Abstract: Methods, systems, and program products of inspecting solar panels using unmanned aerial vehicles (UAVs) are disclosed. A UAV can obtain a position of the Sun in a reference frame, a location of a solar panel in the reference frame, and an orientation of the solar panel in the reference frame. The UAV can determine a viewing position of the UAV in the reference frame based on at least one of the position of the Sun, the location of the solar panel, and the orientation of the solar panel. The UAV can maneuver to the viewing position and point a thermal sensor onboard the UAV at the solar panel. The UAV can capture, by the thermal sensor, a thermal image of at least a portion of the solar panel. A server onboard the UAV or connected to the UAV can detect panel failures based on the thermal image.

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: In some implementations, a UAV flight system can dynamically adjust UAV flight operations based on radio frequency (RF) signal data. For example, the flight system can determine an initial flight plan for inspecting a RF transmitter and configure a UAV to perform an aerial inspection of the RF transmitter. Once airborne, the UAV can collect RF signal data and the flight system can automatically adjust the flight plan to avoid RF signal interference and/or damage to the UAV based on the collected RF signal data. In some implementations, the UAV can collect RF signal data and generate a three-dimensional received signal strength map that describes the received signal strength at various locations within a volumetric area around the RF transmitter. In some implementations, the UAV can collect RF signal data and determine whether a RF signal transmitter is properly aligned.

Abstract: Systems and methods disclosed herein involve monitoring an interior state of a vehicle. A pre-ride image of an interior is recorded prior to initiating a ride A post-ride image of the interior is recorded following completion of the ride. A region of the post-ride image differing from the pre-ride image is detected, with the region of the post-ride image representing a change in the interior. A type of an object depicted in the region of the post-ride image is classified based on features extracted from the region of the post-ride image. In response to classifying the object depicted in the region of the post-ride image as a personal item, a prompt is served to the user to retrieve the object.

Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media for determining asset efficiency. Unmanned Aerial Vehicles (UAVs) may be used to obtain aerial images of locations, property or structures. The aerial images may be geo-rectified, and a ortho-mosaic, digital surface model, or a point cloud may be created. In the context of an operation where mobile assets are used, such as construction or earth moving equipment, location-based event information may be obtained. The location-based event information may be used to determine road segment conditions or road topology where problematic road conditions likely exist.

Abstract: Methods, systems and apparatus, for an unmanned aerial vehicle electromagnetic avoidance and utilization system. One of the methods includes obtaining a flight package indicating a flight pattern associated with inspecting a structure, the flight pattern causing the UAV to remain at a standoff distance from the structure, wherein the standoff distance is based on an electromagnetic field associated with the structure, and wherein the flight pattern is laterally constrained according to a property geofence associated with a right of way of the structure. The UAV is navigated according to the flight pattern, and the UAV captures images of the structure. For an initial portion of the flight pattern, the UAV navigates at an altitude based on the standoff distance and the property geofence towards the structure. The UAV determines a location at which to capture images of the structure, and the UAV provides the captured images to a user device.

Abstract: One variation of a method for identifying a user entering an autonomous vehicle includes: receiving a ride request from the user, the ride request specifying a pickup location; at the autonomous vehicle, autonomously navigating to the pickup location, scanning a field near the autonomous vehicle for a human approaching the autonomous vehicle, and, in response to detecting the human proximal the autonomous vehicle, recording an image of the human; detecting a face of the human in the image; accessing a faceprint characterizing facial features of the user; and, in response to the face of the human detected in the image exhibiting features represented in the faceprint, identifying the human as the user and triggering a door of the autonomous vehicle to unlock for the user.

Abstract: One variation of a method for determining a location of a user includes: at a mobile computing device, receiving from the user a request for pickup by a road vehicle; accessing an optical image recorded by the mobile computing device at approximately the first time; detecting a set of image features in the optical image; accessing an approximate location of the mobile computing device from a geospatial positioning system; accessing a set of known features associated with geographic locations within a threshold distance of the approximate location; in response to detecting correspondence between a first image feature in the set of image features and a first known feature in the set of known features, extrapolating an action geographic location of the mobile computing device based on a particular geographic location associated with the particular known feature; and dispatching an autonomous vehicle to proximal the actual geographic location.

Abstract: One variation of a method for identifying a user entering an autonomous vehicle includes: receiving a ride request from the user, the ride request specifying a pickup location; at the autonomous vehicle, autonomously navigating to the pickup location, scanning a field near the autonomous vehicle for a human approaching the autonomous vehicle, and, in response to detecting the human proximal the autonomous vehicle, recording an image of the human; detecting a face of the human in the image; accessing a faceprint characterizing facial features of the user; and, in response to the face of the human detected in the image exhibiting features represented in the faceprint, identifying the human as the user and triggering a door of the autonomous vehicle to unlock for the user.

Abstract: One variation of a method for customizing motion characteristics of an autonomous vehicle for a user includes: accessing a baseline emotional state of the user following entry of the user into the autonomous vehicle at a first time proximal a start of a trip; during a first segment of the trip, autonomously navigating toward a destination location according to a first motion planning parameter, accessing a second emotional state of the user at a second time, detecting degradation of sentiment of the user based on differences between the baseline and second emotional states; and correlating degradation of sentiment of the user with a navigational characteristic of the autonomous vehicle; modifying the first motion planning parameter of the autonomous vehicle to deviate from the navigational characteristic; and, during a second segment of the trip, autonomously navigating toward the destination location according to the revised motion planning parameter.

