Abstract: Systems and methods for machine-learning-based aircraft icing prediction use supervised and unsupervised learning to process real-time environmental data, such as onboard measurements of outside air temperature and dew point, to predict a risk of icing and determine whether to issue an icing risk alert to an onboard crewmember or a remote operator, and/or to recommend an icing avoidance maneuver. The systems and methods can use reinforcement learning to generate a confidence metric in the predicted risk of icing, to determine a time or distance to predicting icing, and/or to not issue an alert or recommend a maneuver in consideration of historical data in a “library of learning” and/or other flight data such as airspeed, altitude, time of year, and weather conditions. The predictive systems and methods are low-cost and low-power, do not require onboard weather radar, and can be effective for use in smaller aircraft that are completely icing-intolerant.

Abstract: A robot intelligence engine receives highly immersive virtual environment (HIVE) data characterizing a set of robot tasks executed by a test robot in a HIVE, wherein the robot tasks of the set of robot tasks include a robot skill. The robot intelligence engine receives sensor data from a problem detecting robot deployed in an environment of operation that characterizes conditions corresponding to a detected problem and searches the set of robot tasks to identify a subset of the robot tasks that are potentially employable to remedy the detected problem. The robot intelligence engine simulates the subset of robot tasks to determine a likelihood of success for the subset of robot tasks. The simulation generates a set of unsupervised robot tasks that are potentially employable to remedy the detected problem. The robot intelligence engine selects one of the subset of robot tasks or one of the unsupervised robot tasks.

Abstract: In some examples, systems and methods are described for output biasing maneuvers recommendations provided by at least one machine learning maneuver-recommendation (MLM) engine executing on an aerial vehicle. In some examples, output biasing data can be received that includes at least one risk tuning parameter that can influence which of the maneuver recommendations are selected by a maneuver decision engine executing on the aerial vehicle based on a maneuver confidence threshold for implementation by the aerial vehicle. The maneuver confidence threshold can be updated based on the at least one risk tuning parameter to provide an updated maneuver confidence threshold for the output biasing of the maneuvers recommendation provided by the at least one MLM engine. Vehicle command data for implementing a given maneuver recommendation can be outputted based on an evaluation of the updated maneuver confidence threshold.

Abstract: A code development engine can be programmed to evaluate build code that can be representative of program code at an instance of time during or after a software development of the program code to identify and correct coding errors in the build code. A code run-time simulation engine can be programmed to simulate the build code in a modeled program code environment for the program code to identify and correct coding failures in the build code. A build code output module can be programmed to evaluate the build code to determine whether the build code is acceptable for use in a program code environment based on a level of acceptable risk for the build code in response to the coding error and/or coding failure being corrected in the build code.

Abstract: In some examples, design parameter data for an object can be received based on user input. A set of design criteria for the object can be received based on the design parameter data. A search of a learned design virtual reality (VR) database can be implemented to identify a set of candidate designs for the object based on the set of design criteria. The learned design VR database can include a plurality of previously determined designs for the object. Each candidate design for the object can be simulated in a simulation environment based on a learned design simulation database and optimization criteria to identify at least one new design for the object. A ranked design list can be generated ranking each candidate design and the at least one new design for the object based on ranking criteria.

Abstract: A machine learning maneuver model can be programmed to generate maneuver data identifying a plurality of flight paths for maneuvering an aerial vehicle through an adverse weather condition and a flight path confidence score for each flight path of the plurality of flight paths based on at least weather sensor data characterizing the adverse weather condition. The flight path confidence score can be indicative of a probability of successfully maneuvering the aerial vehicle through the adverse weather condition according to a respective flight path. A maneuver decision engine can be programmed to evaluate each flight path confidence score for each flight path relative to a flight path confidence threshold to identify a given flight path of the plurality of flight paths through the adverse weather condition that poses a least amount of structural risk to the aerial vehicle.

Abstract: A code development engine can be programmed to evaluate build code that can be representative of program code at an instance of time during or after a software development of the program code to identify and correct coding errors in the build code. A code run-time simulation engine can be programmed to simulate the build code in a modeled program code environment for the program code to identify and correct coding failures in the build code. A build code output module can be programmed to evaluate the build code to determine whether the build code is acceptable for use in a program code environment based on a level of acceptable risk for the build code in response to the coding error and/or coding failure being corrected in the build code.

