A path planning method for underwater dredging robot based on digital twin model

Abstract

The present invention relates to the field of path planning technology, and discloses a path planning method for an underwater dredging robot based on a digital twin model. The initial weight value is corrected based on the initial dredging path by comprehensively considering the historical success rate factor, meteorological influence factor, underwater biological activity influence factor and water flow influence factor, and finally the initial dredging path with the maximum correction weight value is selected as the optimized dredging path. By introducing the historical success rate factor, the present invention can learn and optimize from past dredging tasks, ensure that the current path planning is based on static topographic maps and historical mission lessons, and improve the reliability of path planning. According to the historical mission success rate factor, it is identified which areas were prone to problems in the past, and these high-risk areas are automatically avoided when planning a new path, further enhancing the intelligence and adaptability of path planning. The consideration of underwater biological activity influence factors enables the robot to autonomously identify and avoid sensitive ecological areas.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a path planning method for an underwater dredging robot based on a digital twin model. Background Art

[0002] Underwater dredging is an important means of maintaining oceans and inland waterways, ports, reservoirs and other waters. It aims to remove sediment, silt and other pollutants deposited on the bottom of the water, ensure the smooth flow of waterways, good water quality, and protect the underwater ecological environment. In recent years, digital twin technology has been widely used in industrial automation, intelligent manufacturing and other fields. Digital twin technology realizes real-time interaction and collaborative work between the physical world and the virtual world by building a virtual model of the physical system. Applying digital twin technology to the path planning of underwater dredging robots can effectively solve the limitations of traditional methods and improve the safety, efficiency and environmental protection of dredging operations.

[0003] Although traditional methods combine pre-drawn underwater terrain maps and known obstacle distribution with The algorithm and graph weight method select the shortest path to perform the dredging task, but this method has many technical defects. First, the static topographic map cannot reflect the dynamic changes of the underwater environment in real time, such as changes in water flow speed and direction, sudden obstacles, and interference from underwater biological activities, which may cause the robot to encounter unforeseen challenges in actual operations, affecting the safety and continuity of the operation. Secondly, the traditional path planning method mainly focuses on static indicators such as dredging operation duration, path length, number of key dredging locations and energy consumption, but fails to fully consider the real-time environmental conditions during the dredging process, such as meteorological conditions, water flow effects, underwater biological activities and other factors, which may lead to insufficient flexibility in path planning and inability to adapt to complex underwater environments. In addition, the existing technology lacks effective use of historical mission success rates, meteorological effects, and historical data on underwater biological activities, and cannot learn and improve from past tasks, resulting in poor robustness and adaptability of path planning. Finally, the traditional method performs poorly in dealing with multi-objective optimization problems, and it is difficult to simultaneously take into account multiple objectives such as dredging efficiency, energy consumption, time cost and ecological impact, and it is easy to compromise in some aspects. Therefore, the existing dredging path planning methods have obvious limitations in dealing with complex dynamic environments, protecting the ecological environment, and utilizing historical data. It is urgent to introduce more intelligent and flexible technical means to improve the overall performance of dredging operations. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a path planning method for an underwater dredging robot based on a digital twin model, comprising:

[0005] Step 1: Establish a digital twin model;

[0006] Step 2, defining several working areas in the digital twin model, and determining a starting point and an end point in the working area;

[0007] Step 3, presetting the dredging task; dividing the work area into several ecological zones according to the preset dredging task, and performing one or several dredging tasks in each ecological zone;

[0008] Step 4, using an autonomous navigation system to determine a plurality of initial dredging paths from the starting point to the end point;

[0009] Step 5, obtaining historical dredging tasks; determining key dredging locations according to the historical dredging tasks, and constructing a topological structure diagram according to the key dredging locations and the initial dredging paths, wherein the key dredging locations are used as topological nodes in the topological structure diagram, and the initial dredging paths are used as edges in the topological structure diagram;

[0010] Step 6: Use the digital twin model to simulate the underwater dredging robot performing the dredging task on the initial dredging path to obtain the dredging operation duration, path length, number of key dredging locations, and energy consumption;

[0011] Step 7, calculating an initial weight value for each initial dredging path in the topological structure diagram according to the dredging operation duration, path length, number of key dredging locations, and energy consumption;

[0012] Step 8, obtaining historical success rate factors, meteorological influence factors, underwater biological activity influence factors, and water flow influence factors, and correcting the initial weight values ​​according to the historical success rate factors, meteorological influence factors, underwater biological activity influence factors, and water flow influence factors to obtain corrected weight values, and taking the initial dredging path with the largest corrected weight value as the optimized dredging path;

[0013] Step 9, the underwater dredging robot performs the dredging task based on the optimized dredging path; in the process of performing the dredging task on the optimized dredging path, the local obstacle avoidance algorithm is combined to perform emergency obstacle avoidance on obstacles to obtain a local optimized dredging path.

[0014] Furthermore, historical success rate factors are obtained, including:

[0015] Step 8a1, according to the historical dredging operation tasks, obtain the success rate of the historical dredging operation tasks, the completion time of each historical dredging operation task, the complexity factor of each historical dredging operation task, the environmental similarity factor of each historical dredging operation task, and the weight of each historical dredging operation task;

[0016] Step 8a2, calculate the historical success rate factor according to the success rate of historical dredging tasks, the completion time of each historical dredging task, the complexity factor of each historical dredging task, the environmental similarity factor of each historical dredging task, and the weight of each historical dredging task.

[0017] Further, the meteorological influencing factors are obtained, including:

[0018] Step 8b1, obtaining meteorological indicators from historical dredging tasks;

[0019] Step 8b2, obtaining the impact degree score of the meteorological index;

[0020] Step 8b3, calculate the meteorological impact factor based on all meteorological indicators and impact degree scores.

