Abstract: An autonomous vehicle that is equipped with image capture devices can use information gathered from the image capture devices to plan a future three-dimensional (3D) trajectory through a physical environment. To this end, a technique is described for image-space based motion planning. In an embodiment, a planned 3D trajectory is projected into an image-space of an image captured by the autonomous vehicle. The planned 3D trajectory is then optimized according to a cost function derived from information (e.g., depth estimates) in the captured image. The cost function associates higher cost values with identified regions of the captured image that are associated with areas of the physical environment into which travel is risky or otherwise undesirable. The autonomous vehicle is thereby encouraged to avoid these areas while satisfying other motion planning objectives.

Abstract: An autonomous vehicle that is equipped with image capture devices can use information gathered from the image capture devices to plan a future three-dimensional (3D) trajectory through a physical environment. To this end, a technique is described for image-space based motion planning. In an embodiment, a planned 3D trajectory is projected into an image-space of an image captured by the autonomous vehicle. The planned 3D trajectory is then optimized according to a cost function derived from information (e.g., depth estimates) in the captured image. The cost function associates higher cost values with identified regions of the captured image that are associated with areas of the physical environment into which travel is risky or otherwise undesirable. The autonomous vehicle is thereby encouraged to avoid these areas while satisfying other motion planning objectives.

Abstract: A technique is introduced for autonomous landing by an aerial vehicle. In some embodiments, the introduced technique includes processing a sensor data such as images captured by onboard cameras to generate a ground map comprising multiple cells. A suitable footprint, comprising a subset of the multiple cells in the ground map that satisfy one or more landing criteria, is selected and control commands are generated to cause the aerial vehicle to autonomously land on an area corresponding to the footprint. In some embodiments, the introduced technique involves a geometric smart landing process to select a relatively flat area on the ground for landing. In some embodiments, the introduced technique involves a semantic smart landing process where semantic information regarding detected objects is incorporated into the ground map.

Abstract: In some examples, an unmanned aerial vehicle (UAV) may control a position of a first camera to cause the first camera to capture a first image of a target. The UAV may receive a plurality of second images from a plurality of second cameras, the plurality of second cameras positioned on the UAV for providing a plurality of different fields of view in a plurality of different directions around the UAV, the first camera having a longer focal length than the second cameras. The UAV may combine at least some of the plurality of second images to generate a composite image corresponding to the first image and having a wider-angle field of view than the first image. The UAV may send the first image and the composite image to a computing device.

Abstract: The technology described herein relates to autonomous aerial vehicle rotor configurations. In some embodiments, the aerial vehicle includes a central body that extends along a longitudinal axis from a forward end to an aft end including a port side opposite a starboard side. Multiple rotor arms each have a proximal end coupled to the central body and a rotor assembly arranged at a distal end to provide propulsion for the aerial vehicle. The rotor assemblies include a first set of rotor assemblies and a second set of rotor assemblies. The first set of rotor assemblies are arranged in a non-inverted configuration on a top side of the aerial vehicle such that each rotor assembly includes an upward-facing rotor. The second set of rotor assemblies are arranged in an inverted configuration on a bottom side of the aerial vehicle such that each rotor assembly includes a downward-facing rotor.

Abstract: Embodiments are described for a stabilization system configured, in some embodiments, for stabilizing image capture from an aerial vehicle (e.g., a UAV). According to some embodiments, the stabilization systems employs both active and passive stabilization means. A passive stabilization assembly includes a counter-balanced suspension system that includes an elongated arm that extends into and is coupled to the body of a vehicle. The counter-balanced suspension system passively stabilizes a mounted device such as an image capture device to counter motion of the UAV while in use. In some embodiment the counter-balanced suspension system passively stabilizes a mounted image capture assembly that includes active stabilization means (e.g., a motorized gimbal and/or electronic image stabilization). In some embodiments, the active and passive stabilization means operate together to effectively stabilize a mounted image capture device to counter a wide range of motion characteristics.

Abstract: Described herein are systems for automated docking of an unmanned aerial vehicle. For example, some systems include an unmanned aerial vehicle including a propulsion mechanism, a battery, and a processing apparatus; and a dock including a landing surface with a funnel geometry shaped to fit a bottom surface of the unmanned aerial vehicle at a base of the funnel, wherein tapered sides of the funnel form corners at the base of the funnel, and a battery charger configured to charge the battery of the unmanned aerial vehicle while the unmanned aerial vehicle is on the landing surface, wherein conducting contacts of the battery charger are on the landing surface, positioned at the bottom of the funnel.

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: A technique is introduced for touchdown detection during autonomous landing by an aerial vehicle. In some embodiments, the introduced technique includes processing perception inputs with a dynamics model of the aerial vehicle to estimate the external forces and/or torques acting on the aerial vehicle. The estimated external forces and/or torques are continually monitored while the aerial vehicle is landing to determine when the aerial vehicle is sufficiently supported by a landing surface. In some embodiments, semantic information associated with objects in the environment is utilized to configure parameters associated with the touchdown detection process.

Abstract: The technology described herein relates to autonomous aerial vehicle technology and, more specifically, to environment illumination for autonomous unmanned aerial vehicles. In some embodiments, a UAV includes upward-facing image capture devices, downward-facing image capture devices, one or more illumination sources, and a computer system. The computer system is configured to direct the one or more illumination sources to selectively emit light into a surrounding physical environment while the UAV is in flight, process images captured by any one or more of the plurality of upward-facing image capture devices or the plurality of downward-facing image capture devices to estimate a position and/or orientation of the aerial vehicle, generate a planned trajectory for the aerial vehicle through a physical environment based on the processing of the images, and control a propulsion system and/or flight surface of the aerial vehicle to cause the aerial vehicle to autonomously maneuver along the planned trajectory.

