Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are described for performing automated mapping of sensors at a location of a property. A monitoring server of a system for monitoring a property obtains mapping information that indicates navigable areas at the property. A drone that communicates with the monitoring server is used to navigate the property. In response to the drone navigating the property, sensors and their respective location at each navigable areas are identified based on the mapping information. The monitoring server associates sensors at each area with a corresponding location of the sensor in a data model of the property. Labels descriptive of the respective sensors are generated based on the location of the identified sensors. The monitoring server determines a mapping of a label to a respective sensor associated with the data model of the property.

Abstract: Methods, systems, and apparatus for drone navigation within a property. A method includes detecting an obstacle in a navigation path of a drone, determining a classification of the obstacle, determining whether to temporarily land based on the classification of the obstacle, and temporarily landing the drone until the obstacle clears the navigation path of the drone.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for receiving a request to deploy an aerial drone to assist an emergency vehicle from a first location to a second location; determining a route to be traversed by the emergency vehicle from the first location to the second location based on the request; and deploying the aerial drone to traverse the route in advance of the emergency vehicle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for drone-assisted thermal monitoring. One of the methods includes determining a first temperature measurement at a first location of a property, navigating from the first location to a second location of the property, determining a second temperature measurement at the second location, generating a thermal model for the property based on the first temperature measurement and the second temperature measurement, and providing the thermal model for output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for receiving a request to deploy an aerial drone to assist an emergency vehicle from a first location to a second location; determining a route to be traversed by the emergency vehicle from the first location to the second location based on the request; and deploying the aerial drone to traverse the route in advance of the emergency vehicle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sensor timing correlation. One of the methods includes obtaining (i) first sensor data from a first sensor and (ii) second sensor data from a second sensor; detecting a representation of an object in both the first sensor data and the second sensor data; determining a predicted physical distance between a first representation of the object in the first sensor data and a second representation of the object in the second sensor data; determining a timing offset between the different sensors using the predicted physical distance between the first representation of the object and the second representation of the object; and adjusting, using the timing offset, subsequent data from the first sensor or the second sensor.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for drones. In some implementations, a method may include obtaining an image of an electrical device; determining a power source of the electrical device based on the image of the electrical device; determining whether the power source of the electrical device is capable of charging a drone based on the image of the electrical device; and based on determining that the power source of the electrical device is capable of charging the drone based on the image of the electrical device, charging the drone with the power source.

Abstract: Methods, systems, and apparatus for drone landing ground station. A method includes determining that a drone is landing on a ground station, based on determining that the drone is landing on the ground station, determining a magnetic field to generate at a first magnetic component at a first position in the ground station and an opposing magnetic polar at a second magnetic component at a second position in the ground station, and generating the magnetic field at the first magnetic component and the opposing magnetic field at the second magnetic component.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for robot navigation. One of the methods includes obtaining one or more images of an area from a robot; detecting two or more lines within the one or more images; identifying at least two of the two or more lines as vanishing lines; determining, using the vanishing lines, a correction maneuver; and controlling the robot to implement the correction maneuver.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining that current data captured at a current location of a drone satisfies localization adjustment criteria; in response to determining that the current data captured at the current location of the drone satisfies the localization adjustment criteria, identifying previously captured image data; determining a previous expected location of the drone based on both an expected change in location of the drone and a first previous location determined from other image data captured before the previously captured image data; determining a location difference between the previous expected location of the drone and a second previous location determined from the previously captured image data; and determining the current location of the drone based on the location difference.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for a mobile docking station. In some implementations, a method for a mobile docking station includes receiving a service request from a first user; determining assignment details based on the service request; determining a plurality of devices to send to a location based on the assignment details; deploying the plurality of devices to the location; receiving data from a first device of the plurality of devices; based on the data, scheduling a pickup of the first device; and deploying a second device for the pickup of the first device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for estimating a robot pose. One of the methods includes the actions of obtaining two or more images captured at two or more locations on a property; detecting feature points at positions within two or more images including first feature points in the first image and second feature points in the second image; comparing the positions of the first feature points in the first image to positions of the second feature points in the second image; obtaining data indicating the two or more locations on the property; comparing the two or more locations; and generating depth data for the feature points for use by a robot navigating the property.