[0021] Furthermore, the influencing factors of underwater biological activities are obtained, including:

[0022] Step 8c1, determining sensitive organisms in the ecological zone;

[0023] Step 8c2, obtaining the number of sensitive organisms in the current ecological zone;

[0024] Step 8c3, in the historical dredging operation tasks of the current ecological zone, obtaining the historical distance between the underwater dredging robot and each sensitive organism in the current ecological zone;

[0025] Step 8c4, obtaining the behavior pattern of sensitive organisms in the current ecological zone;

[0026] Step 8c5, calculating the underwater biological activity influencing factor based on the historical distance between the underwater dredging robot and each sensitive organism in the current ecological zone, the behavior pattern of the sensitive organisms in the current ecological zone, and the number of sensitive organisms in the current ecological zone.

[0027] Furthermore, water flow influencing factors are obtained, including:

[0028] Step 8d1, construct several measurement points in each ecological zone;

[0029] Step 8d2, obtaining the water flow velocity, water flow velocity change, and water flow direction at each measuring point;

[0030] Step 8d3, arranging the water flow velocities at all measuring points from high to low, defining the water flow velocities at the first 2 / 3 as strong water flow, and obtaining the duration of the strong water flow;

[0031] Step 8d4, according to the angle between the historical forward direction of the underwater dredging robot and the water flow direction;

[0032] Step 8d5, calculating the water flow impact factor according to the water flow velocity, the change in water flow velocity, the duration of the strong water flow, and the angle.

[0033] Furthermore, the calculation formula of the correction weight value is:

[0034] ;

[0035] In the formula, represents the correction weight value, represents the initial weight value, represents the historical success rate factor of the k-th historical dredging task, represents the meteorological impact factor of the jth meteorological index, represents the water flow influencing factor of the qth measuring point, m represents the total number of historical dredging tasks, n represents the total number of initial paths, p represents the total number of meteorological indicators, and z represents the total number of measuring points.

[0036] Furthermore, the calculation formula of the historical success rate factor is:

[0037] ;

[0038] In the formula, Represents the historical success rate of dredging tasks, Represents the current time, represents the completion time of the k-th historical dredging task, represents the complexity factor of the k-th historical dredging task, represents the environmental similarity factor of the k-th historical dredging task, represents the weight of the k-th historical dredging task, Represents the adjustment factor.

[0039] Furthermore, the calculation formula of the meteorological impact factor is:

[0040] ;

[0041] In the formula, max represents the maximum value. Represents the impact score of the j-th meteorological indicator.

[0042] Furthermore, in the process of executing the dredging task by the optimized dredging path, the local obstacle avoidance algorithm is combined to perform emergency obstacle avoidance on the obstacles to obtain the local optimized dredging path, which specifically includes:

[0043] Step 91, constructing a local graph around the current position of the underwater dredging robot; the local graph includes a plurality of local nodes and a plurality of forward directions;

[0044] Step 92, using a graph search algorithm to determine the shortest path from the current position of the underwater dredging robot to the surrounding safe area;

[0045] Step 93, the underwater dredging robot moves from the current position along the shortest path to the temporary local node, and the underwater dredging robot bypasses obstacles based on the temporary local node and moves again to the optimized dredging path to obtain the local optimal path; dynamic obstacle avoidance is performed based on the local optimal path.

[0046] The embodiments of the present invention have the following technical effects:

[0047] The present invention corrects the initial weight value by comprehensively considering the historical success rate factor, meteorological influence factor, underwater biological activity influence factor and water flow influence factor based on the initial dredging path, and finally selects the initial dredging path with the maximum correction weight value as the optimized dredging path. This innovative method not only improves the safety, efficiency and environmental protection of dredging operations, but also introduces the ability to autonomously plan paths, bringing significant beneficial effects in many aspects. First, by introducing the historical success rate factor, the present invention can learn and optimize from past dredging tasks, ensuring that the current path planning is not only based on static topographic maps, but also refers to the successful experience and failure lessons of historical tasks, thereby improving the robustness and reliability of path planning. According to the historical task success rate factor, it is identified which areas are prone to problems in the past, and these high-risk areas are automatically avoided when planning new paths, further enhancing the intelligence and adaptability of path planning. Secondly, the introduction of meteorological influence factors enables the robot to autonomously select the most suitable path under different weather conditions, avoid the impact of bad weather on operation efficiency and safety, and ensure the smooth progress of dredging tasks. The robot can dynamically adjust the path according to real-time meteorological data to ensure that the task can be completed efficiently and safely under any weather conditions. Furthermore, the consideration of underwater biological activity influencing factors enables the robot to autonomously identify and avoid sensitive ecological areas, protect the underwater ecological environment, reduce interference with important habitats such as coral reefs and seagrass beds, and embody the concept of environmental protection. By real-time monitoring of underwater biological activities, the robot can automatically adjust the path to avoid affecting sensitive organisms and ensure the ecological friendliness of dredging operations. In addition, the addition of water flow influencing factors enables the robot to autonomously adjust the path according to the real-time water flow conditions, avoid strong water flow areas, reduce energy consumption and improve operating efficiency. The robot can autonomously select the optimal path based on factors such as water flow speed, direction and duration to ensure efficient operation in complex water flow environments. Finally, through the comprehensive evaluation of multiple influencing factors, the present invention realizes multi-objective optimization, ensures the best balance between dredging efficiency, energy consumption, time cost and ecological impact, and improves the safety, efficiency and environmental protection of the overall dredging operation. The robot can autonomously weigh various factors and select the path that best suits the current environmental conditions to ensure that each dredging task can achieve the best effect.

[0048] In summary, the present invention not only solves the limitations of traditional methods, but also provides a more intelligent, flexible and sustainable path planning solution for underwater dredging robots, promoting the development of underwater dredging technology. By autonomously planning the path, the robot can respond to various challenges in real time in a complex and changeable underwater environment, ensuring the safety, continuity and environmental protection of dredging operations.

