Self-adaptive path tracking control method and device for unmanned ship

Abstract

The invention belongs to the technical field of unmanned ship tracking control, and discloses a self-adaptive path tracking control method and device for an unmanned ship. The method comprises the steps of monitoring position data in real time through a boundary judgment algorithm to ensure that a ship is always in a preset safe area; multi-source data of ocean currents, radiation, batteries and the like are synchronously collected, three constraint conditions of predicting a drifting track, a charging area and remaining endurance time are constructed, a global optimal path is dynamically generated by applying a path planning algorithm, and the shortest distance, low energy consumption and high charging benefits are balanced. For energy management, a multi-stage power threshold is preset to trigger a differential loss reduction strategy. In a control layer, calculating propeller control parameters in real time based on path deviation, course deviation and environment interference; through collaborative optimization of global path planning and local control, the autonomous navigation capability, the energy utilization efficiency and the task sustainability of the unmanned ship in a dynamic environment are improved, and the method is suitable for ocean monitoring, resource exploration and other scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned ship tracking control, and more specifically, to an adaptive path tracking control method and device for unmanned ships. Background Art

[0002] The Pacific Ocean is the largest ocean on Earth, with an area accounting for approximately 49.8% of the total ocean area of the Earth. It has a profound impact on the global climate, ecosystem, economy, and social development. It is not only an important transmission channel for global heat and water vapor but also plays a key role in regulating the global climate and maintaining biodiversity. However, due to the vastness and complex environment of the Pacific Ocean, traditional ocean observation methods, such as manned ships, satellite remote sensing, and buoy monitoring, have many limitations.

[0003] Traditional observation ships are limited by manpower, endurance, and adverse weather conditions, making it difficult to conduct continuous observations over long periods and large areas. Although satellite remote sensing can provide large-area observation data, its ability to obtain information below the sea surface is limited, and it is easily interfered by factors such as clouds and sea conditions. Buoy monitoring can only be fixed at specific locations, with a narrow data coverage area, making it difficult to comprehensively reflect the dynamic changes of the ocean environment.

[0004] The world patent application with publication number WO2021035911A1 discloses an unmanned boat path planning method and system based on a data forward and reverse drive linear variable parameter genetic algorithm: receiving the navigation data, ship log, and status information of the unmanned boat; converting the coordinate system of the navigation data and drawing a coordinate map, marking the target point and the real-time position of the unmanned boat in the coordinate map; using the data forward drive linear variable parameter genetic algorithm to generate the optimal trajectory for the unmanned boat path planning. This invention overcomes the disadvantages of traditional genetic algorithms, such as slow convergence speed, low computational efficiency, and easy premature convergence (local optimum).

[0005] Although the above method can meet most scenarios, through research and practical application of the above method and the existing technology, it is found that the above method and the existing technology have at least the following partial defects:

[0006] In a complex dynamic ocean environment, it is impossible to achieve path planning and precise control of an unmanned ship under multiple dynamic constraints.

[0007] In view of this, the present invention proposes an adaptive path tracking control method and device for unmanned ships to solve the above problems. Summary of the Invention

[0008] To overcome the above defects of the existing technology and to achieve the above object, the present invention provides the following technical solution: an adaptive path tracking control method for an unmanned ship, including the following steps:

[0009] Collect the position data of the unmanned ship, and based on the boundary judgment algorithm, judge whether the unmanned ship exceeds the preset boundary according to the position data of the unmanned ship. If it exceeds, proceed to the next step; otherwise, continue to judge;

[0010] Collect and analyze the ocean current data, environmental data, and unmanned ship data corresponding to the position data to obtain the predicted drifting trajectory of the unmanned ship; collect and analyze the radiation data corresponding to the position data to obtain the charging area; collect and analyze the battery data to obtain the predicted remaining endurance time; construct a path planning objective based on the predicted drifting trajectory, charging area, and predicted remaining endurance time, and use the path planning algorithm to perform dynamic path search to obtain the globally optimal path;

[0011] Preset multiple power thresholds, and when the current remaining battery power in the battery data is lower than different thresholds, start the corresponding loss reduction strategy;

[0012] Calculate the path deviation and heading deviation according to the position data and the globally optimal path, and use the path deviation, heading deviation, ocean current data, environmental data, battery data, and globally optimal path as the input of the path tracking model to obtain the control parameters of the unmanned ship thruster; perform real-time adjustment according to the control parameters of the unmanned ship thruster to achieve path tracking control.

