Abstract: Methods for automatically removing collisions between digital mesh objects and moving digital mesh objects between spatial arrangements. The collisions are removed from a set of digital mesh objects using a perturbation method or a mesh deformation method. After removing the collisions, the digital mesh objects are output in a state without collisions between them. The digital mesh objects can be moved between initial and final states based upon motion constraints of the mesh objects and interpolated states of them between the initial and final states. Based upon the constraints and interpolated states, a number of states for movement of the set of digital mesh objects is determined either collectively for the set or individually for each mesh object. The states can be used as digital setups for dental or orthodontic treatment planning.

Abstract: Systems and techniques for training one or more neural networks to automatically identify one or more aspects of a digital representation used in digital oral care are disclosed including identifying one or more aspects of the first digital representation for which additional processing is to be performed, based on a list of 3D elements, generating a predicted representation by labeling those one or more aspects for which additional processing is to be performed, generating an accuracy score that specifies a difference between the one or more predicted representations and one or more respective reference representations that identify the one or more aspects of the first digital representation for which additional processing is to be performed, and modifying at least one aspect of the neural network based on the accuracy score.

Abstract: Methods for automatically removing collisions between digital mesh objects and moving digital mesh objects between spatial arrangements. The collisions are removed from a set of digital mesh objects using a perturbation method or a mesh deformation method. After removing the collisions, the digital mesh objects are output in a state without collisions between them. The digital mesh objects can be moved between initial and final states based upon motion constraints of the mesh objects and interpolated states of them between the initial and final states. Based upon the constraints and interpolated states, a number of states for movement of the set of digital mesh objects is determined either collectively for the set or individually for each mesh object. The states can be used as digital setups for dental or orthodontic treatment planning.

Abstract: Augmented reality-based training systems that can dynamically construct and render AR content based on physical attributes of a user to train the user to correctly fit one or more articles of a personal protective equipment (PPE) onto the user's body. In some examples, an AR system includes a display and a computing device having a memory and one or more processors. The memory can include instructions that, when executed by the processors, simulate a fitting of PPE to a worker. The system can capture an image of a worker, select a digital model of the PPE, determine alignment of the PPE to the worker, and output for display augmented reality content that includes a composite image of the worker overlaid with the digital model of the PPE in accordance with the determined alignment.

Abstract: A computing device includes one or more computer processors, and a memory including instructions that, when executed by the one or more computer processors, cause the one or more computer processors to receive roadway condition data from a first electrically powered scooter for a particular portion of a roadway, wherein the roadway condition data indicates a roadway condition for the particular portion of the roadway, generate, based at least in part on the roadway condition for the particular portion of the roadway, data usable by a computing device associated with the second electrically powered scooter to traverse the particular portion of a roadway, and send the data to the computing device associated with the second electrically powered scooter to traverse the particular portion of the roadway.

Abstract: Systems and techniques are described for training and using a generative adversarial network (GAN) to produce intermediate stages and final setups for clear tray aligners (CTAs) including receiving, by one or more computer processors, a first digital representation of a patient's teeth, using, by the one or more computer processors and to determine a prediction for one or more tooth movements, a generator that is a neural network included in a GAN and that has been trained to predict one or more tooth movements, and producing, by the one or more processors, an output state that includes at least one of a final setup and one or more intermediate stages.

Abstract: The present disclosure includes in one instance an optical article comprising a data rich plurality of retroreflective elements that are configured in a spatially defined arrangement, where the plurality of retroreflective elements comprise retroreflective elements having at least two different retroreflective properties, and where data rich means information that is readily machine interpretable. The present disclosure also includes a system comprising the previously mentioned optical article, an optical system, and an inference engine for interpreting and classifying the plurality of retroreflective elements wherein the optical system feeds data to the inference engine.

Abstract: Techniques are described for automating the design of dental restoration appliances using machine learning models. An example computing device receives transform information associated with a current dental anatomy of a dental restoration patient, provides the transform information associated with the current dental anatomy of the dental restoration patient as input to a machine learning model trained with transform information indicating placement of a dental appliance component with respect to one or more teeth of corresponding dental anatomies, the dental appliance being used for dental restoration treatment for the one or more teeth, and executes the machine learning model using the input to produce placement information for the dental appliance component with respect to the current dental anatomy of the dental restoration patient.

Abstract: A radar-optical fusion article for attachment to a substrate is described. The radar-optical fusion article includes a first retroreflective layer which is configured to retroreflect at least a portion of light having a wavelength in a range from about 400 nm to about 2500 nm. The radar-optical fusion article includes a second retroreflective layer disposed adjacent to the first retroreflective layer. The second retroreflective layer is configured to retroreflect at least a portion of an electromagnetic wave having a frequency in the range from about 0.5 GHz to about 100 GHz.

Abstract: At least some embodiments of the present disclosure directs to a method for processing an input image having an embedded element, comprising the steps of: computing one or more histograms of the input image; identifying a range of interest in one of the one or more histograms; and determining, by the processor, a threshold based on the range of interest. In some embodiments, a computing device processes the input image using the threshold to generate an output image.

