Underwater surveying and mapping method and device for unmanned ship, medium and program product

Abstract

The invention discloses an underwater surveying and mapping method and device for an unmanned ship, a medium and a program product, and relates to the field of data processing. The method comprises the following steps: when the unmanned ship sails in a target water area according to a preset route, acquiring underwater sounding data acquired by an underwater sounding module and surveying and mapping point positioning data acquired by a GNSS positioning module; generating an underwater topographic data set according to the underwater sounding data and the surveying and mapping point positioning data; segmenting the underwater topographic data set into a plurality of underwater topographic data subsets; performing recursive processing on the plurality of underwater topographic data subsets to obtain a plurality of processed underwater topographic data subsets; and generating underwater topographic mapping data according to the plurality of processed subsets of underwater topographic data. The underwater surveying and mapping efficiency and precision of the unmanned ship can be improved, the high-quality underwater topographic data processing efficiency is ensured, and the double bottleneck problems of data processing speed and precision are effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of underwater surveying and mapping technology, and in particular to an underwater surveying and mapping method, equipment, medium and program product for an unmanned vessel. Background Art

[0002] Underwater mapping is a scientific activity that uses sonar, optical or remote sensing technology to accurately measure and depict underwater terrain, landform features and underwater structures. It is of great significance to the fields of water resource development, environmental monitoring, navigation safety and scientific research.

[0003] Traditional underwater surveying and mapping technologies rely primarily on manned vessels equipped with various surveying equipment to collect data. This requirement for direct human involvement not only increases operational costs but also poses potential safety risks. Furthermore, the speed and range of manned vessels are limited, restricting the efficiency and coverage of surveying and mapping efforts, and the amount of data collected is often limited.

[0004] Therefore, related technologies have begun to use unmanned vessels for automated mapping, which can improve mapping efficiency and collect large amounts of underwater terrain data. However, due to the large scale of underwater terrain data collected, related technologies often face dual bottlenecks in data processing speed and accuracy when processing these huge data sets as a whole. Summary of the Invention

[0005] In response to the above-mentioned technical problems and defects, the purpose of the present invention is to provide a method, equipment, medium and program product for underwater mapping by unmanned vessels, which can improve the efficiency and accuracy of underwater mapping by unmanned vessels, ensure high-quality underwater terrain data processing efficiency, and effectively address the dual bottleneck problems of data processing speed and accuracy.

[0006] To achieve the above-mentioned objectives, in a first aspect, the present invention provides an underwater surveying and mapping method for an unmanned vessel, comprising: when the unmanned vessel navigates in a target water area according to a preset route, obtaining underwater bathymetric data collected by an underwater bathymetric module and surveying point positioning data collected by a GNSS positioning module, wherein the underwater bathymetric module and the GNSS positioning module are respectively arranged on the unmanned vessel; generating an underwater terrain data set based on the underwater bathymetric data and the surveying point positioning data; dividing the underwater terrain data set into multiple underwater terrain data subsets; recursively processing the multiple underwater terrain data subsets to obtain multiple processed underwater terrain data subsets; and generating underwater terrain surveying and mapping data based on the multiple processed underwater terrain data subsets.

[0007] By integrating an underwater bathymetric module with a GNSS positioning module, the present invention enables efficient and accurate mapping of the underwater topography of target waters. This system can continuously collect large amounts of underwater topographic data and positioning information without requiring human intervention, significantly reducing operational costs and safety risks. Furthermore, by segmenting the massive underwater topographic dataset into multiple subsets and employing recursive processing techniques, the present invention effectively addresses the bottleneck issues of data processing speed and accuracy in traditional underwater mapping. This segmentation and recursive processing strategy not only improves data processing efficiency but also enhances the ability to capture complex topographic features, ensuring high resolution and accuracy in mapping results.

[0008] In combination with some embodiments of the first aspect, in some embodiments, when the unmanned ship navigates in the target waters according to a preset route, the method also includes: obtaining obstacle identification information collected by an obstacle identification module, which is arranged on the unmanned ship; determining the type and size of the obstacle based on the obstacle identification information; determining an obstacle avoidance strategy based on the type and size of the obstacle; and controlling the unmanned ship to avoid the obstacle according to the obstacle avoidance strategy.

[0009] The technical solutions of the above-mentioned embodiments significantly enhance the autonomous navigation capabilities and safety of unmanned vessels by integrating obstacle identification and avoidance strategies into their underwater mapping process. By acquiring obstacle information in real time and determining its type and size, the unmanned vessel can formulate and execute effective obstacle avoidance strategies based on the characteristics of the obstacles, thereby avoiding potential collisions with them and ensuring the continuity of the mapping mission and the safety of the unmanned vessel. This approach not only improves mapping efficiency but also reduces the risks associated with human intervention, enabling unmanned vessels to perform missions in more complex and changing water environments.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the step of determining an obstacle avoidance strategy based on the type and size of the obstacle includes: when the type of the obstacle is a floating object, determining whether the size of the floating object is greater than a set size threshold; if not, determining the water jet speed and angle based on the size and position of the floating object; generating an obstacle avoidance strategy based on the water jet speed and angle, and the obstacle avoidance strategy is used to enable the water jet on the unmanned boat to jet water according to the water jet speed and angle to drive the floating object away from the driving path of the unmanned boat.

[0011] The technical solution of the above embodiment effectively removes small floating objects by determining their size and adjusting the operating parameters of the water jet accordingly. This method allows the unmanned vessel to continue its mapping mission by jetting water to remove small obstacles in its path without changing its route. This strategy not only improves the unmanned vessel's response speed to dynamic obstacles but also reduces the need for route adjustments required for obstacle avoidance, optimizing mapping path planning.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining whether the size of the floating object is greater than a set size threshold, it also includes: if the size of the floating object is greater than the size threshold, determining the position information, drifting speed and drifting direction of the floating object; determining an obstacle avoidance path based on the size of the floating object, the position information, the drifting speed and the drifting direction; and generating an obstacle avoidance strategy based on the obstacle avoidance path.