[0049] The present invention performs dredging operations by optimizing the dredging path, and adopts a local obstacle avoidance algorithm for emergency obstacle avoidance when encountering obstacles, which brings many significant beneficial effects. First, a local graph is constructed at the current position of the robot and the shortest path from the current position to the surrounding safe area is determined, so that the robot can quickly respond to sudden obstacles and avoid collisions and potential safety risks. This method not only improves the real-time response capability of the robot, but also ensures the continuity and safety of the dredging operation, and can operate stably even in a complex and changeable underwater environment. Secondly, by traveling from the current position along the shortest path to the temporary local node, the robot can effectively bypass obstacles and avoid unnecessary detours, thereby reducing additional energy consumption and time costs and improving dredging efficiency. Thirdly, after bypassing the obstacle based on the temporary local node, the robot can quickly return to the optimized dredging path to ensure the smooth progress of the overall task, and will not disrupt the entire operation plan due to a single obstacle. In addition, by calculating the local optimal path and performing dynamic obstacle avoidance, the robot can flexibly respond to various complex environmental changes under the premise of ensuring safety, thereby enhancing the adaptability and robustness of the system. Finally, the application of the local obstacle avoidance algorithm not only improves the robot's autonomous navigation capability, but also reduces the need for manual intervention, reduces the workload of operators, and further improves the automation level of dredging operations. In summary, the present invention, by combining the optimization of the dredging path and the local obstacle avoidance algorithm, not only solves the limitations of traditional methods in dealing with sudden obstacles, but also provides a more intelligent, efficient and safe solution for underwater dredging robots, promotes the development of underwater dredging technology, and ensures the safety, continuity and environmental protection of dredging operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 It is a flow chart of a path planning method for an underwater dredging robot based on a digital twin model provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0053] Figure 1 is a flow chart of a path planning method for an underwater dredging robot based on a digital twin model provided by an embodiment of the present invention. Figure 1 , specifically including:

[0054] Step 1: Establish a digital twin model.

[0055] Build a high-precision virtual model to simulate the physical environment and dynamic changes of the underwater dredging operation area. The specific steps are:

[0056] 1. Data collection: Use multi-beam sonar, side-scan sonar, LiDAR, high-definition cameras and other equipment to conduct a full-scale scan of the operating area to obtain detailed information such as underwater topography, bottom type, obstacle distribution, etc. Collect historical meteorological data, water flow data, water temperature, salinity and other environmental parameters to ensure that the model can reflect environmental changes in different time periods. Obtain historical records of underwater biological activities, including the distribution and behavior patterns of sensitive species.

[0057] 2. Model construction: Import the collected data into the digital twin platform (such as Unity, MATLAB, Simulink, etc.) to build a three-dimensional virtual model. The model should include elements such as underwater terrain, obstacles, water flow direction and speed, and meteorological conditions. Integrate real-time sensor data interfaces in the model to ensure that the virtual model can be updated in real time to reflect the latest environmental changes when the robot is performing tasks.

[0058] Step 2: define several working areas in the digital twin model, and determine the starting point and the ending point in the working area.

[0059] According to the size of the operating area, the complexity of the terrain, the distribution of obstacles and other factors, the entire area is divided into several working areas. Each working area should have relatively independent geographical features and environmental conditions to facilitate centralized processing by the robot. For example, the port channel can be divided into the entrance area, the main channel area, the berthing area, etc.; the inland waterway can be divided into the upstream area, the midstream area, the downstream area, etc.; the reservoir can be divided into the water inlet area, the reservoir area, the water outlet area, etc. In each working area, one or more starting points and end points are set according to the convenience of the robot's entry and exit and the needs of the dredging task. The starting point is the entrance for the robot to enter the area, and the end point is the exit where the robot leaves after completing the task. Between adjacent working areas, set a reasonable connection path to ensure that the robot can transfer smoothly between different areas. The connection path should avoid complex terrain and obstacles as much as possible to ensure that the robot can transfer quickly and safely from one area to another.

[0060] Step 3, presetting the dredging task; dividing the work area into several ecological zones according to the pre-set dredging task, and each ecological zone performs one or several dredging tasks.

[0061] Each work area is divided into several ecological zones according to the sensitivity of the underwater ecosystem. Common ecological zones include:

[0062] Sensitive ecological areas: such as coral reef reserves, seagrass beds, fish breeding areas, etc. These areas are vital to the ecosystem and are easily affected by human activities.

[0063] Non-sensitive ecological areas: such as port channels, industrial docks, etc. These areas have low ecological sensitivity and fewer restrictions on dredging operations.

[0064] Transition zone: The area between sensitive ecological zones and non-sensitive ecological zones. Dredging operations require certain protective measures, but do not require as strict restrictions as in sensitive ecological zones.

[0065] For sensitive ecological areas, dredging tasks should minimize disturbance to the bottom sediment and avoid destroying the habitats of coral reefs, seagrasses or other sensitive organisms. The selection of dredging equipment should be more gentle, avoiding the use of powerful suction dredgers or excavation equipment. The dredging depth should be strictly controlled to avoid excessive excavation. In addition, the frequency of dredging tasks should be minimized, and only a small amount of dredging may be carried out when necessary, or regular monitoring should be adopted to decide whether dredging is needed based on actual conditions. For non-sensitive ecological areas, dredging tasks can be appropriately increased in intensity and more efficient dredging equipment (such as large suction dredgers, excavators, etc.) can be used to ensure the smooth flow of waterways or meet engineering needs. The frequency of dredging tasks can be flexibly arranged according to the accumulation of sediments to ensure the long-term smooth flow of waterways. For transitional areas, dredging tasks should strike a balance between sensitive ecological areas and non-sensitive ecological areas, ensuring the dredging effect while minimizing the impact on the ecological environment. Medium-intensity dredging equipment can be used, and the dredging depth and frequency can be adjusted based on actual conditions.

