Abstract: A payload retrieval apparatus including a support structure having an upper end and a lower end; a first sloped surface secured to the support structure and a second sloped surface positioned adjacent the first sloped surface; an opening between the first and second sloped surfaces leading to a space to allow a payload retriever attached to a tether suspended from a UAV to travel into the space; an angled channel positioned beneath the first sloped surface having a tether slot to allow for passage of the tether as the payload retriever is drawn through the angled channel; and a payload holder positioned at the end of the angled channel.

Abstract: In some embodiments, an unmanned aerial vehicle (UAV) is provided. The UAV comprises one or more processors; a camera; one or more propulsion devices; and a computer-readable medium having instructions stored thereon that, in response to execution by the one or more processors, cause the UAV to perform actions comprising: receiving at least one image captured by the camera; generating labels for pixels of the at least one image by providing the at least one image as input to a machine learning model; identifying one or more landing spaces in the at least one image based on the labels; determining a relative position of the UAV with respect to the one or more landing spaces; and transmitting signals to the one or more propulsion devices based on the relative position of the UAV with respect to the one or more landing spaces.

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 method includes capturing, by a sensor on an unmanned aerial vehicle (UAV), an image of a delivery location. The method further includes determining, based on the image of the delivery location, a segmentation image. The segmentation image segments the delivery location into a plurality of pixel areas with corresponding semantic classifications. The method also includes determining, based on the segmentation image, a distance-to-obstacle image of a delivery zone at the delivery location. The distance-to-obstacle image comprises a plurality of pixels, each pixel representing a distance in the segmentation image from a nearest pixel area with a semantic classification indicative of an obstacle in the delivery location. Additionally, the method includes selecting, based on the distance-to-obstacle image, a delivery point in the delivery zone. The method also includes positioning the UAV above the delivery point in the delivery zone for delivery of a payload.

Abstract: An unmanned aerial vehicle (UAV) is disclosed that includes a retractable payload delivery system. The payload delivery system can lower a payload to the ground using a delivery device that secures the payload during descent and releases the payload upon reaching the ground. The location of the delivery device can be determined as it is lowered to the ground using image tracking. The UAV can include an imaging system that captures image data of the suspended delivery device and identifies image coordinates of the delivery device, and the image coordinates can then be mapped to a location. The UAV may also be configured to account for any deviations from a planned path of descent in real time to effect accurate delivery locations of released payloads.

Abstract: A method includes obtaining sensor data indicating a tension experienced by a tether while a payload coupling apparatus connected to the tether is lowered from an aerial vehicle using the tether. The method also includes determining, based on the sensor data, a ground contact time at which the payload coupling apparatus or a payload coupled thereto made initial contact with a ground surface. The method additionally includes determining a length of the tether released from the aerial vehicle at the ground contact time. The method further includes determining a tether-based altitude of the aerial vehicle based on the length of the tether released from the aerial vehicle at the ground contact time. The method yet further includes causing the aerial vehicle to perform an operation based on the tether-based altitude.

Abstract: A method includes, during a delivery process of an unmanned aerial vehicle (UAV), receiving, by an image processing system, a depth image captured by a downward-facing stereo camera on the UAV. One or more pixels are within a sample area of the depth image and are associated with corresponding depth values indicative of distances of one or more objects to the downward-facing stereo camera. The method also includes determining, by the image processing system an estimated depth value representative of depth values within the sample area. The method further includes determining that the estimated depth value is below a trigger depth. The method further includes, based at least on determining that the estimated depth value is below the trigger depth, aborting the delivery process of the UAV.

Abstract: An unmanned aerial vehicle (UAV) including a fuselage body having a cavity that forms a cargo bay for transporting a payload, and a lower access opening for lowering the payload from the cargo bay, the lower access opening including a cargo bay door; a winch system positioned in the cargo bay configured to suspend a payload within the cargo bay; and a cargo bay door monitor which is configured to detect when the payload is applying a weight to the cargo bay door.

Abstract: A unmanned aerial vehicle (UAV) includes a fuselage including a top, a bottom, a cavity that forms a cargo bay between the top and the bottom, and a lower access opening in the bottom for lowering a payload from the cargo bay. A movable stage is coupled to the fuselage and adjustable between an upper position in which the stage is above the cargo bay and a lower position in which the stage is at the bottom of the fuselage, the stage including an opening extending through the stage. The UAV also includes a winch disposed in the fuselage and a tether coupled to the winch. The winch is configured to be secured to the payload and is movable through the opening in the stage so as to raise or lower the payload.

Abstract: A method includes causing an aerial vehicle to deploy a tethered component to a particular distance beneath the aerial vehicle by releasing a tether connecting the tethered component to the aerial vehicle. The method also includes obtaining, from a camera connected to the aerial vehicle, image data that represents the tethered component while the tethered component is deployed to the particular distance beneath the aerial vehicle. The method additionally includes determining, based on the image data, a position of the tethered component within the image data. The method further includes determining, based on the position of the tethered component within the image data, a wind vector that represents a wind condition present in an environment of the aerial vehicle. The method yet further includes causing the aerial vehicle to perform an operation based on the wind vector.

