Abstract: Described herein are systems for software version-aware encryption key for secure mutable partitions. For example, some methods include verifying a digital signature of a header for an application image, wherein the header includes a hash of the application image; generating an encryption key based on the hash; encrypting, using the encryption key, data to be written to a writable partition that is mounted with a filesystem of the application image; and decrypting, using the encryption key, data read from the writable partition.

Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media for fleet management of unmanned aerial vehicles, including flight authorization. One of the methods includes maintaining one or more rules associated with authorizing UAVs to implement flight plans. A request to generate a flight plan associated with a job is received, the request including information indicating a flight pattern comprising, at least, one or more waypoints associated with geospatial references. The flight plan is generated based on the request, and an initial authorization check is determined based on the maintained rules and the generated flight plan. Upon a positive determination, access to the generated flight plan is provided by a ground control system, and the flight plan is implemented.

Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media for an unmanned aerial vehicle (UAV) wind turbine inspection system. One of the methods includes obtaining first sensor information by an unmanned aerial vehicle (UAV), the first sensor information describing physical aspects of a wind turbine, including one or more blades of the wind turbine. An orientation of the blades of the wind turbine are determined based on the obtained first sensor information. A flight pattern for the UAV to inspect the blades of the wind turbine is determined, the flight pattern being based on the determined orientation of the blades. Each of the blades of the wind turbine is inspected by the UAV according to the determined flight pattern, the inspection including obtaining second sensor information describing the blades of the wind turbine.

Abstract: Semantic three-dimensional scan is performed for the multi-phase inspection of a structure using an unmanned aerial vehicle (UAV). The multi-phase inspection includes a first inspection phase and a second inspection phase. A UAV performs the first inspection phase of the structure to determine a semantic understanding of components associated with the structure and pose information of the components. Based on the semantic understanding of the components and the pose information, a flight path indicating capture points and camera poses associated with the capture points is determined. The UAV then performs the second inspection phase of the structure according to the flight path, in which all or some of the components are inspected.

Abstract: A base station for an unmanned aerial vehicle includes a base. The base defines a cavity therein and includes a lower surface that defines one or more drainage slots to provide drainage egress from the cavity of the body. The base further includes a landing platform supported by the body. The landing platform includes a front grate in fluid communication with a thermal management system of the base station via a front thermal management duct that is configured to direct the drainage that enters the front thermal management duct through the front grate towards the one or more drainage slots and a rear grate in fluid communication with the thermal management system of the base station via a rear thermal management duct that is configured to direct the drainage that enters the rear thermal management duct through the rear grate towards the one or more drainage slots.

Abstract: Autonomous aerial vehicle technology and, more specifically, autonomous unmanned aerial vehicles with folding collapsible arms are described. In some embodiments, a UAV includes a central body, a plurality of rotor arms, and a plurality of hinge mechanisms is. The plurality of rotor arms each include a rotor unit at a distal end of the rotor arm. The rotor units are configured to provide propulsion for the UAV. The plurality of hinge mechanisms mechanically attach (or couple) proximal ends of the plurality of rotor arms to the central body. Each hinge mechanism is configured to rotate a respective rotor arm of the plurality of rotor arms about an axis of rotation that is at an oblique angle relative to a vertical median plane of the central body to transition between an extended state and a folded state.

Abstract: A vehicle including a body, a camera, and a radius tracking controller. The camera coupled to the body, the camera configured to capture an image of a subject. The radius tracking controller coupled to the body. The radius tracking controller configured to: determine a radius of a virtual sphere around the vehicle based on a configuration of the camera. The radius tracking controller configured to: determine a distance between a vehicle position of the vehicle and a previous target position of the vehicle. The radius tracking controller configured to: determine an intersection between the previous target position and a subject position of the subject relative to the vehicle. The radius tracking controller configured to: set a determined intersection where the vehicle and the subject intersect. A vehicle controller interface module coupled to the body, the vehicle controller interface module configured to move the vehicle towards the determined intersection.

Abstract: Disclosed in this specification are methods, systems and apparatus, including computer programs encoded on non-transitory computer storage media for unmanned aerial vehicle (UAV) flight operation and privacy controls. Based on geofence types, and UAV distance from a geofence, sensors and other devices connected to a UAV are conditionally operational. Image data collected during a UAV flight may be obfuscated by the UAV while in flight, or via a post-flight process using log data generated by the UAV.

Abstract: Embodiments are described for detecting optical discrepancies associated with image capture analyzing pixels in multiple images corresponding to common points of reference in a physical environment. In an embodiment, photometric error values are averaged over time to compute the mean error at each pixel. Once the estimate of the mean error has a sufficient number of updates above a specified value, the estimate is thresholded to provide a mask of any optical discrepancies occurring in the stereo pair of images. Applications include detecting optical discrepancies in images captured for use by a visual navigation system in guiding an autonomous vehicle (e.g., an unmanned aerial vehicle).