[0013] Further, the method for obtaining the predicted drifting trajectory of the unmanned ship includes:

[0014] According to the ocean current data, environmental data, and unmanned ship data corresponding to the position data, based on Newton's laws of motion and hydrodynamics, combined with the ocean current data, environmental data, and unmanned ship data corresponding to the position data, establish the motion equation of the unmanned ship under the action of external forces, extract the acceleration of the unmanned ship from the unmanned ship data, and calculate the position and velocity of the unmanned ship at the next time step by combining the velocity-acceleration formula and the displacement-velocity formula; obtain the position sequence within the preset trajectory period through iterative calculation, and use the position sequence as the predicted drifting trajectory of the unmanned ship.

[0015] Further, the method for obtaining the charging area includes:

[0016] Obtain the UTC time corresponding to the position data of the collected unmanned ship, convert the UTC time to Julian day, calculate the Greenwich sidereal time based on the Julian day, and calculate the local sidereal time according to the Greenwich sidereal time;

[0017] Calculate the mean longitude and the correction term of the Earth's orbital eccentricity according to the Julian day, calculate the solar longitude according to the mean longitude and the correction term of the Earth's orbital eccentricity, calculate the solar right ascension according to the solar longitude, and calculate the hour angle according to the local sidereal time and the solar right ascension;

[0018] Calculate the solar declination angle through the obliquity of the ecliptic and the solar longitude;

[0019] Based on the longitude and latitude coordinates of the unmanned ship, combined with the hour angle and the solar declination angle, calculate the corresponding solar altitude angle, and obtain the sequence of solar altitude angles within a preset future time period through iterative calculation;

[0020] Select the time period when the solar altitude angle in the sequence of solar altitude angles is greater than the preset altitude angle threshold as the daily optimal charging time period;

[0021] Collect the illumination data of the position of the solar panels on the unmanned ship. The illumination data includes the illumination sequence and the cloud movement speed within a preset time period. Use the illumination data as the input of the short-term prediction model to obtain the predicted illumination intensity within a preset future time period;

[0022] Obtain the satellite image in the radiation data, identify the cloud pixels in the image through threshold segmentation, calculate the proportion of the cloud area in the preset sea area, and mark it as the cloud cover rate;

[0023] Obtain the cloud movement speed in the illumination data. Use the cloud cover rate and the cloud movement speed as the input of the cloud prediction model to obtain the sequence of cloud cover rates within a preset future time period;

[0024] If the predicted illumination intensity is greater than the preset illumination intensity threshold and the cloud cover rate within the preset future time period is lower than the preset cover rate threshold, mark the corresponding position of the solar panel as the charging area, and mark the daily optimal charging time period on the charging area.

[0025] Further, the method for obtaining the predicted remaining endurance time includes:

[0026] Obtain the current remaining battery power in the battery data, and obtain the propeller power and the power consumption of the mission equipment. Correct the propeller power according to the ocean current speed and the unmanned ship speed to obtain the corrected value of the propeller power, and calculate the total energy consumption based on the corrected value of the propeller power and the power consumption of the mission equipment;

[0027] Obtain the output electric power, the incident light power and the area of the battery panel of the solar panel to obtain the conversion efficiency of the solar panel;

[0028] Calculate the charging amount corresponding to the current moment according to the illumination intensity and the conversion efficiency of the solar panel, calculate the charging amounts at different moments according to the predicted illumination intensity and the conversion efficiency of the solar panel within the preset future time period, and accumulate the charging amounts at different moments within the preset future time period to obtain the charging amount within the preset future time period;

[0029] Calculate the remaining endurance time based on the current remaining battery power, the charging amount in the preset future time period and the total energy consumption.

[0030] Further, the method for obtaining the globally optimal path includes:

[0031] Obtain a charging area, a drifting risk area, a remaining battery life restricted area, and a preset optimization objective;

[0032] The drifting risk area is an area where the predicted ocean current speed is greater than the preset ocean current speed threshold, and the remaining battery life restricted area is an area where the total path time is greater than the remaining battery life; the preset optimization objectives include minimizing the total energy consumption, maximizing the charging benefit, and the total path time being lower than the remaining battery life;

[0033] Calculate the Euclidean distance between the position data and the charging area; calculate the ratio of the electric energy finally stored in the battery to the total incident light energy to obtain the energy conversion efficiency; calculate the product of the light intensity, the effective area of the solar panel, and the nominal efficiency of the solar panel to obtain the input power of the solar panel; calculate the product of the energy conversion efficiency, the input power of the solar panel, and the effective charging time to obtain the charging benefit; weight the Euclidean distance, the energy conversion efficiency, and the charging benefit, and calculate to obtain the cost function;

[0034] Construct a heuristic function based on the weighted Euclidean distance and the charging area attraction. Among them, the weight of the charging area attraction is negative. By minimizing the cost function and combining the heuristic function for node expansion, a globally optimal path is obtained.

