There is disclosed in one example an apparatus, including: a hardware platform including a processor and a memory; and instructions encoded within the memory to instruct the processor to: receive stored performance data for an aircraft battery, the stored performance data including data that correlate power density to temperature and remaining charge; simulate a planned flight for an aircraft, including predicting a plurality of temperature and remaining charge values; and direct operation of a heat exchange apparatus to precondition the battery to a selected temperature before the planned flight.

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 system for initiating a command of an electric vertical take-off and landing (eVTOL) aircraft includes a flight controller configured to receive a topographical datum, identify an air position as a function of a sensor and the topographical datum, wherein identifying further comprises obtaining a sensor datum as a function of the sensor, and identifying the air position as a function of the sensor datum and the topographical datum using a similarity function, determine a command as a function of the air position, and initiate the command.

A system and method for autonomous flight control with mode selection an electric aircraft is illustrated. The system comprises an altitude-related sensor and a computing device. The altitude-related sensor is coupled to the electric aircraft and is configured to detect an altitude value. The computing device is communicatively connected to the altitude-related sensor and is configured to receive the altitude value from the altitude-related sensor, to determine a flight mode as a function of the altitude value and an altitude threshold, to determine an aircraft adjustment as a function of a determine flight mode, and to generate an autonomous function configured to enact the determined flight mode and an aircraft adjustment automatically.

Systems and methods for operating drones in proximity to objects are disclosed herein. An example method includes determining a change in drone, flight status that involves a rotor of the drone being active, determining presence of a mobile device within a designated clearance area established around the drone, preventing the drone from landing, providing a warning message to a user of the mobile device to clear away from the designated clearance area, detecting that the mobile device and the user are not within the designated clearance area, and causing the drone to land.

A central management server includes a determination module determining a landable local delivery hub among a plurality of local delivery hubs located within a preset radius centered around a destination, when a location information request for the landable local delivery hub is received from an unmanned cargo aircraft; and a control module configured to transmit a landing command including the location information of the determined landable local delivery hub to the unmanned cargo aircraft, and transmit a task execution command to cause the unmanned cargo aircraft to deliver goods to the destination. The determination module determines the landable local delivery hub, based on a combination of an expected landing standby period of the unmanned cargo aircraft, an expected battery consumption amount of the unmanned cargo aircraft, an expected delivery period of the unmanned delivery robot, and an expected battery consumption amount of the unmanned delivery robot.

A computer-implemented method for controlling an unmanned aerial vehicle (UAV) includes identifying a set of target markers based on a plurality of images captured by an imaging device carried by the UAV. The set of target markers includes at least two or more types of target markers that are in close proximity to be detected within a same field of view of the imaging device. The method further includes determining a spatial relationship between the UAV and the set of target markers based at least in part on the plurality of images, and controlling the UAV to approach the set of target markers based at least in part on the spatial relationship while controlling the imaging device to track the set of target markers such that the set of target markers remains within the same field of view of the imaging device.

A ground marker for use in identifying a location associated with a mission performed by an aerial vehicle includes a visible surface with aspects that are positioned at different vertical heights or elevations. The vertical variation in the aspects of the visible surface enhances a level of visibility of the ground marker within images captured by cameras provided aboard the aerial vehicle, resulting in more accurate estimations of ranges to such markers (e.g., altitudes) determined from such images. The visible surface includes one-dimensional or two-dimensional bar codes, alphanumeric characters and symbols thereon and is provided on or within rigid or flexible frames that are adapted to be placed on ground surfaces at the location associated with the mission.

Light emitting device positional tracking systems and methods are provided. In one example, a method includes receiving images captured of a target location comprising a plurality of light emitting devices, where each of the light emitting devices has an associated blinking pattern. The method may further include detecting the blinking pattern for each of the light emitting devices in the images. The method may further include determining a classification for each of the light emitting devices based on its detected blinking pattern. The method may further include aligning a mobile platform with the target location based on the classifications of the light emitting devices. Related devices and systems are also provided.

An aircraft includes first units each including a first sensor, a rotary wing, a driver, and a first drive controller. The first drive controller is configured to generate a drive signal of the rotary wing on the basis of a flying route of the aircraft and a control law based on a flying state detected by the first sensor, and output the drive signal to the driver configured to drive the rotary wing. The control laws of the respective first drive controllers are equal to each other between the first units. The first drive controllers are each configured to generate the drive signals that correspond to all of the first units. The drivers are each configured to drive the corresponding rotary wing on the basis of corresponding one of the drive signals that correspond to all of the first units and that are generated by the first drive controllers.