Intelligent Planning System for Submarine Navigation Routes in Deep-Sea Deduction Scenarios Based on Optimal Control Theory

Abstract

The present invention discloses a deep-sea simulation scenario route path intelligent planning system based on optimal control theory, which relates to the technical field of route path planning, including a data management platform, wherein the data management platform is communicatively connected with an environment perception modeling module, a constraint condition definition module, a global path planning module, a simulation verification module, a control execution module, and a feedback adjustment module. The present invention can accurately detect and analyze the position deviation, speed deviation, and heading deviation during navigation by receiving and fusing deep-sea environmental data and equipment status data in real time. Based on the optimal control theory, the system can quickly formulate an adjustment strategy to ensure that the equipment always remains within a safe navigation range. This real-time feedback and adjustment mechanism greatly improves the safety and reliability of navigation, effectively avoids the risk of collision with obstacles or entering dangerous areas, and provides a solid guarantee for deep-sea operations.

Description

Technical Field

[0001] The present invention relates to the technical field of shipping route planning, and particularly to an intelligent route planning system for deep-sea deduction scenarios based on the optimal control theory. Background Art

[0002] The deep sea is a field with complex environment and extremely harsh conditions, with a high degree of uncertainty. In deep-sea exploration and operations, especially in the application of autonomous vehicles such as unmanned submersibles and underwater robots, a large amount of simulation and deduction is often required in advance to predict possible risks and obstacles during navigation, ensuring the smooth completion of tasks. The optimal control theory provides an optimal control scheme for the system through mathematical models and optimization algorithms. By using the optimal control theory, the safety and efficiency of navigation under different sea conditions can be ensured through the simulation and deduction of the marine environment, vehicle behavior, task objectives, etc.

[0003] In the prior art, there are various obstacles such as underwater obstacles, other vehicles, floating ice, sunken shipwrecks, etc. on the routes of deep-sea operation equipment, which are likely to interfere with route planning. Therefore, how to plan the most suitable route in the deep-sea deduction scenario with complex constraint conditions by combining the optimal control theory is the problem we need to solve. For this reason, an intelligent route planning system for deep-sea deduction scenarios based on the optimal control theory is proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent route planning system for deep-sea deduction scenarios based on the optimal control theory to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is:

[0006] An intelligent route planning system for deep-sea deduction scenarios based on the optimal control theory includes a data management platform, which is communicatively connected to an environment perception and modeling module, a constraint condition definition module, a global path planning module, a simulation verification module, a control execution module, and a feedback adjustment module;

[0007] The environment perception and modeling module is used to collect and sense deep-sea environment data and construct a three-dimensional deep-sea environment model, wherein the deep-sea environment data includes obstacle data and marine dynamic change data;

[0008] The constraint condition definition module is used to define static constraint conditions, dynamic constraint conditions, and performance constraint conditions in the deep-sea environment. Among them, the static constraint conditions are used to define static obstacles in the deep-sea environment, the dynamic constraint conditions are used to define dynamic obstacles in the deep-sea environment, and the performance constraint conditions are used to define the performance indicators of route planning;

[0009] The global path planning module plans the optimal navigation path from the starting point to the ending point based on the optimal control theory and the defined constraint conditions. During the planning process, the path is continuously optimized to meet the performance constraint conditions and avoid all static and dynamic obstacles.

[0010] The simulation verification module is used to perform simulation tests on the optimal navigation path planned based on the optimal control theory in a simulation environment, check whether the path meets the constraint conditions, avoid all obstacles, and then evaluate the performance of the planned navigation path to ensure the optimization of path planning.

[0011] The control execution module is used to convert the latest optimal navigation path into control instructions and send them to the execution system of the deep-sea operation equipment. Based on the optimal control theory, the navigation parameters of the deep-sea operation equipment are adjusted in real time to ensure that the equipment sails along the planned path.

[0012] The feedback adjustment module is used to receive the latest deep-sea environment data and, in combination with the control execution results of the deep-sea operation equipment, perform feedback adjustment on the navigation path.

[0013] A further improvement of the technical solution of the present invention lies in that the environmental perception and modeling module specifically includes:

[0014] Using deep-sea exploration equipment and a deep-sea sensor network, deep-sea environment data including obstacle data and ocean dynamic change data is collected and sensed. Among them, for the obstacle data, it includes seabed terrain data, seabed obstacle data, and dynamic obstacle data. For the ocean dynamic change data, it includes ocean current field data, water temperature data, salinity data, and ocean acoustic data.

[0015] The obtained original deep-sea environment data is preprocessed. Noise data is removed through data cleaning, missing data is repaired or filled, and different types of data are integrated using a multi-sensor data fusion algorithm based on Bayesian fusion to obtain comprehensive environmental information.

[0016] According to the preprocessed obstacle data, a geometric model of the obstacle is created in 3D modeling software. The seabed terrain and obstacles are represented using a regular grid model, and texture mapping is performed on the model. Textures reflecting the characteristics of marine vegetation and rocks are added to enhance the realism of the model.

[0017] Using the preprocessed ocean dynamic change data, a 3D field model representing the distribution of physical and chemical parameters such as seawater temperature, salinity, and flow velocity is created in 3D modeling software. The voxel grid technology is used to represent the characteristics of ocean dynamic changes, and rendering and lighting processing are performed on the model to simulate the reflection and refraction characteristics of seawater to light and enhance the immersion.

[0018] Fuse the three-dimensional obstacle model with the three-dimensional model of ocean dynamic changes to form a complete three-dimensional deep-sea environment model, and use the level of detail (LOD) technology to automatically adjust the detail level of the model according to the viewing distance, and then optimize the fused three-dimensional environment model.

