Visual control method and device for underwater unmanned underwater vehicle, and medium

Abstract

The embodiment of the invention provides a visual control method and device for an underwater unmanned underwater vehicle, and a medium, and the method comprises the steps: responding to a first operation for a BIM model, and generating siltation blocking position information; controlling the unmanned underwater vehicle to travel to a first area along a first path according to the deposition and blockage position information and the underwater position information of the unmanned underwater vehicle; detecting real-time position information of the unmanned underwater vehicle in the first area through a sonar sensor with a preset layout; according to the real-time position information and first video information and first sonar map information acquired by the unmanned underwater vehicle in real time, the unmanned underwater vehicle is controlled to travel to a siltation area indicated by the siltation blocking position information along a second path; and controlling the unmanned underwater vehicle to clean deposits in the deposition area. Through visual display and control of the BIM model terminal, the cleaning error of the unmanned underwater vehicle can be timely handled and timely processed, so that the cleaning effect is improved.

Description

Technical Field

[0001] This invention relates to, but is not limited to, the field of underwater vehicle control technology, and particularly to a visual control method, device, and medium for an unmanned underwater vehicle. Background Technology

[0002] The tailrace gates and trash racks of hydroelectric power stations are prone to accumulating silt, stones, branches, and other debris, which can obstruct the opening and closing of the gates and even damage them. Therefore, regular cleaning of the accumulated debris can ensure smooth gate operation and reduce the failure rate.

[0003] Currently, underwater cleaning robots are prone to errors due to environmental and signal interference when cleaning up silt. When these errors occur, they are difficult to handle in a timely manner, resulting in poor cleaning performance. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0005] The main objective of this invention is to provide a visual control method, device, and medium for underwater unmanned submersibles, which can promptly handle cleaning errors of the unmanned submersible and improve the cleaning effect of underwater sediment.

[0006] In a first aspect, embodiments of the present invention provide a visual control method for an underwater unmanned submersible, applied to a hydropower management system. The hydropower management system is equipped with a visual terminal, which displays a BIM model of a hydropower station. The BIM model is equipped with sonar sensors arranged in a pre-defined layout. The method includes: In response to the first operation on the BIM model, siltation and blockage location information is generated, which is obtained by sonar sensors in the preset layout; Based on the siltation and blockage location information and the unmanned underwater vehicle's launch location information, the unmanned underwater vehicle is controlled to travel along a first path to a first area, where the first area represents the detection range of the sonar sensors in the preset layout. The real-time position information of the unmanned underwater vehicle in the first area is detected by the sonar sensors in the preset layout. Based on the real-time location information and the first video information and first sonar map information acquired by the unmanned underwater vehicle in real time, the unmanned underwater vehicle is controlled to travel along the second path to the siltation area indicated by the siltation blockage location information. Control the unmanned underwater vehicle to clear the silt from the silted-up area.

[0007] In some optional embodiments, after generating the siltation and blockage location information, the method further includes: When the current siltation location indicated by the siltation blockage location information overlaps with the historical siltation location, historical path and historical obstacle information are obtained. The historical path represents the travel path of the unmanned underwater vehicle when clearing the historical siltation location, and the historical obstacle information represents the obstacles on the historical path. The first path is determined based on the historical path, historical obstacle information, and the first information obtained by the unmanned underwater vehicle; If there is no overlap between the current siltation location and the historical siltation location, obtain obstacle map information on the BIM model. The obstacle map information indicates the location, type, and size of obstacles in each area of ​​the BIM model. The first path is determined based on the obstacle map information, the launch location information, the current siltation location, and the second information obtained by the unmanned underwater vehicle. Both the first and second information include sonar information, video information, and hydrological information.

[0008] In some optional embodiments, controlling the unmanned underwater vehicle (UUV) to travel along a first path to a first area based on the siltation blockage location information and the UUV's launch location information includes: If the current siltation location indicated by the siltation blockage location information overlaps with the historical siltation location, the historical path will be configured as the first target path. The unmanned underwater vehicle is controlled to travel along the first target path, and during the travel, it acquires second sonar map information, first hydrological information and second video information in real time; The first real-time obstacle information on the first target path is determined based on the second sonar map information and the second video information; The first obstacle difference information is obtained by comparing the historical obstacle information with the first real-time obstacle information; The first path is obtained by correcting the first target path based on the first obstacle difference information and the first hydrological information, so that the unmanned underwater vehicle can travel along the first path to the first area. If the current siltation location indicated by the siltation blockage location information does not overlap with the historical siltation location, a second target path is determined based on the obstacle map information, the drainage location information, and the current siltation location. The unmanned underwater vehicle is controlled to travel along the second target path, and during the travel, it acquires third sonar map information, second hydrological information and third video information in real time; The second real-time obstacle information on the second target path is determined based on the third sonar map information and the third video information; The obstacle map information is compared with the second real-time obstacle information to obtain the second obstacle difference information; The first path is obtained by correcting the second target path based on the second obstacle difference information and the second hydrological information, so that the unmanned underwater vehicle can travel along the first path to the first area.

[0009] In some optional embodiments, the step of obtaining the first path after correcting the first target path based on the first obstacle difference information and the first hydrological information includes: If the historical obstacle to be avoided on the first road segment representing the first target path is eliminated, the first road segment is changed to a straight road segment, which passes through the area where the eliminated historical obstacle is located; If an obstacle is added to the second segment of the first target path represented by the first obstacle difference information, the minimum detour segment at both ends of the second segment is determined according to the type and size of the added obstacle, and the second segment is changed to the minimum detour segment. The first path is obtained by correcting the first target path based on the water flow velocity and direction represented by the first hydrological information.

[0010] In some optional embodiments, the step of obtaining the first path after correcting the first target path based on the water flow velocity and direction represented by the first hydrological information includes: If the water flow velocity is less than a first velocity threshold, the first target path is configured as the first path; When the water flow velocity is greater than a first velocity threshold and the angle between the water flow direction and the first target path is an acute angle, a first curved path is set according to the water flow direction, the water flow velocity and the first angle, and the first curved path is configured as the first path so that the path trajectory of the unmanned underwater vehicle when traveling along the first curved path coincides with the first target path; When the water flow velocity is greater than the first velocity threshold and the second angle between the water flow direction and the first target path is an obtuse angle, a second curved path is set according to the water flow direction, the water flow velocity and the second angle, and the second curved path is configured as the second path, wherein the second curved path is perpendicular to the water flow direction.

[0011] In some optional embodiments, controlling the unmanned underwater vehicle (UUV) to travel along a second path to the siltation area indicated by the siltation blockage location information based on the real-time location information and the first video information and first sonar map information acquired by the UUV in real time includes: The unmanned underwater vehicle is displayed in real time on the BIM model based on the real-time location information, and a third target path is planned on the BIM model based on the obstacle map information, the real-time location information, and the current siltation location. The third real-time obstacle information on the third target path is determined based on the first sonar map information and the first video information; The second path is obtained by correcting the third target path based on the third real-time obstacle information and the third hydrological information on the third target path; The unmanned underwater vehicle is controlled to travel along the second path to the siltation area indicated by the siltation blockage location information, and the current siltation location is located within the siltation area.