[0066] Step 4: using the autonomous navigation system to determine a number of initial dredging paths from the starting point to the end point.

[0067] In order to ensure that the generated path is both safe and efficient, some constraints need to be set for the autonomous navigation system. These constraints include but are not limited to:

[0068] Avoid obstacles: The path should avoid known fixed obstacles (such as sunken ships, reefs, etc.) and possible moving obstacles (such as other ships, floating objects, etc.). The location information of obstacles can be obtained through real-time sensor data (such as sonar, lidar, etc.) in the digital twin model.

[0069] Water flow influence: The path should avoid strong water flow areas as much as possible, especially when the water flow direction is opposite to the robot's forward direction. This can be evaluated through water flow data (such as flow rate, flow direction, etc.) in the digital twin model.

[0070] Protection of ecologically sensitive areas: The route should avoid sensitive ecological areas (such as coral reefs, seagrass beds, etc.) as much as possible to reduce the impact on the ecological environment. This can be identified through the ecological zone division information in the digital twin model.

[0071] Energy consumption optimization: The path should minimize energy consumption, especially in long-distance silt removal tasks. The energy consumption of different paths can be simulated to select the path with the lowest energy consumption.

[0072] Time cost: The path should minimize the time of dredging operations to ensure that the task can be completed on time. The path with the lowest time cost can be selected by evaluating the length and speed of different paths.

[0073] Based on the selected autonomous navigation algorithm and constraints, several initial desilting paths are generated from the starting point to the end point. The specific steps are as follows:

[0074] Initialize the path planner:

[0075] The starting point and the end point are input into the autonomous navigation system as the starting point and the end point of the path planning.

[0076] Load environmental information such as terrain, obstacles, water flow, ecological zones, etc. in the digital twin model to ensure that the path planner can accurately reflect the actual environment.

[0077] Generate candidate paths:

[0078] Using navigation algorithms such as , RRT, PRM, etc.), generate multiple feasible paths from the starting point to the end point. Each path should meet the above constraints to ensure its safety and feasibility.

[0079] To increase the diversity of paths, randomness can be introduced in the path planning process, such as randomly sampling different connection points between the start and end points in the RRT algorithm, or randomly generating more graph nodes in the PRM algorithm.

[0080] Evaluate path quality:

[0081] Each generated path is evaluated to calculate its performance indicators in terms of desilting time, path length, number of key desilting locations, energy consumption, etc. The simulation function in the digital twin model can be used to simulate the performance of the robot on different paths and obtain detailed evaluation results.

[0082] Based on the evaluation results, several paths with better performance are selected as the initial desilting paths. Usually 5-10 paths can be selected for further analysis and adjustment in the subsequent optimization stage.

[0083] Step 5, obtain historical dredging operation tasks; obtain historical dredging operation tasks; determine key dredging locations based on historical dredging operation tasks, and construct a topological structure diagram based on the key dredging locations and initial dredging paths, wherein the key dredging locations serve as topological nodes in the topological structure diagram, and the initial dredging paths serve as edges in the topological structure diagram.

[0084] Obtain all dredging operation records in the past period from the database, including the starting point, end point, dredging area, type of dredging equipment, dredging time, energy consumption, success or failure, etc. of each mission. Collect environmental data for each mission, such as meteorological conditions (wind speed, wave height, visibility, etc.), water flow data (flow rate, flow direction, etc.), water temperature, salinity, etc., as well as historical records of underwater biological activities. Obtain information such as the distribution of obstacles and the location of sensitive ecological areas in each mission to ensure a comprehensive understanding of the environmental conditions when the mission is executed.

[0085] Key dredging locations refer to those specific locations that have a significant impact on dredging results, operating efficiency, safety, etc. in historical dredging tasks. These locations usually have the following characteristics:

[0086] Areas with high sediment accumulation: Due to factors such as topography and water flow, some areas are prone to the accumulation of large amounts of sediment, silt or other pollutants, causing the waterway to become shallower or the water quality to deteriorate. These areas are the focus of dredging and must be treated as a priority.

[0087] Complex water flow areas: Strong water flow, rapids, whirlpools and other complex water flow areas will affect the robot's operation and dredging effect. Therefore, these areas require special attention to ensure that the robot can complete the dredging task in a safe manner.

[0088] Areas with dense obstacles: Areas with a large number of fixed or moving obstacles (such as shipwrecks, reefs, floating objects, etc.) will increase the difficulty and risk of dredging. The robot needs to be particularly careful to avoid collisions or getting stuck.

[0089] Boundaries of ecologically sensitive areas: Boundaries of sensitive ecological areas such as coral reefs, seagrass beds, and fish breeding areas require special attention to ensure that dredging operations do not have a negative impact on the ecological environment.

[0090] Areas with frequent historical problems: In past dredging tasks, some areas often had problems such as equipment failure and incomplete dredging. These areas may be caused by complex geological conditions and special bottom types, and need to be dealt with in a focused manner.

[0091] Heavy traffic areas: Port channels, areas near docks and other areas with heavy traffic need to be desilted first to ensure safe passage of ships and avoid accidents caused by waterway blockage.

[0092] The determined key desilting locations are used as topological nodes in the topological structure diagram. Each node represents an important desilting location, which may be an area with a lot of sediment accumulation, an area with complex water flow, an area with dense obstacles, the boundary of an ecologically sensitive area, etc. Each node is assigned a unique identifier (such as a number, name, etc.), and its coordinates, characteristics, historical issues, etc. are recorded. This information will be used for subsequent path optimization and task scheduling.

[0093] Finally, a topological structure graph is constructed according to the key dredging positions and the initial dredging paths, wherein the key dredging positions serve as topological nodes in the topological structure graph, and the initial dredging paths serve as edges in the topological structure graph.