[0019] A further improvement of the technical solution of the present invention lies in that: the constraint condition definition module specifically includes:

[0020] Based on the obtained deep-sea environment data and the constructed three-dimensional deep-sea environment model, define static constraint conditions, dynamic constraint conditions, and performance constraint conditions in the deep-sea environment. Among them, the static constraint conditions are to define static obstacles in the deep-sea environment, the dynamic constraint conditions are to define dynamic obstacles in the deep-sea environment, and the performance constraint conditions are to define the performance indicators of route planning;

[0021] For the definition of static constraint conditions, extract static obstacle data from the environmental perception modeling module, classify the obstacles and label their positions, sizes, and shapes, define boundaries for each static obstacle to ensure avoiding the static obstacle area during path planning, and set a safety distance according to the type and size of the obstacles to ensure that the navigation equipment maintains a safe distance from the obstacles. Then store the static constraint conditions as a data structure for use by the global path planning module;

[0022] For the definition of dynamic constraint conditions, extract dynamic obstacle data from the environmental perception modeling module, classify the dynamic obstacles and label their motion characteristics, predict their future positions and paths based on the motion trajectories of the dynamic obstacles, and define dynamic constraint areas for the dynamic obstacles to ensure avoiding the dynamic obstacle area during path planning, and update the dynamic constraint conditions in real time to reflect the latest state of the dynamic obstacles;

[0023] For the definition of performance constraint conditions, extract performance indicators including navigation time, energy consumption, and communication bandwidth, define the maximum allowable navigation time from the starting point to the end point, define the maximum allowable energy consumption during navigation, define the communication bandwidth limit between the navigation equipment and the control center, and convert the performance indicators into specific numerical values. Then store the performance constraint conditions as a data structure for use by the global path planning module;

[0024] Integrate the performance constraint conditions with the static and dynamic constraint conditions to form a complete set of constraint conditions, detect conflicts between the constraint conditions, and resolve the conflicts according to the priority settings. Then output the defined set of constraint conditions to the global path planning module for route planning use.

[0025] A further improvement of the technical solution of the present invention lies in that: the global path planning module specifically includes:

[0026] Read static constraints, dynamic constraints, and performance constraints, and determine the starting and ending positions of the navigation equipment. Based on the deep-sea three-dimensional environment model provided by the environmental perception modeling module, understand the obstacle distribution and ocean dynamic information;

[0027] On the premise of meeting the static constraints, use the heuristic search algorithm to generate a preliminary path from the starting point to the ending point, avoiding major static obstacles, and according to the dynamic constraints, real-time monitor the positions and movement trends of dynamic obstacles, and adjust the path to avoid dynamic obstacles;

[0028] On the basis of meeting the static and dynamic constraints, optimize the path by adjusting path nodes and changing the sailing speed to shorten the sailing time, reduce energy consumption, and ensure the adequacy of communication bandwidth;

[0029] Check whether the planned path meets all constraints. If the path does not meet the constraints, repeat the path planning and adjust the parameters to continuously iterate and optimize the path until the optimal navigation path that meets all constraints is found.

[0030] A further improvement of the technical solution of the present invention lies in that: the simulation verification module specifically includes:

[0031] Based on the deep-sea three-dimensional environment model, create a virtual deep-sea environment in the simulation software (Gazebo), including seabed topography, obstacles, and ocean dynamic changes, and import the physical and dynamic models of the navigation equipment into the simulation environment to ensure that its behavior is consistent with the real equipment. At the same time, set simulation parameters including time step and simulation speed according to actual needs;

[0032] Import the optimal navigation path generated by the global path planning module into the simulation environment as the reference trajectory of the navigation equipment, and visualize the path in the simulation environment for observation and analysis;

[0033] Start the navigation equipment in the simulation environment and sail according to the planned path, and real-time monitor the state of the navigation equipment, including position, speed, and attitude;

[0034] In the simulation environment, run the optimal navigation path and perform constraint condition checks to check whether the path meets the static constraints and dynamic constraints. If the path violates any constraints, the simulation verification module will record the violation situation and feedback it to the global path planning module for re-planning;

[0035] According to the simulation results, perform performance evaluations on the optimal navigation path, including sailing time, energy consumption, and communication bandwidth utilization rate, calculate the path performance evaluation index, and compare the evaluation results with the performance constraints to check whether the path meets the performance requirements;

[0036] Analyze the data generated during the simulation test, identify potential problems and optimization spaces in path planning, and generate a simulation report based on the analysis results to summarize the performance and existing problems of path planning. Then, according to the simulation results and analysis report, put forward path optimization suggestions to the global path planning module, including adjusting path nodes and changing the sailing speed;

[0037] According to the optimization suggestions, the global path planning module re-plans the path and submits the new path to the simulation verification module for re-testing. Repeat the simulation test process and continuously iterate to optimize the path until the optimal path that meets all constraint conditions is found.

[0038] A further improvement of the technical solution of the present invention lies in: the calculation process of the path performance evaluation index is as follows:

[0039] Combined with the defined performance constraint conditions, determine the theoretical maximum values of the maximum allowable sailing time, maximum allowable energy consumption, and communication bandwidth;

[0040] Run the optimal sailing path in the simulation environment, record the actual sailing time of the sailing equipment from the starting point to the end point, repeat the simulation test N times, and obtain multiple sailing time data;

[0041] Calculate and record the energy consumption of the sailing equipment in each simulation through the dynamic model in the simulation software, monitor the communication data volume between the sailing equipment and the control center, and calculate the communication bandwidth utilization rate, that is, the ratio of the actual communication bandwidth to the theoretical maximum value of the communication bandwidth;

[0042] For each simulation, calculate the normalized value of the sailing time, the normalized value of the energy consumption, and the normalized value of the communication bandwidth utilization rate;

[0043] Add the normalized value of the sailing time, the normalized value of the energy consumption, and the normalized value of the communication bandwidth utilization rate to calculate the comprehensive performance index of each simulation;

[0044] Integrate the comprehensive performance indexes of each simulation, calculate the average value of the sum of squares of the comprehensive performance indexes to obtain the average performance indexes of all simulations, analyze the root mean square of all the average performance indexes of the simulations, and then take the reciprocal of the root mean square and multiply by 100 to calculate the path performance evaluation index;

[0045] Analyze the path performance evaluation index. If the path performance evaluation index is close to 100, it indicates that the path performance is excellent and meets all performance constraint conditions. If the path performance evaluation index is low, it indicates that the path performance is poor and needs to be optimized.