[0012] In some optional embodiments, controlling the unmanned underwater vehicle to clear silt from the silted area includes: The unmanned underwater vehicle is controlled to acquire sonar imagery and video information of the siltation area. The first location of the sediment is determined based on the two-dimensional sonar information in the sediment sonar map information. The first contour information of the sediment is determined based on the three-dimensional sonar information in the sediment sonar map information; After correcting the first siltation location based on the siltation video information, the target siltation location is obtained; after correcting the first contour information, the siltation contour information is obtained; and the siltation type information is identified. The size information of the silt is determined based on the siltation video information corresponding to the target siltation location and the preset trash rack size information; A cleaning plan is determined based on the silt size information, the silt outline information, the target silt location, and the silt type information. According to the cleaning plan, the unmanned underwater vehicle is controlled to clean up the silt at the target siltation location.

[0013] In some optional embodiments, determining the cleaning plan based on the silt size information, the silt outline information, the target silt location, and the silt type information includes: Based on the target siltation location, determine the first cleaning priority corresponding to the siltation located at different locations; The second cleaning priority corresponding to sludge of different sizes and shapes is determined based on the sludge size information and the sludge outline information; Based on the information on the type of silt, a third cleaning priority is determined for different types of silt. Obtain the first weight coefficient corresponding to the first cleanup priority, the second weight coefficient corresponding to the second cleanup priority, and the third weight coefficient corresponding to the third cleanup priority; The first target priority is determined based on the first cleanup priority, the second cleanup priority, the third cleanup priority, the first weight coefficient, the second weight coefficient, and the third weight coefficient; The correlation coefficients between various sediments were determined using network analysis. The second target priority is obtained by correcting the first target priority based on the correlation coefficient. Configure the priority of the second target to the cleanup order corresponding to the cleanup scheme.

[0014] In a second aspect, embodiments of the present invention provide a visualization control device for an underwater unmanned submersible, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the visualization control method for the underwater unmanned submersible described in the first aspect.

[0015] Thirdly, a computer storage medium stores computer-executable instructions, which are used to execute the visualization control method for the underwater unmanned submersible described in the first aspect.

[0016] The beneficial effects of this invention include: in response to a first operation on the BIM model, generating siltation and blockage location information, which is obtained by sonar sensors in a preset layout; controlling the unmanned underwater vehicle (UUV) to travel along a first path to a first area based on the siltation and blockage location information and the UUV's launch location information, where the first area represents the detection range of the sonar sensors in the preset layout; detecting the real-time location information of the UUV in the first area using the sonar sensors in the preset layout; controlling the UUV to travel along a second path to the siltation area indicated by the siltation and blockage location information based on the real-time location information and the first video information and first sonar map information acquired by the UUV in real time; and controlling the UUV to clear silt in the siltation area. In this embodiment, the real-time position of the unmanned underwater vehicle (UUV) is visually presented through the BIM model of the hydropower station. The location of siltation is obtained based on the pre-laid sonar sensors, thereby improving the accuracy of siltation location and ensuring the accuracy of the path planned on the BIM model. Furthermore, the environmental information is determined in real time through the sonar and video information acquired by the UUV, and the UUV is located in real time through the pre-laid sonar sensors, thereby precisely controlling the UUV to complete the siltation removal. Moreover, through the visualization and control on the BIM model, errors in the UUV's removal can be responded to and processed in a timely manner, thereby improving the removal effect.

[0017] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of a system platform architecture for executing a visual control method for an underwater unmanned submersible, according to an embodiment of the present invention; Figure 2 This is a flowchart of a visual control method for an underwater unmanned submersible provided in one embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the generation of a first curve path according to an embodiment of the present invention; Figure 4 This is a schematic diagram illustrating the generation of a second curve path according to an embodiment of the present invention; Figure 5 This is a visualization interface diagram of a BIM model provided in one embodiment of the present invention.

[0019] Figure label: The system platform architecture is 1000, the processor is 1100, and the memory is 1200. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0021] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0022] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0023] like Figure 1 As shown, Figure 1 This is a schematic diagram of a system platform architecture for executing a visual control method for an underwater unmanned submersible, according to an embodiment of the present invention.

[0024] exist Figure 1 In the example, the system platform architecture 1000 includes a processor 1100 and a memory 1200, which can be connected via a bus or other means. Figure 1 Taking the example of a connection between China and Israel via a bus.

[0025] Memory 1200, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory 1200 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 1200 may optionally include memory remotely located relative to processor 1100, and these remote memories can be connected to the solid-state device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0026] Those skilled in the art will understand that the system platform architecture 1000 can be applied to 5G communication network systems and subsequent evolved mobile communication network systems, etc., and this embodiment does not specifically limit it.

[0027] It will be understood by those skilled in the art that Figure 1The system platform architecture 1000 shown does not constitute a limitation on the embodiments of the present invention. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0028] This application provides a visual control method, device, and medium for underwater unmanned submersibles, which will be described in detail in the following embodiments.

[0029] like Figure 2 As shown, this embodiment of the invention provides a visual control method for an underwater unmanned submersible, applied to a hydropower management system. The hydropower management system is equipped with a visualization terminal, which displays a BIM model of a hydropower station. The BIM model has a layout interface for pre-defined sonar sensors. Through this layout interface, a comprehensive judgment can be made based on the interference from other equipment and the environment affecting the hydropower station, as well as the historical sensor layout detection data, thereby generating a relatively reasonable sensor layout scheme. Multiple sonar sensors are placed at different locations on the BIM model to improve the accuracy of the sonar sensor placement, thus enhancing the correctness of siltation detection.

[0030] It should be noted that the sonar sensor can be installed inside or outside the BIM model; this embodiment does not impose any specific limitations on it.

[0031] It should be noted that the multiple sonar sensors in the preset layout can be evenly distributed or distributed in different areas according to the actual layout requirements. This embodiment does not impose any specific limitations on this.

[0032] Applied to the aforementioned hydraulic management system, a visual control method for an underwater unmanned submersible includes steps S100, S200, S300, S400, and S500.

[0033] Step S100: In response to the first operation on the BIM model, generate siltation and blockage location information, which is obtained by sonar sensors in the preset layout. Step S200: Based on the siltation and blockage location information and the unmanned underwater vehicle's launch location information, control the unmanned underwater vehicle to travel along the first path to the first area, where the first area represents the detection range of the sonar sensors in the preset layout; Step S300: Detect the real-time position information of the unmanned underwater vehicle in the first area using the sonar sensors in the preset layout; Step S400: Based on the real-time location information and the first video information and first sonar map information acquired by the unmanned underwater vehicle in real time, control the unmanned underwater vehicle to travel along the second path to the siltation area indicated by the siltation blockage location information; Step S500: Control the unmanned underwater vehicle to clear the silt in the siltation area.

