First and second movers can make communication with each other by means of a communication system in which a signal-receiving unit of the first mover receives from a satellite a signal indicative of a position coordinate of itself, a control unit of the first mover makes a pattern indicative of a position coordinate of the first mover, a display unit of the first mover displays the pattern, an image pickup unit of the second mover photographs the pattern, and a control unit of the second mover deciphers the thus photographed pattern to thereby control a position of the second mover in accordance with the thus deciphered pattern.

A method for detecting anomalies in a swarm system comprises: collecting first movement data from multiple vehicles moving as a swarm in a first scenario; generating first training data based on positioning data and second training data based on multi-channel inertial sensor data from the first movement data; training a first learning model using the first training data and multiple second learning models using the second training data for each vehicle; receiving real-time second movement data from vehicles moving as a swarm in a second scenario; generating first input data based on positioning data from the second movement data; inputting the first input data into the first learning model to detect abnormal vehicles in real-time; generating second input data for abnormal vehicles based on inertial sensor data from the second movement data; and inputting the second input data into the corresponding second learning model to identify abnormal channels in the inertial measurement unit of abnormal vehicles.

This invention relates to insect-like robots empowered by generative artificial intelligence (Gen-AI), specifically designed to address critical challenges in agriculture and environmental monitoring. The robotic bee, mantis, and dragonfly can autonomously perform essential tasks such as crop pollination, pest control, and detailed farmland inspection. These robots feature lifelike designs with components such as heads with integrated high-resolution cameras, antennae for communication, specialized mouthparts, thoraxes housing CPUs and actuators, and wings with thin-film photovoltaic solar materials. The AI models function as the brains, processing data captured by various sensors to provide real-time guidance and control commands. Leveraging advanced technologies and sustainable power sources, these robotic insect-like robots enhance productivity, sustainability, and efficiency in agricultural practices, contributing to a more secure and eco-friendly future.

Disclosed is a marker allocation method. According to an airport shape and an airport size of an unmanned aerial vehicle airport and a standard shape and a standard size of a takeoff and landing point, a target layout of an unmanned aerial vehicle airport that includes takeoff and landing points is determined. Further, an initial takeoff and landing point is determined from the takeoff and landing points included in the target layout. Markers respectively allocated to the takeoff and landing points are determined from a predetermined marker set that includes markers of different image content, by using the initial takeoff and landing point as a start point, according to a predetermined search algorithm, and with a constraint that similarity between a marker of any one of the multiple takeoff and landing points and markers of other takeoff and landing points in a specified neighborhood thereof is the lowest.

A system comprises a GNSS sensor onboard an aerial vehicle; a monitor warning system (MWS) that determines whether the vehicle is in a GNSS denied environment; and a flight management system that includes a landing guidance module, and a database having location coordinates of landing sites. Onboard vision sensors and a radar velocity system (RVS) communicate with the guidance module. When the MWS determines that the vehicle is in a GNSS denied environment, the guidance module calculates an optimal flight path by receiving image data from the vision sensors; receiving position, velocity and altitude data from the RVS; receiving location coordinates of a landing site; processing the image data, and the position, velocity and altitude data, to determine a location of the vehicle and provide 3D imaging of a route to the landing site; and calculating a flight path angle to the landing site, using vehicle and landing site coordinates.

System and method are disclosed for multi-phase process of automated data capture for photogrammetry and 3D model building of an unknown object (311) in an unknown environment. Planner module (152) generates a flight plan (413) for a camera drone (110) to fly autonomously on a flight path along a virtual polygon grid (302) defined above the target object (311) during a survey phase. Model builder computer (153) receives a point cloud dataset (321) captured by LiDAR sensor on camera drone (301) during survey flight and constructs low resolution 3D mesh (331) of the target object (311). Planner module (152) generates a flight path (413) for camera drone inspection phase with virtual waypoints surrounding the target object (311) at a marginal distance from the surface defined by the low resolution 3D mesh (331). Model builder (153, 163) builds a high resolution 3D model (422) of the target object (311) using photogrammetry processing of high resolution images captured by camera drone (411, 412) during inspection phase.