A drone including a front section, a wing structure supported by a rotor located behind the front section, and a propeller at the rear. The wing structure including two wings rotating the rotor, the wing structure being able to move between a flight configuration, in which the rotor is immobile relative to the front section and the propulsion provided by the propeller, and a flight configuration with the wing structure rotating, in which the rotor is rotated relative to the front section, the rotor being connected to the front section with a possibility of orienting its axis of rotation relative thereto in order able to direct the drone in the rotary wing structure configuration by acting on said orientation.

A propulsion system, comprising: a fan blade housing; a plurality of fan blades within the fan blade housing; one or more rows of permanent magnets, affixed to the outside of the fan blade housing; one or more fan blade bearings; one or more magnetic field generators affixed to the one or more fan blade bearings and corresponding to the one or more rows of permanent magnets, the magnetic field generators configured to cause the permanent magnets to be propelled forward in the same direction, thereby causing the fan blade housing to which they are attached, and the fan blades within, to spin.

An exemplary unmanned aerial vehicle (UAV) mountable to a conductor of an aerial power transmission line system includes a body having a rotor system, a motivation system attached to the body to motivate the UAV along the conductor, a battery carried by the body and electrically connected to at least one of the rotor system and the motivation system, a monitoring tool mounted with the body and an inductive coil carried by the body and in electric connection with the battery, wherein the inductive coil is configured to harvest electricity from the aerial power transmission line system and charge the battery.

A method and system for detecting a typical object of a transmission line based on UAV federated learning. The method includes: determining a detection model for a typical object of a transmission line by YOLOv3 object detection algorithm according to a prior database for the typical object; dividing a UAV network into multiple federated learning units; acquiring pictures, taken by the UAV network, of the typical object and tags corresponding to each picture to determine a training database; training, based on Horovod framework and FATE federated learning framework, each federated learning unit according to the training database and the detection model for the typical object, and determining the trained UAV network according to the trained federated learning unit; and determining, by the trained UAV network, the typical object in each picture. A congestion of communication links is avoided, thereby improving detection efficiency.

A multi-modal robot capable of legged and aerial locomotion includes a body structure including a plurality of legs, each leg having at least one joint; a plurality of thrusters connected to the body structure; and a plurality of actuators for controlled movement of the legs and thrusters. The plurality of actuators are embedded within composite housing structures in the body structure. The composite housing structures are formed by additive printing of composite material over components of the actuators. The composite housing structures are reinforced by layers of continuous carbon fiber material. A method of constructing an actuator for use in a multi-modal robot is also disclosed. Additionally, a computer-implemented method is disclosed to identify particular locations and sizes of components in multi-modal robots providing the lowest total cost of transport.

Methods and systems are described herein for generating composite data streams. A data stream processing system may receive multiple data streams from, for example, multiple unmanned vehicles and determine, based on the type of data within each data stream, a machine learning model for each data stream for processing the type of data. Each machine learning model may receive the frames of a corresponding data stream and output indications and locations of objects within those data streams. The data stream processing system may then generate a composite data stream with indications of the detected objects.

A method (400) of capturing and processing electroluminescence (EL) images (1910) of a PV array (40) is disclosed herein. In a described embodiment, the method 400 includes controlling the aerial vehicle (20) to fly along a flight path to capture EL images (1910) of corresponding PV array subsections (512b) of the PV array (40), deriving respective image quality parameters from at least some of the captured EL images, dynamically adjusting a flight speed of the aerial vehicle along the flight path, based on the respective image quality parameters for capturing the EL images (1910) of the PV array subsections (512b), extracting a plurality of frames (1500) of the PV array subsection (512b) from the EL images (1910); determining a reference frame having a highest image quality of the PV array subsection (512b) from among the extracted frames (2100); performing image alignment of the extracted frames (2100) to the reference frame to generate image aligned frames (2130), and processing the image aligned frames (2130) to produce an enhanced image (2140) of the PV array subsection (512b) having a higher resolution than the reference frame. A system, image processing device, and aerial vehicle for the method thereof are also disclosed.

A method of communicating between an aerial vehicle and a cellular radio access network is described. In some cases, the method includes determining a current location of the aerial vehicle; determining, in response to the current location, a location of a nearest cell of the cellular radio access network; and processing communications between the aerial vehicle and the cellular radio access network, using the nearest cell as a serving cell. When the method is performed on-board an aerial vehicle, the method further includes orienting a directional antenna of the aerial vehicle toward the location of the nearest cell.

This disclosure describes an aerial vehicle, such as an unmanned aerial vehicle (“UAV”), which includes a plurality of maneuverability propulsion mechanisms that enable the aerial vehicle to move in any of the six degrees of freedom (surge, sway, heave, pitch, yaw, and roll). The aerial vehicle may also include a lifting propulsion mechanism that operates to generate a force sufficient to maintain the aerial vehicle at an altitude.

A method (10) for restoring a microwave link is provided. The method (10) is performed by a network entity (7) and comprises receiving (11) information from a node (3) controlling a microwave antenna (5), the information indicating that an obstacle is at least partly obscuring the microwave antenna (5), and instructing (12), based on the received information, an unmanned aerial vehicle (6) adapted for maintenance work to fly to a given location for removing the obstacle on the microwave antenna (5). A method (40) in a network node (3), a method (70) in an unmanned aerial vehicle (6) and devices are also provided.