Abstract: Solutions are provided for auto-labeling sensor data for machine learning (ML). An example includes: determining a platform's own position; recording, from a sensor aboard the platform, sensor data comprising a sensor image; receiving position data for at least one intruder object (e.g., a nearby airborne object); based at least on the position data for the intruder object and the platform's position, determining a relative position and a relative velocity of the intruder object; based at least on the relative position and a relative velocity of the intruder object and a field of view of the sensor, determining an expected position of the intruder object in the sensor image; labeling the sensor image, wherein the labeling comprises annotating the sensor image with a region of interest and an object identification; and training an artificial intelligence (AI) model using the labeled sensor image.

Abstract: In an example, a method is described. The method includes causing one or more sensors arranged on an aircraft to acquire, over a window of time, first data associated with a first object that is within an environment of the aircraft, where the one or more sensors include one or more of a light detection and ranging (LIDAR) sensor, a radar sensor, or a camera, causing an array of microphones arranged on the aircraft to acquire, over approximately the same window of time as the first data is acquired, first acoustic data associated with the first object, and training a machine learning model by using the first acoustic data as an input value to the machine learning model and by using an azimuth, a range, an elevation, and a type of the first object identified from the first data as ground truth output labels for the machine learning model.

Abstract: In an example, a method is described. The method includes causing one or more sensors arranged on an aircraft to acquire, over a window of time, first data associated with a first object that is within an environment of the aircraft, where the one or more sensors include one or more of a light detection and ranging (LIDAR) sensor, a radar sensor, or a camera, causing an array of microphones arranged on the aircraft to acquire, over approximately the same window of time as the first data is acquired, first acoustic data associated with the first object, and training a machine learning model by using the first acoustic data as an input value to the machine learning model and by using an azimuth, a range, an elevation, and a type of the first object identified from the first data as ground truth output labels for the machine learning model.

Abstract: A fuel cell-based power system comprises a fuel cell configured for continuously receiving a first reactant and a second reactant to produce chemical reactions that generate electrical power, water, and heat, a coolant subsystem configured for circulating a primary coolant in association with the fuel cell, thereby absorbing the generated heat, a tank configured for storing a reactant, and a reactant distribution subsystem configured for conveying the reactant from the tank to an independent system, the fuel cell as the first reactant, and the coolant subsystem as a secondary coolant to remove the absorbed heat from the primary coolant and/or a water accumulator. The secondary coolant may be conveyed to a gas thruster as a gas after the absorbed heat has been removed from the secondary coolant. The reactant may boil off of a cryogenic liquid or vapor or gas transformed from a cryogenic liquid via a heater.

Abstract: Solutions are provided for auto-labeling sensor data for machine learning (ML). An example includes: determining a platform's own position; recording, from a sensor aboard the platform, sensor data comprising a sensor image; receiving position data for at least one intruder object (e.g., a nearby airborne object); based at least on the position data for the intruder object and the platform's position, determining a relative position and a relative velocity of the intruder object; based at least on the relative position and a relative velocity of the intruder object and a field of view of the sensor, determining an expected position of the intruder object in the sensor image; labeling the sensor image, wherein the labeling comprises annotating the sensor image with a region of interest and an object identification; and training an artificial intelligence (AI) model using the labeled sensor image.

Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data can be generated for each distinct image. This and other methods can be used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.

Abstract: A computer-implemented method for generating a training image set includes retrieving, from at least one memory device, model data corresponding to a three-dimensional (3-D) model of a target object, and creating a plurality of two-dimensional (2-D) synthetic images from the model data. The 2-D synthetic images include a plurality of views of the 3-D model. The method also includes creating a plurality of semantic segmentation images by identifying a plurality of pixels that define the target object in the 2-D synthetic image, and assigning a semantic segmentation label to the identified pixels of the target object. The method further includes generating linking data associating each of the semantic segmentation labels with a corresponding one of the 2-D synthetic images, and storing the training image set including the 2-D synthetic images, the semantic segmentation labels, and the linking data.

Abstract: Example implementations relate to autonomous airport runway navigation. An example system includes a first sensor and a second sensor coupled to an aircraft at a first location and a second location, respectively, and a computing system configured to receive sensor data from one or both of the first sensor and the second sensor to detect airport markings positioned proximate a runway. The computing system is further configured to identify a centerline of the runway based on the airport markings and receive sensor data from both of the first sensor and the second sensor to determine a lateral displacement that represents a distance between a reference point of the aircraft and the centerline of the runway. The computing system is further configured to control instructions that indicate adjustments for aligning the reference point of the aircraft with the centerline of the runway during subsequent navigation of the aircraft.

Abstract: In an example, a method is described. The method includes causing one or more sensors arranged on an aircraft to acquire, over a window of time, first data associated with a first object that is within an environment of the aircraft, where the one or more sensors include one or more of a light detection and ranging (LIDAR) sensor, a radar sensor, or a camera, causing an array of microphones arranged on the aircraft to acquire, over approximately the same window of time as the first data is acquired, first acoustic data associated with the first object, and training a machine learning model by using the first acoustic data as an input value to the machine learning model and by using an azimuth, a range, an elevation, and a type of the first object identified from the first data as ground truth output labels for the machine learning model.

Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.

Abstract: Systems, methods, and computer-readable media storing instructions for determining cross-track error of an aircraft on a taxiway are disclosed herein. The disclosed techniques capture electronic images of a portion of the taxiway using cameras or other electronic imaging devices mounted on the aircraft, pre-process the electronic images to generate regularized image data, apply a trained multichannel neural network model to the regularized image data to generate a preliminary estimate of cross-track error relative to the centerline of the taxiway, and post-process the preliminary estimate to generate an estimate of cross-track error of the aircraft. Further embodiments adjust a GPS-based location estimate of the aircraft using the estimate of cross-track error or adjust the heading of the aircraft based upon the estimate of cross-track error.

Abstract: A fuel cell-based power system comprises a fuel cell configured for continuously receiving a first reactant and a second reactant to produce chemical reactions that generate electrical power, water, and heat, a coolant subsystem configured for circulating a primary coolant in association with the fuel cell, thereby absorbing the generated heat, a tank configured for storing a reactant, and a reactant distribution subsystem configured for conveying the reactant from the tank to an independent system, the fuel cell as the first reactant, and the coolant subsystem as a secondary coolant to remove the absorbed heat from the primary coolant and/or a water accumulator. The secondary coolant may be conveyed to a gas thruster as a gas after the absorbed heat has been removed from the secondary coolant. The reactant may be boil off of a cryogenic liquid or vapor or gas transformed from a cryogenic liquid via a heater.

Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.

Abstract: A fuel cell-based power system comprises a fuel cell configured for continuously receiving a first reactant and a second reactant to produce chemical reactions that generate electrical power, water, and heat, a coolant subsystem configured for circulating a primary coolant in association with the fuel cell, thereby absorbing the generated heat, a tank configured for storing a reactant, and a reactant distribution subsystem configured for conveying the reactant from the tank to an independent system, the fuel cell as the first reactant, and the coolant subsystem as a secondary coolant to remove the absorbed heat from the primary coolant and/or a water accumulator. The secondary coolant may be conveyed to a gas thruster as a gas after the absorbed heat has been removed from the secondary coolant. The reactant may boil off of a cryogenic liquid or vapor or gas transformed from a cryogenic liquid via a heater.

Abstract: Example implementations relate to autonomous airport runway navigation. An example system includes a first sensor and a second sensor coupled to an aircraft at a first location and a second location, respectively, and a computing system configured to receive sensor data from one or both of the first sensor and the second sensor to detect airport markings positioned proximate a runway. The computing system is further configured to identify a centerline of the runway based on the airport markings and receive sensor data from both of the first sensor and the second sensor to determine a lateral displacement that represents a distance between a reference point of the aircraft and the centerline of the runway. The computing system is further configured to control instructions that indicate adjustments for aligning the reference point of the aircraft with the centerline of the runway during subsequent navigation of the aircraft.

Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.

Abstract: A level sensor assembly includes a fiber that is configured to be at least partially disposed in a tank and to be coupled to a light source and to a light detector. The fiber includes a plurality of sensing regions spaced apart along a length of the fiber. Each sensing region of the plurality of sensing regions includes a Bragg grating configured to generate a reflection spectrum responsive to incident light and a strain layer around the Bragg grating. Each strain layer is configured to induce a strain on the fiber at a respective Bragg grating based on a temperature of the strain layer such that shifts in the reflection spectra of the Bragg gratings indicate which of the sensing regions are submerged in a liquid.

Abstract: A level sensor assembly includes a fiber that is configured to be at least partially disposed in a tank and to be coupled to a light source and to a light detector. The fiber includes a plurality of sensing regions spaced apart along a length of the fiber. Each sensing region of the plurality of sensing regions includes a Bragg grating configured to generate a reflection spectrum responsive to incident light and a strain layer around the Bragg grating. Each strain layer is configured to induce a strain on the fiber at a respective Bragg grating based on a temperature of the strain layer such that shifts in the reflection spectra of the Bragg gratings indicate which of the sensing regions are submerged in a liquid.

Abstract: A fuel cell-based power system comprises a fuel cell configured for continuously receiving a first reactant and a second reactant to produce chemical reactions that generate electrical power, water, and heat, a coolant subsystem configured for circulating a primary coolant in association with the fuel cell, thereby absorbing the generated heat, a tank configured for storing a reactant, and a reactant distribution subsystem configured for conveying the reactant from the tank to an independent system, the fuel cell as the first reactant, and the coolant subsystem as a secondary coolant to remove the absorbed heat from the primary coolant and/or a water accumulator. The secondary coolant may be conveyed to a gas thruster as a gas after the absorbed heat has been removed from the secondary coolant. The reactant may be boil off of a cryogenic liquid or vapor or gas transformed from a cryogenic liquid via a heater.