working area. At least a portion of the manipulator is rotatable with respect to the frame such that the gripper is moveable lengthways along the conveyor within the working area.

A sorting-based garbage classification method and a sorting-based garbage classification device are provided. The method utilizes quantitative features of domestic garbage components and adopts bubble sort algorithm to build a sorting model to sort and classify domestic garbage. The method is more in line with technical requirements of downstream incineration, pyrolysis gasification and so on, and has the features of high fault tolerance rate and high operation efficiency, and is characterized by controllable environmental impact, flexible product form and high energy utilization efficiency in the operation process.

A method for reducing radiologically-contaminated waste is provided. The method comprises treating radiologically-contaminated surfaces and subsurfaces. The method comprises consolidating soil waste. The method comprises employing real-time scanning technology to classify waste based at least in part on a threshold of radiological contamination. The waste is sorted based on the classification. The waste is disposed of via at least one of different disposal routes, based at least in part on the classification.

Embodiments described herein relate to hardware and software for waste item detection and recognition, along with an education or feedback system. Embodiments described herein use artificial intelligence, which embodies machine learning and computer vision, to detect waste items and generate feedback to nudge the user to dispose the waste items into appropriate receptacles while generating smart operational insights of a designated premise.