[0046] A further improvement of the technical solution of the present invention lies in: the control execution module specifically includes:

[0047] Receive the latest optimal navigation path from the global path planning module. The path information includes waypoint coordinates, speed requirements, and sailing directions, and decompose the path into a series of discrete waypoints. Each waypoint contains position information (longitude, latitude, depth) and navigation parameters (speed, heading angle);

[0048] Establish a kinematic model of the deep - sea operation equipment, and calculate a series of control instructions, including thruster thrust, rudder angle adjustment, and buoyancy adjustment, etc., according to the optimal navigation path and the kinematic model of the deep - sea operation equipment, so as to enable the equipment to sail along the planned path. Then send the generated control instructions to the execution system of the deep - sea operation equipment through the communication system;

[0049] Real - time monitor the status indicators of the deep - sea operation equipment through the sensor network, including position, speed, attitude, and depth information. Analyze the position deviation, speed deviation, attitude deviation, and depth deviation of each data point within the monitoring period, and combine with the reference values of each status indicator to calculate the equipment status evaluation index, and judge whether the equipment is in an abnormal operation state. Among them, the abnormal operation state includes position deviation, speed deviation, attitude abnormality, and depth abnormality;

[0050] According to the optimal navigation path and real - time status data, adopt the optimal control theory (PID control) to adjust the navigation parameters, calculate the control instructions for the current waypoint, ensure that the equipment sails along the planned path, and dynamically adjust the speed and heading angle according to the real - time status and environmental changes of the equipment to adapt to the complex deep - sea environment. Among them, the control instructions for the current waypoint include position control, speed control, heading control, and depth control;

[0051] Send the control instructions to the execution system of the deep - sea operation equipment through the communication link. After receiving the instructions, the execution system distributes the thruster thrust, adjusts the navigation attitude, continuously monitors the equipment status and environmental information, and forms a closed - loop control loop. Once a deviation or abnormal situation is found, immediately make adjustments and corrections to ensure that the equipment always stays on the planned path. Among them, the deviation or abnormal situation includes depth over - limit, attitude abnormality, and communication interruption.

[0052] A further improvement of the technical solution of the present invention lies in that the expression of the equipment status evaluation index is:

[0053] ;

[0054] In the formula, ES is the equipment status evaluation index, which is used to comprehensively evaluate the operation status of the equipment, M is the number of data points within the monitoring period, is the position deviation of the j - th data point, is the reference value of the position deviation, indicating the maximum allowable position deviation during normal operation, is the speed deviation of the j - th data point, is the reference value of the speed deviation, representing the maximum allowable speed deviation during normal operation. is the attitude deviation of the j-th data point. is the reference value of the attitude deviation, representing the maximum allowable attitude deviation during normal operation. is the depth deviation of the j-th data point. is the reference value of the depth deviation, representing the maximum allowable depth deviation during normal operation. The value range of ES is [0, 100]. When the device state fully conforms to the reference value, ES is close to 100, indicating that the device is in good operating condition.

[0055] A further improvement of the technical solution of the present invention lies in that: the feedback adjustment module specifically includes:

[0056] The feedback adjustment module receives the latest deep-sea environment data from the environment perception and modeling module and receives the real-time state data of the deep-sea operation device from the control execution module. Then, it fuses the deep-sea environment data and the device state data to generate a unified input data format for subsequent processing.

[0057] By comparing the difference between the actual navigation trajectory and the planned path, it detects whether there is a path deviation, analyzes the path deviation, including path position deviation, path speed deviation, and heading deviation, and calculates the deviation risk assessment coefficient by comprehensively considering the path position deviation, path speed deviation, and heading deviation according to the magnitude and direction of the deviation, evaluates its impact on the navigation safety of the device and the task completion, and determines whether there is a risk that the deviation causes the device to enter a dangerous area or violate the constraint conditions.

[0058] According to the deviation analysis results, formulate corresponding feedback adjustment strategies, including adjusting the heading angle, changing the speed, and re-planning the local path, etc., and perform real-time adjustment of the navigation path according to the adjustment strategy to ensure that the deep-sea operation device can navigate along the planned path safely and efficiently.

[0059] Feed back the adjusted path and related data to the global path planning module for reference in subsequent path planning, and feed back the path adjustment information to the environment perception module to update the deep-sea three-dimensional environment model.

[0060] A further improvement of the technical solution of the present invention lies in that: the expression of the deviation risk assessment coefficient is:

[0061] ;

[0062] In the formula, DR is the deviation risk assessment coefficient, which is used to comprehensively evaluate the impact of the path deviation on the navigation safety of the device and the task completion. M is the number of data points within the monitoring period. is the path position deviation of the j-th data point, representing the combination of the horizontal position deviation and the vertical position deviation. is the reference value of the path position deviation, representing the maximum allowable position deviation during normal operation. is the speed deviation of the j-th data point, representing the difference between the current speed and the planned speed. is the reference value of the speed deviation, representing the maximum allowable speed deviation during normal operation. is the heading deviation of the j-th data point, representing the difference between the current heading angle and the planned heading angle. is the reference value of the heading deviation, representing the maximum allowable heading deviation during normal operation. The value range of DR is between 0 and 1. When the path deviation of the device completely conforms to the reference value, DR approaches 1, indicating that the device is in good operating condition and the risk is low.

[0063] Due to the adoption of the above technical solution, the technical progress achieved by the present invention compared with the prior art is as follows:

[0064] The present invention provides an intelligent path planning system for deep-sea deduction scenarios based on the optimal control theory. By receiving and fusing deep-sea environment data and device status data in real time, it can accurately detect and analyze position deviation, speed deviation, and heading deviation during navigation. Based on the optimal control theory, the system can quickly formulate adjustment strategies to ensure that the device always stays within the safe navigation range. This real-time feedback and adjustment mechanism greatly improves the safety and reliability of navigation, effectively avoiding the risk of collision with obstacles or entering dangerous areas, and providing a solid guarantee for deep-sea operations.

