A computer-implemented method includes: receiving, by a computing device, input data for identifying one or more landing site candidates for an aerial vehicle. The input data includes a set of criteria, terrain information, and obstacle information. The method further includes identifying, by the computing device, the one or more landing site candidates based on the input data and the criteria; providing, by the computing device, information regarding the identified one or more landing site candidates.

To bring an aircraft in flight to a runway, an automatic trajectory generation system obtains a procedure, called STARI procedure, which provides a final trajectory flyable by the aircraft to land on the runway, such that from the entry point of the final trajectory or from any point above it, a holding loop pattern of a predefined shape is flyable in order to dissipate energy if necessary. The automatic trajectory generation system then computes a lateral trajectory, avoiding any terrain relief, meteorological obstacles and military zones, between the current position of the aircraft and the entry point or a point above it, based on performance adapted to an operational state of the aircraft. An overall trajectory is thus obtained, by linking the computed lateral trajectory and the final trajectory of the STARI procedure, including iterations of the holding loop pattern if necessary.

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.

A highly safe drone is provided. A remote controller and a drone are connected to each other through a network and cooperate to operate. The drone includes a flight control unit, a flight start command reception unit receiving a flight start command from a user, a drone determination unit determining a configuration of the drone itself, an external environment determination unit determining an external environment of the drone. The drone system has a plurality of states including a takeoff diagnosis state and satisfies a condition transitioning to another state. The takeoff diagnosis state includes a drone determination state where the drone determination unit determines the configuration of the drone itself and an external environment determination state where the external environment determination unit determines the external environment. The drone system makes the drone to takeoff after transitioning to the takeoff diagnosis state upon receiving the flight start command.

An automatic trajectory generation method for an aircraft in flight to exit a meteorological alert situation which: obtains polygons representative of meteorological obstacles; defines two circles centered to the right and to the left with respect to a current in-flight position, of a minimum radius in accordance with the operational state of the aircraft; identifies, for each polygon, candidate external sides for the aircraft to exit; defines straight lines perpendicular to the candidate external sides and tangent to one or both of the circles; determines, for each straight line, a candidate safety position, which is located at a margin distance outside any polygon; forms candidate exit trajectories between the current in-flight position and each candidate safety position; and selects the candidate trajectory which minimizes a time of exposure of the aircraft to any meteorological obstacle. Also a system and an aircraft with such a system.

Disclosed are methods, systems, and non-transitory computer-readable media for detecting wind shear conditions in an urban airspace. For instance, the method may include obtaining aircraft information related to an aircraft in the urban airspace, accessing three-dimensional building information corresponding to the airspace, obtaining wind speed and direction data from a plurality of sensors provided about the airspace, and detecting wind shear conditions in at least a portion of the airspace based on the obtained wind speed and direction data. The method may further include determining real-time flight safety parameters in the portion of the airspace based on the wind shear conditions detected in at least the portion of the airspace, analyzing the determined real-time flight safety parameters along a designated flight path through the portion of the airspace to determine whether an unsafe flight condition exists, and transmitting the analysis to the aircraft or a remote operating station.

The preferred embodiments relate to a method for controlling a flight movement of an aerial vehicle for landing the aerial vehicle, including: recording of first image data by means of a first camera device, which is provided on an aerial vehicle, and is configured to record an area of ground, wherein the first image data is indicative of a first sequence of first camera images. The method also includes recording of second image data by means of a second camera device, which is provided on the aerial vehicle, and is configured to record the area of ground, wherein the second image data is indicative of a second sequence of second camera images.

Disclosed are methods, systems, and non-transitory computer-readable medium for managing energy use in a vehicle. For instance, the method may include receiving forecasted data from a first external source, receiving real-time data corresponding to at least one weather parameter at a first location at a first time, and continuously determining whether to perform an adjustment to a control parameter of the vehicle by using a machine learning model that is based on the forecasted data for the at least one weather parameter, the real-time data for the at least one weather parameter, a battery condition of the vehicle, and/or an estimated amount of energy consumed by traveling along a first navigation path.

A UAV (unmanned aerial vehicle) including a first barometer and a processing unit is provided. The first barometer provides a first air pressure value. The processing unit is coupled to the first barometer for receiving the first air pressure value from the first barometer, performing timing-synchronization on the first air pressure value provided by the first barometer and an external reference air pressure value provided by an external reference barometer to obtain a timing-synchronized first air pressure value and recalculating the timing-synchronized first air pressure value to generate a compensated air pressure value, wherein the processing unit performs data fusion calculation on the first air pressure value, the compensated air pressure value and a sensor data to obtain a target fused data and real-timely controls the altitude and the posture of the UAV according to the target fused data.

An intelligence, surveillance, and reconnaissance system is disclosed including a ground station and one or more aerial vehicles. The aerial vehicles are autonomous systems capable of communicating intelligence data to the ground station and be used as part of a missile delivery package. A plurality of aerial vehicles can be configured to cast a wide net of reconnaissance over a large area on the ground including smaller overlapping reconnaissance areas provided by each of the plurality of the aerial vehicles.