Abstract: A system includes a personal protective equipment (PPE) configured to be worn by an agent. The PPE includes a sensor assembly comprising a radar device configured to generate radar data, a microphone configured to capture speech input from the agent, and an inertial measurement device configured to generate inertial data. The system includes a computing device configured to: process sensor data from the sensor assembly, the sensor data including at least the radar data and the inertial data, to generate pose data of the agent based on the processed sensor data, the pose data including a location and an orientation of the agent as a function of time, to process the speech input to identify an item of interest in an environment in which the PPE is deployed, and to form mapping information for the environment with the item of interest being marked, based on the processed speech input.

Abstract: The disclosure describes systems (2) of navigating a hazardous environment (8). The system includes personal protective equipment (PPE) (13) and computing device(s) (32) configured to process sensor data from the PPE (13), generate pose data of an agent (10) based on the processed sensor data, and track the pose data as the agent (10) moves through the hazardous environment (8). The PPE (13) may include an inertial measurement device to generate inertial data and a radar device to generate radar data for detecting a presence or arrangement of objects in a visually obscured environment (8). The PPE (13) may include a thermal image capture device to generate thermal image data for detecting and classifying thermal features of the hazardous environment (8). The PPE (13) may include one or more sensors to detect a fiducial marker (21) in a visually obscured environment (8) for identifying features in the visually obscured environment (8).

Abstract: Methods for generating multiple orthodontic treatment options for a digital 3D model of teeth in malocclusion. The method generates a plurality of different orthodontic treatment plans for the teeth and displays in a user interface the digital 3D model of teeth in malocclusion with a visual indication of each of the plurality of different orthodontic treatment plans. The visual indication of the treatment plans can be overlaid on the digital 3D model of teeth in malocclusion and possibly include aligners, brackets, or a combination of aligners and brackets. A doctor, technician, or other user can then select one of the treatment plans for a particular patient.

Abstract: Methods for generating stages for a portion of orthodontic aligner treatment for a digital 3D model of teeth in malocclusion. The methods generate a subset of stages of setups among a complete set of stages of setups for aligner treatment of the teeth. The subset of stages can be selected from a complete set of stages, based upon a target intermediate setup, or sequentially generated from one stage to the next in the subset. Aligners for the subset of stages of setups can then be manufactured without having to make a complete set of aligners. A method to generate a setup for the aligner treatment compares the digital 3D model of teeth in malocclusion to a plurality of setups for historical cases of teeth in malocclusion that have undergone aligner treatment.

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.

Abstract: Aspects of the present disclosure relate to methods, devices, and systems using speech recognition in a dental procedure. The method can include receiving, by a computing device, voice input data that specifies dental information for a patient. The method can also include analyzing, by the computing device, the voice input data to process the dental information. Based on the identified dental treatment information, the method can include generating, by the computing device, one or more custom dental prescriptions for the patient.

Abstract: An automated method for generating a final setup for orthodontic treatment. The method includes receiving a digital 3D model of teeth in an initial state. The method computes a scoring function based upon metrics related to the initial state to generate a corresponding score, perturbs the state of the teeth through translations and rotations of a tooth or set of teeth to generate a perturbed state of the teeth, and updates the state of the teeth based upon the score and the perturbed state of the teeth to generate one or more final setups representing a final state of the teeth after the orthodontic treatment.

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 N model (e.g., a neural network). In some cases, the real images are clustered and representative style images are selected from the clusters.

Abstract: In general the invention is directed to systems and methods to identify conductors that may be used as part of a power transmission line system. In one embodiment, the invention is directed to a computer-implemented method of evaluating an electric conductor for an overhead power transmission line, comprising: receiving requirements data defining requirements for an overhead power transmission line; receiving conductor data that define at least two conductors to be evaluated; after receiving conductor data for the plurality of conductors to be evaluated, automatically modeling expected operating performance for at least two conductors using conductor assessment software running on a computer, wherein modeling at least comprises, for at least one of the conductors to be evaluated, calculating the conductor's maximum ampacity within the constraints defined by the requirements data; and, based on the modeling, identifying at least one conductor that meets the requirements for the power transmission line.

Abstract: In general the invention is directed to systems and methods to identify conductors that may be used as part of a power transmission line system. In one embodiment, the invention is directed to a computer-implemented method of evaluating an electric conductor for an overhead power transmission line, comprising: receiving requirements data defining requirements for an overhead power transmission line; receiving conductor data that define at least two conductors to be evaluated; after receiving conductor data for the plurality of conductors to be evaluated, automatically modeling expected operating performance for at least two conductors using conductor assessment software running on a computer, wherein modeling at least comprises, for at least one of the conductors to be evaluated, calculating the conductor's maximum ampacity within the constraints defined by the requirements data; and, based on the modeling, identifying at least one conductor that meets the requirements for the power transmission line.

Abstract: In general, techniques are described for the creation and execution of accurate models for the manufacture of complex, multi-layered materials. The techniques may be used to calculate variations of a process parameter within the material during the manufacturing process. A method comprises receiving segment data that partitions a manufacturing process into a set of segments having at least one layer of a material. For example, the segment data may partition the manufacturing processes along a path traversed by the material within the manufacturing process. The method further comprises receiving curvature data for the layers, and calculating values for a process parameter through the layers of the segments as a function of the curvature data. The method may comprise invoking a one-dimensional model, such as a one-dimensional finite difference model, to calculate the values for the defined segments and layers.

Abstract: In general, the invention is directed to a system of reusable software components that allow computational models to be seamlessly integrated into an executable software program, such as process management software within a manufacturing facility. The system includes a set of objects that encapsulate computational models and provide generic interfaces for invoking the models. A control module is embedded within the software program to invoke the computational models in parallel. The system may further include a model aggregator to receive input values from the control module and to distribute the input values to the objects for use during model execution. The system can be used to quickly and easily provide the results of one or more process models to line operators and process engineers during the manufacturing process, allowing the process engineer or line operator to more readily understand and adjust the process.

Abstract: In general, techniques are described for the creation and execution of accurate models for the manufacture of complex, multi-layered materials. The techniques may be used to calculate variations of a process parameter within the material during the manufacturing process. A method comprises receiving segment data that partitions a manufacturing process into a set of segments having at least one layer of a material. For example, the segment data may partition the manufacturing processes along a path traversed by the material within the manufacturing process. The method further comprises receiving curvature data for the layers, and calculating values for a process parameter through the layers of the segments as a function of the curvature data. The method may comprise invoking a one-dimensional model, such as a one-dimensional finite difference model, to calculate the values for the defined segments and layers.

Abstract: In general, the invention is directed to a system of reusable software components that allow computational models to be seamlessly integrated into an executable software program, such as process management software within a manufacturing facility. The system includes a set of objects that encapsulate computational models and provide generic interfaces for invoking the models. A control module is embedded within the software program to invoke the computational models in parallel. The system may further include a model aggregator to receive input values from the control module and to distribute the input values to the objects for use during model execution. The system can be used to quickly and easily provide the results of one or more process models to line operators and process engineers during the manufacturing process, allowing the process engineer or line operator to more readily understand and adjust the process.