[0094] Step 6: Use the digital twin model to simulate the underwater dredging robot performing the dredging task on the initial dredging path to obtain the dredging operation duration, path length, number of key dredging locations, and energy consumption.

[0095] The initial dredging path is imported into the digital twin model, and the simulation of the dredging task is started, so that the robot can perform the dredging operation according to the selected initial dredging path. In the simulation process, the duration of the dredging operation, the length of the path, the number of key dredging locations, and the energy consumption are obtained.

[0096] Step 7: According to the duration of dredging operation , path length 、Number of key desilting locations , Energy consumption , calculate the initial weight value for each initial dredging path in the topological structure diagram .

[0097] .

[0098] Step 8, obtain the historical success rate factor, meteorological influence factor, underwater biological activity influence factor, and water flow influence factor, correct the initial weight value according to the historical success rate factor, meteorological influence factor, underwater biological activity influence factor, and water flow influence factor to obtain the corrected weight value, and use the initial dredging path with the largest corrected weight value as the optimized dredging path.

[0099] Get the historical success rate factors, including:

[0100] Step 8a1, based on the historical dredging tasks, obtain the success rate of the historical dredging tasks, the completion time of each historical dredging task, the complexity factor of each historical dredging task, the environmental similarity factor of each historical dredging task, and the weight of each historical dredging task.

[0101] Count the number of successfully completed tasks and the total number of tasks in all historical tasks, and calculate the overall success rate For each historical task, record its actual completion time .

[0102] The complexity factor is used to measure the difficulty of each historical desilting task. Complex tasks usually require more time, resources and operating skills, so the probability of successful completion may be lower. The complexity factor can be comprehensively evaluated through multiple dimensions, mainly including the following aspects:

[0103] Number of key desilting locations: Key desilting locations refer to those areas that are crucial to the desilting effect, such as areas with more sediment accumulation, areas with complex water flow, areas with dense obstacles, etc. The more key desilting locations there are, the more complex the task will be.

[0104] Number of obstacles: Obstacles (such as shipwrecks, reefs, floating objects, etc.) will increase the difficulty of dredging tasks. The robot needs to bypass or avoid these obstacles, which increases the complexity and risk of the operation.

[0105] Water flow complexity: Complex water flow conditions such as strong currents, rapids, and whirlpools will increase the difficulty of dredging tasks, especially when the water flow direction is opposite to the robot's forward direction, the robot's operation difficulty will increase significantly. Extract the water flow data for each task from the historical task records. Use the frequency of changes in water flow speed and flow direction as indicators.

[0106] Impact on ecologically sensitive areas: Missions near sensitive ecological areas such as coral reefs, seagrass beds, and fish breeding areas require special care to ensure that dredging operations do not have a negative impact on the ecological environment. This increases the operational difficulty and time cost of the mission. The distance between the dredging operation and sensitive ecological areas is used as an indicator.

[0107] Finally, the weighted sum of the above four indicators is used to obtain the complexity factor.

[0108] The environmental similarity factor is used to measure the similarity between the environmental conditions of the historical dredging tasks and the current task environment. The higher the similarity, the more valuable the successful experience of the historical tasks is for reference. The environmental similarity factor mainly considers the following aspects:

[0109] Water depth: Water depth is one of the important factors affecting dredging tasks. The difficulty and operation methods of dredging may be different under different water depths. Calculate the difference between the historical task water depth and the current task water depth as the similarity evaluation indicator. You can use relative error or standardized difference as the similarity score.

[0110] Water flow conditions: Water flow speed and direction have a great impact on the dredging task, especially in areas with strong water flow, which significantly increases the difficulty of robot operation. Calculate the similarity between the water flow conditions of the historical tasks and the water flow conditions of the current task. You can use methods such as Euclidean distance or cosine similarity for comparison.

[0111] Water quality: Water quality (such as turbidity, sand content, etc.) will affect the efficiency and effectiveness of dredging equipment. Calculate the similarity between the water quality of historical tasks and the water quality of the current task. You can use the normalized difference or correlation coefficient as the similarity score.

[0112] Substrate type: Substrate type (such as silt, rock, coral, etc.) will affect the selection and operation of dredging equipment. Calculate the similarity between the historical task substrate type and the current task substrate type. You can use classification matching or fuzzy matching methods to compare.

[0113] Meteorological conditions: Meteorological conditions (such as wind speed, wave height, visibility, etc.) will affect the robot's operational safety and dredging effect. Calculate the similarity between the meteorological conditions of the historical mission and the meteorological conditions of the current mission. You can use the normalized difference or correlation coefficient as the similarity score.

[0114] The environment similarity factor is obtained based on the weighted sum of the above similarity scores.

[0115] The weight of each historical dredging task is assigned based on the complexity factor. The higher the complexity factor, the greater the weight, and the lower the complexity factor, the smaller the weight.

[0116] Step 8a2, calculate the historical success rate factor according to the success rate of historical dredging tasks, the completion time of each historical dredging task, the complexity factor of each historical dredging task, the environmental similarity factor of each historical dredging task, and the weight of each historical dredging task.

[0117] ;

[0118] In the formula, Represents the historical success rate of dredging tasks, Represents the current time, represents the completion time of the k-th historical dredging task, represents the complexity factor of the k-th historical dredging task, represents the environmental similarity factor of the k-th historical dredging task, represents the weight of the k-th historical dredging task, Represents the adjustment factor.

[0119] Calculating the historical success rate factor through the above formula can provide an important reference for subsequent path optimization. This formula comprehensively considers multiple key factors such as the success rate, completion time, complexity factor, environmental similarity factor and weight of historical dredging tasks, and weights the historical data at different time points through an exponential decay function, so that recent historical data has a greater impact on the current task. In this way, it can not only effectively evaluate the success probability of the current task, but also help identify paths with higher success rates and more in line with current environmental conditions. Therefore, in the process of path optimization, the use of historical success rate factors can significantly improve the accuracy and reliability of path selection, thereby improving the efficiency and success rate of the overall dredging operation.

