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.

Systems, methods, and devices that can be used to augment and address various deficiencies such as vision system impairment in autonomous robotic systems are described herein. A system may include at least one sensing device that is used to monitor data and trigger corrective operations in response to detected low visibility or obstructed conditions such as a sun glare condition.

The present disclosure provides a method for docking a self-moving device with a charging station, wherein the charging station is connected to a boundary line, and the method comprises the following steps: controlling the self-moving device to move from the current position close to a docking boundary; judging whether the self-moving device senses the boundary line signal during the moving process; if the self-moving device senses the boundary line signal before it reaches the docking boundary or when it reaches the docking boundary, controlling the self-moving device to move towards the charging station through the boundary line signal until the docking is successful; if the self-moving device has not sense the boundary line signal when it reaches the docking boundary, controlling the self-moving device to move from the docking boundary to the boundary line until the boundary line signal is sensed. The present disclosure sets the docking boundary and controls the self-moving device to move close to the docking boundary to find the boundary line, thereby improving the regression efficiency of the self-moving device.

An acquisition processing part acquires a captured image from a camera which is installed on a work vehicle. A detection processing part detects an obstacle on the basis of the captured image which is acquired by the acquisition processing part. When an obstacle is detected by the detection processing part, a reception processing part receives a traveling stop instruction for stopping automatic traveling of the work vehicle or a traveling continuation instruction for continuing automatic traveling of the work vehicle. A traveling processing part stops the automatic traveling of the work vehicle when the reception processing part receives the traveling stop instruction, and continues the automatic traveling of the work vehicle when the reception processing part receives the traveling continuation instruction.

This disclosure describes monitoring and operating subsea well systems, such as to perform operations in the construction and control of targets in a subsea environment. A submerisble ROV that performs operations in the construction and control of targets (e.g., well completion components) in a subsea environment, the ROV has one or more imaging devices that capture data that is processed to provide information that assists in the control and operations of the ROV and/or well completion system while the ROV is subsea.

Disclosed are a method and apparatus for detecting a near-field object, a medium and an electronic device. In the present disclosure, the characteristics of an automatic exposure apparatus before and after light supplement of a light supplement lamp are used, two images are shot in the same direction before and after light supplement of the light supplement lamp, and whether the near-field object exists is determined through comparison of the two images. Without adding additional apparatuses, the task of discovering the near-field objects by a self-walking device is completed by using the existing apparatus, and the collision between the self-walking device and the near-field object is avoided.

System and method for taking inventory of a plurality of objects within a structure. The method is executed by a controller of an autonomous mobile robot and comprises causing the said robot to navigate through at least a portion of the structure, causing at least one camera of the robot to acquire a plurality of positioning images at a first resolution and determining that at least one positioning image contains an image of a predetermined landmark. In response to determining that the at least one positioning image contains the image of the predetermined landmark, the autonomous mobile robot navigates to a predetermined data collection position, the at least one camera of the autonomous mobile robot acquires at least one inventory image at a second resolution, the second image resolution being greater than the first resolution, and a plurality of inventory labels are extracted from the at least one inventory image.

A robot includes: at least one sensor configured to detect an external environment within a viewing zone of the at least one sensor; at least one memory storing information on a travel space including a privacy protection zone; and at least one processor configured to: identify whether the viewing zone of the at least one sensor will be within a predetermined distance from the privacy protection zone while the robot travels along a travel path in the travel space, based on identifying that the viewing zone of the at least one sensor will be within the predetermined distance, determine whether the viewing zone of the at least one sensor will overlap with the privacy protection zone based on the travel path, and based on determining that the viewing zone of the at least one sensor will overlap with the privacy protection zone, change a heading direction of the robot from a first heading direction to a second heading direction to prevent the viewing zone of the at least one sensor from overlapping with the privacy protection zone.

A system for determining a crop edge and a self-propelled harvester using the system for automatic control are disclosed. The system comprises a camera that generates optical information of a front environment of the harvester. The system further includes a computing unit that analyzes the images using artificial intelligence so that a planted area of a field on which a plant crop is located may be delimited from a remaining residual area of the field, thereby determining the plant crop. In turn, the computing unit is further configured to determine the crop edge of the plant crop based on the determination of the plant crop and to automatically control the harvester based on the determination of the crop edge.

Provided is a mobile object control device including a storage medium storing a computer-readable command and a processor connected to the storage medium, the processor executing the computer-readable command to: acquire a photographed image, which is obtained by photographing surroundings of a mobile object by a camera mounted on the mobile object, and an input instruction sentence, which is input by a user of the mobile object; detect a stop position of the mobile object corresponding to the input instruction sentence in the photographed image by inputting at least the photographed image and the input instruction sentence into a trained model including a pre-trained visual-language model, the trained model being trained so as to receive input of at least an image and an instruction sentence to output a stop position of the mobile object corresponding to the instruction sentence in the image; and cause the mobile object to travel to the stop position.