[0013] Using the technical solutions of the above-mentioned embodiments, a comprehensive obstacle avoidance strategy for large floating objects is proposed based on the obstacle's location, drifting speed, and direction. By accurately measuring the dynamic characteristics of large floating objects, the unmanned vessel can predict their future position and plan a safe path to avoid the obstacle. This approach enables the unmanned vessel to make more accurate and rational obstacle avoidance decisions when encountering large obstacles, improving the success rate of obstacle avoidance while also ensuring the integrity and accuracy of surveying and mapping data.

[0014] In combination with some embodiments of the first aspect, in some embodiments, the step of determining an obstacle avoidance strategy based on the type and size of the obstacle includes: if the type of the obstacle is a static obstacle, determining the position information of the static obstacle; determining an obstacle avoidance path based on the size and position information of the static obstacle; and generating an obstacle avoidance strategy based on the obstacle avoidance path.

[0015] The technical solutions of the above embodiments provide an obstacle avoidance strategy for static obstacles based on their location and size. By determining the exact location of static obstacles, the unmanned vessel can plan a safe path to avoid these fixed obstacles. This approach enables unmanned vessels to effectively avoid static obstacles such as seabed rocks and sunken ships when performing surveying and mapping missions, ensuring navigation safety and the accuracy of surveying and mapping data. It also improves the unmanned vessel's autonomous navigation capabilities in complex underwater environments.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the step of determining an obstacle avoidance strategy based on the type and size of the obstacle includes: if the type of the obstacle is a dynamic obstacle, determining the position information, moving speed, and direction of the dynamic obstacle; determining an obstacle avoidance path based on the size of the dynamic obstacle, the position information, and the moving speed and direction; and generating an obstacle avoidance strategy based on the obstacle avoidance path.

[0017] Using the technical solutions of the above embodiments, an obstacle avoidance strategy for dynamic obstacles is proposed that takes into account the speed and direction of the obstacle. By monitoring the movement of dynamic obstacles in real time, the unmanned vessel can predict their future positions and formulate an obstacle avoidance path accordingly. This approach enables the unmanned vessel to flexibly respond to dynamic obstacles such as ships and marine life, improving its obstacle avoidance capabilities in dynamic environments and ensuring the smooth progress of surveying and mapping missions and the safety of the unmanned vessel.

[0018] In combination with some embodiments of the first aspect, in some embodiments, the obstacle identification information includes an obstacle image; and the step of determining the type and size of the obstacle based on the obstacle identification information includes: inputting the obstacle image into a preset obstacle identification model to obtain the type and size of the obstacle.

[0019] The technical solution of the above embodiment, through the introduction of obstacle image recognition technology, improves the accuracy and automation of obstacle identification. By inputting obstacle images into a preset recognition model, the unmanned vessel can automatically identify the type and size of obstacles without human intervention. This method not only improves the efficiency of obstacle information acquisition but also reduces obstacle avoidance decision errors caused by human error, thereby enhancing the autonomy of the unmanned vessel and the reliability of its obstacle avoidance strategy.

[0020] In a second aspect, an embodiment of the present invention provides an electronic device, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0021] In a third aspect, the present invention provides a computer-readable storage medium comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0022] In a fourth aspect, the present invention provides a computer program product comprising instructions, which, when the computer program product is run on an electronic device, enables the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0023] It is understood that the electronic device provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided by the present invention. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods and will not be repeated here.

[0024] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: 1. Improving underwater surveying efficiency and accuracy: Automating the underwater surveying process significantly improves data processing speed and accuracy. The underwater bathymetric and GNSS positioning modules onboard the unmanned vessel collect precise underwater topographic data in real time, while the application of recursive processing technology enables rapid and detailed processing of large data sets. This approach not only reduces the need for manual operations and lowers costs, but also enhances the efficiency and accuracy of underwater topographic surveying by increasing the degree of automation in data processing.

[0025] 2. Enhanced autonomous obstacle avoidance capabilities for unmanned vessels: This system provides powerful autonomous obstacle avoidance capabilities for unmanned vessels. The obstacle recognition module acquires obstacle information and intelligently determines avoidance paths and strategies based on obstacle type, size, location, speed, and direction, enabling the unmanned vessel to navigate safely in a variety of complex environments. This intelligent obstacle avoidance system makes the unmanned vessel more flexible and reliable in mission execution, reducing the risk of equipment damage caused by collisions with obstacles.

[0026] 3. Optimizing the navigation safety and mission execution of unmanned vessels: Obstacle image recognition technology further improves the accuracy of unmanned vessels' obstacle recognition. Combined with obstacle avoidance strategies, the unmanned vessel can take appropriate avoidance measures for different types of obstacles (such as floating objects, static obstacles, and dynamic obstacles). This not only optimizes the navigation safety of the unmanned vessel, but also ensures the continuity and efficiency of underwater mapping missions. This allows the unmanned vessel to successfully complete mapping missions even in waters with a high number of obstacles, improving mission success rates and data availability. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and those skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings: Figure 1 Schematic diagram of the connection relationship between the data processing module, underwater depth measurement module and GNSS positioning module in an embodiment of the present invention; Figure 21 is a flow chart of an underwater mapping method for an unmanned vessel according to an embodiment of the present invention; Figure 3 1 is a flow chart of another underwater mapping method for an unmanned vessel according to an embodiment of the present invention; Figure 4 It is a schematic diagram of the architecture of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. As used in the specification of the present invention, the singular expressions "a," "an," "above," "the," and "this" are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used in the present invention refers to any and all possible combinations of one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying relative importance or implicitly indicating the quantity of the technical features indicated. Thus, a feature designated "first" or "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present invention, unless otherwise specified, "plurality" means two or more.

[0030] It should also be noted that, unless otherwise clearly specified and limited, in the embodiments of the present invention, terms such as "setting" and "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal connection of two components; it can be a wired communication connection or a wireless communication connection. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The embodiments of the present invention are described in detail below.

[0031] The embodiment of the present invention provides an underwater mapping method for an unmanned vessel, which can be applied to the data processing module 101, such as Figure 1 As shown, the data processing module 101 is connected to the underwater depth measurement module 102 and the GNSS (Global Navigation Satellite System) positioning module 103 respectively, and the underwater depth measurement module 102 and the GNSS positioning module 103 are respectively set on the unmanned ship.

[0032] The underwater depth sounding module 102 includes but is not limited to a sonar detection module and a multi-beam depth sounding module.