Abstract: Techniques are described for automating the design of dental restoration appliances using neural networks. An example computing device receives transform information associated with a current dental anatomy of a dental restoration patient, provides the transform information associated with the current dental anatomy of the dental restoration patient as input to a neural network trained with transform information indicating placement of a dental appliance component with respect to one or more teeth of corresponding dental anatomies, the dental appliance being used for dental restoration treatment for the one or more teeth, and executes the neural network using the input to produce placement information for the dental appliance component with respect to the current dental anatomy of the dental restoration patient.

Abstract: Machine learning, or geometric deep learning, applied to various dental processes and 5 solutions. In particular, generative adversarial networks apply machine learning to smile design—finished smile, appliance rendering, scan cleanup, restoration appliance design, crown and bridges design, and virtual debonding. Vertex and edge classification apply machine learning to gum versus teeth detection, teeth type segmentation, and brackets and other orthodontic hardware. Regression applies machine learning to coordinate systems, diagnostics, case complexity, and 0 prediction of treatment duration. Automatic encoders and clustering apply machine learning to grouping of doctors, or technicians, and preferences.

Abstract: A personal protective equipment (PPE) interrogation device that uses auditory or visual data to ascertain a readiness state of the article of PPE. The auditory or visual data come from an inspection of the article of personal protective equipment in advance of determining whether the article ready for use.

Abstract: A filter cartridge for a respirator includes an RFID chip encoding a digital change management policy (DCMP) indicating a useful lifespan of the cartridge, so that the cartridge may be replaced at the end of the useful lifespan. In some examples, a system includes a respirator comprising a facepiece and an air blower; a removable contaminant capture cartridge installed within the respirator and configured to remove contaminants from the air as the air passes through the contaminant capture cartridge, wherein the contaminant capture cartridge comprises a radio frequency identification (RFID) chip encoding a digital change management policy (DCMP) indicating a useful lifespan of the contaminant capture cartridge; and a computing device configured to read the DCMP from the RFID chip or write the DCMP to the RFID chip.

Abstract: Augmented reality-based training systems are described that dynamically construct and render AR content based on physical attributes of a user to train the user to correctly fit one or more articles of a personal protective equipment (PPE) onto the user's body. In some examples, an AR system includes a display and a computing device having a memory and one or more processors. The memory includes instructions that when executed by the processors simulate a fitting of a PPE to a worker by capturing at least a first image of the worker; selecting a digital model of the PPE; determining an alignment of the digital model of the PPE to the first image of the worker; and outputting for display augmented reality content comprising a composite of a least a second image of the worker overlaid with the digital model of the PPE in accordance with the determined alignment.

Abstract: The present disclosure includes in one instance an optical article comprising a data rich plurality of retroreflective elements that are configured in a spatially defined arrangement, where the plurality of retroreflective elements comprise retroreflective elements having at least two different retroreflective properties, and where data rich means information that is readily machine interpretable. The present disclosure also includes a system comprising the previously mentioned optical article, an optical system, and an inference engine for interpreting and classifying the plurality of retroreflective elements wherein the optical system feeds data to the inference engine.

Abstract: An infrastructure article includes a signal receiver device configured to receive a wireless signal from a signal emitter device configured at an electrically powered scooter; and a controller configured to determine information, coded in the wireless signal, that is based on an operator proficiency of an operator of the electrically powered scooter; and to perform, based at least in part on the information that indicates the operator proficiency of the operator of the electrically powered scooter, at least one operation.

Abstract: Techniques are described for automating the design of dental restoration appliances using neural networks. An example computing device receives transform information associated with a current dental anatomy of a dental restoration patient, provides the transform information associated with the current dental anatomy of the dental restoration patient as input to a neural network trained with transform information indicating placement of a dental appliance component with respect to one or more teeth of corresponding dental anatomies, the dental appliance being used for dental restoration treatment for the one or more teeth, and executes the neural network using the input to produce placement information for the dental appliance component with respect to the current dental anatomy of the dental restoration patient.

Abstract: The present disclosure includes in one instance an optical article comprising a data rich plurality of retroreflective meats that are configured in a spatially defined arrangement, where the plurality of retroreflective elements comprise retroreflective elements having at least two different retroreflective properties, and where data rich means information that is readily machine interpretable. The present disclosure also includes a system comprising the previously mentioned optical article, an optical system, and an inference engine for interpreting and classifying the plurality of retroreflective elements wherein the optical system feeds data to the inference engine.

Abstract: Systems and methods for image recognition are provided. A style-transfer neural network is trained for each real image to obtain a trained style-transfer neural network. The texture or style features of the real images are transferred, via the trained style-transfer neural network, to a target image to generate styled images which are used for training an image-recognition machine learning model (e.g., a neural network). In some cases, the real images are clustered and representative style images are selected from the clusters.