Abstract: Aerial images captured by a first device are received. A landmark is identified in an aerial image of the aerial images. A determination is made, based on data in a data store, that the landmark is identified as a control point. Precise location information is associated with the control point in the data store. The precise location information indicates a location of a second device at a time that a third device that is different from the second device captured a prior image that includes the landmark. Imagery are generated using photogrammetry software based on the aerial image and the precise location information.

Abstract: A modular vehicle management system is described, comprising a controller module configured to control different types of carrier modules. The controller module includes a computer system and optionally one or more sensors. The computer system is configured to perform operations comprising detecting whether a carrier module is connected to the controller module. If the carrier module is connected to the controller module, the carrier module is authenticated. If the authentication fails, operation of the vehicle is inhibited. The control module is configured to determine carrier module capabilities including information regarding a navigation processing device, and/or a radio modem. The controller adapts to the capabilities of the controller module. Using information from the sensors and the navigation processing device, the vehicle management system navigates the vehicle.

Abstract: Described herein are systems for automated docking of an unmanned aerial vehicle. For example, some systems include a landing surface configured to hold an unmanned aerial vehicle; a box configured to enclose the landing surface in a first arrangement of the dock and expose the landing surface in a second arrangement of the dock; and a retractable arm, wherein the landing surface is positioned at an end of the retractable arm and the retractable arm is configured to extend to move the landing surface outside of the box and contract to pull the landing surface inside of the box.

Abstract: Disclosed herein are systems and methods for operating an unmanned aerial vehicle (UAV). A method includes capturing a raw video stream input using one or more camera sensors of the UAV, receiving user-commanded motion data representative of motion commanded by a user of the UAV, and receiving total-motion data representative of motion of the one or more camera sensors including the motion commanded by the user. Residual motion data is generated by subtracting the user-commanded motion data from the total-motion data. A frame-based stabilization process operates using the residual motion data, while a rolling-shutter stabilization process operates using the total-motion data. Outputs of the stabilization processes are fused to generate mesh data, which is applied to the raw video stream to produce a stabilized video stream. Separately utilizing different motion data for distinct stabilization processes can enhance stabilization performance and viewing experience.

Abstract: Sports and fitness applications for an autonomous unmanned aerial vehicle (UAV) are described. In an example embodiment, a UAV can be configured to track a human subject using perception inputs from one or more onboard sensors. The perception inputs can be utilized to generate values for various performance metrics associated with the activity of the human subject. In some embodiments, the perception inputs can be utilized to autonomously maneuver the UAV to lead the human subject to satisfy a performance goal. The UAV can also be configured to autonomously capture images of a sporting event and/or make rule determinations while officiating a sporting event.

Abstract: An unmanned aerial vehicle (UAV) system includes one or more processors and one or more computer storage media storing instructions that when executed by the one or more processors, cause the one or more processors to perform operations that include obtaining flight information of the UAV; determining one or more modifications based on the flight information; and transmitting data messages over data buses based on the one or more modifications.

Abstract: A landing platform for a base station that is configured to dock with an unmanned aerial vehicle (UAV). The landing platform includes: a stage that defines landing areas, which are configured to receive the UAV during docking; alignment members that are configured to engage and reposition the UAV during a first stage of alignment; and a charging hub that is configured for electrical connection to the UAV. The charging hub includes a registration member, which is configured to mechanically interface with and reposition the UAV on the landing platform during a second stage of alignment, and a charging head that is repositionable in relation to the registration member from a normal position into a deflected position during a third stage of alignment to facilitate engagement of corresponding electrical contacts on the UAV and the charging head.

Abstract: Systems, methods, and software for operating an unmanned aerial vehicle (UAV) having one or more camera sensors. A method includes capturing a video stream using the camera sensor(s) of the UAV. The method includes determining a capability of a ground station communicably coupled to the UAV to annotate the video stream. In response to determining that the ground station is capable to annotate the video stream, the method includes transmitting the video stream to the ground station without annotations. Alternatively, in response to determining that the ground station is incapable to annotate the video stream, drawing annotations on the video stream to generate an annotated video stream, and transmitting the annotated video stream to the ground station. Embodiments of the present technology provide enhanced interoperability between UAVs and different types of ground stations to improve streamlining and quality of user experiences as compared to conventional systems and techniques.

Abstract: A method of docking an unmanned aerial vehicle (UAV) with a base station. The method includes: landing the UAV on a landing platform of the base station; generally aligning the UAV with a charging hub of the base station; extending the charging hub; and repositioning a locking mechanism on the charging hub from an unlocked position into a locked position to thereby secure the charging hub to the UAV.