[0033] The sonar detection module is a key component of the underwater depth sounding system. It uses the propagation characteristics of sound waves in water to detect underwater objects and terrain. The module transmits sound waves of a specific frequency and receives the echoes reflected back, measuring the time from the emission to the return of the sound waves, thereby calculating the distance and position of underwater objects. The sonar detection module usually includes one or more transducers for transmitting and receiving sound waves. It can provide information about underwater obstacles, sediments, seabed topography, etc., and is crucial for applications such as underwater navigation, obstacle detection, and terrain mapping. The design of the sonar detection module enables it to adapt to different underwater environments, such as deep sea, shallow waters, or areas with complex terrain, ensuring accurate detection results under various conditions.

[0034] A multibeam bathymetry module is an underwater mapping tool that can simultaneously transmit and receive multiple beams of sound waves to cover a wider area of ​​water, enabling efficient and high-resolution underwater topography mapping. Compared to traditional single-beam sonar, a multibeam bathymetry module can collect larger amounts of data in a shorter period of time, producing more detailed seafloor topography. Typically equipped with multiple transducer arrays, this module can simultaneously transmit sound waves in different directions and receive echoes from all directions. By precisely measuring the propagation time and angle of each beam's sound waves, a multibeam bathymetry module generates three-dimensional data of the underwater topography. This data is of great value in marine geological research, resource exploration, environmental monitoring, and navigation safety. The design of a multibeam bathymetry module ensures stable operation in a wide range of water depths and environmental conditions, providing high-quality mapping data.

[0035] The GNSS positioning module 103 is a high-precision positioning device that receives signals from global navigation satellite systems (such as the US GPS, Russia's GLONASS, the EU's Galileo system, and China's BeiDou system) and uses the known positions of the satellites and the signal propagation time to determine the receiver's precise geographic location. The GNSS module provides three-dimensional coordinate information, including longitude, latitude, and altitude, as well as a timestamp, which is crucial for ensuring the accurate georeferencing of underwater mapping data.

[0036] The underwater mapping method of this embodiment achieves efficient and accurate mapping of the underwater terrain of the target waters by integrating an underwater depth measurement module and a GNSS positioning module. In the automated and intelligent data collection process of the unmanned vessel, this embodiment can continuously collect a large amount of underwater terrain data and positioning information. This data collection process does not require human intervention, thereby significantly reducing operating costs and safety risks. At the same time, by segmenting the huge underwater terrain data set into multiple subsets and adopting recursive processing technology, the bottleneck problem of data processing speed and accuracy in traditional underwater mapping is effectively solved. This segmentation and recursive processing strategy not only improves the efficiency of data processing, but also enhances the ability to capture complex terrain features, ensuring high resolution and high accuracy of the mapping results.

[0037] The underwater topographic mapping data generated by this method in this embodiment can provide important data support for fields such as water resource development, environmental monitoring, navigation safety, and scientific research, greatly promoting the development and application of underwater mapping technology.

[0038] The following combination Figure 2 The following describes the surveying and mapping method of this embodiment, which includes the following steps: Step 201 : When the unmanned vessel navigates in the target waters according to a preset route, the underwater bathymetric data collected by the underwater bathymetric module and the surveying point positioning data collected by the GNSS positioning module are obtained.

[0039] The underwater bathymetry module transmits sound waves, receives their echoes, and measures the time it takes for the sound waves to return, thereby calculating the depth of the underwater terrain. Underwater bathymetry data reflects the ups and downs of the underwater terrain and the details of the seabed topography. Meanwhile, the GNSS positioning module receives signals from satellites in Earth orbit and uses triangulation to determine the precise position of the unmanned vessel, including longitude, latitude, and possibly altitude. This positioning data provides the necessary geographic reference for the bathymetry data, ensuring its spatial accuracy. The data processing module combines this bathymetry and positioning data to generate a comprehensive dataset containing depth and position information, providing the basis for subsequent terrain analysis and 3D model construction. The automation and integration of this process significantly improves the efficiency and accuracy of data collection, while also reducing the need for manual operation and enhancing the safety and reliability of the entire surveying and mapping process.

[0040] Step 202: Generate an underwater terrain data set based on the underwater bathymetric data and the surveying point positioning data.

[0041] The data processing module integrates and processes the underwater bathymetric data and survey point positioning data to generate a comprehensive underwater topography dataset. This process first involves data synchronization, ensuring that each piece of bathymetric data accurately matches its corresponding location data. The data processing module uses the survey point positioning data provided by the GNSS positioning module to determine the specific geographic location of each survey point in the target waters. The data processing module then uses specialized Geographic Information System (GIS) software or customized algorithms to convert this scattered point data into a continuous topographic surface. This typically involves interpolation techniques such as kriging or inverse distance weighted (IDW) interpolation to fill gaps in the data and generate a smooth and continuous terrain model. Furthermore, the data processing module performs data cleaning to remove outliers and noise, ensuring the accuracy and reliability of the dataset. Ultimately, the resulting underwater topography dataset contains rich topographic information, providing a solid data foundation for subsequent analysis and applications.

[0042] Step 203: Segment the underwater terrain data set into multiple underwater terrain data subsets.

[0043] Specifically, the data processing module segments the massive underwater terrain dataset into multiple smaller subsets. This step aims to improve data processing efficiency and flexibility, especially when dealing with large datasets. Segmentation strategies are often based on geographic location, data density, or specific terrain features. For example, data subsets can be divided according to different areas of water or depth ranges. Each subset will contain a relatively concentrated amount of terrain data, which helps to pool processing resources and optimize the computational process.

[0044] Furthermore, segmenting the data into subsets facilitates parallel processing, allowing multiple processing units to work simultaneously on different data subsets, significantly increasing overall processing speed. During the segmentation process, the data processing module ensures clear boundaries between each subset and seamless data transfer between subsets to avoid discontinuities or overlaps in the final terrain model. This segmentation strategy enables the data processing module to more efficiently and quickly manage and process large amounts of underwater terrain data, laying the foundation for generating high-precision 3D terrain models.

[0045] Step 204 : recursively process the multiple underwater terrain data subsets to obtain multiple processed underwater terrain data subsets.