Abstract: Methods, systems, and apparatus for drone-assisted sensor mapping are disclosed. A method includes detecting a sensor in a detection area of a drone; based on detecting the sensor in the detection area of the drone, detecting the drone in sensor data captured by the sensor; determining a detection area of the sensor based on movement of the drone after the drone is detected; and determining a destination for the drone based on the detection area of the sensor. The method may include mapping boundaries of the detection area of the sensor to a map of an area where the sensor is located. The sensor can be a passive infrared sensor, an active infrared sensor, a radar sensor, a sonar sensor, a time of flight sensor, a structured light sensor, or a lidar sensor.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for an ultrasonic sensor. One of the systems includes a first ultrasonic assembly that includes a first waveguide formed by a first monolithic body, and a first ultrasonic transducer mounted to the first waveguide, wherein the first monolithic body includes a first mounting surface adapted to couple to the first ultrasonic transducer and a first coupling surface adapted to couple to an outer surface of a pipe; and a second ultrasonic assembly that includes a second waveguide formed by a second monolithic body, and a second ultrasonic transducer mounted to the second waveguide, wherein the second monolithic body includes a second mounting surface adapted to couple to the second ultrasonic transducer and a second coupling surface adapted to couple to the outer surface of the pipe.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for assistive robotic manipulation of building controls. In some implementations, a method includes obtaining sensor data from a property at a first time; obtaining sensor data from the property at a second time; determining whether the sensor data from the first time and the second time satisfy a criteria; in response to determining the criteria is satisfied, generating a mapping between an interface and a device; and providing the mapping to a robot for activating the device.

Abstract: Methods, systems, and apparatus a drone for installing sensors. A method includes determining to emulate a view of a camera at a particular location with a drone, deploying the drone to the particular location, obtaining an image captured by a drone, and emulating the view of the camera with the image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for navigation using planar landmarks. In some implementations, images depicting an area of a property captured by a camera are obtained. Landmarks in the area are identified based on the images. An expected stability for each of the landmarks are determined. A map for the area is generated based on the expected stability for each of the landmarks. The map is transmitted to one or more electronic devices.

Abstract: A monitoring system that is configured to monitor a property is disclosed. The monitoring system includes a passive infrared (PIR) sensor configured to generate reference PIR data that represents motion within an area of the property; an auxiliary sensor configured to generate auxiliary sensor data that represents an attribute of the area of the property; and a motion sensor device. The motion sensor device is configured to: obtain the reference PIR data; determine that a first set of motion detection criteria is satisfied by the reference PIR data; in response to determining that the first set of motion detection criteria is satisfied by the reference PIR data, obtain the auxiliary sensor data; obtain a second set of motion detection criteria based on the reference PIR data and the auxiliary sensor data; and determine whether the second set of motion detection criteria is satisfied by additional PIR data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for exemplar generation and localization. In some implementations, a method includes obtaining sensor data from a robot traversing a route at a property; determining sampling rates along the route using the sensor data obtained from the robot; selecting images from the sensor data as exemplars for robot localization using the sampling rates along the route; determining that a second robot is in a localization phase at the property; and providing representations of the exemplars for robot localization to the second robot.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for robotic building inspection. In some implementations, one or more data objects that specify one or more requirements for a property are accessed. Sensor data of the property is obtained using a drone or other robotic device that has one or more sensors. A map is generated from the sensor data. An issue with the property is identified by comparing the map with the one or more data objects. A notification is generated based on the comparison where the notification includes an indication of the issue. The notification is transmitted to a computing device of a user.