[0034] Specifically, the unmanned underwater vehicle of this application is equipped with sonar equipment, a cutting device, a gripping device, and a video recording device. The sonar equipment can acquire surrounding sonar information in real time, thereby generating corresponding sonar map information. The video recording device can acquire surrounding video information in real time, and then, based on the video information and sonar map information, it can identify obstacles and silt to be cleared. The equipped cutting device can cut silt such as trees, and the gripping device can grasp silt such as trees, stones, and plastics. For trees that are difficult to cut and large stones, other clearing devices can be used for assistance, or ropes can be tied to large silt for assistance with ground-based devices, etc. The specific clearing method is not limited here.

[0035] On the BIM model of the hydropower station on the visualization terminal, performing operations such as siltation detection (e.g., clicking the button to start underwater sonar detection, selecting the reservoir area / trash rack area to be detected) is the first operation. The sonar sensors pre-positioned on the BIM model (their actual installation locations and detection ranges are marked in the BIM model, such as the bottom of the reservoir, around the inlet, and both sides of the trash rack) synchronously start underwater detection upon receiving the command, acquiring sonar maps of the underwater environment through sound wave reflection. The system analyzes the sonar maps, identifies siltation areas with abnormal reflection signals (high silt density, strong sound wave reflection, forming bright areas), and automatically marks the actual physical location of the siltation area on the BIM model of the visualization terminal using the three-dimensional coordinate system of the BIM model; this intuitively presents the specific siltation areas and the locations of siltation blockages.

[0036] The launch location of the unmanned underwater vehicle (UUV) (such as a hydroelectric power station dock launch platform or dedicated launch port) is marked on the BIM model as the starting point. Simultaneously, the first area (the edge of the pre-defined sonar sensor's detection range, such as the area 10m from the nearest sonar sensor) is also marked on the BIM model. Combining the underwater topography (such as reservoir depth distribution and reef locations) and fixed structures (such as dams, water pipelines, and diversion tunnels) in the BIM model, an optimal first path from the launch location to the first area is automatically planned. On the BIM model of the visualization terminal, the UUV's icon (bound to inertial navigation data) can be seen in real time traveling along the first path, with the path trajectory displayed as dynamic lines. If the UUV deviates slightly from the path due to water currents, the system will automatically fine-tune the path instructions to ensure it ultimately reaches the first area.

[0037] Once the unmanned underwater vehicle (UUV) enters the first area, multiple sonar sensors pre-installed on the BIM model operate synchronously. The UUV's onboard sonar transponder receives the acoustic signals emitted by the sensors and immediately responds. The system combines the known coordinates of multiple sonar sensors (calibrated in the BIM model) and calculates the UUV's real-time 3D coordinates using triangulation (or time difference positioning). The UUV's icon position is then updated in real-time on the BIM model of the visualization terminal, providing intuitive monitoring. While navigating the first area, the UUV simultaneously activates its onboard high-definition camera and sonar equipment to acquire first-hand video information (underwater real-world footage) and first-hand sonar imagery information (close-range environmental detection data). This data is then transmitted back to the visualization terminal for simultaneous observation of the underwater real-world scene and local sonar images, supplementing the environmental details of the BIM model. Based on the acquired data, a second path from the current real-time location to the siltation area is automatically planned on the BIM model. If the visualization terminal shows that the UUV deviates from the second path, the system automatically generates a correction command, which is sent to the UUV via sonar sensors or radio signals to adjust its direction.

[0038] The unmanned underwater vehicle (UUV) is controlled to move along a second path. During the journey, the UUV simultaneously activates a high-definition camera (or other video and image acquisition devices, which are not limited here) and hydrological sensors (a set of sensors that collect various hydrological data such as water temperature and current velocity; the specific sensor type and number are set according to requirements and are not limited here). It continuously collects image and hydrological information to supplement the real-time underwater environment information. The image information can identify small obstacles not detected by sonar (such as protruding bolts or gravel), whether the grid structure is deformed, scattered small debris on the path, and the appearance of the debris. The hydrological information can determine the real-time water flow direction (with or against the current), current velocity, and whether there is turbulence on the path, while also determining data such as water turbidity and temperature. Combining the collected image and hydrological data, the second path is optimized to control the UUV to accurately reach the silted-up area.

[0039] After the unmanned underwater vehicle arrives at the siltation area, it obtains detailed information about the silt (such as size, outline, and type) through its own equipment. The system automatically formulates a cleaning strategy (such as using mechanical grippers to pick up small stones and using cutting tools to remove tangled branches) and displays the cleaning plan and steps on a visual terminal.

[0040] The unmanned underwater vehicle (UUV) performs cleaning operations according to the cleaning strategy (such as gripping, cutting, and suction), and the operation process is transmitted back to the visualization terminal in real time via first-level video information. The visualization terminal can clearly see the entire process of the silt being cleaned, and the cleaning progress will be updated synchronously on the BIM model (e.g., 40% of the silt area has been cleaned, and entangled debris has been cut off). If any abnormal situation occurs during the cleaning process (such as loss of UUV attitude control, tool jamming, or sudden change in water flow), the visualization terminal will immediately issue an alarm, and the staff can manually issue instructions to stop the operation and evacuate the safe area. At the same time, the system will continuously monitor the distance between the UUV and the surrounding structures and the force of tool operation to avoid damage to the fence, dam, or UUV. After the UUV completes the cleaning, it will take video and sonar images of the silt area again and transmit them back to the visualization terminal. The system compares the data before and after the cleaning, confirms that the silt has been removed to a safe threshold, marks the cleaning as complete on the BIM model, and the UUV returns to the launch point according to the preset path, thus ending the entire cleaning process.

[0041] This application presents all aspects of the process—from locating the blockage and planning the route to the underwater vehicle positioning and cleanup operations—in a visually intuitive BIM model. Through sonar positioning and multi-source data fusion, the route planning is precise, the cleanup strategy is highly targeted, blind operations are avoided, and the cleanup efficiency is high. Furthermore, through visual monitoring and automatic safety threshold control, the risk of equipment damage and cleanup errors is reduced, improving the accuracy and safety of the cleanup.

[0042] In some optional embodiments, after generating the siltation and blockage location information, the method further includes: S110. If the current siltation location indicated by the siltation blockage location information overlaps with the historical siltation location, obtain historical path and historical obstacle information. The historical path represents the travel path of the unmanned underwater vehicle when clearing the historical siltation location, and the historical obstacle information represents the obstacles on the historical path. Specifically, the system retrieves historical siltation location information (three-dimensional coordinates of previously cleared siltation areas); compares the current siltation location information (coordinates of the siltation area detected by sonar this time) with the historical siltation location; if the overlapping area of ​​the coordinate range of the two is greater than 30% (a custom threshold, not specifically limited), it is determined that there is an overlapping location (such as the core part of the current siltation area overlapping with the area cleared last year).