[0035] Further, the charging area attraction is obtained by summing the attractions of all charging areas, and the attraction is the ratio of the light intensity corresponding to the charging area to the Euclidean distance.

[0036] Further, in the method for obtaining the globally optimal path, a trigger condition for dynamic path adjustment is also preset. When the trigger condition is reached, a replanning of the globally optimal path is performed; the trigger conditions include: the deviation value between the actual drifting trajectory and the predicted drifting trajectory is greater than the preset deviation threshold; the predicted remaining battery life is lower than the preset battery life safety threshold.

[0037] Further, the method for the boundary judgment algorithm to judge whether the unmanned ship exceeds the preset boundary according to the position data of the unmanned ship includes:

[0038] Preset the boundary of the observation area, and pre-calibrate the boundary coordinates of the observation area through GIS;

[0039] Obtain the current longitude and latitude coordinates of the unmanned ship through GIS, and calculate the Euclidean distance between the current longitude and latitude coordinates of the unmanned ship and the boundary coordinates in real time. If the Euclidean distance exceeds the preset distance threshold, immediately trigger path replanning.

[0040] Further, the method for starting the corresponding loss reduction strategy includes:

[0041] Preset a first threshold, a second threshold, and a third threshold. When the battery level is lower than the first threshold, suspend the preset secondary tasks. When the battery level is lower than the second threshold, only retain the preset core tasks. When the battery level is lower than the third threshold, force the return journey or enter the sleep mode, and the return path planning preferably points to the charging area;

[0042] Take the path deviation, heading deviation, ocean current data, environmental data, battery data, and the global optimal path as the inputs of the path tracking model to obtain the control parameters of the unmanned ship thrusters; perform real-time adjustment according to the control parameters of the unmanned ship thrusters to achieve path tracking control.

[0043] Further, the method for achieving path tracking control includes:

[0044] According to the position data of the unmanned ship, calculate the difference between the actual position and the nearest point on the preset path to obtain the path deviation; calculate the difference between the current heading and the preset heading to obtain the heading deviation;

[0045] Take the path deviation, heading deviation, ocean current data, environmental data, battery data, and the global optimal path as the inputs of the path tracking model to obtain the control parameters of the unmanned ship thrusters; perform real-time adjustment according to the control parameters of the unmanned ship thrusters to achieve path tracking control.

[0046] An unmanned ship adaptive path tracking control device for implementing the unmanned ship adaptive path tracking control method includes:

[0047] Boundary judgment module: Collect the position data of the unmanned ship, and based on the boundary judgment algorithm, judge whether the unmanned ship exceeds the preset boundary according to the position data of the unmanned ship. If it exceeds, continue to the next step; otherwise, continue to judge;

[0048] Path planning module: Collect and analyze the ocean current data, environmental data, and unmanned ship data corresponding to the position data to obtain the predicted drift trajectory of the unmanned ship; collect and analyze the radiation data corresponding to the position data to obtain the charging area; collect and analyze the battery data to obtain the predicted remaining endurance time; construct a path planning target based on the predicted drift trajectory, charging area, and predicted remaining endurance time, and use the path planning algorithm to perform dynamic path search to obtain the global optimal path;

[0049] Adaptive loss reduction module: Preset multiple levels of power thresholds, and when the current remaining battery power in the battery data is lower than different thresholds, activate the corresponding loss reduction strategies;

[0050] Path tracking module: Calculate the path deviation and heading deviation according to the position data and the global optimal path, take the path deviation, heading deviation, ocean current data, environmental data, battery data, and the global optimal path as the inputs of the path tracking model to obtain the control parameters of the unmanned ship thrusters; perform real-time adjustment according to the control parameters of the unmanned ship thrusters to achieve path tracking control.

[0051] Technical effects and advantages of the unmanned ship adaptive path tracking control method and device of the present invention:

[0052] The present invention monitors the position of the unmanned ship in real time through a boundary judgment algorithm to ensure that it is always within a preset safe area; at the same time, it integrates ocean current data, radiation data, and environmental data, dynamically predicts the drifting trajectory and identifies the charging area, and combines the remaining battery power with a multi-level power threshold strategy, etc., and uses the A* algorithm combined with the Dijkstra algorithm to optimize the path planning, balancing the shortest path and charging benefits to extend the endurance; it also uses the real-time feedback of path deviation and heading deviation, and uses the path tracking model to optimize the control parameters of the thruster, reduce the navigation error, and automatically trigger the loss reduction strategy when the power is low; through the collaborative optimization of global path planning and local control, the present invention solves the problem of path planning and precise control of the unmanned ship in the open ocean environment under multiple dynamic constraints, significantly improves the autonomous navigation ability, energy utilization efficiency, and mission sustainability of the unmanned ship in the dynamic environment, and is applicable to scenarios such as ocean monitoring and resource exploration. Description of the Drawings