[0120] Obtain meteorological influencing factors, including:

[0121] Step 8b1, obtaining meteorological indicators from historical dredging tasks.

[0122] Meteorological indicators include wave height, wind speed, rainfall, temperature and humidity.

[0123] Step 8b2, obtaining the impact score of the meteorological index.

[0124] The impact degree score of this embodiment is preferably an adverse impact degree of a meteorological indicator, and it is mapped to a score interval from 0 to 1, where 0 represents completely favorable and 1 represents very unfavorable.

[0125] Exemplarily, wind speed: 0-5 m / s: 0 (favorable); 5-10 m / s: 0.3 (moderately unfavorable); 10-15 m / s: 0.7 (somewhat unfavorable); 15 m / s: 1 (very unfavorable).

[0126] Wave height: 0-0.5 m: 0 (favorable); 0.5-1.0 m: 0.4 (moderately unfavorable); 1.0-1.5 m: 0.8 (relatively unfavorable); 1.5 m: 1 (very unfavorable).

[0127] Rainfall: 0-10 mm / h: 0 (favorable); 10-20 mm / h: 0.3 (moderately unfavorable); 20-30 mm / h: 0.7 (relatively unfavorable); 30 mm / h: 1 (very unfavorable).

[0128] Temperature: 10-25°C: 0 (favorable); 25-30°C: 0.2 (slightly unfavorable); 30-35°C: 0.5 (moderately unfavorable); 35°C or <10°C: 1 (very unfavorable).

[0129] Humidity: 30%-60%: 0 (favorable); 60%-80%: 0.3 (moderately unfavorable); 80%: 1 (very unfavorable).

[0130] Step 8b3, calculate the meteorological impact factor based on all meteorological indicators and impact degree scores.

[0131] ;

[0132] In the formula, max represents the maximum value. Represents the impact score of the j-th meteorological indicator.

[0133] Obtain the influencing factors of underwater biological activities, including:

[0134] Step 8c1, determining sensitive organisms in the ecological zone.

[0135] Step 8c2, obtaining the number of sensitive organisms in the current ecological zone.

[0136] Step 8c3, in the historical dredging operation tasks of the current ecological zone, obtain the historical distance between the underwater dredging robot and each sensitive organism in the current ecological zone.

[0137] Among them, sensitive organisms, quantities, and distances are obtained through the digital twin model.

[0138] Step 8c4, obtaining the behavior patterns of sensitive organisms in the current ecological zone.

[0139] The behavior patterns of sensitive organisms include stationary, migrating, and reproducing. Different behavior patterns have different effects on robots.

[0140] Step 8c5, calculating the underwater biological activity influencing factor based on the historical distance between the underwater dredging robot and each sensitive organism in the current ecological zone, the behavior pattern of the sensitive organisms in the current ecological zone, and the number of sensitive organisms in the current ecological zone.

[0141] ;

[0142] Consider the historical distance between the underwater dredging robot and each sensitive organism in the e-th ecological zone , the number of sensitive organisms in the e-th ecological zone , behavioral patterns of sensitive organisms in the e-th ecological zone The underwater biological activity impact function is used to calculate the underwater biological activity impact factor.

[0143] ; Represents the distance calculation function; The maximum safe distance between the robot and sensitive organisms in the ecological zone during historical dredging operations.

[0144] ; Represents the population counting function of sensitive organisms. The maximum number of sensitive organisms in the ecoregion during the historical dredging operation mission.

[0145] When the behavior mode is static, ; When the behavior mode is migration, ; When the behavior mode is reproduction, .

[0146] Obtain water flow influencing factors, including:

[0147] Step 8d1, construct several measurement points in each ecological zone.

[0148] Step 8d2, obtaining the water flow velocity, water flow velocity change, and water flow direction at each measuring point.

[0149] Step 8d3, arrange the water flow velocities at all measuring points from high to low, define the water flow velocities in the first 2 / 3 as strong water flow, and obtain the duration of the strong water flow.

[0150] Step 8d4, obtaining the historical angle between the forward direction of the underwater dredging robot and the water flow direction.

[0151] Step 8d5, calculating the water flow impact factor according to the water flow velocity, the change in water flow velocity, the duration of the strong water flow, and the angle.

[0152] First, the maximum and minimum water flow velocities are determined based on the dredging tasks that can be successfully performed in the past. Less than the minimum water velocity , assign 0 to the water flow velocity part of the water flow impact factor. Greater than the maximum water velocity , assign 1 to the water flow velocity part of the water flow influencing factor; when the water flow velocity Greater than or equal to the minimum water flow rate And less than or equal to the maximum water flow velocity , assign the water velocity part of the water flow influencing factor: ;

[0153] Secondly, determine the allowable angle based on the dredging tasks that can be successfully performed in the past ; When the angle The absolute value is less than the allowed angle , assign 0 to the angle part of the water flow influence factor; when the absolute value of the angle is greater than 90°, assign 1 to the angle part of the water flow influence factor; when the angle Greater than or equal to the allowable angle And less than or equal to 90°, the angle part of the water flow influencing factor is assigned: .

[0154] Thirdly, the maximum change in water flow intensity and the minimum change in water flow intensity are determined based on the dredging tasks that can be successfully performed in the past. Less than the minimum change in water flow intensity , assign 0 to the change in water velocity in the water flow influencing factor. Greater than the maximum change in water flow intensity , assign 1 to the change in water flow velocity in the water flow impact factor. Greater than or equal to the minimum change And less than or equal to the maximum change , assign the water velocity change part of the water flow influencing factor: .