Abstract: In some embodiments, a non-transitory computer-readable medium having logic stored thereon is provided. The logic, in response to execution by one or more processors of an unmanned aerial vehicle (UAV), causes the UAV to perform actions comprising receiving at least one ADS-B message from an intruder aircraft; generating a intruder location prediction based on the at least one ADS-B message; comparing the intruder location prediction to an ownship location prediction to detect conflicts; and in response to detecting a conflict between the intruder location prediction and the ownship location prediction, determining a safe landing location along a planned route for the UAV and descending to land at the safe landing location.

Abstract: In some embodiments, a mobile computing device comprising one or more processors, a display, and a non-transitory computer-readable medium is provided. The computer-readable medium has logic stored thereon that, in response to execution by the one or more processors, causes the mobile computing device to perform actions comprising: determining, by the mobile computing device, a location associated with flight plan information; transmitting, by the mobile computing device, the location to a restriction management system; receiving, by the mobile computing device from the restriction management system, information for presenting a checklist including checklist items indicating statuses of flight restriction conditions associated with the location; generating, by the mobile computing device, an interface having a format based on whether all checklist items are passed, wherein the interface includes a map, a pin, and a checklist; and presenting, by the mobile computing device, the interface on the display.

Abstract: Described herein are methods and systems that help facilitate the summoning and loading of a pickup and delivery unmanned aerial vehicle (UAV). In particular, a computing system may display a graphical interface including an interface feature that indicates UAV assignments. That computing system may receive a message including a UAV identifier that identifies a particular UAV assigned to a particular item based on a UAV-assignment request for the particular item. And the computing system may use the received UAV identifier as a basis for displaying, on the graphical interface, (i) a graphical identifier of the particular UAV assigned to the particular item based on the UAV-assignment request for the particular item and (ii) a graphical identifier of the particular item.

Abstract: A computer-implemented method comprises receiving, by an image processing system, a depth image captured by a stereo camera on an unmanned aerial vehicle (UAV). One or more pixels of the depth image are associated with corresponding depth values indicative of distances of one or more objects to the stereo camera. The image processing system determines that one or more pixels of the depth image are associated with invalid depth values. The image processing system infers, based on a distribution of the one or more pixels of the depth image that are associated with invalid depth values, a presence of a potential obstacle in an environment of the UAV. The UAV is controlled based on the inferred presence of the potential obstacle.

Abstract: Systems, devices, and techniques for active thermal control of energy storage units are described. In some embodiments, an unmanned aerial vehicle (UAV) includes a battery pack. The battery pack includes a plurality of battery cells and an enclosure coupled with the plurality of battery cells to physically retain the plurality of battery cells in an arrangement. The arrangement defines a void space between the plurality of battery cells. The UAV also includes a cooling system configured to cool the battery cells. The cooling system includes a source of forced convection fluidically coupled with the battery pack to drive a cooling fluid through the void space. The cooling system also includes a cooling controller electrically coupled with the source of forced convection to controllably activate the source of forced convection.

Abstract: An unmanned aerial vehicle (UAV) includes a fuselage, electronics disposed with the fuselage, a heat sink, and a solar shield. The heat sink is thermally connected to the electronics and includes a cooling plate disposed on or extends through an exterior surface of the fuselage. The cooling plate is exposed to an external environment of the UAV to conduct heat from the electronics to the external environment via convection. The solar shield extends over the cooling plate and defines an air scoop within which the cooling plate is disposed. The air scoop directs airflow from the external environment across the cooling plate. The solar shield shades the cooling plate from solar radiation to prevent or reduce solar heating of the cooling plate.

Abstract: A package coupling apparatus for securing a package to an unmanned aerial vehicle (UAV) is provided. The package coupling apparatus includes a hanger and a strap coupled to the hanger. The hanger includes a base configured to be positioned adjacent to the package and a handle extending up from the base. The handle includes a handle opening and a bridge that extends over the handle opening. The bridge is configured to be secured by a component of the UAV. The strap is configured to surround the package and secure the package to the hanger.

Abstract: Example implementations relate to a method of dynamically updating a transport task of a UAV. The method includes receiving, at a transport-provider computing system, an item provider request for transportation of a plurality of packages from a loading location at a given future time. The method also includes assigning, by the transport-provider computing system, a respective transport task to each of a plurality of UAVs, where the respective transport task comprises an instruction to deploy to the loading location to pick up one or more of the plurality of packages. Further, the method includes identifying, by the transport-provider system, a first package while or after a first UAV picks up the first package. Yet further, the method includes based on the identifying of the first package, providing, by the transport-provider system, a task update to the first UAV to update the respective transport task of the first 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.