[0053] Figure 1 Schematic diagram of the unmanned ship adaptive path tracking control method of Embodiment 1 of the present invention;

[0054] Figure 2 Schematic diagram of the solar panel layout of Embodiment 1 of the present invention;

[0055] Figure 3 Schematic diagram of the method flow of Embodiment 2 of the present invention;

[0056] Figure 4 Schematic diagram of the structure of the unmanned ship adaptive path tracking control device of Embodiment 3 of the present invention. Detailed Embodiments

[0057] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] Embodiment 1

[0059] Please refer to Figure 1 As shown, the unmanned ship adaptive path tracking control method described in this embodiment includes the following steps:

[0060] Collect the position data of the unmanned ship. Based on the boundary judgment algorithm, judge whether the unmanned ship exceeds the preset boundary according to the position data of the unmanned ship. If it exceeds, perform path planning for the unmanned ship; otherwise, continue to judge. The position data includes longitude and latitude coordinates, heading angle, pitch angle, and roll angle. Collecting the position data of the unmanned ship and continuously monitoring whether it exceeds the preset boundary based on the boundary judgment algorithm is the core of the safety guarantee for the adaptive path tracking control of the unmanned ship. The boundary judgment algorithm continuously compares the actual position with the coordinates of the geographical fence. Once the risk of crossing the boundary or the boundary has been crossed is detected, it immediately triggers dynamic path replanning (such as starting the A* algorithm to re-search for a safe path), and adjusts the heading through the thruster control parameters to force the unmanned ship back to the safe area. At the same time, the boundary judgment provides constraints for path planning to ensure that the globally optimal path is always within the legal water area, avoiding breaking through the safety threshold due to the algorithm blindly pursuing efficiency. In addition, this function can also cooperate with the energy management module. When there is a charging area in the direction of crossing the boundary, the path is preferentially adjusted to balance the safety and endurance requirements.

[0061] The method for judging whether the unmanned ship exceeds the preset boundary based on the boundary judgment algorithm according to the position data of the unmanned ship includes:

[0062] Preset the boundary of the observation area, and pre-calibrate the boundary coordinates of the observation area through GIS;

[0063] Obtain the current longitude and latitude coordinates of the unmanned ship through GIS, and calculate the Euclidean distance between the current longitude and latitude coordinates of the unmanned ship and the boundary coordinates in real time. If the Euclidean distance exceeds the preset distance threshold, immediately trigger path replanning.

[0064] Collect and analyze the ocean current data, environmental data, and unmanned ship data corresponding to the position data to obtain the predicted drift trajectory of the unmanned ship; collect and analyze the radiation data corresponding to the position data to obtain the charging area; collect and analyze the battery data to obtain the predicted remaining endurance time; construct a path planning target based on the predicted drift trajectory, charging area, and predicted remaining endurance time, and use the path planning algorithm to perform dynamic path search to obtain the globally optimal path;

[0065] The method for obtaining the predicted drift trajectory of the unmanned ship includes:

[0066] According to the ocean current data corresponding to the position data, such as ocean current velocity, ocean current direction, etc., environmental data, such as wind speed, wind direction, wave height, wave direction, and wave period, etc.; unmanned ship data, such as the acceleration, angular velocity, and attitude angle of the hull, etc., based on Newton's laws of motion and hydrodynamics, combined with the ocean current data, environmental data, and unmanned ship data corresponding to the position data, establish the motion equation of the unmanned ship under the action of external forces, such as ; ; ; where is the mass of the unmanned ship; is the hull velocity vector; is time; is the thruster thrust, calculated based on the product of the hull acceleration and the mass of the unmanned ship; is the ocean current force; is the wind force; is the wave force; is the resistance; is the seawater density; is the hull displacement volume; is the ocean current velocity; is the resistance coefficient; is the hull area facing the current; is the actual acceleration of the unmanned ship; the acceleration of the unmanned ship is extracted from the unmanned ship data, and the position and velocity of the unmanned ship at the next time step are calculated by combining the velocity-acceleration formula and the displacement-velocity formula; the position sequence within the preset trajectory period is obtained through iterative calculation, and the position sequence is used as the predicted drifting trajectory of the unmanned ship.