[0065] The present invention provides an intelligent path planning system for deep-sea deduction scenarios based on the optimal control theory, which can adjust the navigation path and navigation parameters in real time according to deep-sea environment and device status data. Guided by the optimal control theory, it ensures that the device always maintains the best state during navigation. By optimizing the heading angle, speed, and path planning, the system can significantly reduce navigation time and energy consumption, improve navigation efficiency. At the same time, the system can also intelligently allocate thruster thrust and adjust buoyancy according to task requirements and device performance to further reduce energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0067] Figure 1 is a schematic diagram of the system function modules of the present invention;

[0068] Figure 2 is a schematic diagram of the working process of the control execution module of the present invention. Detailed implementation manners

[0069] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0070] Embodiment 1, as Figure 1 shown, the present invention provides an intelligent path planning system for deep-sea deduction scenario navigation routes based on the optimal control theory, including a data management platform, which is communicatively connected to an environment perception and modeling module, a constraint condition definition module, a global path planning module, a simulation verification module, a control execution module, and a feedback adjustment module;

[0071] An environmental perception modeling module is used to collect and sense deep - sea environmental data and construct a three - dimensional deep - sea environmental model. Among them, the deep - sea environmental data includes obstacle data and ocean dynamic change data. The deep - sea exploration equipment and deep - sea sensor network are used to collect and sense the deep - sea environmental data including obstacle data and ocean dynamic change data. Among them, for the obstacle data, it includes seabed terrain data, seabed obstacle data, and dynamic obstacle data. The elevation data of the seabed terrain, including seamounts, canyons, trenches, etc., is obtained through a multibeam echosounder (MBES). Synthetic aperture sonar (SAS) is used to detect obstacles on the seabed, including sunken shipwrecks, rocks, artificial structures, etc. Underwater sensor networks are used to monitor dynamic obstacles, including other vehicles, ice floes, marine organisms, etc. For the ocean dynamic change data, it includes ocean current field data, water temperature data, salinity data, and ocean acoustic data. An anemometer carried by a buoy, a mooring buoy, or an AUV is used to measure the ocean current speed and direction to obtain the flow field information. A CTD (conductivity - temperature - depth profiler) is used to measure the water temperature, salinity, and depth profile data to understand the physical properties of the ocean. Acoustic sensors are used to monitor the acoustic environment in the ocean, including the noise level and the sound speed profile. The acquired original deep - sea environmental data is pre - processed. Noise data is removed through data cleaning, missing data is repaired or filled, and a Bayesian - based multi - sensor data fusion algorithm is used to integrate different types of data to obtain comprehensive environmental information. According to the pre - processed obstacle data, a geometric model of the obstacle is created in 3D modeling software. A regular grid model is used to represent the seabed terrain and obstacles, and texture mapping is performed on the model, adding textures reflecting the characteristics of marine vegetation and rocks to enhance the realism of the model. Using the pre - processed ocean dynamic change data, a three - dimensional field model representing the distribution of physical and chemical parameters such as seawater temperature, salinity, and flow velocity is created in 3D modeling software, and the voxel grid technology is used to represent the characteristics of ocean dynamic changes. The model is rendered and illuminated to simulate the reflection and refraction characteristics of seawater to light and enhance the immersion. The three - dimensional obstacle model is fused with the three - dimensional ocean dynamic change model to form a complete three - dimensional deep - sea environmental model, and the level of detail (LOD) technology is used to automatically adjust the level of detail of the model according to the viewing distance, and then the fused three - dimensional environmental model is optimized;

[0072] Constraint condition definition module, used to define static constraint conditions, dynamic constraint conditions and performance constraint conditions in the deep - sea environment. Among them, the static constraint condition is to define static obstacles in the deep - sea environment, the dynamic constraint condition is to define dynamic obstacles in the deep - sea environment, and the performance constraint condition is to define the performance indicators of route planning. Based on the obtained deep - sea environment data and the constructed three - dimensional deep - sea environment model, define the static constraint conditions, dynamic constraint conditions and performance constraint conditions in the deep - sea environment. Among them, the static constraint condition is to define static obstacles in the deep - sea environment, the dynamic constraint condition is to define dynamic obstacles in the deep - sea environment, and the performance constraint condition is to define the performance indicators of route planning. For the definition of static constraint conditions, extract static obstacle data from the environmental perception and modeling module, classify the obstacles and label their positions, sizes and shapes, define boundaries for each static obstacle to ensure avoiding the static obstacle area during path planning, and set safety distances according to the types and sizes of the obstacles to ensure that the navigation equipment keeps a safe distance from the obstacles. Then store the static constraint conditions as a data structure for the global path planning module to use. For the definition of dynamic constraint conditions, extract dynamic obstacle data from the environmental perception and modeling module, classify the dynamic obstacles and label their motion characteristics, predict their future positions and paths based on the motion trajectories of the dynamic obstacles, and define dynamic constraint regions for the dynamic obstacles to ensure avoiding the dynamic obstacle area during path planning, and update the dynamic constraint conditions in real - time to reflect the latest state of the dynamic obstacles. For the definition of performance constraint conditions, extract performance indicators including navigation time, energy consumption and communication bandwidth, define the maximum allowable navigation time from the starting point to the end point, define the maximum allowable energy consumption during navigation, define the communication bandwidth limit between the navigation equipment and the control center, and convert the performance indicators into specific numerical values. Then store the performance constraint conditions as a data structure for the global path planning module to use. Integrate the performance constraint conditions with the static and dynamic constraint conditions to form a complete set of constraint conditions, detect conflicts between the constraint conditions, and resolve the conflicts according to the priority settings. Then output the defined set of constraint conditions to the global path planning module for route planning to use;

[0073] The global path planning module plans the optimal navigation path from the starting point to the ending point based on the optimal control theory and the defined constraint conditions. During the planning process, it continuously optimizes the path to meet the performance constraint conditions and avoid all static and dynamic obstacles. It reads the static constraint conditions, dynamic constraint conditions, and performance constraint conditions, and determines the starting and ending positions of the navigation equipment. Based on the three-dimensional deep-sea environment model provided by the environmental perception modeling module, it understands the obstacle distribution and ocean dynamic information. On the premise of meeting the static constraint conditions, it uses the heuristic search algorithm to generate a preliminary path from the starting point to the ending point, avoiding the main static obstacles. According to the dynamic constraint conditions, it real-time monitors the positions and movement trends of the dynamic obstacles, and adjusts the path to avoid the dynamic obstacles. On the basis of meeting the static and dynamic constraint conditions, it optimizes the performance of the path by adjusting the path nodes and changing the sailing speed, so as to shorten the sailing time, reduce the energy consumption, and ensure the adequacy of the communication bandwidth. It checks whether the planned path meets all the constraint conditions. If the path does not meet the constraint conditions, it repeats the path planning and adjusts the parameters to continuously iterate and optimize the path until the optimal navigation path that meets all the constraint conditions is found;

