Abstract: In some embodiments, a method for autonomous navigation of an unmanned aerial vehicle (UAV) is provided. The UAV determines a tracked position using at least one positioning sensor of the UAV. The UAV captures an image using a camera of the UAV. The UAV determines a visual position confidence area using the captured image. The UAV checks the tracked position using the visual position confidence area to determine whether the tracked position is accurate. In response to determining that the tracked position is not accurate, the UAV causes a corrective action based on the visual position confidence area to be taken.

Abstract: A method includes determining an operational condition associated with an unmanned aerial vehicle (UAV). The method includes, responsive to determining the operational condition, causing the UAV to perform a pre-flight check. The pre-flight check includes hovering the UAV above a takeoff location. The pre-flight check includes, while hovering the UAV, moving one or more controllable components of the UAV in accordance with a predetermined sequence of movements. The pre-flight check includes obtaining, by one or more sensors of the UAV, sensor data indicative of a flight response of the UAV to moving the one or more controllable components while hovering the UAV. The pre-flight check includes comparing the sensor data to expected sensor data associated with an expected flight response to the predetermined sequence of movements while hovering the UAV. The pre-flight check includes, based on comparing the sensor data to the expected sensor data, evaluating performance of the UAV.

Abstract: Unmanned aerial vehicle (UAV) navigation systems include a UAV charging pad positioned at a storage facility, a plurality of fiducial markers positioned at the storage facility, and a UAV. Each of the fiducial markers is associated with a fiducial dataset storing a position of the corresponding fiducial marker, and the fiducial datasets are stored in a fiducial map. The UAV includes a camera and logic that when executed causes the UAV to image a first fiducial marker, to access from the fiducial map a first fiducial dataset storing the position of the first fiducial marker, and to navigate based upon the first fiducial dataset.

Abstract: Described is a method that involves operating an unmanned aerial vehicle (UAV) to begin a flight, where the UAV relies on a navigation system to navigate to a destination. During the flight, the method involves operating a camera to capture images of the UAV's environment, and analyzing the images to detect features in the environment. The method also involves establishing a correlation between features detected in different images, and using location information from the navigation system to localize a feature detected in different images. Further, the method involves generating a flight log that includes the localized feature. Also, the method involves detecting a failure involving the navigation system, and responsively operating the camera to capture a post-failure image. The method also involves identifying one or more features in the post-failure image, and determining a location of the UAV based on a relationship between an identified feature and a localized feature.

Abstract: In some embodiments, a method of determining an estimated location of a UAV is provided. A captured image is received from a camera of the UAV. Semantic labels are generated by the UAV for a plurality of objects visible in the captured image. The UAV compares the semantic labels to reference labels associated with a reference map to determine a current location estimate. The UAV updates an accumulated location estimate using the current location estimate, and the UAV determines the estimated location of the UAV based on the accumulated location estimate.

Abstract: Described is a method that involves operating an unmanned aerial vehicle (UAV) to begin a flight, where the UAV relies on a navigation system to navigate to a destination. During the flight, the method involves operating a camera to capture images of the UAV's environment, and analyzing the images to detect features in the environment. The method also involves establishing a correlation between features detected in different images, and using location information from the navigation system to localize a feature detected in different images. Further, the method involves generating a flight log that includes the localized feature. Also, the method involves detecting a failure involving the navigation system, and responsively operating the camera to capture a post-failure image. The method also involves identifying one or more features in the post-failure image, and determining a location of the UAV based on a relationship between an identified feature and a localized feature.

Abstract: A method for automated assignment of a staging pad to an unmanned aerial vehicle (UAV) includes: launching the UAV from a launch location; tracking a drift of the UAV from the launch location; determining a subsequent position of the UAV after the launching based upon geofiducial navigation; calculating an estimated position of the launch location by offsetting the subsequent position by the drift; attempting to match the estimated position to an available staging pad of a plurality of staging pads; and assigning the UAV to the available staging pad when the estimated position successfully matches to the available staging pad.