[0046] Specifically, the data processing module uses recursive processing technology to conduct in-depth analysis and optimization of multiple sub-sets of underwater terrain data. The recursive processing uses a divide-and-conquer algorithm, which allows multiple iterative processing of each subset to gradually improve the speed and accuracy of data processing.

[0047] Recursive processing is an iterative process that applies the same algorithm to each subset of underwater terrain data, aiming to extract, classify, and interpolate terrain features. This approach, through repeated application of the algorithm, progressively optimizes the data quality of each subset, enhancing the accuracy of terrain feature recognition and improving data continuity and integrity. Recursive processing allows the algorithm to refine terrain features, fill data gaps, and classify distinct terrain areas with each iteration, laying a solid foundation for generating accurate underwater terrain mapping data.

[0048] Terrain feature extraction specifically refers to the algorithm identifying and extracting key terrain features, such as submarine mountains, trenches, and seabed slopes. These features are crucial for understanding the physical structure of the water.

[0049] Data classification specifically means that by classifying terrain data, different terrain areas can be distinguished, such as sediment-covered areas and rocky areas, which helps in subsequent analysis and application.

[0050] Interpolation specifically refers to the use of interpolation algorithms to estimate and fill in missing data points in areas where data is sparse or missing to generate a continuous terrain surface. This ensures the integrity and consistency of the terrain data.

[0051] The advantage of recursive processing in this embodiment is that it can gradually improve the accuracy and quality of data processing. Each iteration builds on the results of the previous iteration to further refine and optimize the data. This approach is particularly suitable for processing complex underwater terrain data because it allows the algorithm to focus processing on local areas, thereby improving efficiency. Furthermore, recursive processing can adapt to the complexity of the terrain. By analyzing data at different scales, even subtle topographic changes can be accurately captured.

[0052] Step 205 : Generate underwater terrain mapping data based on the multiple processed underwater terrain data subsets.

[0053] The data processing module integrates the recursively processed subsets of underwater terrain data to generate complete underwater terrain mapping data. This step reassembles the segmented and processed local data to construct a comprehensive understanding of the entire target water area. The data processing module will use advanced geographic information system (GIS) technology or customized data processing algorithms to accurately align and fuse the data of each subset according to their geographical location. This process may include data interpolation, splicing, and correction to ensure the consistency and accuracy of the entire dataset. The generated underwater terrain mapping data will provide a detailed and accurate view of the water area topography.

[0054] The data processing module then constructs a three-dimensional underwater terrain model of the target waters based on the underwater terrain mapping data. Three-dimensional modeling software or algorithms can be used to convert the two-dimensional terrain data into a three-dimensional visualization model. The model-building process may include steps such as mesh generation, surface rendering, and visual enhancement to ensure that the model is both scientifically accurate and intuitively understandable. A three-dimensional underwater terrain model can intuitively display the topographic features of the waters, such as submarine mountains, ditches, and sediment distribution, providing researchers and decision-makers with intuitive visual information. This model not only helps to better understand the physical environment of the waters but also supports various applications such as navigation safety analysis, resource exploration planning, and environmental impact assessment. Through this three-dimensional visualization, professionals in related fields can plan and make decisions more effectively.

[0055] In some embodiments, when the unmanned vessel is navigating in the target waters according to a preset route, Figure 3 As shown, the method of this embodiment may further include the following steps: Step 301: Obtain obstacle identification information collected by the obstacle identification module.

[0056] Among them, the obstacle recognition module is set on the unmanned ship. The data processing module receives and processes the data collected by the obstacle recognition module on the unmanned ship. The obstacle recognition module is usually equipped with a variety of sensors, such as cameras, radars, sonars or optical sensors, which can detect and identify potential obstacles on the navigation path of the unmanned ship. These obstacles may include reefs, shipwrecks, floating objects or other underwater structures. The data processing module needs to obtain data from these sensors in real time and convert the raw perception data into usable information for further analysis and processing. This step is the basis for the safe navigation and effective execution of the unmanned ship's mission, as it provides raw data for subsequent obstacle analysis and obstacle avoidance decisions.

[0057] Step 302: Determine the type and size of the obstacle based on the obstacle identification information.

[0058] Among them, the types of obstacles may include floating objects, static obstacles and dynamic obstacles.

[0059] The data processing module uses the information obtained from the obstacle identification module to further analyze and determine the specific type and size of the obstacle. This process may involve using image recognition algorithms, machine learning models, or expert systems to classify and measure obstacles.

[0060] By analyzing the shape, size, material, and echo characteristics of obstacles, the data processing module can identify whether the obstacles are natural or man-made, and the degree of threat they may pose to the unmanned vessel. Accurate information on obstacle type and size is crucial for developing effective obstacle avoidance strategies, as different types of obstacles may require different countermeasures.

[0061] In some embodiments, the obstacle identification information includes an obstacle image. This step may specifically include: inputting the obstacle image into a preset obstacle identification model to obtain the type and size of the obstacle.

[0062] The obstacle identification information received by the data processing module includes obstacle images captured by sensors on the unmanned vessel. In order to extract useful information from these images, the data processing module inputs the image data into a pre-trained obstacle recognition model. This model may be based on machine learning or deep learning algorithms, capable of identifying and classifying various types of obstacles, such as reefs, shipwrecks, floating objects, etc. The model analyzes the features of the image, such as shape, texture, color, and size, to determine the specific type of obstacle. At the same time, it can also estimate the size of the obstacle, which usually involves image processing techniques such as edge detection, contour tracking, and size estimation algorithms. In this way, the data processing module can accurately identify the type and size of the obstacle, providing key information for the subsequent formulation of obstacle avoidance strategies.

[0063] In this embodiment, the application scenario of the obstacle recognition model has certain specificity, which is mainly reflected in the navigation conditions of the unmanned ship in the water environment. This requires the obstacle recognition model to be able to adapt to the changing lighting, water surface reflection, wave interference, and the shapes and sizes of various obstacles. The obstacle recognition model needs to maintain high accuracy under different weather conditions, including clear, cloudy, foggy or nighttime, and be able to handle image distortion and blur caused by water surface fluctuations. In addition, the obstacle recognition model must also be able to identify and distinguish various types of obstacles, such as floating garbage, ships, reefs and other natural or man-made objects, as well as their different postures and directions on the water surface. These specificities require the model to use a wide and representative image dataset when training, and specific image preprocessing techniques may be required to enhance the model's adaptability to environmental changes.