[0074] The simulation verification module is used to conduct simulation tests on the optimal navigation path planned based on the optimal control theory in a simulation environment, check whether the path meets the constraint conditions, and avoid all obstacles, and then evaluate the performance of the planned navigation path to ensure the optimization of path planning. Based on the deep-sea three-dimensional environment model, a virtual deep-sea environment is created in the simulation software (Gazebo), including seabed terrain, obstacles, and ocean dynamic changes, and the physical and dynamic models of the navigation equipment are imported into the simulation environment to ensure that its behavior is consistent with the real equipment. At the same time, simulation parameters including time step and simulation speed are set according to actual needs. The optimal navigation path generated by the global path planning module is imported into the simulation environment as the reference trajectory of the navigation equipment, and the path is visualized in the simulation environment for observation and analysis. The navigation equipment is started in the simulation environment and sails according to the planned path, and the state of the navigation equipment, including position, speed, and attitude, is monitored in real time. In the simulation environment, the optimal navigation path is run to conduct constraint condition checks, and it is checked whether the path meets the static constraint conditions and dynamic constraint conditions. If the path violates any constraint conditions, the simulation verification module will record the violation situation and feedback it to the global path planning module for re-planning. Among them, for static constraint checks, it is checked whether the navigation equipment avoids all static obstacles and maintains a safe distance. For dynamic constraint checks, it is checked whether the navigation equipment avoids all dynamic obstacles and adjusts the path according to its motion trend. According to the simulation results, performance evaluations of the optimal navigation path, including navigation time, energy consumption, and communication bandwidth utilization rate, are carried out, the path performance evaluation index is calculated, and the evaluation results are compared with the performance constraint conditions to check whether the path meets the performance requirements. The data generated during the simulation test process is analyzed to identify potential problems and optimization spaces in path planning, and according to the analysis results, a simulation report is generated to summarize the performance and existing problems of path planning. Then, according to the simulation results and analysis report, path optimization suggestions, including adjusting path nodes and changing the navigation speed, are put forward to the global path planning module. According to the optimization suggestions, the global path planning module re-plans the path and submits the new path to the simulation verification module for re-testing. The simulation test process is repeated, and the path is continuously iteratively optimized until the optimal path that meets all constraint conditions is found;

[0075] The calculation process of the path performance evaluation index is as follows:

[0076] Combined with the defined performance constraints, determine the maximum allowable navigation time, the maximum allowable energy consumption, and the theoretical maximum of the communication bandwidth. Run the optimal navigation path in the simulation environment, record the actual navigation time of the navigation equipment from the starting point to the ending point, repeat the simulation test N times, obtain multiple navigation time data, calculate and record the energy consumption of the navigation equipment in each simulation through the dynamic model in the simulation software, monitor the communication data volume between the navigation equipment and the control center, calculate the communication bandwidth utilization rate, that is, the ratio of the actual communication bandwidth to the theoretical maximum of the communication bandwidth. For each simulation, calculate the normalized value of the navigation time, the normalized value of the energy consumption, and the normalized value of the communication bandwidth utilization rate. Add the normalized value of the navigation time, the normalized value of the energy consumption, and the normalized value of the communication bandwidth utilization rate to calculate the comprehensive performance index for each simulation. Combine the comprehensive performance indices of each simulation, calculate the average value of the sum of the squares of the comprehensive performance indices, obtain the average performance index of all simulations, and analyze the root mean square of all simulation average performance indices. Then take the reciprocal of the root mean square and multiply by 100 to calculate the path performance evaluation index. Analyze the path performance evaluation index. If the path performance evaluation index is close to 100, it indicates that the path performance is excellent and meets all performance constraints. If the path performance evaluation index is low, it indicates that the path performance is poor and needs to be optimized. Among them, if the navigation time is too long, consider optimizing the path nodes to reduce the path length. If the energy consumption is too high, consider adjusting the navigation speed or optimizing the path to reduce the energy consumption. If the communication bandwidth utilization rate is low, consider optimizing the path to reduce communication interference or adjusting the communication strategy;

[0077] The expression of the path performance evaluation index is:

[0078] ;

[0079] In the formula, PI is the path performance evaluation index, which is used to comprehensively evaluate the performance of the path. N is the total number of simulation tests, is the navigation time in the i-th simulation, is the maximum allowable navigation time specified in the performance constraints, is the energy consumption in the i-th simulation, is the maximum allowable energy consumption specified in the performance constraints, is the communication bandwidth utilization rate in the i-th simulation, is the theoretical maximum of the communication bandwidth. The value range of PI is [0, 100]. The closer PI is to 100, the better the path performance. The closer PI is to 0, the worse the path performance. When the path fully meets all performance constraints, PI is close to 100. When the path seriously violates the performance constraints, PI is close to 0. If the navigation time, energy consumption, and communication bandwidth utilization rate of the path are all close to the optimal values of the performance constraints, the PI value is higher. If the navigation time or energy consumption of the path exceeds the allowable range, or the communication bandwidth utilization rate is low, the PI value will decrease significantly;

[0080] A control execution module, which is used to convert the latest optimal navigation path into control instructions and send them to the execution system of the deep-sea operation equipment. Based on the optimal control theory, it adjusts the navigation parameters of the deep-sea operation equipment in real time to ensure that the equipment sails along the planned path;

[0081] A feedback adjustment module, which is used to receive the latest deep-sea environment data and, in combination with the control execution results of the deep-sea operation equipment, make feedback adjustments to the navigation path.

[0082] Example 2, as Figure 2 shown, on the basis of Example 1, the present invention provides a technical solution: Preferably, the control execution module specifically includes:

[0083] Receive the latest optimal navigation path from the global path planning module. The path information includes waypoint coordinates, speed requirements, and navigation directions. Decompose the path into a series of discrete waypoints. Each waypoint contains position information (longitude, latitude, depth) and navigation parameters (speed, heading angle). Establish a kinematic model of the deep-sea operation equipment. According to the optimal navigation path and the kinematic model of the deep-sea operation equipment, calculate a series of control instructions, including thruster thrust, rudder angle adjustment, and buoyancy adjustment, etc., to enable the equipment to sail along the planned path. Then, send the generated control instructions to the execution system of the deep-sea operation equipment through the communication system. Real-time monitor the status indicators of the deep-sea operation equipment through the sensor network, including position, speed, attitude, and depth information. Analyze the position deviation, speed deviation, attitude deviation, and depth deviation of each data point within the monitoring period. Combine with the reference values of each status indicator to calculate the equipment status evaluation index, and judge whether the equipment is in an abnormal operating state. Among them, the abnormal operating state includes position deviation, speed deviation, attitude abnormality, and depth abnormality. The position deviation is to check whether the equipment deviates from the planned path. The speed deviation is to check whether the equipment speed meets the planned requirements. The attitude abnormality is to check whether the equipment attitude exceeds the safe range. The depth abnormality is to check whether the equipment depth exceeds the safe range. According to the optimal navigation path and real-time status data, adopt the optimal control theory (PID control) to adjust the navigation parameters, calculate the control instructions for the current waypoint, ensure that the equipment sails along the planned path, and dynamically adjust the speed and heading angle according to the real-time status and environmental changes of the equipment to adapt to the complex deep-sea environment. Among them, the control instructions for the current waypoint include position control, speed control, heading control, and depth control. The position control is to use a PID controller to adjust the position of the equipment to make it close to the target waypoint. The speed control is to adjust the thruster thrust according to the deviation between the target speed and the current speed. The heading control is to adjust the rudder angle according to the deviation between the target heading angle and the current heading angle. The depth control is to adjust the buoyancy according to the deviation between the target depth and the current depth. Send the control instructions to the execution system of the deep-sea operation equipment through the communication link. After receiving the instructions, the execution system distributes the thruster thrust, adjusts the navigation attitude, continuously monitors the equipment status and environmental information, and forms a closed-loop control loop. Once a deviation or abnormal situation is found, immediately make adjustments and corrections to ensure that the equipment always stays on the planned path. Among them, the deviation or abnormal situation includes depth overlimit, attitude abnormality, and communication interruption. The depth overlimit needs to check whether the equipment depth exceeds the safe range. The attitude abnormality needs to check whether the equipment attitude exceeds the safe range. The communication interruption needs to check whether the communication link is normal;

[0084] The expression of the equipment status evaluation index is:

[0085] ;

[0086] In the formula, ES is the equipment status evaluation index, which is used to comprehensively evaluate the operating status of the equipment. M is the number of data points within the monitoring period. is the position deviation of the j-th data point. is the reference value of the position deviation, representing the maximum allowable position deviation during normal operation. is the speed deviation of the j-th data point. is the reference value of the speed deviation, representing the maximum allowable speed deviation during normal operation. is the attitude deviation of the j-th data point. is the reference value of the attitude deviation, representing the maximum allowable attitude deviation during normal operation. is the depth deviation of the j-th data point. is the reference value of the depth deviation, representing the maximum allowable depth deviation during normal operation. The value range of ES is [0, 100]. When the equipment status fully conforms to the reference value, ES is close to 100, indicating that the equipment is in good operating condition. When the equipment status seriously deviates from the reference value, ES is close to 0, indicating that the equipment is in abnormal operating condition. If the position, speed, attitude, and depth deviations of the equipment are all small and close to the reference value, the ES value is high. If a large deviation occurs in a certain key parameter of the equipment, the ES value will decrease significantly, indicating that the equipment may be in an abnormal operating state.

[0087] The feedback adjustment module specifically includes:

[0088] The feedback adjustment module receives the latest deep - sea environment data from the environmental perception and modeling module and the real - time status data of the deep - sea operation equipment from the control execution module. Then, it fuses the deep - sea environment data and the equipment status data to generate a unified input data format for subsequent processing. By comparing the difference between the actual navigation trajectory and the planned path, it detects whether there is a path deviation, analyzes the path deviation, including path position deviation, path speed deviation, and heading deviation, and calculates the deviation risk assessment coefficient by comprehensively considering the path position deviation, path speed deviation, and heading deviation according to the magnitude and direction of the deviation. It evaluates its impact on the navigation safety of the equipment and the completion of the task, and determines whether the deviation poses a risk of the equipment entering a dangerous area or violating the constraint conditions. Among them, the path position deviation is calculated as the deviation between the actual navigation trajectory and the planned path, the path speed deviation is calculated as the deviation between the actual navigation speed and the planned speed, and the heading deviation is calculated as the deviation between the actual navigation heading angle and the planned heading angle. According to the deviation analysis results, corresponding feedback adjustment strategies are formulated, including adjusting the heading angle, changing the speed, and re - planning the local path, etc. And according to the adjustment strategy, the navigation path is adjusted in real - time to ensure that the deep - sea operation equipment can navigate safely and efficiently along the planned path. The adjusted path and related data are fed back to the global path planning module to provide a reference for subsequent path planning, and the path adjustment information is fed back to the environmental perception module to update the deep - sea three - dimensional environment model;

[0089] The expression of the deviation risk assessment coefficient is:

[0090] ;

[0091] In the formula, DR is the deviation risk assessment coefficient, which is used to comprehensively evaluate the impact of path deviation on the navigation safety of the equipment and the completion of the task. M is the number of data points within the monitoring period, is the path position deviation of the j - th data point, representing the comprehensive horizontal and vertical position deviations, is the reference value of the path position deviation, representing the maximum allowable position deviation during normal operation, is the speed deviation of the j - th data point, representing the difference between the current speed and the planned speed, is the reference value of the speed deviation, representing the maximum allowable speed deviation during normal operation, is the heading deviation of the j - th data point, representing the difference between the current heading angle and the planned heading angle, It is the reference value of the course deviation, representing the maximum allowable course deviation during normal operation. The value range of DR is between 0 and 1. When the path deviation of the device completely conforms to the reference value, DR approaches 1, indicating that the device is in good operating condition and the risk is low. When the path deviation of the device seriously deviates from the reference value, DR approaches 0, indicating that the device is in abnormal operating condition and the risk is high. If the position deviation, speed deviation, and course deviation of the device are all small, the DR value is high, indicating that the device is in good operating condition and the risk is low. If a large deviation occurs in a certain key parameter of the device, the DR value will decrease significantly, indicating that the device may be in a high-risk state.