Abstract: A method includes determining an operational condition associated with an unmanned aerial vehicle (UAV). The method includes, responsive to determining the operational condition, causing the UAV to perform a pre-flight check. The pre-flight check includes hovering the UAV above a takeoff location. The pre-flight check includes, while hovering the UAV, moving one or more controllable components of the UAV in accordance with a predetermined sequence of movements. The pre-flight check includes obtaining, by one or more sensors of the UAV, sensor data indicative of a flight response of the UAV to moving the one or more controllable components while hovering the UAV. The pre-flight check includes comparing the sensor data to expected sensor data associated with an expected flight response to the predetermined sequence of movements while hovering the UAV. The pre-flight check includes, based on comparing the sensor data to the expected sensor data, evaluating performance of the UAV.

Abstract: Systems and methods for validating a position of an unmanned aerial vehicle (UAV) are provided. A method can include receiving map data for a location, the map data including labeled data for a plurality of landmarks in a vicinity of the location. The method can include generating image data for the location, the image data being derived from images of the vicinity generated by the UAV including at least a subset of the plurality of landmarks. The method can include determining a visual position of the UAV using the image data and the map data. The method can include determining a Global Navigation Satellite System (GNSS) position of the UAV. The method can include generating an error signal using the visual position and the GNSS position. The method can also include validating the GNSS position in accordance with the error signal satisfying a transition condition.

Abstract: A computer-implemented method comprises receiving an image captured by a camera on an unmanned aerial vehicle (UAV). The image depicts an environment below the UAV. A feature mask associated with the image is generated via a machine learning model that is trained to identify and semantically label pixels representing the environment depicted in the image. One or more reference tiles associated with the environment are retrieved. The reference tiles are associated with particular geographic locations and specify semantically labeled pixels representing the geographic locations. The semantically labeled pixels of the feature mask are correlated with the semantically labeled pixels of at least one of the one or more reference tiles to determine the geographic location of the UAV in the environment.

Abstract: An apparatus for visual navigation of a UAV includes a geo-fiducial mat and a plurality of geo-fiducials. The geo-fiducial mat includes a landing pad region that provides a location for aligning with a landing pad of a UAV. The geo-fiducials each includes a two-dimensional (2D) pattern that visually conveys a code. The 2D pattern has a shape from which a visual navigation system of the UAV can visually triangulate a position of the UAV.

Abstract: Described is a method that involves operating an unmanned aerial vehicle (UAV) to begin a flight, where the UAV relies on a navigation system to navigate to a destination. During the flight, the method involves operating a camera to capture images of the UAV's environment, and analyzing the images to detect features in the environment. The method also involves establishing a correlation between features detected in different images, and using location information from the navigation system to localize a feature detected in different images. Further, the method involves generating a flight log that includes the localized feature. Also, the method involves detecting a failure involving the navigation system, and responsively operating the camera to capture a post-failure image. The method also involves identifying one or more features in the post-failure image, and determining a location of the UAV based on a relationship between an identified feature and a localized feature.

Abstract: Described is a method that involves operating an unmanned aerial vehicle (UAV) to begin a flight, where the UAV relies on a navigation system to navigate to a destination. During the flight, the method involves operating a camera to capture images of the UAV's environment, and analyzing the images to detect features in the environment. The method also involves establishing a correlation between features detected in different images, and using location information from the navigation system to localize a feature detected in different images. Further, the method involves generating a flight log that includes the localized feature. Also, the method involves detecting a failure involving the navigation system, and responsively operating the camera to capture a post-failure image. The method also involves identifying one or more features in the post-failure image, and determining a location of the UAV based on a relationship between an identified feature and a localized feature.