[0043] Retrieve historical path and obstacle information corresponding to the overlapping locations from the database and synchronize it to the BIM model on the visualization terminal.

[0044] S120. Determine the first path based on the historical path, historical obstacle information, and the first information obtained by the unmanned underwater vehicle; Specifically, the first set of information includes sonar information, video information, and hydrological information. Sonar information refers to the initial sonar map (covering the approximate area from the launch point to the first zone) detected by the UAV's own sonar, identifying large obstacles and terrain changes. Video information consists of initial video footage (close-up environmental scenes) captured by a high-definition camera, used to supplement sonar blind spots and identify small obstacles. Hydrological information includes real-time water flow velocity, flow direction, and water turbidity, displayed on the BIM model as dynamic arrows (indicating flow direction) and numerical labels. The system completes data fusion in the visualization terminal backend, corrects historical paths, and generates the first path.

[0045] S130. If there is no overlap between the current siltation location and the historical siltation location, obtain obstacle map information on the BIM model. The obstacle map information indicates the obstacle location, obstacle type, and obstacle size in each area of ​​the BIM model. Specifically, if the overlap area between the coordinate range of the current siltation location and the historical siltation location is less than or equal to 30% (a custom threshold, not specifically limited), it is determined that there is no overlapping location. The system retrieves obstacle map information covering the water release location, the current siltation location, and the entire first area from the hydropower station BIM model and displays it intuitively on the visualization terminal. The obstacle location is accurately marked using 3D coordinates and located on the BIM model using color icons; obstacle types are distinguished by different icons; and the size of the obstacle is indicated by the actual dimensions next to the icon.

[0046] S140. Determine the first path based on the obstacle map information, the launch location information, the current siltation location, and the second information obtained by the unmanned underwater vehicle. The first information and the second information both include sonar information, video information, and hydrological information.

[0047] Specifically, the second information is of the same type as the first information (sonar information, video information, and hydrological information), and the detection range of the second information is the new path area from the launch location to the first area.

[0048] The path generation objective is to achieve the shortest path and safe driving. Combining the BIM obstacle map and second information, a first path is generated. Path constraints are the starting point (water entry point), the ending point (edge ​​of the first area), and the target direction (current siltation location), which are marked on the BIM model. Path selection must maintain a safe distance from obstacles and the turning angle must be ≤90°.

[0049] The system divides the underwater space into 0.1m × 0.1m × 0.1m three-dimensional grids using a raster method. Combined with BIM obstacle maps, it labels passable grids (green) and impassable grids (red). The system uses the A* algorithm to search for the optimal passable grid chain (the grid chain traversed by the optimal path that satisfies the path generation objective and path constraints), generating an initial path, displayed as a blue dashed line on the BIM model. For newly added unlabeled obstacles (such as floating branches), avoidance inflection points are added to the initial path (marked with yellow obstacle icons and blue detour lines on the BIM model). The system is also adapted to hydrological information to reduce speed consumption. Finally, the optimal first passable path is generated.

[0050] In some optional embodiments, controlling the unmanned underwater vehicle (UUV) to travel along a first path to a first area based on the siltation blockage location information and the UUV's launch location information includes: S201. If the current siltation location indicated by the siltation blockage location information overlaps with the historical siltation location, the historical path is configured as the first target path. Specifically, when the current siltation area overlaps with the siltation area that has been cleared in the past, the driving path of the unmanned underwater vehicle during the past clearing (historical path) is directly configured as the first target path, reusing the verified basic driving path to improve the efficiency of path generation.

[0051] S202. Control the unmanned underwater vehicle to travel along the first target path, and acquire second sonar map information, first hydrological information and second video information in real time during the travel; Specifically, the unmanned underwater vehicle is controlled to travel along the first target path. During the process, it continuously acquires second sonar map information (detecting obstacles and terrain at medium and long distances through sonar equipment), first hydrological information (real-time water flow speed, direction, water turbidity, etc., detected by the onboard hydrological detection sensors) and second video information (capturing details of nearby obstacles and real-time environmental scenes, acquired by the onboard video device).

[0052] S203. Determine the first real-time obstacle information on the first target path based on the second sonar map information and the second video information; Specifically, by combining the differences in reflected signals from the second sonar map (different objects have different reflected sonar signals) with the intuitive images from the second video information, the first real-time obstacle information on the first target path can be accurately identified, including parameters such as the obstacle's location, type (fixed, floating, biological, etc.), and size.

[0053] S204. The first obstacle difference information is obtained by comparing the historical obstacle information with the first real-time obstacle information; Specifically, the historical obstacle information corresponding to the historical path (path obstacles recorded during previous cleanups) is compared item by item with the first real-time obstacle information to obtain the first obstacle difference information, mainly covering situations such as historically present but not present; historically absent but present; historically present but still existing.

[0054] S205. After correcting the first target path based on the first obstacle difference information and the first hydrological information, the first path is obtained so that the unmanned underwater vehicle travels along the first path to the first area. Specifically, the first target path is adjusted based on the first obstacle difference information and the first hydrological information; the avoidance inflection points of the disappeared obstacles are deleted, the detour lines of the existing obstacles are added, the avoidance details of the remaining obstacles are optimized, and the driving speed and path direction are adjusted in combination with the water flow conditions (such as optimizing the diagonal downstream section when going against the current). The corrected path is the first path, and the unmanned underwater vehicle travels along this path to the first area.

[0055] S206. If the current siltation location indicated by the siltation blockage location information does not overlap with the historical siltation location, determine the second target path based on the obstacle map information, the drainage location information, and the current siltation location. Specifically, if the current siltation location does not overlap with the historical siltation location, a completely new target path is planned. Based on the obstacle map information provided by the BIM model (including the location, type, and size of obstacles in each area), the launch location information of the unmanned underwater vehicle, and the current siltation location, a second target path is generated using path planning algorithms (such as the grid method and the A* algorithm) to ensure that the path avoids fixed obstacles, maintains a safe distance, and is efficient.

[0056] S207. Control the unmanned underwater vehicle to travel along the second target path, and acquire third sonar map information, second hydrological information and third video information in real time during the travel; Specifically, the unmanned underwater vehicle is controlled to travel along the second target path, while simultaneously acquiring third sonar imagery information (detecting unknown obstacles at medium and long distances), second hydrological information (real-time water flow, turbidity, turbulence, etc.), and third video information (identifying temporary obstacles and environmental details at close range).

[0057] S208. Determine the second real-time obstacle information on the second target path based on the third sonar map information and the third video information; Specifically, by combining third sonar map information and third video information, the second real-time obstacle information on the second target path is accurately identified, with a focus on capturing temporary obstacles not marked in the BIM map (such as floating branches, piles of rubble, schools of fish, etc.) and obstacles whose marked dimensions do not match the actual dimensions.