[0092] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent path planning system for deep - sea deduction scenarios based on optimal control theory, including a data management platform, characterized in that: The data management platform is communicatively connected to an environmental perception and modeling module, a constraint condition definition module, a global path planning module, a simulation and verification module, a control execution module, and a feedback adjustment module; The environmental perception and modeling module is used to collect and perceive deep-sea environmental data and construct a three-dimensional deep-sea environmental model. Among them, the deep-sea environmental data includes obstacle data and ocean dynamic change data; The constraint condition definition module is used to define static constraint conditions, dynamic constraint conditions, and performance constraint conditions in the deep-sea environment; The global path planning module plans the optimal navigation path from the starting point to the ending point based on the optimal control theory and the defined constraint conditions; The global path planning module specifically includes: Read static constraint conditions, dynamic constraint conditions, and performance constraint conditions, and determine the starting point and ending point positions of the navigation equipment. Based on the three-dimensional deep-sea environmental model provided by the environmental perception and modeling module, understand the obstacle distribution and ocean dynamic information; On the premise of meeting the static constraint conditions, use the heuristic search algorithm to generate a preliminary path from the starting point to the ending point, avoid major static obstacles, and according to the dynamic constraint conditions, monitor the position and movement trend of dynamic obstacles in real time, and adjust the path to avoid dynamic obstacles; On the basis of meeting the static and dynamic constraint conditions, optimize the performance of the path by adjusting path nodes and changing the navigation speed; Check whether the planned path meets all constraint conditions. If the path does not meet the constraint conditions, repeat the path planning and adjust the parameters to continuously iterate and optimize the path until the optimal navigation path that meets all constraint conditions is found; The simulation and verification module is used to perform simulation tests on the optimal navigation path planned based on the optimal control theory in the simulation environment, check whether the path meets the constraint conditions, and then evaluate the performance of the planned navigation path; The control execution module is used to convert the latest optimal navigation path into control instructions and send them to the execution system of the deep-sea operation equipment; The feedback adjustment module is used to receive the latest deep-sea environmental data and, in combination with the control execution results of the deep-sea operation equipment, perform feedback adjustment on the navigation path.

2. The intelligent route planning system for deep-sea deduction scenarios based on the optimal control theory according to claim 1, wherein: The environmental perception and modeling module specifically includes: Use deep-sea exploration equipment and deep-sea sensor networks to collect and perceive deep-sea environmental data including obstacle data and ocean dynamic change data. Among them, for obstacle data, it includes seabed terrain data, seabed obstacle data, and dynamic obstacle data. For ocean dynamic change data, it includes ocean current field data, water temperature data, salinity data, and ocean acoustic data; Perform preprocessing on the acquired original deep-sea environmental data, remove noise data through data cleaning, and use a multi-sensor data fusion algorithm based on Bayesian fusion to integrate different types of data to obtain comprehensive environmental information; According to the preprocessed obstacle data, create a geometric model of the obstacle in 3D modeling software, use a regular grid model to represent the seabed terrain and obstacles, and perform texture mapping on the model, adding textures reflecting the characteristics of marine vegetation and rocks; Using the preprocessed ocean dynamic change data, create a three-dimensional field model representing the distribution of physical and chemical parameters such as seawater temperature, salinity, and flow velocity in a three-dimensional modeling software, and use voxel grid technology to represent the characteristics of ocean dynamic changes. Render and perform lighting processing on the model to simulate the reflection and refraction characteristics of seawater to light; Fuse the three-dimensional model of obstacles with the three-dimensional model of ocean dynamic changes to form a complete three-dimensional deep-sea environment model, and use the level of detail technology to automatically adjust the level of detail of the model according to the viewing distance, and then perform optimization processing on the fused three-dimensional environment model.

3. The intelligent planning system for the seaway path of the deep-sea deduction scenario based on the optimal control theory according to claim 2, wherein: The constraint condition definition module specifically includes: Based on the obtained deep-sea environment data and the constructed three-dimensional deep-sea environment model, define static constraint conditions, dynamic constraint conditions, and performance constraint conditions in the deep-sea environment. Among them, the static constraint conditions are to define static obstacles in the deep-sea environment, the dynamic constraint conditions are to define dynamic obstacles in the deep-sea environment, and the performance constraint conditions are to define the performance indicators of route planning; For the definition of static constraint conditions, extract static obstacle data from the environmental perception modeling module, classify the obstacles and label their positions, sizes, and shapes, define boundaries for each static obstacle to ensure avoiding the static obstacle area during path planning, and set a safety distance according to the type and size of the obstacle. Then store the static constraint conditions as a data structure for use by the global path planning module; For the definition of dynamic constraint conditions, extract dynamic obstacle data from the environmental perception modeling module, classify the dynamic obstacles and label their motion characteristics. Based on the motion trajectory of the dynamic obstacles, predict their future positions and paths, and define a dynamic constraint area for the dynamic obstacles, and update the dynamic constraint conditions in real time to reflect the latest state of the dynamic obstacles; For the definition of performance constraint conditions, extract performance indicators including sailing time, energy consumption, and communication bandwidth, define the maximum allowable sailing time from the starting point to the ending point, define the maximum allowable energy consumption during sailing, define the communication bandwidth limit between the sailing equipment and the control center, and convert the performance indicators into specific values. Then store the performance constraint conditions as a data structure for use by the global path planning module; Integrate the performance constraint conditions with the static and dynamic constraint conditions to form a complete set of constraint conditions, detect conflicts between the constraint conditions, and resolve the conflicts according to the priority settings. Then output the defined set of constraint conditions to the global path planning module for route planning use.

4. The intelligent route planning system for deep - sea deduction scenarios based on the optimal control theory according to claim 3, characterized in that: The simulation verification module specifically includes: Based on the three-dimensional deep-sea environment model, create a virtual deep-sea environment in the simulation software, including seabed terrain, obstacles, and ocean dynamic changes, and import the physical and dynamic models of the sailing equipment into the simulation environment. At the same time, set simulation parameters including time step and simulation speed according to actual needs; Import the optimal navigation route generated by the global path planning module into the simulation environment as the reference trajectory of the sailing equipment, and visualize the path in the simulation environment; Start the sailing equipment in the simulation environment and sail according to the planned path, and monitor the state of the sailing equipment in real time, including position, speed, and attitude; In the simulation environment, run the optimal navigation path and conduct constraint condition checks to verify whether the path meets the static and dynamic constraint conditions. If the path violates any constraint conditions, the simulation verification module will record the violations and feedback them to the global path planning module for re-planning; Based on the simulation results, conduct performance evaluations of the optimal navigation path, including sailing time, energy consumption, and communication bandwidth utilization. Calculate the path performance evaluation index and compare the evaluation results with the performance constraint conditions to check whether the path meets the performance requirements; Analyze the data generated during the simulation test, identify potential problems and optimization spaces in path planning, and generate a simulation report based on the analysis results to summarize the performance and existing problems of path planning. Then, based on the simulation results and analysis report, provide path optimization suggestions to the global path planning module, including adjusting path nodes and changing the sailing speed; According to the optimization suggestions, the global path planning module re-plans the path and submits the new path to the simulation verification module for re-testing. Repeat the simulation test process and continuously iterate to optimize the path until the optimal path that meets all constraint conditions is found.

