An unmanned aerial vehicle is described and includes a computer carried by the unmanned aerial vehicle to control flight of the unmanned aerial vehicle and at least one sensor. The unmanned aerial vehicle is caused to fly to a specific location within a facility, where the unmanned aerial vehicle enters a hover mode, where the unmanned aerial vehicle remains in a substantially fixed location hovering over the specific location within the facility and sends raw or processing results of sensor data from the sensor to a remote server system.

A long-distance drone having a main body, a left hind wing, a right hind wing, a left forewing, and a right forewing. There is a left linear support connecting the left forewing to the left hind wing, and a right linear support connecting the right forewing to the right hind wing. A plurality of propellers are disposed on the left and the right linear supports.

Provided is a smart surveillance system that includes one unmanned aerial vehicle (UAV), a plurality of Internet of Things (IoT) terminals distributed in a surveillance area, and a plurality of base stations distributed in the surveillance area, wherein the UAV selects any IoT terminal from among the plurality of IoT terminals using deep learning auction training, receives surveillance data from the selected IoT terminal, and transmits the surveillance data to a data center through the Internet and any one base station among the plurality of base stations.

Systems and methods for providing UAV-based digital escort drones in visitor management and access control systems are provided. A visitor management and access control system can identify a need for escorting a visitor through the region and transmit a signal to a drone that identifies a starting location and a destination location in the region. Responsive to receiving the signal, the drone can escort the visitor along a path from the starting location to the destination location, and an access privilege device carried by the drone can open a secured door or access a secured area along the path.

A power station inspection system and a power station inspection method are disclosed. A power station inspection system includes an unmanned aerial vehicle, and an unmanned aerial vehicle flight controller, a central controller, and at least two types of data collection terminals that are disposed on the unmanned aerial vehicle. The central controller is configured to control the unmanned aerial vehicle flight controller, so that the unmanned aerial vehicle flight controller controls flight of the unmanned aerial vehicle. The central controller is further configured to control the at least two types of data collection terminals to collect at least two types of component image data of a power station component in a flight process of the unmanned aerial vehicle.

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.

A solar-powered fire tower structure has an array of solar panels positioned to provide power to the tower, one or more cameras to receive power from the solar panels, and a communications link to provide communication from the fire tower. A fire-retardant projectile has a casing of having a standardized size, a payload of a fire-retardant material, and a firing mechanism to propel the projectile out of a barrel.

A long-distance drone having a main body, a left hind wing, a right hind wing, a left forewing, and a right forewing. There is a left linear support connecting the left forewing to the left hind wing, and a right linear support connecting the right forewing to the right hind wing. A plurality of propellers are disposed on the left and the right linear supports.

A goal of the disclosure is to provide real-time adjustment of a deep learning-based tracking system to track a moving individual without using a labeled set of training data. Disclosed are systems and methods for tracking a moving individual with an autonomous drone. Initialization video data of the specific individual is obtained. Based on the initialization video data, real-time training of an input neural network is performed to generate a detection neural network that uniquely corresponds to the specific individual. Real-time video monitoring data of the specific individual and the surrounding environment is captured. Using the detection neural network, target detection is performed on the real-time video monitoring data and a detection output corresponding to a location of the specific individual within a given frame of the real-time video monitoring data is generated. Based on the detection output, first tracking commands are generated to maneuver and center the camera on the location of the specific individual.

An information processing device 1 includes a feature detection unit 28 for detecting, from a construction image acquired by an imaging device by capturing an image of a construction that includes a plurality of unit structures respectively having identical or similar external structures, a feature relating to the external structures, and a unit structure estimation unit 29 for estimating parts of the construction image that correspond respectively to the plurality of unit structures included in the construction on the basis of a plurality of the detected features.