A dual agent reinforcement learning autonomous system (DARLAS) for the autonomous operation of aircraft and/or provide pilot assistance. DARLAS includes an artificial neural network, safe agent, and cost agent. The safe agent is configured to calculate safe reward Q values associated with landing the aircraft at a predetermined destination or calculated emergency destination. The cost agent is configured to calculate cost reward Q values associated with maximum fuel efficiency and aircraft performance. The safe and cost reward Q values are based on state-action vectors associated with an aircraft, which may include state data and action data. The system may include a user output device that provides an indication of an action to a user. The action corresponds to an agent action having the highest safe reward Q value and the highest cost require Q value. DARLAS prioritizes the highest safe reward Q value in the event of conflict.

A process and machine configured to predict and preempt an undesired load and/or bending moment on a part of a vehicle resulting from an exogenous or a control input. The machine may include a predictor with an algorithm for converting parameters from a state sensed upwind from the part into an estimated normal load on the part and a prediction, for a future time, of a normal load scaled for a weight of the aerospace vehicle. The machine may: produce, using a state upwind from the part on the aerospace vehicle and/or a maneuver input, a predicted state, load and bending moment on the part at a time in the future; derive a command preempting the part from experiencing the predicted load and bending moment; and actuate the command just prior to the part experiencing the predicted state, thereby alleviating the part from experiencing the predicted load and bending moment.

A process and machine configured to predict and preempt an undesired load and/or bending moment on a part of a vehicle resulting from an exogenous or a control input. The machine may include a predictor with an algorithm for converting parameters from a state sensed upwind from the part into an estimated normal load on the part and a prediction, for a future time, of a normal load scaled for a weight of the aerospace vehicle. The machine may: produce, using a state upwind from the part on the aerospace vehicle and/or a maneuver input, a predicted state, load and bending moment on the part at a time in the future; derive a command preempting the part from experiencing the predicted load and bending moment; and actuate the command just prior to the part experiencing the predicted state, thereby alleviating the part from experiencing the predicted load and bending moment.

A flight controller of a drone calculates a target attitude of the drone on a port based on the result of acquisition by an anemometer. The flight controller of the drone controls each of a plurality of rotors independently, and controls each of the rotors so as to make the drone on the port take a target attitude.

A flight controller of a drone calculates a target attitude of the drone on a port based on the result of acquisition by an anemometer. The flight controller of the drone controls each of a plurality of rotors independently, and controls each of the rotors so as to make the drone on the port take a target attitude.

An aircraft, an aircraft control method, and a computer readable storage medium. An aircraft including: a gyroscope used for measuring the angular velocity of the yaw angle of the aircraft; a processor used for determining a yaw control signal of the aircraft on the basis of the angular velocity of the yaw angle without considering the acceleration of the aircraft; and an execution mechanism used for adjusting the flight of the aircraft on the basis of the yaw control signal.

A process and machine configured to predict and preempt an undesired load and/or bending moment on a part of a vehicle resulting from an exogenous or a control input. The machine may include a predictor with an algorithm for converting parameters from a state sensed upwind from the part into an estimated normal load on the part and a prediction, for a future time, of a normal load scaled for a weight of the aerospace vehicle. The machine may: produce, using a state upwind from the part on the aerospace vehicle and/or a maneuver input, a predicted state, load and bending moment on the part at a time in the future; derive a command preempting the part from experiencing the predicted load and bending moment; and actuate the command just prior to the part experiencing the predicted state, thereby alleviating the part from experiencing the predicted load and bending moment.

Using a set of airflow sensors disposed on an airfoil of an aircraft, first airflow data including an amount of airflow experienced at each airflow sensor at a first time is measured. Using a trained neural network model, the first airflow data is analyzed to determine an airflow state of the aircraft. In response to determining that the aircraft is in the abnormal airflow state, a control surface and a power unit of the aircraft are adjusted. Responsive to the adjusting, the aircraft is returned to the normal airflow state.

A process and machine configured to predict and preempt an undesired load and/or bending moment on a part of a vehicle resulting from an exogenous or a control input. The machine may include a predictor with an algorithm for converting parameters from a state sensed upwind from the part into an estimated normal load on the part and a prediction, for a future time, of a normal load scaled for a weight of the aerospace vehicle. The machine may: produce, using a state upwind from the part on the aerospace vehicle and/or a maneuver input, a predicted state, load and bending moment on the part at a time in the future; derive a command preempting the part from experiencing the predicted load and bending moment; and actuate the command just prior to the part experiencing the predicted state, thereby alleviating the part from experiencing the predicted load and bending moment.

A process and machine configured to predict and preempt an aerodynamic disturbance. The machine may include a BDE (Bhan-Donahue-Endres) adaptor configured to that comprises a specially programmed processor that has an adaptive learning control and rules to: modify a control augmentation system on an aerospace vehicle, to preclude an undesired state of the aerospace vehicle unaccounted for by control laws in current control augmentation systems; form a prediction for an airspeed of the aerospace vehicle that replaces an airspeed input from a sensor of the aerospace vehicle, in a phase of operation prone to instrumentation error, into the control augmentation system; generate an estimate, based upon the prediction, of an anticipated disturbance to a desired state of the aerospace vehicle; and generate, based upon the estimate, a command to a control element of the aerospace vehicle that preempts the undesired state of the aerospace vehicle.