Abstract: One example includes a system control architecture that includes local control systems to provide respective condition signals associated with situational awareness conditions of an associated system architecture. A central system controller receives the condition signals, generates a control scheme for control of operational aspects of the associated system architecture based on the condition signals, and generates control signals based on the control scheme. The control scheme defines contributions of each of the local control systems to a control authority of each of the operational aspects. Operational components provide mechanical control of each of the operational aspects of the associated system architecture in response to the respective control signals to implement the control scheme.

Abstract: A machine learning maneuver model can be programmed to generate maneuver data identifying a plurality of flight paths for maneuvering an aerial vehicle through an adverse weather condition and a flight path confidence score for each flight path of the plurality of flight paths based on at least weather sensor data characterizing the adverse weather condition. The flight path confidence score can be indicative of a probability of successfully maneuvering the aerial vehicle through the adverse weather condition according to a respective flight path. A maneuver decision engine can be programmed to evaluate each flight path confidence score for each flight path relative to a flight path confidence threshold to identify a given flight path of the plurality of flight paths through the adverse weather condition that poses a least amount of structural risk to the aerial vehicle.

Abstract: In some examples, systems and methods are described for output biasing maneuvers recommendations provided by at least one machine learning maneuver-recommendation (MLM) engine executing on an aerial vehicle. In some examples, output biasing data can be received that includes at least one risk tuning parameter that can influence which of the maneuver recommendations are selected by a maneuver decision engine executing on the aerial vehicle based on a maneuver confidence threshold for implementation by the aerial vehicle. The maneuver confidence threshold can be updated based on the at least one risk tuning parameter to provide an updated maneuver confidence threshold for the output biasing of the maneuvers recommendation provided by the at least one MLM engine. Vehicle command data for implementing a given maneuver recommendation can be outputted based on an evaluation of the updated maneuver confidence threshold.

Abstract: Systems and methods for machine-learning-based aircraft icing prediction use supervised and unsupervised learning to process real-time environmental data, such as onboard measurements of outside air temperature and dew point, to predict a risk of icing and determine whether to issue an icing risk alert to an onboard crewmember or a remote operator, and/or to recommend an icing avoidance maneuver. The systems and methods can use reinforcement learning to generate a confidence metric in the predicted risk of icing, to determine a time or distance to predicting icing, and/or to not issue an alert or recommend a maneuver in consideration of historical data in a “library of learning” and/or other flight data such as airspeed, altitude, time of year, and weather conditions. The predictive systems and methods are low-cost and low-power, do not require onboard weather radar, and can be effective for use in smaller aircraft that are completely icing-intolerant.

Abstract: One example includes a system control architecture that includes local control systems to provide respective condition signals associated with situational awareness conditions of an associated system architecture. A central system controller receives the condition signals, generates a control scheme for control of operational aspects of the associated system architecture based on the condition signals, and generates control signals based on the control scheme. The control scheme defines contributions of each of the local control systems to a control authority of each of the operational aspects. Operational components provide mechanical control of each of the operational aspects of the associated system architecture in response to the respective control signals to implement the control scheme.

Abstract: An aerial vehicle maneuvers in compliance with applicable aviation regulations by formulating a request to air traffic control (ATC) for permission to perform a proposed maneuver, overlaying, as a sub-modulated secondary signal, data characterizing the request on top of a primary ADS-B signal such that the primary ADS-B signal is not interfered with, and transmitting an ADS-B message comprising the primary and secondary signals. Permission can likewise be transmitted and received from ATC using ADS-B overlay communication. The aerial vehicle can conduct emergency maneuvers in the absence of permission and update ATC as to flight path deviations taken using ADS-B overlay communication, without the need for a voice radio and by using existing ADS-B digital communications.

Abstract: A method for controlling a remote controlled locomotive that is part of a train to insure effective braking, the method including calculating an estimated total energy of a train, calculating a threshold representing a predetermined braking capability limit of the locomotive, determining whether the estimated total energy is at least one of approaching and exceeding the threshold, and decreasing a velocity of the train until the threshold is at least one of no longer being approached and is no longer exceeded.

Abstract: A system to determine a location of rolling stock, the system including a transmitting device proximate a surface on which a rolling stock rides upon, a signal comprising at least one of location data and unique identification data of the transmitting device that is emitted from the transmitting device only when the rolling stock is proximate the transmitting device, and a receiving device that receives the signal.