[0064] The obstacle recognition model training process first involves collecting and preparing a diverse image dataset. These images should include a variety of obstacles that an unmanned vessel may encounter in the surface environment, such as buoys, ships, reefs, and other floating objects. These images need to be captured under varying lighting conditions, weather conditions, and water surface conditions to ensure the model's adaptability to a variety of real-world navigation environments. Subsequently, these images are accurately annotated to identify the type, location, and size of obstacles. Leveraging these annotated images, deep learning techniques, specifically convolutional neural networks (CNNs), serve as the model's foundational architecture. During the training phase, the model learns image features through forward propagation and optimizes network weights through backpropagation to minimize prediction error. To improve the model's generalization, data augmentation techniques can be used to artificially expand the training set, including operations such as image rotation, scaling, and color changes. Furthermore, regularization techniques, such as dropout, can be introduced to prevent overfitting. After model training, performance is evaluated on an independent test set to ensure the model's accuracy and reliability in real-world applications. This process may require multiple iterations and parameter adjustments until the model achieves satisfactory performance.

[0065] Step 303: Determine an obstacle avoidance strategy based on the type and size of the obstacle.

[0066] Among them, the obstacle avoidance strategy is a series of decisions and action plans used by unmanned ships to identify, evaluate and avoid obstacles on the navigation path when performing missions. These strategies are based on data collected from sensors such as radar, sonar, cameras, etc., and the data processing module analyzes this information to determine the location, size and possible movement trajectory of obstacles. The core of the obstacle avoidance strategy is to ensure that the unmanned ship safely bypasses obstacles and avoids collisions while maintaining mission efficiency. This usually involves real-time path planning, which may include changing heading or speed, and pausing mission execution when necessary to reassess the situation. The design of the obstacle avoidance strategy must take into account the operating limitations of the unmanned ship, the dynamic changes in environmental conditions, and the priority of the mission to achieve optimal navigation in various situations.

[0067] In this step, when determining the obstacle avoidance strategy, the data processing module will first analyze the type and size information provided by the obstacle identification module. Through this data, the data processing module can determine whether the obstacle poses a direct threat to the unmanned ship and the extent of the threat. For example, large fixed obstacles such as reefs may require the unmanned ship to make major course adjustments, while small or moving obstacles may only require slight avoidance. The data processing module will consider the current speed, heading and surrounding environment of the unmanned ship, as well as the location, size and possible movement trend of the obstacle to calculate the best obstacle avoidance path. This may include calculating multiple potential obstacle avoidance routes and evaluating the safety, efficiency and impact of each route on the mission objectives. Ultimately, the module will select an obstacle avoidance strategy that ensures the safety of the unmanned ship while minimizing the impact on mission execution, and convert this strategy into specific navigation instructions to guide the unmanned ship to take corresponding obstacle avoidance actions.

[0068] In some embodiments, when the obstacle is a floating object, step 303 may specifically include: S1. Determine whether the size of the floating object is greater than a set size threshold.

[0069] Based on the information provided by the obstacle recognition module, the data processing module determines whether the obstacle encountered is a floating object and whether its size exceeds a preset size threshold. This size threshold is a safety parameter used to distinguish between large floating objects that may pose a threat to the unmanned vessel and small floating objects that can be ignored. If the floating object is smaller than this threshold, it may not pose a direct threat to the unmanned vessel's navigation safety, and different obstacle avoidance measures can be taken. This step is crucial to the obstacle avoidance strategy, as it determines the basis and direction of subsequent actions.

[0070] If the size of the floating object is not greater than the size threshold, it means that the floating object is small and can be effectively moved or driven away from the navigation path of the unmanned boat by spraying water using the water jet of the unmanned boat. Then, step S21 can be entered.

[0071] If the size of the floating object is larger than the size threshold, it means that the floating object is too large to be effectively moved or driven away from the navigation path of the unmanned ship by the thrust generated by the water jet. In this case, the floating object may require greater force to be moved due to its large size and mass, and the water jet is usually designed to handle smaller obstacles. They may not have enough power to affect the position of large floating objects. Therefore, the unmanned ship needs to take other obstacle avoidance measures, such as replanning the navigation path or taking emergency evasive actions, to ensure the safety of the unmanned ship and its onboard equipment, while avoiding potential damage to the environment. Then, step S31 can be entered.

[0072] S21. Determine the water jet speed and angle based on the size and position of the floating object.

[0073] If the size of the floating object is smaller than a set threshold, the data processing module calculates the required water jet velocity and angle based on the object's size and position. This calculation takes into account the relative position of the unmanned vessel and the floating object, the vessel's current speed, the performance of the water jet, and the expected effect of the floating object's movement. By precisely controlling the water jet parameters, the unmanned vessel can effectively drive the floating object away from its path, thus avoiding a collision. This step demonstrates the flexibility and intelligence of the unmanned vessel system, enabling it to respond quickly and accurately to varying circumstances.

[0074] Specifically, the data processing module first determines the water jet speed and angle by analyzing the real-time position of the floating object and the current heading of the unmanned vessel. Using this information, it calculates the relative position between the unmanned vessel and the floating object. The data processing module then assesses the size of the floating object to predict its potential movement and speed under the influence of the water current. Based on this data, the data processing module applies physical dynamics principles and fluid dynamics models to calculate the water jet speed and angle that will most effectively propel the floating object out of the unmanned vessel's path. This typically involves simulating the jet force, water flow direction, and floating object reaction, as well as considering the performance of the unmanned vessel's jets. Ultimately, the data processing module generates a set of precise jet parameters that guide the unmanned vessel's water jets for precise operation, ensuring that the floating object is safely removed from the unmanned vessel's navigation path while minimizing the impact on the vessel's navigation performance. This process requires real-time data processing and rapid decision-making capabilities to cope with the ever-changing water surface environment and obstacle dynamics.