Abstract: A method for automated assignment of a staging pad to an unmanned aerial vehicle (UAV) includes: launching the UAV from a launch location; tracking a drift of the UAV from the launch location; determining a subsequent position of the UAV after the launching based upon geofiducial navigation; calculating an estimated position of the launch location by offsetting the subsequent position by the drift; attempting to match the estimated position to an available staging pad of a plurality of staging pads; and assigning the UAV to the available staging pad when the estimated position successfully matches to the available staging pad.

Abstract: An apparatus for visual navigation of a UAV includes a geo-fiducial mat and a plurality of geo-fiducials. The geo-fiducial mat includes a landing pad region that provides a location for aligning with a landing pad of a UAV. The geo-fiducials each includes a two-dimensional (2D) pattern that visually conveys a code. The 2D pattern has a shape from which a visual navigation system of the UAV can visually triangulate a position of the UAV.

Abstract: An apparatus for visual navigation of a UAV includes a geo-fiducial mat and a plurality of geo-fiducials. The geo-fiducial mat includes a landing pad region that provides a location for aligning with a landing pad of a UAV and a survey point. The geo-fiducials are each specified for a unique directional and offset position in or about the landing pad region relative to the survey point. The geo-fiducials each includes a two-dimensional (2D) pattern that visually conveys an alphanumerical code. The 2D pattern has a shape from which a visual navigation system of the UAV can visually triangulate a position of the UAV.

Abstract: A technique for validating a balcony to receive delivery of a parcel via a UAV includes obtaining a first identification of a general location of the balcony; generating a first image representing a building including the balcony where the first image is selected based upon the location identified; obtaining a second identification or a confirmation of a precise location of the balcony in the building where the second identification or the confirmation are received in response to an end-user interaction with the first image; determining a deliverability score based at least in part on the precise location of the balcony; and indicating an enrollment status to the end-user where the enrollment status is generated based upon the deliverability score.

Abstract: A method includes determining an operational condition associated with an unmanned aerial vehicle (UAV). The method includes, responsive to determining the operational condition, causing the UAV to perform a pre-flight check. The pre-flight check includes hovering the UAV above a takeoff location. The pre-flight check includes, while hovering the UAV, moving one or more controllable components of the UAV in accordance with a predetermined sequence of movements. The pre-flight check includes obtaining, by one or more sensors of the UAV, sensor data indicative of a flight response of the UAV to moving the one or more controllable components while hovering the UAV. The pre-flight check includes comparing the sensor data to expected sensor data associated with an expected flight response to the predetermined sequence of movements while hovering the UAV. The pre-flight check includes, based on comparing the sensor data to the expected sensor data, evaluating performance of the UAV.

Abstract: Unmanned aerial vehicle (UAV) navigation systems include a UAV charging pad positioned at a storage facility, a plurality of fiducial markers positioned at the storage facility, and a UAV. Each of the fiducial markers is associated with a fiducial dataset storing a position of the corresponding fiducial marker, and the fiducial datasets are stored in a fiducial map. The UAV includes a camera and logic that when executed causes the UAV to image a first fiducial marker, to access from the fiducial map a first fiducial dataset storing the position of the first fiducial marker, and to navigate based upon the first fiducial dataset.

Abstract: Unmanned aerial vehicle (UAV) navigation systems include a UAV charging pad positioned at a storage facility, a plurality of fiducial markers positioned at the storage facility, and a UAV. Each fiducial marker is associated with a fiducial dataset storing a position of the fiducial marker, and each fiducial dataset is stored in a fiducial map. The UAV has a navigation system that includes a camera, a fiducial navigation sub-system, a non-fiducial navigation sub-system, and logic that when executed causes the UAV to image a first fiducial marker with the camera, to transition from a non-fiducial navigation mode to a fiducial navigation mode, to access from the fiducial map the fiducial dataset storing the position of the first fiducial marker, and to navigate based upon the fiducial dataset storing the position of the first fiducial marker, into alignment with and land on the UAV charging pad.