[0067] By real-time monitoring of the ocean current velocity, direction, and meteorological conditions (such as wind speed, wave height), etc., and combining the current state of the unmanned ship (such as heading, thruster power), the system can construct a high-precision drifting model to predict the position deviation in the future period; this prediction result provides key input for path planning: on the one hand, high-risk areas (such as rapids) are avoided in advance in the global path search to optimize the path energy consumption; on the other hand, the ocean current interference is compensated in real time in the local control, and the thruster control parameters are adjusted to reduce the deviation between the actual navigation trajectory and the planned path. In addition, the predicted drifting trajectory can cooperate with the boundary judgment algorithm, and when it is found that the boundary may be crossed in the future period, the path replanning is triggered in advance to ensure the navigation safety.

[0068] The methods for obtaining the charging area include:

[0069] Obtain the UTC time corresponding to the position data of the unmanned ship, convert the UTC time to the Julian day, calculate the Greenwich sidereal time based on the Julian day, and calculate the local sidereal time according to the Greenwich sidereal time;

[0070] Calculate the mean ecliptic longitude and the correction term of the Earth's orbital eccentricity according to the Julian day, calculate the solar ecliptic longitude according to the mean ecliptic longitude and the correction term of the Earth's orbital eccentricity, calculate the solar right ascension according to the solar ecliptic longitude, and calculate the hour angle according to the local sidereal time and the solar right ascension;

[0071] Calculate the solar declination angle through the obliquity of the ecliptic and the solar ecliptic longitude;

[0072] Based on the longitude and latitude coordinates of the unmanned ship, combined with the hour angle and the solar declination angle, calculate the corresponding solar altitude angle, and obtain the solar altitude angle sequence within the preset future period through iterative calculation;

[0073] Select the period when the solar altitude angle in the solar altitude angle sequence is greater than the preset altitude angle threshold as the daily optimal charging period;

[0074] Collect the illumination data of the position of the solar panels on the unmanned ship. The illumination data includes the illumination sequence and the cloud movement speed within a preset period, and use the illumination data as the input of the short-term prediction model to obtain the predicted illumination intensity within a preset future period;

[0075] Obtain the satellite image in the radiation data, identify the cloud pixels in the image through threshold segmentation, calculate the proportion of the cloud area in the preset sea area, and mark it as the cloud cover rate;

[0076] Obtain the cloud movement speed in the illumination data, use the cloud cover rate and the cloud movement speed as the input of the cloud prediction model, and obtain the cloud cover rate sequence within a preset future period;

[0077] If the predicted illumination intensity is greater than the preset illumination intensity threshold and the cloud cover rate within the preset future period is lower than the preset cover rate threshold, mark the corresponding position of the solar panel as the charging area and mark the daily optimal charging period on the charging area.

[0078] The training method of the cloud prediction model includes:

[0079] Pre-collect B groups of cloud prediction data. The cloud prediction data includes the cloud cover rate and the cloud movement speed, as well as the corresponding cloud cover rate sequence within a preset future period.

[0080] Use the cloud cover rate and the cloud movement speed as the input of the cloud prediction model, and use the corresponding cloud cover rate sequence within the preset future period as the output of the cloud prediction model. With the goal of minimizing the error between the output corresponding cloud cover rate sequence within the preset future period and the actual corresponding cloud cover rate sequence within the preset future period, optimize the network parameters of the cloud prediction model through a natural inspiration optimization algorithm, obtain the network parameters corresponding to the minimum error between the output corresponding cloud cover rate sequence within the preset future period and the actual corresponding cloud cover rate sequence within the preset future period, and use the cloud prediction model constructed by the corresponding network parameters as the trained cloud prediction model.

[0081] By monitoring the light intensity in real time, the system dynamically generates a charging priority map. During path planning, the charging benefit term in the cost function guides the unmanned ship to preferentially go to high-light areas to replenish energy. When the battery power is lower than the threshold, this data-driven system forcibly adjusts the path weight, and even if it has to detour, it must reach the charging area. At the same time, it can combine the predicted drifting trajectory and the predicted remaining endurance time to ensure that the total path time does not exceed the predicted remaining endurance time, avoiding mission interruption due to energy exhaustion. In addition, the radiation data can also be linked with the cloud cover prediction. When it is detected that the charging area is about to be blocked, path replanning is triggered in advance to achieve dynamic optimization of energy utilization.