Abstract: One variation of a method for monitoring an interior state of an autonomous vehicle includes: at the autonomous vehicle, recording a pre-ride image of an interior of the autonomous vehicle prior to initiating a ride; following completion of the ride, recording a post-ride image of the interior of the autonomous vehicle; detecting a region of the post-ride image differing from the pre-ride image, the region of the post-ride image representing a change in the interior of the autonomous vehicle following occupancy of the autonomous vehicle by a user; classifying a type of an object depicted in the region of the post-ride image based on features extracted from the region of the post-ride image; and in response to classifying the object depicted in the region of the post-ride image as a personal item, serving a prompt to the user to retrieve the object from the autonomous vehicle.

Abstract: One variation of a method for determining a location of a user includes: at a mobile computing device, receiving from the user a request for pickup by a road vehicle; accessing an optical image recorded by the mobile computing device at approximately the first time; detecting a set of image features in the optical image; accessing an approximate location of the mobile computing device from a geospatial positioning system; accessing a set of known features associated with geographic locations within a threshold distance of the approximate location; in response to detecting correspondence between a first image feature in the set of image features and a first known feature in the set of known features, extrapolating an action geographic location of the mobile computing device based on a particular geographic location associated with the particular known feature; and dispatching an autonomous vehicle to proximal the actual geographic location.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for ground control point assignment and determination. One of the methods includes receiving information describing a flight plan for the UAV to implement, the flight plan identifying one or more waypoints associated with geographic locations assigned as ground control points. A first waypoint identified in the flight plan is traveled to, and an action to designate a surface at the associated geographic location is designated as a ground control point. Location information associated with the designated surface is stored. The stored location information is provided to an outside system for storage.

Abstract: Methods, systems, and program products of inspecting solar panels using unmanned aerial vehicles (UAVs) are disclosed. A UAV can obtain a position of the Sun in a reference frame, a location of a solar panel in the reference frame, and an orientation of the solar panel in the reference frame. The UAV can determine a viewing position of the UAV in the reference frame based on at least one of the position of the Sun, the location of the solar panel, and the orientation of the solar panel. The UAV can maneuver to the viewing position and point a thermal sensor onboard the UAV at the solar panel. The UAV can capture, by the thermal sensor, a thermal image of at least a portion of the solar panel. A server onboard the UAV or connected to the UAV can detect panel failures based on the thermal image.

Abstract: In some implementations, a UAV flight system can dynamically adjust UAV flight operations based on radio frequency (RF) signal data. For example, the flight system can determine an initial flight plan for inspecting a RF transmitter and configure a UAV to perform an aerial inspection of the RF transmitter. Once airborne, the UAV can collect RF signal data and the flight system can automatically adjust the flight plan to avoid RF signal interference and/or damage to the UAV based on the collected RF signal data. In some implementations, the UAV can collect RF signal data and generate a three-dimensional received signal strength map that describes the received signal strength at various locations within a volumetric area around the RF transmitter. In some implementations, the UAV can collect RF signal data and determine whether a RF signal transmitter is properly aligned.

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: In some implementations, a UAV flight system can dynamically adjust UAV flight operations based on thermal sensor data. For example, the flight system can determine an initial flight plan for inspecting a flare stack and configure a UAV to perform an aerial inspection of the flare stack. Once airborne, the UAV can collect thermal sensor data and the flight system can automatically adjust the flight plan to avoid thermal damage to the UAV based on the thermal sensor data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for ground control point assignment and determination. One of the methods includes receiving information describing a flight plan for the UAV to implement, the flight plan identifying one or more waypoints associated with geographic locations assigned as ground control points. A first waypoint identified in the flight plan is traveled to, and an action to designate a surface at the associated geographic location is designated as a ground control point. Location information associated with the designated surface is stored. The stored location information is provided to an outside system for storage.

Abstract: Methods, systems and apparatus, for an unmanned aerial vehicle electromagnetic avoidance and utilization system. One of the methods includes obtaining a flight package indicating a flight pattern associated with inspecting a structure, the flight pattern causing the UAV to remain at a standoff distance from the structure, wherein the standoff distance is based on an electromagnetic field associated with the structure, and wherein the flight pattern is laterally constrained according to a property geofence associated with a right of way of the structure. The UAV is navigated according to the flight pattern, and the UAV captures images of the structure. For an initial portion of the flight pattern, the UAV navigates at an altitude based on the standoff distance and the property geofence towards the structure. The UAV determines a location at which to capture images of the structure, and the UAV provides the captured images to a user device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for ground control point assignment and determination. One of the methods includes receiving information describing a flight plan for the UAV to implement, the flight plan identifying one or more waypoints associated with geographic locations assigned as ground control points. A first waypoint identified in the flight plan is traveled to, and an action to designate a surface at the associated geographic location is designated as a ground control point. Location information associated with the designated surface is stored. The stored location information is provided to an outside system for storage.