[0058] S209. The obstacle map information is compared with the second real-time obstacle information to obtain the second obstacle difference information; Specifically, the obstacle map information of the BIM model is compared with the second real-time obstacle information to obtain the second obstacle difference information, and key difference points such as the map not being marked but existing in real time and the map marking size deviation are obtained.

[0059] S210. After correcting the second target path based on the second obstacle difference information and the second hydrological information, the first path is obtained so that the unmanned underwater vehicle travels along the first path to the first area.

[0060] Specifically, the second target path is modified based on the second obstacle difference information and the second hydrological information. This means adding avoidance inflection points for newly added obstacles, increasing the safe distance for obstacles with size deviations, and adjusting the path and speed for turbulent / high turbidity conditions. The modified path is the first path, and the unmanned underwater vehicle travels along this path to the first area.

[0061] In some optional embodiments, the step of obtaining the first path after correcting the first target path based on the first obstacle difference information and the first hydrological information includes: S2051. If the historical obstacle to be avoided on the first road segment representing the first target path by the first obstacle difference information is eliminated, the first road segment is changed to a straight road segment, and the straight road segment passes through the area where the eliminated historical obstacle is located. Specifically, if the first obstacle difference information shows that the historical obstacle to be avoided on the first segment of the first target path has been eliminated, the original first segment will be directly adjusted to a straight segment. This straight segment passes through the area where the eliminated historical obstacle was located, and there is no need to retain the turning points or detour curves set in the original segment to avoid the historical obstacle, so as to shorten the travel distance and improve traffic efficiency.

[0062] S2052. If an obstacle is added to the second segment of the first target path represented by the first obstacle difference information, the minimum detour segment at both ends of the second segment is determined according to the type and size of the added obstacle, and the second segment is changed to the minimum detour segment. Specifically, when the first obstacle difference information shows that there is a new obstacle on the second segment of the first target path, the specific type of the new obstacle (e.g., fixed obstacles: gravel, pipes; floating obstacles: branches, fishing nets; biological obstacles: schools of fish) and its actual size (e.g., diameter, length, volume, etc.) are first determined. Then, based on this information, the minimum detour segment that can bypass the new obstacle is calculated and determined. The minimum detour segment must meet the following principles: maintaining a safe distance from the new obstacle (set according to the size of the obstacle, e.g., small obstacles ≥ 0.3m, large obstacles ≥ 0.5m), a gentle turning angle, and the shortest path length. Finally, the original second segment is replaced with the minimum detour segment to ensure that the new obstacle is avoided without significantly deviating from the original driving direction.

[0063] S2053. The first path is obtained by correcting the first target path based on the water flow velocity and direction represented by the first hydrological information.

[0064] Specifically, after adjusting the path based on obstacle differences, the path is further optimized and corrected by combining the water flow velocity and direction represented by the first hydrological information. Through multi-dimensional corrections based on obstacle differences and hydrological conditions, a final first path is formed, ensuring both safety and efficiency in driving.

[0065] In some optional embodiments, the step of obtaining the first path after correcting the first target path based on the water flow velocity and direction represented by the first hydrological information includes: S2054. If the water flow velocity is less than the first velocity threshold, configure the first target path as the first path. Specifically, if the water flow speed is less than the first speed threshold (this threshold is a preset critical speed at which the water flow affects the movement of the unmanned underwater vehicle, such as 0.3 m / s), it means that the current water flow conditions can negligibly interfere with the unmanned underwater vehicle's movement along its original path. There is no need to adjust the path, and the first target path can be directly determined as the first path.

[0066] S2055. When the water flow velocity is greater than the first velocity threshold and the first angle between the water flow direction and the first target path is an acute angle, a first curved path is set according to the water flow direction, the water flow velocity and the first angle, and the first curved path is configured as the first path so that the path trajectory of the unmanned underwater vehicle when traveling along the first curved path coincides with the first target path. Specifically, if the water flow velocity is greater than the first velocity threshold, and the first angle between the water flow direction and the first target path is an acute angle (i.e., the water flow direction is in the same direction as the original direction of travel of the submersible or in a small-angle oblique assist state), then the first curved path is planned and set according to the specific water flow direction, water flow velocity, and the value of the first angle. (Refer to...) Figure 3The core design of the first curved path is to offset the lateral thrust of the water flow by using the curve shape, so as to ensure that the actual trajectory of the submersible coincides with the preset trajectory of the first target path. This not only helps to improve the driving efficiency with the help of the water flow, but also avoids deviation from the target route due to the impact of the water flow.

[0067] S2056. When the water flow velocity is greater than the first velocity threshold and the second angle between the water flow direction and the first target path is an obtuse angle, a second curved path is set according to the water flow direction, the water flow velocity and the second angle, and the second curved path is configured as the second path, wherein the second curved path is perpendicular to the water flow direction.

[0068] Specifically, if the water flow velocity exceeds the first velocity threshold, and the second angle between the water flow direction and the first target path is an obtuse angle (i.e., the water flow direction is opposite to or obliquely obstructing the original direction of the submersible), then a second curved path is planned and set based on the water flow direction, water flow velocity, and the second angle. (Refer to...) Figure 4 The second curved path needs to be perpendicular to the direction of the water flow. By adjusting the direction of travel, the direct resistance of the water flow can be avoided, reducing the power consumption of the submersible. At the same time, the overall trajectory must be oriented towards the first area. Finally, the second curved path is determined as the first path.

[0069] In some optional embodiments, controlling the unmanned underwater vehicle (UUV) to travel along a second path to the siltation area indicated by the siltation blockage location information, based on the real-time location information and the first video information and first sonar map information acquired by the UUV in real time, includes: S410. Display the unmanned underwater vehicle on the BIM model in real time according to the real-time location information, and plan a third target path on the BIM model according to the obstacle map information, the real-time location information and the current siltation location; Specifically, refer to Figure 5 The system synchronizes the real-time location information of the underwater vehicle (UV) detected by sonar sensors to the BIM model of the hydraulic management system. The UV's 3D coordinates and operational status are displayed in real-time on the model as dynamic icons, ensuring that staff can intuitively grasp the UV's position. Subsequently, the system combines pre-stored obstacle map information (including the location, type, and size of obstacles in each area), the UV's current real-time location, and the current siltation location indicated by the siltation blockage location information (located within the siltation area). Using built-in path planning algorithms (such as the grid method and A* algorithm), it automatically plans an initial optimal route from the UV's current location to the siltation area on the BIM model, i.e., the third target path. This path planning aims to avoid known obstacles, maintain a safe distance, minimize the route, and head towards the siltation area, providing a basic operational framework for the UV.