[0155] Finally, the maximum duration of strong water flow is determined based on the dredging tasks that can be successfully performed in the past. and the shortest duration of strong water flow. Less than the shortest duration of strong water flow , is the duration of strong water flow in the water flow impact factor Partially assigned 0, when the duration of strong water flow Greater than the shortest duration of strong water flow , is the duration of strong water flow in the water flow impact factor Partially grant 1, when the duration of strong water flow Greater than or equal to the shortest duration of strong water flow And less than or equal to the maximum duration of strong water flow , assign the duration of strong water flow in the water flow impact factor: .

[0156] In summary, the water flow influencing factor is obtained by adding each of the above assigned values.

[0157] ;

[0158] In the formula, represents the correction weight value, represents the initial weight value, represents the historical success rate factor of the k-th historical dredging task, represents the meteorological impact factor of the jth meteorological index, represents the water flow influence factor at the qth measurement point, represents the scoring function, The distance between the underwater dredging robot and each sensitive organism in the e-th ecological zone, represents the number of sensitive organisms in the e-th ecological zone, represents the behavior pattern of sensitive organisms in the e-th ecological zone, m represents the total number of historical dredging tasks, n represents the total number of initial paths, p represents the total number of meteorological indicators, z represents the total number of measurement points, and g represents the total number of ecological zones.

[0159] By comprehensively analyzing the success rate factors, meteorological influencing factors, water flow influencing factors, and ecological sensitivity indicators of historical dredging tasks, the planning and execution efficiency of dredging operations can be significantly improved. Specifically, this multi-factor comprehensive evaluation method can help identify the best operation time and path, and reduce the risk of operation delays and failures caused by adverse meteorological conditions or complex water flow environments. In addition, by quantifying ecological sensitivity indicators, it is possible to minimize the impact on the ecological environment while ensuring operation efficiency and achieve the goal of sustainable development. Therefore, this method not only improves the success rate and efficiency of operations, but also enhances environmental protection awareness, providing a more scientific and reliable decision-making basis for future dredging operations.

[0160] Step 9, the underwater dredging robot performs the dredging task based on the optimized dredging path; in the process of performing the dredging task on the optimized dredging path, the local obstacle avoidance algorithm is combined to perform emergency obstacle avoidance on obstacles to obtain a local optimized dredging path.

[0161] Step 91, constructing a local graph around the current position of the underwater dredging robot; the local graph includes a number of local nodes and a number of forward directions.

[0162] When the underwater dredging robot detects obstacles in front or around, it immediately starts sensors such as sonar, lidar, and cameras to scan the environment around the current position. Based on the data obtained by the sensor, a local graph is constructed around the current position of the robot. The local graph should include several local nodes and several forward directions. Each node represents a possible moving position, and each edge represents a feasible path from one node to another. The scope of the local graph can be set according to actual needs, usually a certain radius around the current position of the robot (such as 10 meters to 50 meters), to ensure that all potential obstacles and safe areas can be covered. In the local graph, all detected obstacles (such as shipwrecks, reefs, floating objects, etc.) and surrounding terrain features (such as slope, depth changes, etc.) are marked. Determine the safe area in the local graph, that is, the area where the robot can pass safely without encountering obstacles. The safe area can be determined by analyzing factors such as terrain, water flow, and bottom type. Set several local nodes in the local graph, which can be possible temporary stops or turning points for the robot. The selection of local nodes should consider the following factors: Safety: Avoid approaching obstacles or strong water flow areas to ensure that the robot can arrive safely. Select nodes that the robot can reach quickly and leave easily to reduce unnecessary detours.

[0163] Step 92, using a graph search algorithm to determine the shortest path from the current position of the underwater dredging robot to the surrounding safe area.

[0164] The robot's current position is used as the starting node, and the safe area in the local graph is used as the target node, which are input into the selected graph search algorithm. All nodes and edges in the local graph are loaded to ensure that the algorithm can accurately reflect the complexity and dynamic changes of the current environment. Run the graph search algorithm, expanding the nodes layer by layer until the shortest path from the current position to the surrounding safe area is found. The path should meet the following conditions: Avoid obstacles: Make sure that the path does not pass through any obstacles or dangerous areas. Minimize path length: Select the path with the shortest path length to reduce the robot's movement time in non-operating areas. Output the shortest path found in a format that can be executed by the robot, including the coordinates and directions of all nodes on the path. This path will serve as the basis for the robot's next move.

[0165] Step 93, the underwater dredging robot moves from the current position along the shortest path to the temporary local node, and the underwater dredging robot bypasses obstacles based on the temporary local node and moves again to the optimized dredging path to obtain the local optimal path; dynamic obstacle avoidance is performed based on the local optimal path.

[0166] The underwater dredging robot moves along the path from the current position according to the shortest path found in step 92, and gradually approaches the temporary local node. The temporary local node is the key position for the robot to return to the optimized dredging path after bypassing the obstacle.

[0167] During the return process, the robot should continue to monitor the surrounding environment in real time to ensure the safety and feasibility of the path. If new obstacles or environmental changes are found, the robot can immediately adjust the path to ensure a smooth return to the optimized dredging path.

[0168] Through the above steps, the robot successfully bypasses obstacles and returns to the optimized dredging path, forming a local optimal path. This path not only avoids obstacles, but also minimizes additional movement time and energy consumption, ensuring the continuity and efficiency of the dredging task.