Abstract: The technology described herein relates to autonomous aerial vehicle technology and, more specifically, to image stabilization systems for autonomous aerial vehicles. In some embodiments, a UAV including a central body, an image capture assembly that couples the image capture assembly to the central body. The image stabilization assembly is configured to provide structural protection and support around the image capture assembly while passively isolating the image capture assembly from vibrations and other motion of the central body while the UAV is in flight.

Abstract: The technology described herein relates to autonomous aerial vehicle technology and, more specifically, to autonomous unmanned aerial vehicle with folding collapsible arms. In some embodiments, a UAV including a central body, a plurality of rotor arms, and a plurality of hinge mechanisms is disclosed. 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: Methods and systems are described for new paradigms for user interaction with an unmanned aerial vehicle (referred to as a flying digital assistant or FDA) using a portable multifunction device (PMD) such as smart phone. In some embodiments, a user may control image capture from an FDA by adjusting the position and orientation of a PMD. In other embodiments, a user may input a touch gesture via a touch display of a PMD that corresponds with a flight path to be autonomously flown by the FDA.

Abstract: A technique is introduced for touchdown detection during autonomous landing by an aerial vehicle. In some embodiments, the introduced technique includes processing perception inputs with a dynamics model of the aerial vehicle to estimate the external forces and/or torques acting on the aerial vehicle. The estimated external forces and/or torques are continually monitored while the aerial vehicle is landing to determine when the aerial vehicle is sufficiently supported by a landing surface. In some embodiments, semantic information associated with objects in the environment is utilized to configure parameters associated with the touchdown detection process.

Abstract: Described herein are systems for roof scan using an unmanned aerial vehicle. For example, some methods include capturing, using an unmanned aerial vehicle, an overview image of a roof of a building from above the roof; presenting a suggested bounding polygon overlaid on the overview image to a user; determining a bounding polygon based on the suggested bounding polygon and user edits; based on the bounding polygon, determining a flight path including a sequence of poses of the unmanned aerial vehicle with respective fields of view at a fixed height that collectively cover the bounding polygon; fly the unmanned aerial vehicle to a sequence of scan poses with horizontal positions matching respective poses of the flight path and vertical positions determined to maintain a consistent distance above the roof; and scanning the roof from the sequence of scan poses to generate a three-dimensional map of the roof.

Abstract: Described herein are systems and methods for structure scan using an unmanned aerial vehicle. For example, some methods include accessing a three-dimensional map of a structure; generating facets based on the three-dimensional map, wherein the facets are respectively a polygon on a plane in three-dimensional space that is fit to a subset of the points in the three-dimensional map; generating a scan plan based on the facets, wherein the scan plan includes a sequence of poses for an unmanned aerial vehicle to assume to enable capture, using image sensors of the unmanned aerial vehicle, of images of the structure; causing the unmanned aerial vehicle to fly to assume a pose corresponding to one of the sequence of poses of the scan plan; and capturing one or more images of the structure from the pose.

Abstract: Embodiments are described for a stabilization system configured, in some embodiments, for stabilizing image capture from an aerial vehicle (e.g., a UAV). According to some embodiments, the stabilization systems employs both active and passive stabilization means. A passive stabilization assembly includes a counter-balanced suspension system that includes an elongated arm that extends into and is coupled to the body of a vehicle. The counter-balanced suspension system passively stabilizes a mounted device such as an image capture device to counter motion of the UAV while in use. In some embodiment the counter-balanced suspension system passively stabilizes a mounted image capture assembly that includes active stabilization means (e.g., a motorized gimbal and/or electronic image stabilization). In some embodiments, the active and passive stabilization means operate together to effectively stabilize a mounted image capture device to counter a wide range of motion characteristics.

Abstract: Described herein are systems for automated docking of an unmanned aerial vehicle. For example, some systems include an unmanned aerial vehicle including a propulsion mechanism, an image sensor, and processing apparatus; and a dock including a landing surface configured to hold the unmanned aerial vehicle and a fiducial on the landing surface, wherein the processing apparatus is configured to: control the propulsion mechanism to cause the unmanned aerial vehicle to fly to a first location in a vicinity of the dock; access one or more images captured using the image sensor; detect the fiducial in at least one of the one or more images; determine a pose of the fiducial based on the one or more images; and control, based on the pose of the fiducial, the propulsion mechanism to cause the unmanned aerial vehicle to land on the landing surface.

Abstract: An actuator is introduced that utilizes the forces that result from placing a current carrying coil in a magnetic field to rotate a connected object about at least one axis. In some embodiments, the introduced coil actuator includes a coil of conductor coupled to an arm or other type of structural element that extends radially from an axis of rotation. The introduced coil actuator can be utilized to provide motion control in a variety of different applications such as gimbal mechanisms. In some embodiments, the introduced coil actuator can be implemented in a gimbal mechanism for adjusting an orientation of a device such as a camera relative to a connected platform such as the body of an aerial vehicle.

Abstract: Methods and systems are described for new paradigms for user interaction with an unmanned aerial vehicle (referred to as a flying digital assistant or FDA) using a portable multifunction device (PMD) such as smart phone. In some embodiments, a user may control image capture from an FDA by adjusting the position and orientation of a PMD. In other embodiments, a user may input a touch gesture via a touch display of a PMD that corresponds with a flight path to be autonomously flown by the FDA.