A method for orbit control of a satellite in orbit around the Earth and for desaturation of an angular momentum storage device of satellite is disclosed having two articulated arms each supporting a propulsion unit. The method includes determining a maneuver plan having at least two thrust maneuvers, a first thrust maneuver to be executed using the propulsion unit of one of the articulated arms and a second thrust maneuver to be executed using the propulsion unit of the other articulated arm, controlling the articulated arms and the propulsion units according to the maneuver plan, at least one of the first and second thrust maneuvers being a thrust maneuver referred to as discontinuous, composed of at least two separate consecutive thrust sub-maneuvers.

A vehicle includes a tilt rotor that is aft of a fixed wing and that is attached to the fixed wing via a pylon. A flight computer configured to instruct the tilt rotor to produce a maximum downward angle including by updating an actuator authority database associated with the flight computer to reflect the maximum downward angle, and generating a rotor control signal for the tilt rotor using the updated actuator authority database that reflects the maximum downward angle, wherein the maximum downward angle is adjustable.

A weather drone (100) comprising: a first sensor (101) configured to repeatedly measure one or more parameters indicative of weather; a memory (103) coupled to the first sensor (101) and configured to store data recorded by the first sensor (101), the data comprising a series of repeatedly measured parameters; and a processor (104) coupled to the first sensor (104) and the memory (103). The processor (104) is configured to analyse the data as it is being recorded by the first sensor (101), and determine if the data exceeds a first threshold value and/or falls below a second threshold value. If the processor (104) determines that the data exceeds the first threshold value and/or falls below the second threshold value on at least one occasion, the processor (104) is configured to prevent the storage of further data from the first sensor (101) in the memory (102).

A device and method for remotely controlling an unmanned aerial vehicle based on reinforcement learning are disclosed. An embodiment provides a device for remotely controlling an unmanned aerial vehicle based on reinforcement learning, where the device includes a processor and a memory connected to the processor, and the memory includes program instructions that can be executed by the processor to determine an inclination direction corresponding to the hand pose of a user, the movement direction of the hand, and the angle in the inclination direction based on sensing data associated with the pose of the hand or the movement of the hand acquired by way of at least one sensor, and determine one of a movement direction, a movement speed, a mode change, a figural trajectory, and a scale of the figural trajectory of the unmanned aerial vehicle according to the determined inclination direction, movement direction, and angle.

An exchange network comprising a plurality of exchange stations, in which each of the exchange stations comprises at least one drone operative to function as a flying crane, a temporary storage space, and at least one designated stopping area for on-road vehicles operative to carry cargo. Each of the exchange stations uses the respective local crane-drones to unload cargo from certain vehicles arriving at one of the respective local designated stopping areas, temporary store the cargo, and then load the cargo onboard certain other vehicles arriving at one of the respective local designated stopping areas, thereby exchanging carriers, and thus generating a transport route for the cargo which is the combination of different parts of transport routes of different carriers. The exchange network may use predetermined routes of many scheduled carriers to plan a routing scheme for the cargo, thereby propagating the cargo between exchange stations in a networked fashion.

Provided is a posture changing device for changing a posture of an aerosol container mounted on an unmanned aerial vehicle, the posture changing device including: a posture selecting unit for selecting a posture of the aerosol container from a plurality of candidate postures; and a posture changing unit for changing a posture of the aerosol container to the posture selected from the plurality of candidate postures. Also provided is a posture changing method for changing a posture of an aerosol container mounted on an unmanned aerial vehicle, the posture changing method including: selecting a posture of the aerosol container from a plurality of candidate postures; and changing a posture of the aerosol container to the posture selected from the plurality of candidate postures.

In a general aspect, a handheld controller device includes a housing and a trigger assembly. The housing is configured to be held in the hands of a user. The trigger assembly includes a pair of triggers extending outward from a side of the handheld controller device and configured to move along respective trigger paths. A coupling assembly is disposed inside the housing and connected to the pair of triggers. The coupling assembly is configured to transfer motion between the pair of triggers such that, when either of the triggers moves towards the housing along its respective trigger path, the coupling assembly moves the other trigger an equal distance away from the housing along its trigger path. Circuitry in the housing includes one or more sensors and a microcontroller configured to receive sensor signals and, in response, generate aircraft control data (e.g., for a flight simulation or remotely controlled flyable aircraft).

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 computer-implemented method of enabling optimisation of trajectory for a vehicle, the method comprising: determining a trajectory for the vehicle using: an algorithm; a vehicle model defining path constraints for the vehicle through space; a propulsion system model defining parameters of a propulsion system of the vehicle; an objective function defining one or more objectives; and controlling output of the determined trajectory.

A system for identifying an aspect of interest on a vehicle that includes a local AI system that can analyze sensor data from an on-site sensor to make an attempt to identify the aspect of interest according to first criterion. The aspect of interest can be information printed on the vehicle and/or on a seal of the vehicle. If the local AI system is unable to identify and validate the information on the first effort, it can consult with a central/global AI system that can leverage its own database and other local systems at other locations for subsequent attempts at identifying and validating the aspects of interest.