[0075] Below, this embodiment provides a basic mathematical model to illustrate how to estimate the jet velocity v and angle θ based on the size and position of the floating object. Assume the following parameters: d: The size of the floating object (e.g., diameter or width). r: The distance between the UAV and the floating object. k: A constant related to the performance of the ejector, which may depend on the power and design of the ejector. m: An experimental coefficient used to adjust the calculated value of the ejection angle.

[0076] θ: Jet angle (the angle with the sailing direction of the unmanned vessel). v: Jet velocity.

[0077] A simplified mathematical model can include the following formula: The calculation of v takes into account the relative size of the floating object, d / r. This means that if the size of the floating object relative to the unmanned vessel increases, or the distance from the unmanned vessel decreases, a greater jet velocity is required to effectively move the floating object. The constant k is used to adjust the velocity to match the actual performance of the jet.

[0078] The jet angle θ is calculated using the inverse tangent function, which is based on the ratio of the float's size to its distance. This angle is designed to aim the water jet directly at the center of the float, thereby most effectively propelling it.

[0079] S22: Generate an obstacle avoidance strategy based on the water jet speed and angle.

[0080] The obstacle avoidance strategy is used to enable the water jet on the unmanned boat to spray water according to the water jet speed and angle, so as to drive the floating object away from the driving path of the unmanned boat.

[0081] Based on the judgments and calculations from the first two steps, the data processing module generates a detailed obstacle avoidance strategy. This strategy directs the water jets on the unmanned vessel to spray water at a specific speed and angle to push floating objects away from the vessel's path. The implementation of the obstacle avoidance strategy requires precise execution by the unmanned vessel's control system to ensure the accuracy and timeliness of the jetting action. This strategy not only considers the current obstacle situation but also predicts the possible movement trajectory of floating objects to ensure that the unmanned vessel can safely and effectively avoid obstacles. In this way, the unmanned vessel can navigate autonomously in complex and changing water environments while minimizing the impact on mission execution.

[0082] S31. Determine the location information, drifting speed and drifting direction of the floating object.

[0083] When the data processing module determines that the size of a floating object is larger than a preset size threshold, it further analyzes and determines the object's detailed location, drifting speed, and drifting direction. This step involves real-time tracking of the object's motion, which may be achieved through continuous image recognition, sensor data, or GPS tracking. The accuracy of this location information is crucial for the subsequent calculation of the obstacle avoidance path, as it directly affects the effectiveness of the obstacle avoidance strategy. Data on drifting speed and direction help predict the future location of the floating object, providing the unmanned vessel with sufficient time and information to plan a safe obstacle avoidance path. The comprehensive analysis of this information provides the unmanned vessel with comprehensive data support, ensuring that it can make accurate obstacle avoidance decisions.

[0084] S32: Determine an obstacle avoidance path according to the size, position information, drifting speed, and drifting direction of the floating object.

[0085] Specifically, when determining the obstacle avoidance path, the data processing module will first analyze the key parameters of the floating object, such as its size, location information, drifting speed and drifting direction. The data processing module will use the current position and drifting speed of the floating object to predict its possible future position, thereby evaluating its potential impact on the unmanned ship's navigation route. Next, the module will consider the unmanned ship's current heading, speed and other factors of the surrounding environment, such as ocean currents, wind speed and other obstacles, to calculate a safe obstacle avoidance path. This calculation process may involve complex algorithms, such as artificial potential field methods, A* search algorithms or other path planning algorithms, which can plan an optimal path to avoid floating objects while taking into account the dynamics and safety of the unmanned ship. In addition, the data processing module will also evaluate the feasibility of the obstacle avoidance path to ensure that the unmanned ship will not encounter other obstacles or exceed operating limits when performing obstacle avoidance actions.

[0086] Ultimately, the module generates a detailed obstacle avoidance path, guiding the unmanned vessel to safely navigate around large floating objects and continue its mission. This process requires the data processing module to possess efficient data processing capabilities and accurate prediction models to ensure the unmanned vessel can navigate safely and accurately in complex and changing water environments.

[0087] S33: Generate an obstacle avoidance strategy based on the obstacle avoidance path.

[0088] Based on the above obstacle avoidance path, the data processing module will generate a specific obstacle avoidance strategy. The obstacle avoidance strategy not only includes the specific navigation actions that the unmanned ship should take, such as changing course, adjusting speed or making an emergency stop, but may also involve re-planning of tasks or adjustment of priorities. The generation of this strategy needs to take into account the real-time status of the unmanned ship, changes in environmental conditions and the urgency of the task. The implementation of the obstacle avoidance strategy requires that the control system of the unmanned ship can accurately execute the instructions of the data processing module to ensure the timeliness and accuracy of the obstacle avoidance action. In addition, the obstacle avoidance strategy should also have a certain degree of flexibility to adapt to changing navigation conditions and potential emergencies. Through the implementation of this strategy, the unmanned ship can ensure the safety and reliability of navigation while maintaining mission efficiency.

[0089] In some embodiments, if the obstacle is a static obstacle, step 302 may further include: (11) Determine the location information of the static obstacle.

[0090] The data processing module first identifies the obstacle as a static obstacle, such as a reef or underwater structure. Once the obstacle is confirmed to be a static obstacle, the data processing module uses the sensors carried by the unmanned vessel, such as sonar or optical sensors, to accurately determine the location information of the obstacle. This information usually includes the longitude and latitude coordinates of the obstacle, the water depth position, and possible three-dimensional spatial coordinates. Accurate location information is crucial for subsequent obstacle avoidance path planning because it is directly related to whether the unmanned vessel can safely bypass the obstacle. In addition, the module may also take into account the terrain features around the obstacle, such as the slope and undulations of the seabed terrain, to ensure that the obstacle avoidance path not only avoids the obstacle, but also takes into account the feasibility and safety of navigation.

[0091] (12) Determine an obstacle avoidance path based on the size of the static obstacle and the position information.