[0070] S420. Determine the third real-time obstacle information on the third target path based on the first sonar map information and the first video information; Specifically, the submersible continuously collects primary sonar imagery and primary video data during its operation. The system performs real-time analysis and processing on these two types of data: utilizing the differences in sound wave reflection from the primary sonar imagery, it identifies obstacles at medium to long distances (such as unmarked reefs or large debris piles) and terrain undulations (such as deep trenches or protrusions) along the path to the third target; through the high-definition real-view images from the primary video data, it captures small obstacles at close range (such as pebbles, floating objects, and protruding fences) and environmental details (such as changes in water turbidity and the surface condition of obstacles). By combining the analysis results of both types of data, the system accurately determines the real-time information of the third obstacle along the path to the third target, including the obstacle's specific location, type, size, shape, and distance from the path.

[0071] S430. The second path is obtained by correcting the third target path based on the third real-time obstacle information and the third hydrological information on the third target path; Specifically, after acquiring the third real-time obstacle information, the third target path is modified in conjunction with the third hydrological information along the path (real-time water flow speed, direction, presence of turbulence, etc.). During the modification process, if new obstacles are found on the path based on the third real-time obstacle information, a minimum detour section needs to be planned (meeting the requirements of maintaining a safe distance from the obstacle and smooth turning); if the obstacle is a small, avoidable obstacle, the path direction is slightly adjusted to avoid significant deviation from the original planned route. At the same time, path details are optimized based on the third hydrological information: in downstream sections, the driving direction can be appropriately adjusted to utilize the water flow; in upstream or turbulent sections, the driving is optimized to a curved path to ensure the stability of the submersible's attitude and speed; if the water is turbid and the video image is not clear enough, the sonar detection frequency needs to be increased, and the path modification is supplemented based on the sonar data. After the above dual modification of obstacle avoidance and hydrological condition adaptation, the third target path is optimized into a safe and feasible second path.

[0072] S440. Control the unmanned underwater vehicle to travel along the second path to the siltation area indicated by the siltation blockage location information, wherein the current siltation location is located within the siltation area.

[0073] Specifically, the system sends the revised second path to the unmanned underwater vehicle (UUV) and controls the UUV to autonomously travel along this path. During the journey, the UUV continuously reports its real-time location information, and the BIM model updates the UUV's dynamics synchronously. Staff can monitor the entire path execution process through a visual terminal. If sudden obstacles or abrupt changes in hydrological conditions are encountered, the system can dynamically fine-tune the second path based on the real-time transmitted first video information, first sonar map information, and location information to ensure that the UUV always travels along a safe route and ultimately accurately arrives at the siltation area indicated by the siltation blockage location information (where the current siltation location is within this area).

[0074] In some alternative embodiments, controlling the unmanned underwater vehicle to clear silt from the silted area includes: S510. Control the unmanned underwater vehicle to acquire siltation sonar map information and siltation video information in the siltation area; Specifically, the unmanned underwater vehicle is controlled to conduct all-round exploration in the siltation area. Through its onboard sonar equipment and high-definition camera, it acquires sonar map information and video information of the siltation in the area, providing basic data for siltation analysis.

[0075] S520. Determine the first siltation location of the siltation material based on the two-dimensional sonar information in the siltation sonar map information; Specifically, the two-dimensional sonar data in the sedimentation sonar map information is analyzed, and the preliminary distribution location of the sediment in the planar space is determined based on the correlation of the position coordinates of the sound wave reflection, i.e. the first sedimentation location, thus clarifying the approximate location of the sediment.

[0076] S530. Determine the first contour information of the sediment based on the three-dimensional sonar information in the sediment sonar map information; Specifically, three-dimensional sonar data is extracted from the sonar map information of the sediment, and the spatial morphological characteristics of the sediment are restored through three-dimensional modeling technology. The preliminary shape structure of the sediment is constructed to obtain the first contour information, including morphological parameters such as the height of the sediment protrusion and the extent of its extension.

[0077] S540. After correcting the first siltation position based on the siltation video information, the target siltation position is obtained; after correcting the first contour information, the siltation contour information is obtained; and the siltation type information is identified. Specifically, the location and contour information obtained earlier is optimized and corrected by combining the video information of the siltation: the coordinate deviation of the first siltation location is calibrated by the intuitive presentation of the video, the core distribution area of ​​the silt is accurately located, and the target siltation location is obtained; the detailed features of the first contour information are refined, and the local morphology not captured by the sonar detection is supplemented to form accurate silt contour information; at the same time, based on the appearance, texture and other features of the silt in the video, the siltation type information (such as flexible debris, rigid debris, loose silt, etc.) is identified and determined.

[0078] S550. Determine the size information of the silt based on the siltation video information corresponding to the target siltation location and the preset trash rack size information; Specifically, for the target siltation location, the corresponding siltation video information is retrieved, and the images of the visible trash rack bars in the video are extracted. Combined with the preset actual size information of the trash rack (such as the bar spacing and bar width), the actual physical size of the silt is calculated by the image pixel ratio conversion method, forming the silt size information (such as length, width, height, diameter, etc.).

[0079] S560. Determine a cleaning plan based on the silt size information, the silt outline information, the target silt location, and the silt type information; Specifically, based on comprehensive information on silt size, silt outline, target silt location, and silt type, a precise cleaning plan is developed to suit the current silt situation, taking into account factors such as the selection of cleaning tools (e.g., mechanical grippers, cutting tools, suction devices), the formulation of operational strategies (e.g., gripping angle, cutting method, suction path), and the planning of the cleaning sequence (e.g., starting with easy areas and then moving to difficult areas, starting with core areas and then moving to peripheral areas).

[0080] S570. Control the unmanned underwater vehicle to clean up the silt at the target siltation location according to the cleaning plan.

[0081] Specifically, the established cleanup plan is translated into specific operational instructions and issued to the unmanned underwater vehicle (UUV). The UUV is then controlled to move to the target location of the siltation and perform cleanup operations (such as gripping, cutting, and suction) according to the plan to ensure effective removal of the silt. During the cleanup process, the UUV continuously transmits real-time video and location information to monitor the progress and effectiveness of the cleanup. If necessary, the cleanup plan can be dynamically adjusted to prevent errors and improve the cleanup results.

[0082] In some optional embodiments, determining the cleaning plan based on the silt size information, the silt outline information, the target silt location, and the silt type information includes: S561. Determine the first cleaning priority corresponding to the silt located at different locations based on the target silt location; Specifically, based on the distance between the target siltation location and key facilities of the hydropower station (such as the trash rack inlet, diversion tunnel inlet, and generator unit intake) and the degree of impact on water flow, the first priority for cleaning siltation at different locations is determined. For example, siltation ≤5m from the core inlet area of ​​the trash rack is given high priority because it directly affects water flow efficiency; siltation 10-20m from key facilities is given medium priority; and siltation far from key facilities and with minimal impact on water flow is given low priority, thus clarifying the urgency of cleaning siltation at different locations.