[0082] The methods for obtaining the predicted remaining endurance time include:

[0083] Obtain the current remaining power in the battery data, and obtain the thruster power and the power consumption of the mission equipment. Correct the thruster power according to the ocean current speed and the speed of the unmanned ship to obtain the corrected thruster power value, and calculate the total energy consumption based on the corrected thruster power value and the power consumption of the mission equipment;

[0084] Obtain the output electric power, incident light power, and panel area of the solar panel to obtain the conversion efficiency of the solar panel; among them, due to the limited area of the hull deck, in order to make full use of solar energy resources, flexible photovoltaic solar panels with high wattage are selected, and the size and specifications are customized according to the surface shape of the hull to achieve maximum bending laying and increase the solar collection area. For details, please refer to Figure 2 . In addition to laying on the hull deck, some solar panels can also be considered to be installed on the mast bracket to further expand the solar collection area; the lithium battery that stores the electric energy converted by the solar panel is also placed in a specially designed battery compartment at the bottom of the unmanned ship. The battery compartment adopts multiple protection measures such as sealing, waterproofing, fireproofing, and heat insulation, which can ensure that the battery works in a safe and stable environment, and at the same time effectively reduce the impact of the battery pack weight on the ship's center of gravity and improve the navigation stability of the hull.

[0085] Calculate the charging amount corresponding to the current moment according to the light intensity and the conversion efficiency of the solar panel, calculate the charging amounts at different moments according to the predicted light intensity and the conversion efficiency of the solar panel within the preset future time period, and accumulate the charging amounts at different moments within the preset future time period to obtain the charging amount within the preset future time period;

[0086] Calculate the remaining endurance time based on the current remaining battery power, the charging amount within the preset future time period, and the total energy consumption.

[0087] By real-time monitoring of the remaining battery power, discharge rate, and historical energy consumption data, accurately predict the remaining endurance time, providing key constraint conditions for path planning: in the global path search, the remaining endurance time directly determines the upper limit of the total path time, forcing the algorithm to select a feasible path with the lowest energy consumption or the greatest charging benefit; in the dynamic adjustment stage, when the remaining endurance time is lower than the preset endurance safety threshold (such as 2 hours), trigger a low-power mode or a loss reduction strategy to prioritize going to the charging area, and re-plan the shortest charging path through the A* algorithm. In addition, predicting the remaining endurance time also coordinates with predicting the drifting trajectory. By calculating the ratio of the total path time (including drifting deviation) to the remaining endurance time, the path feasibility is evaluated in real time to ensure that the unmanned ship can still maintain energy balance under environmental interference and avoid mission interruption or equipment disconnection due to power exhaustion.

[0088] Methods for obtaining the global optimal path include:

[0089] Obtain the charging area, drifting risk area, endurance restricted area, and preset optimization objectives;

[0090] The drifting risk area is the area where the predicted ocean current speed is greater than the preset ocean current speed threshold, and the endurance restricted area is the area where the total path time is greater than the remaining endurance time; the preset optimization objectives include minimizing the total energy consumption, maximizing the charging benefit, and the total path time being lower than the remaining endurance time;

[0091] Calculate the Euclidean distance between the position data and the charging area; calculate the ratio of the electric energy finally stored in the battery to the total incident light energy to obtain the energy conversion efficiency; calculate the product of the light intensity, the effective area of the solar panel, and the nominal efficiency of the solar panel to obtain the input power of the solar panel; calculate the product of the energy conversion efficiency, the input power of the solar panel, and the effective charging time to obtain the charging benefit; weight the Euclidean distance, energy conversion efficiency, and charging benefit, and calculate to obtain the cost function;

[0092] Construct a heuristic function based on the weighted Euclidean distance and the attraction of the charging area. Among them, the weights of the Euclidean distance and the attraction of the charging area can be obtained by optimizing through a nature-inspired optimization algorithm. The weight of the attraction of the charging area is negative, and the attraction of the charging area is obtained by summing the attractions of all charging areas. The attraction is the ratio of the light intensity corresponding to the charging area to the Euclidean distance; among them, the closer to the charging area, the lower the heuristic value. By minimizing the cost function and combining the heuristic function for node expansion, the global optimal path is obtained;

[0093] Preset the trigger conditions for dynamic path adjustment. When the trigger conditions are met, re-plan the global optimal path. The trigger conditions include: the deviation value between the actual drifting trajectory and the predicted drifting trajectory is greater than the preset deviation threshold; the predicted remaining endurance time is lower than the preset endurance safety threshold;

[0094] The triggering conditions may also include environmental mutations (such as sudden storms (wind speed greater than the preset wind speed threshold, wave height greater than the preset wave height threshold), cloud cover over the charging area (light intensity change rate higher than the preset change rate threshold, cloud cover rate of the charging area greater than the preset cloud cover rate threshold), sudden water temperature changes (water temperature change rate greater than the preset change threshold), and communication interruption (losing contact with the control center for more than the preset disconnection duration), etc.).