5. The intelligent planning system for the deep-sea deduction scenario route according to claim 4 based on the optimal control theory, characterized in that: The calculation process of the path performance evaluation index is as follows: Combined with the defined performance constraint conditions, determine the maximum allowable sailing time, the maximum allowable energy consumption, and the theoretical maximum value of the communication bandwidth; Run the optimal navigation path in the simulation environment, record the actual sailing time of the navigation equipment from the starting point to the ending point, and repeat the simulation test N times to obtain multiple sailing time data; Calculate and record the energy consumption of the navigation equipment in each simulation through the dynamic model in the simulation software, monitor the communication data volume between the navigation equipment and the control center, and calculate the communication bandwidth utilization rate, which is the ratio of the actual communication bandwidth to the theoretical maximum value of the communication bandwidth; For each simulation, calculate the normalized value of the sailing time, the normalized value of the energy consumption, and the normalized value of the communication bandwidth utilization rate; Add the normalized value of the sailing time, the normalized value of the energy consumption, and the normalized value of the communication bandwidth utilization rate to calculate the comprehensive performance index for each simulation; Integrate the comprehensive performance indices of each simulation, calculate the average value of the sum of squares of the comprehensive performance indices to obtain the average performance index of all simulations, analyze the root mean square of all simulation average performance indices, and then take the reciprocal of the root mean square and multiply by 100 to calculate the path performance evaluation index; Analyze the path performance evaluation index. If the path performance evaluation index is close to 100, it indicates that the path performance is excellent and meets all performance constraint conditions. If the path performance evaluation index is low, it indicates that the path performance is poor and needs to be optimized.

6. The intelligent path planning system for deep-sea deduction scenarios based on the optimal control theory according to claim 5, characterized in that: The control execution module specifically includes: Receive the latest optimal navigation path from the global path planning module. The path information includes waypoint coordinates, speed requirements, and sailing directions, and decompose the path into a series of discrete waypoints. Each waypoint contains position information and sailing parameters; Establish the kinematic model of the deep-sea operation equipment, and calculate a series of control instructions, including thruster thrust, rudder angle adjustment, and buoyancy adjustment, based on the optimal navigation path and the kinematic model of the deep-sea operation equipment. Then, send the generated control instructions to the execution system of the deep-sea operation equipment through the communication system; Real-time monitor the status indicators of deep-sea operation equipment through a sensor network, including position, speed, attitude, and depth information. Analyze the position deviation, speed deviation, attitude deviation, and depth deviation of each data point within the monitoring period. Combine with the reference values of each status indicator to calculate the equipment status evaluation index, and determine whether the equipment is in an abnormal operating state. Among them, the abnormal operating state includes position deviation, speed deviation, attitude abnormality, and depth abnormality; According to the optimal navigation path and real-time status data, adopt the optimal control theory to adjust the navigation parameters, calculate the control instructions for the current waypoint, and dynamically adjust the speed and heading angle according to the real-time status and environmental changes of the equipment. Among them, the control instructions for the current waypoint include position control, speed control, heading control, and depth control; Send the control instructions to the execution system of the deep-sea operation equipment through the communication link. After receiving the instructions, the execution system allocates the thruster thrust, adjusts the navigation attitude, continuously monitors the equipment status and environmental information, and forms a closed-loop control loop. Once a deviation or abnormal situation is detected, immediately make adjustments and corrections. Among them, the deviation or abnormal situation includes depth overlimit, attitude abnormality, and communication interruption.

7. The intelligent route planning system for deep - sea deduction scenarios based on the optimal control theory according to claim 6, characterized in that: The expression of the equipment status evaluation index is: ； Where ES is the equipment status evaluation index, M is the number of data points within the monitoring period, is the position deviation of the j-th data point, is the reference value of the position deviation, is the speed deviation of the j-th data point, is the reference value of the speed deviation, is the attitude deviation of the j-th data point, is the reference value of the attitude deviation, is the depth deviation of the j-th data point, is the reference value of the depth deviation. The value range of ES is [0, 100]. When the equipment status fully conforms to the reference value, ES approaches 100, indicating that the equipment is in good operating condition.

8. The intelligent route planning system for deep-sea deduction scenarios based on the optimal control theory according to claim 7, characterized in that: The feedback adjustment module specifically includes: The feedback adjustment module receives the latest deep-sea environment data from the environmental perception and modeling module, and receives the real-time status data of the deep-sea operation equipment from the control execution module. Then, it fuses the deep-sea environment data and the equipment status data to generate a unified input data format; By comparing the difference between the actual navigation trajectory and the planned path, detect whether there is a path deviation, analyze the path deviation, including path position deviation, path speed deviation, and heading deviation, and calculate the deviation risk assessment coefficient based on the magnitude and direction of the deviation, comprehensively considering the path position deviation, path speed deviation, and heading deviation. Evaluate its impact on the navigation safety and task completion of the equipment, and determine whether there is a risk that the deviation will cause the equipment to enter a dangerous area or violate the constraint conditions; According to the deviation analysis results, formulate corresponding feedback adjustment strategies, including adjusting the heading angle, changing the speed, and re-planning the local path, and make real-time adjustments to the navigation path according to the adjustment strategies; Feed back the adjusted path and related data to the global path planning module, and feed back the path adjustment information to the environmental perception module to update the deep-sea three-dimensional environment model.

9. The intelligent route planning system for deep-sea deduction scenarios based on the optimal control theory according to claim 8, characterized in that: The expression of the deviation risk assessment coefficient is: ； Wherein, DR is the deviation risk assessment coefficient, M is the number of data points within the monitoring period, is the path position deviation of the j-th data point, is the reference value of the path position deviation, is the speed deviation of the j-th data point, is the reference value of the speed deviation, is the course deviation of the j-th data point, is the reference value of the course deviation. The value range of DR is between 0 and 1. When the path deviation of the device completely conforms to the reference value, DR approaches 1, indicating that the device is in good operating condition and the risk is low.

Images