A method is provided for detecting and avoiding conflict along a current route of a robot. The method includes accessing or determining trajectories of the robot and a nearby moving object forward in time from their respective current positions, and detecting a conflict from a comparison of the trajectories. The method includes selecting a maneuver to avoid the conflict, and outputting an indication of the maneuver for use in at least one of guidance, navigation or control of the robot to avoid the conflict. Selection of the maneuver includes determining a plurality of angles that describe the conflict such as those at which the robot and moving object observe one another, and/or an angle between their trajectories, and evaluating the plurality of angles to select the maneuver.

The application relates to a target acquisition system (100) for an unmanned aircraft (106) according to an embodiment. The system comprises goggles (110) and the unmanned aircraft. The unmanned aircraft equipped with a camera (124) and a measuring unit (230) is configured to transmit location data (DS, KA, DE) related to a location (MS) of a target (102) to the goggles. The goggles are configured to form an augmented reality user interface (LK) by means of at least one goggle lens (212) for controlling the unmanned aircraft. The goggles equipped with an orientation detector (213) are configured to present to a wearer (108) of the goggles the location of the target as an augmented reality target object (MB) in the user interface based on the received target location data and an orientation (SA) of the goggles as detected by the orientation detector.

The present invention relates to a self-propelled vehicle (100) comprising:a light emitting device for emitting light pulses out of the self-propelled vehicle (100); and-an imaging device (1) for capturing an image of a region located out of the self-propelled vehicle (100), the imaging device (1) comprising a shutter; whereinthe light emitting device is coordinated with the shutter of the imaging device (1), such that an image (50) is captured by the imaging device (1) during at least part of the duration of a light pulse; wherein:the light emitting device is configured to emit light pulses wherein each light pulse has a duration of less than 5000 ?s. The invention also relates to a method of capturing images (50) from a self-propelled vehicle (100).

A method for controlling a UAV includes: receiving a takeoff control command, where the takeoff control command is used to control the UAV to take off; in response to the takeoff control command, when the UAV is not equipped with the safety protection device, prohibiting the UAV from taking off, and/or when the UAV is equipped with the safety protection device, controlling the UAV to take off. This method enhances the safety and usability of the UAV.

The present invention provides a method for decelerating and redirecting an airborne platform, comprising the steps of retaining a flexible airfoil in non-deployed form in controllably releasable secured relation with each corresponding rotor arm of a multi-rotor drone; and upon detecting rate of descent of said drone in a first direction to be greater than a predetermined value, triggering release of one or more of said retained airfoils from said corresponding rotor arm and causing each of said released airfoils to be circumferentially displaced from a first rotor arm to a second rotor arm of said drone to occlude an adjacent inter-arm region, wherein each of said circumferentially displaced airfoils generates a sufficient value of localized lift that causes said descending drone to change its direction of descent from said first direction to a second direction.

The invention relates to a computer-implemented surveillance method for surveilling an area of interest using a set of drones, the surveillance method including monitoring a number of operational drones among the set of drones. If a change in the number of operational drones is detected, performing a segmentation step for segmenting the area of interest into N sub-areas, N being the current number of operational drones; and performing an affectation step for affecting each operational drone to a respective sub-area for surveilling said sub-area.

A method for flight control of an aircraft with multiple actuators during flight is disclosed. For each actuator, a control command is computed according to at least one predetermined control law and based on pilot inputs and sensor measurements in relation to a physical state of the aircraft. The respective control commands are provided to the actuators. The control commands are independently monitored by estimating or measuring a current physical state of the aircraft and comparing it with the control commands. This comparison includes checking whether the control commands stabilize the aircraft in a stable state in the absence of both disturbances and pilot inputs according to at least one predefined criterion. If the monitoring indicates a lack of stability, transmission of the control commands is prevented and a backup control command is computed for each actuator.

A tilt rotor-based linear multi-rotor unmanned aerial vehicle (UAV) structure for crop protection and a control method thereof are provided. The tilt rotor-based linear multi-rotor UAV structure for crop protection includes main lift power structures, tilt power structures, and a main frame structure, where the main frame structure is located in a middle; the main lift power structures are distributed at left and right ends of the main frame structure; and the tilt power structures are symmetrically distributed between the main frame structure and the main lift power structures. A vector power structure is adopted to ensure flexible attitude changes and smoother and more accurate UAV operations, and improve the operation efficiency. Meanwhile, the tilt rotor-based linear multi-rotor UAV structure is adapted to the complex working environment in China's ever-changing terrains.

A wind condition learning device according to the present disclosed technique includes: an input terminal to which a learning data set is input; and a calculator including AI to perform learning on the basis of the learning data set, in which one piece of the learning data set is a wind condition altitude distribution model value following a power law on an inflow side, and the other piece of the learning data set includes a wind speed average value, a wind speed maximum value, turbulence energy, or turbulence intensity in a wind condition distribution of an environmental space obtained by simulation.

A system for scanning shipping containers, comprising an unmanned vehicle, the unmanned vehicle includes a sensor, a processor, and a memory. The memory includes instructions for execution. The instructions, when executed by the processor, cause the unmanned vehicle to move along faces of a shipping container, and record container data collected from the sensor while scanning the shipping container.