Training an encoder is provided. The method comprises inputting a current state of a number of aircraft into a recurrent layer of a neural network, wherein the current state comprises a reduced state in which a value of a specified parameter is missing. An action applied to the aircraft is input into the recurrent layer concurrently with the current state. The recurrent layer learns a value for the parameter missing from current state, and the output of the recurrent layer is input into a number of fully connected hidden layers. The hidden layers, according to the current state, learned value, and current action, determine a residual output that comprises an incremental difference in the state of the aircraft resulting from the current action.

An embodiment method for controlling operation of an aerial vehicle in an aerial vehicle control system includes approving entry of the aerial vehicle into an aerial vehicle operation zone from a take-off and landing facility of a departure location built into the aerial vehicle control system, controlling an operation of the aerial vehicle in the aerial vehicle operation zone, and approving exit of the aerial vehicle from the aerial vehicle operation zone into a take-off and landing facility of a destination location.

An aircraft and method of operating an aircraft include a flight formation control unit configured to automatically transition the aircraft into an automatic flight formation mode in response to the aircraft being within one or both of a predetermined speed or a predetermined range in relation to at least one other aircraft flying within the automatic flight formation mode. The flight formation control unit can be further configured to automatically transition the aircraft out of the automatic flight formation mode in response to detection of a control signal received from one or more flight controls of the aircraft. The flight formation control unit can be further configured to automatically cycle the aircraft and the at least one other aircraft to different positions during the automatic flight formation mode.

An assembly is configured for connection to an unmanned aerial vehicle (UAV) and comprises a plurality of emulator devices each configured for attachment to the UAV and a plurality of first connection tethers each configured to operably couple a respective one of the plurality of emulator devices to the UAV at a respective spacing from the UAV. The emulator devices each comprise an emulation component configured to provide, to a target detection system, a characteristic associated with a respective type of airborne object. The plurality of respective first connection tethers each comprises material that does not substantially reflect RF energy. During flight of the UAV, when the assembly is connected, each respective emulator device maintains the respective spacing from the UAV and emulates the characteristic to the target detection system, such that the assembly emulates, to the target detection system, a plurality of airborne objects.

The processor supplies flight commands to the flight control system by selectively blending pilot input with control signals from the autopilot. The processor generates a projected recovery trajectory through successive iterations, each beginning at the current aircraft location and using a recovery constraint selectable by the processor to influences a degree of flight aggressiveness. A detection system that identifies and invokes a state of threat existence if a threat exists along the projected recovery trajectory. The processor during threat existence in a first iteration commands an initial soft recovery, with permitted blended pilot input. If the threat exists on subsequent iteration, the processor commands a more aggressive recovery while attenuating blended pilot input.

A flight control apparatus includes a detection unit that detects within a predetermined range of an air vehicle another air vehicle. A specifying unit specifies a type of the detected other air vehicle. A determining unit determines a possibility that the air vehicle and the other air vehicle will collide, based on an attribute relating to movement of the other air vehicle. When it is determined that a possibility of collision exists, a flight control unit controls the flight of the air vehicle according to the specified type of the other air vehicle to avoid collision with the other air vehicle.

A method and a system for establishing a route of an unmanned aerial vehicle are provided. The method includes identifying an object from surface scanning data and shaping a space, which facilitates autonomous flight, as a layer, collecting surface image data for a flight path from the shaped layer, and analyzing a change in image resolution according to a distance from the object through the collected surface image data and extracting an altitude value on a flight route.

Provided are a method and device for setting a flight path reflecting an air space of a drone. The method may include receiving flight data collected by the drone; calculating a path error score indicating an extent of deviation of the drone from a planned flight path by comparing the received flight data with the planned flight path of the drone; adjusting the preset air space of the drone based on the path error score; and generating a new flight path of the drone based on the adjusted air space of the drone and a destination.

This application provides an uncrewed aerial vehicle control method, an apparatus, and a system. An uncrewed aerial vehicle or a network device identifies a risk of a flight path, to manage the flight path of the uncrewed aerial vehicle, thereby ensuring flight safety of the uncrewed aerial vehicle.

An electric aircraft comprises a single passenger seat, vertical takeoff and landing capable rotorcraft with an amphibious undercarriage for ground or water landing and takeoff. An electrical power system includes an independent battery for each motor with quick-swap mechanism to enable drained batteries to be easily removed for external charging and swapped for a charged replacement battery. A ballistic recovery system may be deployed to safely land the aircraft in the event of an emergency and may be manually deployed in response to the passenger activating a deployment mechanism integrated into handles within the cockpit. An on-board flight control system includes an automated flight controller that places constraints on flight maneuvers, and a manual flight controller provides a passenger with a limited level of control over the flight.