[0095] Through the multi-objective optimization strategy, the above steps use the predicted drifting trajectory as the environmental constraint, the charging area as the energy gain point, and the remaining endurance time as the time window constraint. Under the coordination of the global optimal search of the A* algorithm and the local dynamic adjustment of the Dijkstra algorithm, a feasible path that takes into account the shortest distance, low energy consumption, high charging benefit, and risk avoidance is generated in real time. It can quickly find the initial optimal path through the heuristic function of the A* algorithm; use the remaining endurance time as a hard constraint to ensure the feasibility of the path; the above method significantly improves the path robustness, energy utilization efficiency, and task completion rate of the unmanned ship in complex marine environments.

[0096] Preset multi-level power thresholds. When the current remaining battery power in the battery data is lower than different thresholds, start the corresponding loss reduction strategy;

[0097] The method of starting the corresponding loss reduction strategy includes:

[0098] Preset the first threshold, the second threshold, and the third threshold. When the power is lower than the first threshold, suspend the preset secondary tasks. When the power is lower than the second threshold, only retain the preset core tasks; when the power is lower than the third threshold, force the return voyage or enter the sleep mode, and the return path planning preferably points to the charging area.

[0099] The above method divides the battery power into a safe area (such as ≥50%), a warning area (such as 30% - 50%), and a critical area (such as <30%) through the first threshold, the second threshold, and the third threshold, and can dynamically adjust the path planning priority and control strategy; in the warning area, the system increases the weight of the charging benefit and forces the path to tilt towards the high-light area; in the critical area, trigger the low-power mode (such as reducing the thruster power) and start the Dijkstra algorithm to re-plan the shortest charging path. At the same time, combine the predicted remaining endurance time and the predicted drifting trajectory to ensure that the total path time ≤ the remaining endurance time, and avoid losing control due to power exhaustion; significantly improve the energy utilization rate and survival ability of the unmanned ship in long-duration tasks, and ensure its continuous operation ability in complex environments.

[0100] Calculate the path deviation and heading deviation based on the position data and the global optimal path. Use the path deviation, heading deviation, ocean current data, environmental data, battery data, and global optimal path as the inputs of the path tracking model to obtain the control parameters for the unmanned ship thrusters. Make real-time adjustments according to the control parameters of the unmanned ship thrusters to achieve path tracking control. The control parameters of the unmanned ship thrusters include the adjustment amount of the thruster thrust and the deflection angle of the rudder.

[0101] The method for achieving path tracking control includes:

[0102] Based on the position data of the unmanned ship, calculate the difference between the actual position and the nearest point on the preset path to obtain the path deviation. Calculate the difference between the current heading and the preset heading to obtain the heading deviation.

[0103] Use the path deviation, heading deviation, ocean current data, environmental data, battery data, and global optimal path as the inputs of the path tracking model to obtain the control parameters for the unmanned ship thrusters. Make real-time adjustments according to the control parameters of the unmanned ship thrusters to achieve path tracking control.

[0104] The training method of the path tracking model includes:

[0105] Pre-collect F groups of path tracking data, where the path tracking data includes path deviation, heading deviation, ocean current data, environmental data, battery data, global optimal path, and the corresponding control parameters of the unmanned ship thrusters.

[0106] Use the path deviation, heading deviation, ocean current data, environmental data, battery data, and global optimal path as the inputs of the path tracking model, and use the corresponding control parameters of the unmanned ship thrusters as the outputs of the path tracking model. With the goal of minimizing the error between the output corresponding control parameters of the unmanned ship thrusters and the actual corresponding control parameters of the unmanned ship thrusters, optimize the network parameters of the path tracking model through a natural inspiration optimization algorithm to obtain the network parameters corresponding to the minimum error between the output corresponding control parameters of the path tracking model and the actual corresponding control parameters of the unmanned ship thrusters. Use the path tracking model constructed by the corresponding network parameters as the trained path tracking model.

[0107] The above steps compensate for path deviation (lateral error) and heading deviation (angle error) in real time, dynamically adjust the thruster thrust and rudder angle through the path tracking model, and reduce the deviation between the navigation trajectory and the planned path; it also combines ocean current data to predict the interference force and feedforward compensates for the impact of the water flow on the hull to reduce the trajectory deviation caused by environmental disturbances; it can also optimize the propulsion strategy in combination with the remaining battery power, reduce the thrust at low battery levels to extend the endurance, and maintain the heading through fine-tuning of the rudder angle; in complex scenarios (such as narrow channels), ensure navigation safety through control parameter constraints (such as maximum rudder angle, minimum thrust). This closed-loop control architecture realizes seamless connection from path planning to physical execution, and significantly improves the tracking accuracy and anti-interference ability of the unmanned ship in the dynamic ocean environment.