[0083] S562. Determine the second cleaning priority corresponding to silt of different sizes and contours based on the silt size information and the silt outline information; Specifically, the priority is determined by combining the size and contour information of the silt. In terms of size, large silt with a diameter / length greater than 50cm (the specific size can be selected according to the actual situation and is not limited here) is set as high priority, medium-sized silt with a diameter of 10-50cm is set as medium priority, and small silt with a diameter of less than 10cm is set as low priority. In terms of contour, irregular polyhedral silt with sharp protrusions (which can easily scratch equipment or grids) is upgraded by one level, while regular spherical and flat silt maintains its original size priority, ultimately forming a second priority for cleaning that takes into account both size and contour risks.

[0084] S563. Determine the third cleaning priority corresponding to different types of silt based on the silt type information; Specifically, the priority is determined based on the difficulty and severity of the debris removal. Flexible debris (such as fishing nets and long branches, which can easily entangle underwater vehicle tools or fences) is set as high priority; rigid debris (such as stones and metal blocks, which can easily cause physical blockages) is set as medium priority; and loose silt and fine particles (which are easy to remove and have little short-term impact) are set as low priority, thus clarifying the order of treatment for different types of debris.

[0085] S564. Obtain the first weight coefficient corresponding to the first cleanup priority, the second weight coefficient corresponding to the second cleanup priority, and the third weight coefficient corresponding to the third cleanup priority; Specifically, based on the actual operation and maintenance needs of the hydropower station, weight coefficients are preset for the first, second, and third cleaning priorities. For example, if the primary goal is to ensure the smooth operation of critical facilities, the first weight coefficient is set to 0.4; if the focus is on equipment safety and damage prevention, the second weight coefficient is set to 0.3; and if the core objective is to quickly handle high-risk debris, the third weight coefficient is set to 0.3 (the specific weights can be dynamically adjusted according to the actual scenario).

[0086] S565. Determine the first target priority based on the first cleanup priority, the second cleanup priority, the third cleanup priority, the first weight coefficient, the second weight coefficient, and the third weight coefficient; Specifically, the first, second, and third cleaning priorities of each sediment are quantified into numerical values, and the first target priority is calculated using a weighted summation formula.

[0087] S566. Determine the correlation coefficients between various sediments using network analysis. Specifically, the Analytic Network Analysis (ANP) method is used to construct a sediment correlation matrix to analyze the mutual influence relationships between sediments (e.g., sediment A blocks the clearing path of sediment B, sediment C and sediment D are different parts of the same entanglement). By comparing pairs of sediments, the correlation strength is determined, and the correlation coefficient between each sediment is quantified (the value ranges from 0 to 1, with larger values ​​indicating a stronger correlation). For example, the correlation coefficient for sediments that obstruct each other is set to 0.8, and the correlation coefficient for sediments with no direct influence is set to 0.1.

[0088] S567. The second target priority is obtained by correcting the first target priority according to the correlation coefficient; Specifically, the priority of the first target is adjusted based on the correlation coefficient. For closely related sediment groups, if one sediment has a higher priority in its first target, the priority of its associated sediments is increased (increase = correlation coefficient × difference between the priority of the higher-priority sediment and its own). If there is a dependency that A must be cleared before B can be cleared, even if A's first target priority is lower than B's, B's priority is adjusted to be at the same level as A or only one level lower, ensuring the continuity of the clearing logic. The final priority of the second target is obtained after the adjustment.

[0089] S568. Configure the priority of the second target to the cleaning order corresponding to the cleaning scheme.

[0090] Specifically, the sediment is sorted from highest to lowest priority according to the secondary objective, forming the cleaning order in the cleanup plan. The sediment with the highest priority is cleaned first, and sediments of the same priority are sorted according to their distance from the current position of the submersible from near to far or in the direction of the current, to ensure that the cleanup process is efficient and without repeated trips, and finally completes the configuration of the cleanup plan.

[0091] Implementing the embodiments of the present invention has the following beneficial effects: In response to a first operation on the BIM model, siltation and blockage location information is generated, which is obtained by sonar sensors in a preset layout; the unmanned underwater vehicle (UUV) is controlled to travel along a first path to a first area based on the siltation and blockage location information and the UUV's launch location information, where the first area represents the detection range of the sonar sensors in the preset layout; the real-time location information of the UUV in the first area is detected by the sonar sensors in the preset layout; the UUV is controlled to travel along a second path to the siltation area indicated by the siltation and blockage location information based on the real-time location information and the first video information and first sonar map information acquired by the UUV in real time; and the UUV is controlled to clear silt in the siltation area. In this embodiment, the real-time position of the unmanned underwater vehicle (UUV) is visually presented through the BIM model of the hydropower station. The location of siltation is obtained based on the pre-laid sonar sensors, thereby improving the accuracy of siltation location and ensuring the accuracy of the path planned on the BIM model. Furthermore, the environmental information is determined in real time through the sonar and video information acquired by the UUV, and the UUV is located in real time through the pre-laid sonar sensors, thereby precisely controlling the UUV to complete the siltation removal. Moreover, through the visualization and control on the BIM model, errors in the UUV's removal can be responded to and processed in a timely manner, thereby improving the removal effect.

[0092] In addition, one embodiment of the present invention provides a visual control device for an underwater unmanned submersible, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0093] The processor and memory can be connected via a bus or other means.

[0094] It should be noted that the computer in this embodiment may correspond to, for example, including, Figure 1 The memory and processor in the illustrated embodiment can constitute Figure 1 The system architecture platform shown in the embodiment is part of the same inventive concept, and therefore has the same implementation principle and beneficial effects, which will not be described in detail here.

[0095] The non-transient software program and instructions required to implement the methods of the above embodiments are stored in memory. When executed by a processor, the visualization control method of the underwater unmanned submersible described above is executed, for example, the method described above is executed. Figure 2 Method steps S100 to S500.

[0096] Furthermore, one embodiment of the present invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are used to execute the aforementioned visualization control method for an underwater unmanned submersible, for example, to execute the above-described... Figure 2 Method steps S100 to S500.

[0097] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as processors, such as central processing units, digital signal processors, or microprocessors executing software, or as hardware, or as integrated circuits, such as application-specific integrated circuits. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0098] The above provides a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A visual control method for an underwater unmanned submersible, characterized in that, Applied to a hydropower management system, the hydropower management system is equipped with a visualization terminal, the visualization terminal is equipped with a BIM model of a hydropower station, and the BIM model is equipped with sonar sensors in a pre-laid layout, including: In response to the first operation on the BIM model, siltation and blockage location information is generated, which is obtained by sonar sensors in the preset layout; Based on the siltation and blockage location information and the unmanned underwater vehicle's launch location information, the unmanned underwater vehicle is controlled to travel along a first path to a first area, where the first area represents the detection range of the sonar sensors in the preset layout. The real-time position information of the unmanned underwater vehicle in the first area is detected by the sonar sensors in the preset layout. Based on the real-time location information and the first video information and first sonar map information acquired by the unmanned underwater vehicle in real time, the unmanned underwater vehicle is controlled to travel along the second path to the siltation area indicated by the siltation blockage location information. Control the unmanned underwater vehicle to clear the silt from the silted-up area.

