Collision avoidance is an important issue for unmanned autonomous vehicles (UAVs). As such, UAVs can be outfitted with a simple and inexpensive sensor for use in collision avoidance. The sensor can be attached to a gimbal and can include a RADAR transmit antenna, a RADAR receive antenna, and an optical camera. The RADAR transmit antenna and RADAR receive antenna are part of a RADAR system. The optical camera and the RADAR system are bore sighted to one another by aligning their fields of view. The optical camera captures an image of a target when the RADAR system indicates the target is in the field of view. The RADAR system and image data can be used to determine a target trajectory. The target trajectory can be used to avoid a collision with the target.

Collision avoidance is an important issue for unmanned autonomous vehicles (UAVs). As such, UAVs can be outfitted with a simple and inexpensive sensor for use in collision avoidance. The sensor can be attached to a gimbal and can include a RADAR transmit antenna, a RADAR receive antenna, and an optical camera. The RADAR transmit antenna and RADAR receive antenna are part of a RADAR system. The optical camera and the RADAR system are bore sighted to one another by aligning their fields of view. The optical camera captures an image of a target when the RADAR system indicates the target is in the field of view. The RADAR system and image data can be used to determine a target trajectory. The target trajectory can be used to avoid a collision with the target.

A drone training method includes: inputting a plurality of wind speed components into a corresponding plurality of fuzzy functions, to generate a plurality of wind speed membership values respectively; selecting one from the plurality of wind speed membership values corresponding to each of the wind speed components, and generating a rule value based on the wind speed membership values corresponding to each of the wind speed components; inputting the plurality of wind speed components into one of inference functions, where each rule value corresponds to one of the inference functions as a weight respectively, and calculating a function sum of a plurality of inference functions corresponding to each of the wind speed components; generating a regression model after calculating an error function base on each offset component and the function sum corresponding to each of the wind speed components and optimizing the error function.

A drone training method includes: inputting a plurality of wind speed components into a corresponding plurality of fuzzy functions, to generate a plurality of wind speed membership values respectively; selecting one from the plurality of wind speed membership values corresponding to each of the wind speed components, and generating a rule value based on the wind speed membership values corresponding to each of the wind speed components; inputting the plurality of wind speed components into one of inference functions, where each rule value corresponds to one of the inference functions as a weight respectively, and calculating a function sum of a plurality of inference functions corresponding to each of the wind speed components; generating a regression model after calculating an error function base on each offset component and the function sum corresponding to each of the wind speed components and optimizing the error function.

Provided is a method for adaptive mowing control of a mowing robot, the method relates to the technical field of the mowing robot. The method includes: performing block segmentation on a real-time operation environment image into a near-field environment image portion and a far-field environment image portion based on an operation travel speed of a mowing robot and using an effective imaging distance as a segmentation parameter, wherein a maximum operation travel speed is positively proportional to an area proportion of the near-field environment image portion in the real-time operation environment image. The area proportion does not exceed 25%, and the area proportion is related to ambient light intensity. By dividing the real-time operation environment image into the near-field and the far-field environment image portions, the method reduces computing power consumption in processing the real-time operation environment image.

Provided is a method for adaptive mowing control of a mowing robot, the method relates to the technical field of the mowing robot. The method includes: performing block segmentation on a real-time operation environment image into a near-field environment image portion and a far-field environment image portion based on an operation travel speed of a mowing robot and using an effective imaging distance as a segmentation parameter, wherein a maximum operation travel speed is positively proportional to an area proportion of the near-field environment image portion in the real-time operation environment image. The area proportion does not exceed 25%, and the area proportion is related to ambient light intensity. By dividing the real-time operation environment image into the near-field and the far-field environment image portions, the method reduces computing power consumption in processing the real-time operation environment image.

A vertical takeoff and landing vehicle which includes an allocation block that receives a set of desired forces or desired moments and a health metric associated with at least one of: (1) a motor controller or (2) a rotor that operates in a vertical takeoff and landing mode at least some of the time. A command signal is determined per a first manner that attempts to satisfy both the set of desired forces or desired moments and the health metric. If the command signal is unable to be determined in the first manner, a second manner is used that prioritizes flight control associated with one or more of a roll axis or a pitch axis over flight control associated with a yaw axis where the axes are mutually orthogonal. The command signal is output to the motor controller that controls the rotor using the command signal.

An unmanned vehicle management system according to an aspect includes: a collection unit configured to collect video data acquired by an unmanned vehicle and natural disaster data related to natural disasters from information sources; a storage unit configured to store the video data and the natural disaster data; an analysis unit configured to extract feature amounts of the video data and the natural disaster data, and predict a high-risk area where a risk of natural disaster occurrence is higher than in other areas; a prediction unit configured to compare the video data and the natural disaster data collected during a disaster with the video data and the natural disaster data collected during normal times, and predict a disaster occurrence area where a disaster will occur; and a deployment unit configured to determine deployment of the unmanned vehicle and a rescuer based on the high-risk area and the disaster occurrence area.

An unmanned vehicle management system according to an aspect includes: a collection unit configured to collect video data acquired by an unmanned vehicle and natural disaster data related to natural disasters from information sources; a storage unit configured to store the video data and the natural disaster data; an analysis unit configured to extract feature amounts of the video data and the natural disaster data, and predict a high-risk area where a risk of natural disaster occurrence is higher than in other areas; a prediction unit configured to compare the video data and the natural disaster data collected during a disaster with the video data and the natural disaster data collected during normal times, and predict a disaster occurrence area where a disaster will occur; and a deployment unit configured to determine deployment of the unmanned vehicle and a rescuer based on the high-risk area and the disaster occurrence area.

Embodiments of the present application provide a method, device, storage medium, and electronic device for controlling flight equipment, wherein the method includes: acquiring positioning position information from a positioning system deployed on a target flight equipment; detecting an operating state of the positioning system according to positioning position information, wherein the operating state comprises: normal state and abnormal state; when the operating state is an abnormal state, controlling the target flight equipment to return to a ground control terminal according to the relative position information between the target flight equipment and the ground control terminal of the target flight equipment.