[0169] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0170] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it 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 it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A path planning method for an underwater dredging robot based on a digital twin model, characterized in that: include: Step 1: Establish a digital twin model; Step 2, defining several working areas in the digital twin model, and determining a starting point and an end point in the working area; Step 3, preset dredging task; According to the preset dredging operation tasks, the working area is divided into several ecological zones, and each ecological zone performs one or several dredging operation tasks; Step 4, using an autonomous navigation system to determine a plurality of initial dredging paths from the starting point to the end point; Step 5, obtaining historical dredging tasks; determining key dredging locations according to the historical dredging tasks, and constructing a topological structure diagram according to the key dredging locations and the initial dredging paths, wherein the key dredging locations are used as topological nodes in the topological structure diagram, and the initial dredging paths are used as edges in the topological structure diagram; Step 6: Use the digital twin model to simulate the underwater dredging robot performing the dredging task on the initial dredging path to obtain the dredging operation duration, path length, number of key dredging locations, and energy consumption; Step 7, calculating an initial weight value for each initial dredging path in the topological structure diagram according to the dredging operation duration, path length, number of key dredging locations, and energy consumption; The calculation formula is as follows: ； in, represents the initial weight value, Indicates the duration of dredging operation. represents the path length, Indicates the number of key desilting locations, Indicates energy consumption; Step 8, obtaining historical success rate factors, meteorological influence factors, underwater biological activity influence factors, and water flow influence factors, and correcting the initial weight values ​​according to the historical success rate factors, meteorological influence factors, underwater biological activity influence factors, and water flow influence factors to obtain corrected weight values, and taking the initial dredging path with the largest corrected weight value as the optimized dredging path; The calculation formula of the correction weight value is: ； In the formula, represents the correction weight value, represents the initial weight value, represents the historical success rate factor of the k-th historical dredging task, represents the meteorological impact factor of the jth meteorological index, represents the flow influencing factor of the qth measuring point, m represents the total number of historical dredging tasks, n represents the total number of initial paths, p represents the total number of meteorological indicators, and z represents the total number of measuring points; Step 9, the underwater dredging robot performs the dredging task based on the optimized dredging path; in the process of performing the dredging task on the optimized dredging path, the local obstacle avoidance algorithm is combined to perform emergency obstacle avoidance on obstacles to obtain a local optimized dredging path.

2. According to the method for underwater dredging robot path planning based on digital twin model in claim 1, it is characterized in that: Get the historical success rate factors, including: Step 8a1, according to the historical dredging operation tasks, obtain the success rate of the historical dredging operation tasks, the completion time of each historical dredging operation task, the complexity factor of each historical dredging operation task, the environmental similarity factor of each historical dredging operation task, and the weight of each historical dredging operation task; Step 8a2, calculate the historical success rate factor according to the success rate of historical dredging tasks, the completion time of each historical dredging task, the complexity factor of each historical dredging task, the environmental similarity factor of each historical dredging task, and the weight of each historical dredging task.

3. According to claim 2, a method for underwater dredging robot path planning based on a digital twin model is characterized in that: Obtain meteorological influencing factors, including: Step 8b1, obtaining meteorological indicators from historical dredging tasks; Step 8b2, obtaining the impact degree score of the meteorological index; Step 8b3, calculate the meteorological impact factor based on all meteorological indicators and impact degree scores.

4. According to claim 3, a path planning method for an underwater dredging robot based on a digital twin model is characterized in that: Obtain the influencing factors of underwater biological activities, including: Step 8c1, determining sensitive organisms in the ecological zone; Step 8c2, obtaining the number of sensitive organisms in the current ecological zone; Step 8c3, in the historical dredging tasks of the current ecological zone, obtaining the historical distance between the underwater dredging robot and each sensitive organism in the current ecological zone; Step 8c4, obtaining the behavior pattern of sensitive organisms in the current ecological zone; Step 8c5, calculating the underwater biological activity influencing factor based on the historical distance between the underwater dredging robot and each sensitive organism in the current ecological zone, the behavior pattern of the sensitive organisms in the current ecological zone, and the number of sensitive organisms in the current ecological zone.

5. According to claim 4, a method for underwater dredging robot path planning based on a digital twin model is characterized in that: Obtain water flow influencing factors, including: Step 8d1, construct several measurement points in each ecological zone; Step 8d2, obtaining the water flow velocity, water flow velocity change, and water flow direction at each measuring point; Step 8d3, arranging the water flow velocities at all measuring points from high to low, defining the water flow velocities at the first 2 / 3 as strong water flow, and obtaining the duration of the strong water flow; Step 8d4, according to the angle between the historical forward direction of the underwater dredging robot and the water flow direction; Step 8d5, calculating the water flow impact factor according to the water flow velocity, the change in water flow velocity, the duration of the strong water flow, and the angle.

6. The underwater dredging robot path planning method based on a digital twin model according to claim 5 is characterized in that: The calculation formula of the historical success rate factor is: ； In the formula, Represents the historical success rate of dredging tasks, Represents the current time, represents the completion time of the k-th historical dredging task, represents the complexity factor of the k-th historical dredging task, represents the environmental similarity factor of the k-th historical dredging task, represents the weight of the k-th historical dredging task, Represents the adjustment factor.

7. The underwater dredging robot path planning method based on a digital twin model according to claim 5 is characterized in that: The calculation formula of meteorological impact factor is: ； In the formula, max represents the maximum value. Represents the impact score of the j-th meteorological indicator.

8. The underwater dredging robot path planning method based on a digital twin model according to claim 1 is characterized in that: In the process of executing the dredging task by the optimized dredging path, the local obstacle avoidance algorithm is combined to perform emergency obstacle avoidance to obtain the local optimized dredging path, which specifically includes: Step 91, constructing a local graph around the current position of the underwater dredging robot; the local graph includes a plurality of local nodes and a plurality of forward directions; Step 92, using a graph search algorithm to determine the shortest path from the current position of the underwater dredging robot to the surrounding safe area; Step 93, the underwater dredging robot moves from the current position along the shortest path to the temporary local node, and the underwater dredging robot bypasses obstacles based on the temporary local node and moves again to the optimized dredging path to obtain the local optimal path; dynamic obstacle avoidance is performed based on the local optimal path.

Images