[0092] Specifically, when determining the obstacle avoidance path, the data processing module first uses the UAV's sensor system to collect precise location information for static obstacles. This may include the obstacle's latitude and longitude coordinates, underwater depth, and relative orientation to the UAV. The module then combines the obstacle's dimensional data to assess its potential impact on the UAV's navigation path. Using this information, the data processing module runs an obstacle avoidance algorithm, such as the graph-search-based A* algorithm or the Dijkstra algorithm, to calculate a safe path to avoid the obstacle. During this process, the module considers the UAV's heading, speed, maneuvering characteristics, and the geometry of the obstacle to ensure that the calculated path not only avoids the obstacle but also meets the UAV's navigational dynamics. Furthermore, the module evaluates other environmental factors, such as ocean currents, wind speed, and other possible obstacles, to optimize the obstacle avoidance path for both safety and efficiency. Ultimately, the data processing module generates a detailed obstacle avoidance path to guide the UAV safely around the static obstacle and continue its mission. This process requires the data processing module to have efficient data processing capabilities and accurate prediction models to ensure that the unmanned ship can navigate safely and accurately in complex and changing water environments.

[0093] (13) Generate an obstacle avoidance strategy based on the obstacle avoidance path.

[0094] The data processing module generates a specific obstacle avoidance strategy based on the determined obstacle avoidance path. This strategy not only involves adjusting the UAV's navigation direction and speed but may also involve adjusting mission priorities or replanning the voyage. The data processing module converts the obstacle avoidance path into a series of specific operational instructions, which instruct the UAV's control system to make necessary adjustments, such as changing course, adjusting speed, or performing an emergency stop. The implementation of the obstacle avoidance strategy requires the UAV to respond quickly and accurately to ensure effective obstacle avoidance during actual navigation.

[0095] In addition, the data processing module will continuously monitor the status of obstacles and the navigation status of the unmanned ship so that the obstacle avoidance strategy can be dynamically adjusted when necessary to ensure the safety of the unmanned ship during the entire navigation process and the smooth completion of the mission.

[0096] In some embodiments, if the obstacle is a dynamic obstacle, step 303 may further specifically include: (21) Determine the location information, moving speed and direction of the dynamic obstacle.

[0097] When the data processing module identifies an obstacle as a dynamic type, such as another moving ship, it will initiate a specialized tracking algorithm to determine the real-time location of the obstacle. This includes not only the current coordinates of the obstacle, but also its speed and direction of movement. Through sensors carried by the unmanned vessel, such as radar, sonar, or vision systems, the module can monitor the dynamic changes of obstacles in real time. This data is crucial for predicting the future location of obstacles because it directly affects the effectiveness of obstacle avoidance strategies. The data processing module will use this information to build a dynamic model to predict the possible location of the obstacle when the unmanned vessel approaches, thereby providing accurate input data for the next step of obstacle avoidance path planning.

[0098] (22) Determine an obstacle avoidance path based on the size of the dynamic obstacle, the position information, and the moving speed and direction.

[0099] Specifically, when determining the obstacle avoidance path, the data processing module first receives and analyzes the size, position information, movement speed and direction data of dynamic obstacles in real time. These data are usually provided by the unmanned ship's sensor system, such as radar, sonar or visual sensors. Using this information, the module predicts the future position and possible movement trajectory of the obstacle. Next, the data processing module uses advanced path planning algorithms, such as the probability-based rapid obstacle avoidance algorithm (PRM) or vector field obstacle avoidance (VFH), to evaluate all possible paths between the current position of the unmanned ship and the target position to avoid obstacles. During the calculation process, the data processing module takes into account the dynamic characteristics of the unmanned ship, such as speed, turning radius and acceleration limits, as well as environmental factors such as ocean currents and wind speeds, to ensure the feasibility and safety of the selected path.

[0100] By comparing the risks and efficiencies of different paths, the module ultimately determines an optimal obstacle avoidance path that minimizes potential conflicts with dynamic obstacles while maintaining the continuity and efficiency of the UAV's mission. The determined obstacle avoidance path is then converted into specific navigation instructions, guiding the UAV to safely circumvent obstacles and continue its mission.

[0101] (23) Generate an obstacle avoidance strategy based on the obstacle avoidance path.

[0102] The data processing module generates a specific obstacle avoidance strategy based on the determined obstacle avoidance path. The obstacle avoidance strategy not only includes adjusting the navigation direction and speed of the unmanned ship, but may also involve adjusting the priority of the task or re-planning the voyage. The data processing module will convert the obstacle avoidance path into a series of specific operating instructions. These instructions will guide the control system of the unmanned ship to make necessary adjustments, such as changing the course, adjusting the speed, or making an emergency stop. The implementation of the obstacle avoidance strategy requires the unmanned ship to respond quickly and accurately to ensure that obstacles can be effectively avoided during actual navigation. In addition, the module will continue to monitor the dynamics of obstacles and the navigation status of the unmanned ship so that the obstacle avoidance strategy can be dynamically adjusted when necessary to ensure the safety of the unmanned ship throughout the navigation process and the smooth completion of the mission.

[0103] Step 304: Control the unmanned boat to avoid obstacles according to the obstacle avoidance strategy.

[0104] Based on the determined obstacle avoidance strategy, the data processing module executes specific obstacle avoidance actions through the unmanned vessel's control system. This may involve adjusting the vessel's heading and speed, or using external forces to push obstacles away from the vessel to ensure the vessel safely navigates around them. The control system must precisely execute the data processing module's instructions while maintaining the vessel's stability and maneuverability.

[0105] During the obstacle avoidance process, the data processing module continuously monitors the status of obstacles and the navigation status of the unmanned vessel, adjusting the obstacle avoidance strategy as necessary. This step is crucial to ensuring the safe execution of the unmanned vessel's mission, demonstrating its autonomous navigation and intelligent decision-making capabilities.

[0106] An embodiment of the present invention provides an underwater mapping method for an unmanned vessel, which aims to improve the efficiency and accuracy of underwater mapping while ensuring that the unmanned vessel can safely avoid obstacles during navigation. As the unmanned vessel navigates the target waters according to a preset route, an underwater bathymetric module and a GNSS positioning module are used to collect underwater bathymetric data and mapping point positioning data, respectively. By integrating these data, an underwater terrain dataset is generated, which is further segmented into multiple underwater terrain data subsets for more efficient processing. The data processing module recursively processes these subsets, ultimately generating high-quality underwater terrain mapping data, which provides a basis for subsequent analysis and application.