2. The visual control method for an underwater unmanned submersible according to claim 1, characterized in that, After generating the location information of the siltation blockage, the method further includes: When the current siltation location indicated by the siltation blockage location information overlaps with the historical siltation location, historical path and historical obstacle information are obtained. The historical path represents the travel path of the unmanned underwater vehicle when clearing the historical siltation location, and the historical obstacle information represents the obstacles on the historical path. The first path is determined based on the historical path, historical obstacle information, and the first information obtained by the unmanned underwater vehicle; If there is no overlap between the current siltation location and the historical siltation location, obtain obstacle map information on the BIM model. The obstacle map information indicates the location, type, and size of obstacles in each area of ​​the BIM model. The first path is determined based on the obstacle map information, the launch location information, the current siltation location, and the second information obtained by the unmanned underwater vehicle. Both the first and second information include sonar information, video information, and hydrological information.

3. The visual control method for an underwater unmanned submersible according to claim 2, characterized in that, The step of controlling the unmanned underwater vehicle (UUV) to travel along a first path to the first area based on the siltation and blockage location information and the UUV's launch location information includes: If the current siltation location indicated by the siltation blockage location information overlaps with the historical siltation location, the historical path will be configured as the first target path. The unmanned underwater vehicle is controlled to travel along the first target path, and during the travel, it acquires second sonar map information, first hydrological information and second video information in real time; The first real-time obstacle information on the first target path is determined based on the second sonar map information and the second video information; The first obstacle difference information is obtained by comparing the historical obstacle information with the first real-time obstacle information; The first path is obtained by correcting the first target path based on the first obstacle difference information and the first hydrological information, so that the unmanned underwater vehicle can travel along the first path to the first area. If the current siltation location indicated by the siltation blockage location information does not overlap with the historical siltation location, a second target path is determined based on the obstacle map information, the drainage location information, and the current siltation location. The unmanned underwater vehicle is controlled to travel along the second target path, and during the travel, it acquires third sonar map information, second hydrological information and third video information in real time; The second real-time obstacle information on the second target path is determined based on the third sonar map information and the third video information; The obstacle map information is compared with the second real-time obstacle information to obtain the second obstacle difference information; The first path is obtained by correcting the second target path based on the second obstacle difference information and the second hydrological information, so that the unmanned underwater vehicle can travel along the first path to the first area.

4. The visual control method for an underwater unmanned submersible according to claim 3, characterized in that, The step of correcting the first target path based on the first obstacle difference information and the first hydrological information to obtain the first path includes: If the historical obstacle to be avoided on the first road segment representing the first target path is eliminated, the first road segment is changed to a straight road segment, which passes through the area where the eliminated historical obstacle is located; If an obstacle is added to the second segment of the first target path represented by the first obstacle difference information, the minimum detour segment at both ends of the second segment is determined according to the type and size of the added obstacle, and the second segment is changed to the minimum detour segment. The first path is obtained by correcting the first target path based on the water flow velocity and direction represented by the first hydrological information.

5. The visual control method for an underwater unmanned submersible according to claim 4, characterized in that, The step of obtaining the first path by correcting the first target path based on the water flow velocity and direction represented by the first hydrological information includes: If the water flow velocity is less than a first velocity threshold, the first target path is configured as the first path; When the water flow velocity is greater than a first velocity threshold and the angle between the water flow direction and the first target path is an acute angle, a first curved path is set according to the water flow direction, the water flow velocity and the first angle, and the first curved path is configured as the first path so that the path trajectory of the unmanned underwater vehicle when traveling along the first curved path coincides with the first target path; When the water flow velocity is greater than the first velocity threshold and the second angle between the water flow direction and the first target path is an obtuse angle, a second curved path is set according to the water flow direction, the water flow velocity and the second angle, and the second curved path is configured as the second path, wherein the second curved path is perpendicular to the water flow direction.

6. The visual control method for an underwater unmanned submersible according to claim 2, characterized in that, The step of controlling the unmanned underwater vehicle (UUV) to travel along a second path to the siltation area indicated by the siltation blockage location information based on the real-time location information and the first video information and first sonar map information acquired by the UUV in real time includes: The unmanned underwater vehicle is displayed in real time on the BIM model based on the real-time location information, and a third target path is planned on the BIM model based on the obstacle map information, the real-time location information, and the current siltation location. The third real-time obstacle information on the third target path is determined based on the first sonar map information and the first video information; The second path is obtained by correcting the third target path based on the third real-time obstacle information and the third hydrological information on the third target path; The unmanned underwater vehicle is controlled to travel along the second path to the siltation area indicated by the siltation blockage location information, and the current siltation location is located within the siltation area.

7. The visual control method for an underwater unmanned submersible according to claim 1, characterized in that, The control of the unmanned underwater vehicle to clear silt from the silted-up area includes: The unmanned underwater vehicle is controlled to acquire sonar imagery and video information of the siltation area. The first location of the sediment is determined based on the two-dimensional sonar information in the sediment sonar map information. The first contour information of the sediment is determined based on the three-dimensional sonar information in the sediment sonar map information; After correcting the first siltation location based on the siltation video information, the target siltation location is obtained; after correcting the first contour information, the siltation contour information is obtained; and the siltation type information is identified. The size information of the silt is determined based on the siltation video information corresponding to the target siltation location and the preset trash rack size information; A cleaning plan is determined based on the silt size information, the silt outline information, the target silt location, and the silt type information. According to the cleaning plan, the unmanned underwater vehicle is controlled to clean up the silt at the target siltation location.

8. The visual control method for an underwater unmanned submersible according to claim 7, characterized in that, The step of determining the cleaning plan based on the silt size information, the silt outline information, the target silt location, and the silt type information includes: Based on the target siltation location, determine the first cleaning priority corresponding to the siltation located at different locations; The second cleaning priority corresponding to sludge of different sizes and shapes is determined based on the sludge size information and the sludge outline information; Based on the information on the type of silt, a third cleaning priority is determined for different types of silt. Obtain the first weight coefficient corresponding to the first cleanup priority, the second weight coefficient corresponding to the second cleanup priority, and the third weight coefficient corresponding to the third cleanup priority; The first target priority is determined based on the first cleanup priority, the second cleanup priority, the third cleanup priority, the first weight coefficient, the second weight coefficient, and the third weight coefficient; The correlation coefficients between various sediments were determined using network analysis. The second target priority is obtained by correcting the first target priority based on the correlation coefficient. Configure the priority of the second target to the cleanup order corresponding to the cleanup scheme.

9. A visual control device for an underwater unmanned submersible, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the visual control method for the underwater unmanned submersible according to any one of claims 1-8.

10. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, which are used to execute the visualization control method for the underwater unmanned submersible according to any one of claims 1-8.

Images