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: 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 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 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.