[0107] The obstacle recognition module plays a crucial role in the navigation of the unmanned vessel. It collects obstacle identification information in real time and uses this information to determine the type and size of the obstacle. The data processing module then develops a corresponding obstacle avoidance strategy based on the obstacle type. For example, when a floating object is detected, the module determines whether its size exceeds a set size threshold. If the floating object is smaller than the threshold, the water jet speed and angle are determined based on its size and position, generating a corresponding obstacle avoidance strategy that uses the water jet to drive the floating object away from the unmanned vessel's navigation path.

[0108] If the size of a floating object exceeds a threshold, the data processing module further determines its location, drifting speed, and direction. Based on this information, it calculates an obstacle avoidance path to ensure the unmanned vessel can safely circumvent the obstacle. For static obstacles, the module determines their location and plans an avoidance path based on their size and location. For dynamic obstacles, the module monitors their movement in real time, determining their location, speed, and direction, and uses this information to calculate an avoidance path.

[0109] Obstacle recognition information also includes obstacle images. The data processing module inputs these images into a pre-set obstacle recognition model to determine the type and size of the obstacle. This process ensures that the unmanned vessel can quickly and accurately identify and respond to various obstacles in complex water environments, thereby improving navigation safety and mission execution efficiency.

[0110] In summary, the embodiments of the present invention provide a technical solution that comprehensively considers underwater mapping and obstacle avoidance. Through efficient data processing and intelligent obstacle avoidance strategies, it ensures the safety and accuracy of unmanned vehicles performing underwater mapping tasks. This method is not only applicable to underwater mapping but can also be widely applied to other surface or underwater equipment requiring autonomous navigation and obstacle avoidance, providing important technical support for research and application in related fields.

[0111] The method provided in the above embodiment can be executed by a data processing module, which is an electronic device. The following describes the electronic device in the embodiment of the present invention from the perspective of hardware processing. Figure 4 , which is a schematic diagram of a physical device structure of an electronic device in an embodiment of the present invention.

[0112] It should be noted that Figure 4 The structure of the electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0113] like Figure 4As shown, the electronic device includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 into the random access memory (RAM) 403, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in the RAM 403. The CPU 401, ROM 402 and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0114] The following components are connected to the I / O interface 405: an input section 406 including an audio input device, a push button switch, and the like; an output section 407 including a liquid crystal display (LCD), an audio output device, an indicator light, and the like; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like, is installed in the drive 410 as needed so that computer programs read therefrom can be installed into the storage section 408 as needed.

[0115] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, the computer program including a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409 and / or installed from a removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the various functions defined in the present invention are performed.

[0116] It should be noted that specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0118] Specifically, the electronic device of this embodiment includes a processor and a memory, the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the electronic device to execute the method provided by the above embodiment.

[0119] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not incorporated into the electronic device. The storage medium carries one or more computer programs, and when executed by a processor of the electronic device, the electronic device implements the methods provided in the above embodiments.

[0120] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

[0121] As used in the above embodiments, the term “when…” may be interpreted to mean “if…” or “after…” or “in response to determining…” or “in response to detecting…”, depending on the context. Similarly, the phrases “upon determining…” or “if (stated condition or event) is detected” may be interpreted to mean “if determining…” or “in response to determining…” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0122] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. An underwater mapping method for an unmanned vessel, characterized in that: include: When the unmanned ship is navigating in the target waters according to a preset route, underwater depth sounding data collected by an underwater depth sounding module and surveying point positioning data collected by a GNSS positioning module are obtained, and the underwater depth sounding module and the GNSS positioning module are respectively arranged on the unmanned ship; Generate an underwater terrain data set according to the underwater bathymetric data and the surveying point positioning data; dividing the underwater terrain data set into a plurality of underwater terrain data subsets; recursively processing the plurality of underwater terrain data subsets to obtain a plurality of processed underwater terrain data subsets; Underwater topographic mapping data is generated based on the plurality of processed underwater topographic data subsets.

2. The method according to claim 1, characterized in that When the unmanned ship navigates in the target waters according to the preset route, the method further includes: Obtaining obstacle identification information collected by an obstacle identification module, wherein the obstacle identification module is disposed on the unmanned vessel; determining the type and size of the obstacle according to the obstacle identification information; determining an obstacle avoidance strategy based on the type and size of the obstacle; The unmanned boat is controlled to avoid obstacles according to the obstacle avoidance strategy.

3. The method according to claim 2, characterized in that The step of determining the obstacle avoidance strategy according to the type and size of the obstacle comprises: When the type of the obstacle is a floating object, determining whether the size of the floating object is greater than a set size threshold; If not, determining the water jet speed and angle according to the size and position of the floating object; An obstacle avoidance strategy is generated according to the water jet speed and angle, and the obstacle avoidance strategy is used to enable the water jet on the unmanned ship to jet water according to the water jet speed and angle, so as to drive the floating object away from the driving path of the unmanned ship.

4. The method according to claim 3, characterized in that After the step of determining whether the size of the floating object is greater than a set size threshold, the method further includes: If the size of the floating object is greater than the size threshold, determining the position information, drifting speed and drifting direction of the floating object; Determine an obstacle avoidance path according to the size of the floating object, the position information, the drifting speed and the drifting direction; An obstacle avoidance strategy is generated according to the obstacle avoidance path.

5. The method according to claim 2, characterized in that: The step of determining the obstacle avoidance strategy according to the type and size of the obstacle comprises: If the type of the obstacle is a static obstacle, determining the position information of the static obstacle; Determining an obstacle avoidance path according to the size of the static obstacle and the position information; An obstacle avoidance strategy is generated according to the obstacle avoidance path.

6. The method according to claim 2, characterized in that The step of determining the obstacle avoidance strategy according to the type and size of the obstacle comprises: If the type of the obstacle is a dynamic obstacle, determining the location information, moving speed and direction of the dynamic obstacle; Determining an obstacle avoidance path according to the size of the dynamic obstacle, the location information, and the moving speed and direction; An obstacle avoidance strategy is generated according to the obstacle avoidance path.

7. The method according to claim 2, characterized in that The obstacle identification information includes an obstacle image; The step of determining the type and size of the obstacle according to the obstacle identification information comprises: The obstacle image is input into a preset obstacle recognition model to obtain the type and size of the obstacle.

8. An electronic device, characterized in that: including one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on an electronic device, the electronic device is caused to execute the method as claimed in any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is executed on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 7.

Images