[0108] Embodiment 2

[0109] Please refer to Figure 3 As shown, this embodiment provides a method for judging whether an unmanned ship exceeds a preset boundary based on an approximate convex hull decomposition boundary judgment algorithm according to the position data of the unmanned ship, including the following steps:

[0110] Step 1: Obtain the boundary vertex coordinate sequence of the unmanned ship or the preset observation area, and arrange it in a clockwise or counterclockwise order;

[0111] Step 2: Traverse all vertices and calculate the vector directions of the predecessor vertex and the successor vertex of each vertex;

[0112] Step 3: Calculate the difference between the vertex and its predecessor vertex, and the difference between the successor vertex and the vertex, then calculate the cross product of the two differences to obtain the cross product symbol. If the symbol is negative, the vertex is a concave point, otherwise it is a convex point. Record all concave points to generate a concave point list;

[0113] Step 4: Apply the selected dividing line to decompose the polygon contour into two sub-polygons; where the polygon is composed of the concave point list of the unmanned ship or the preset observation area;

[0114] Step 5: Repeat Steps 2 - 4 to perform concave point detection and segmentation on each sub-polygon until all sub-polygons are convex polygons;

[0115] Step 6: If the merging result of two adjacent sub-polygons is still a convex polygon, then merge them, and give priority to merging the sub-polygons sharing the longest common side;

[0116] Step 7: Summarize the merging results to obtain a set of vertex sets of convex sub-polygons of the unmanned ship or the preset observation area;

[0117] Step 8: Obtain the boundary coordinates corresponding to the vertex set of the convex sub-polygon of the pre-calibrated observation area through GIS;

[0118] Step 9: Obtain the longitude and latitude coordinates corresponding to the vertex set of the convex sub-polygon of the unmanned ship through GIS, and calculate in real time the Euclidean distance between the longitude and latitude coordinates corresponding to the vertex set of the convex sub-polygon of the unmanned ship and the boundary coordinates corresponding to the vertex set of the convex sub-polygon of the observation area. If the Euclidean distance exceeds the preset distance threshold, immediately trigger path replanning.

[0119] The selection method of the dividing line includes:

[0120] For each concave point, connect the concave point to other vertices, and select the dividing line that meets the following conditions:

[0121] Condition 1: The sub-polygon after division contains the fewest concave points;

[0122] Condition 2: The dividing line does not intersect with other sides.

[0123] Through the convex hull inclusion judgment, the above method steps can quickly determine whether the unmanned ship exceeds the preset boundary, trigger path replanning or emergency steering of the thruster; decompose the irregular observation area into a convex hull set, reduce the geometric calculation complexity of boundary judgment, and are applicable to the dynamically expanding marine monitoring scenario; provide accurate convex hull boundary constraints for the A* algorithm to ensure that the globally optimal path is always within the safe area and avoid the discrete error of the traditional grid method; combine the predicted drift trajectory and ocean current data to predict the cross-border risk in the future period, adjust the path direction in advance, and achieve forward-looking safety control; when the charging area is located on the convex hull boundary, quickly calculate the nearest charging path through convex hull decomposition, and balance the battery life demand and safety constraints. The above method significantly improves the real-time performance and geometric adaptability of boundary judgment, and provides an efficient boundary management means for the safe and autonomous navigation of unmanned ships in complex sea areas.

[0124] Embodiment 3

[0125] Please refer to Figure 4 As shown, the unmanned ship adaptive path tracking control device in this embodiment includes the following steps:

[0126] Boundary judgment module: Collect the position data of the unmanned ship, and based on the boundary judgment algorithm, judge whether the unmanned ship exceeds the preset boundary according to the position data of the unmanned ship. If it exceeds, continue to the next step; otherwise, continue to judge;

[0127] Path planning module: Collect and analyze the ocean current data, environmental data, and unmanned ship data corresponding to the position data to obtain the predicted drift trajectory of the unmanned ship; collect and analyze the radiation data corresponding to the position data to obtain the charging area; collect and analyze the battery data to obtain the predicted remaining battery life; construct a path planning target based on the predicted drift trajectory, charging area, and predicted remaining battery life, and use the path planning algorithm to perform dynamic path search to obtain the globally optimal path;

[0128] Adaptive loss reduction module: preset multiple levels of power thresholds, and when the current remaining battery power in the battery data is lower than different thresholds, start the corresponding loss reduction strategy;

[0129] Path tracking module: calculate the path deviation and heading deviation based on the position data and the global optimal path, use the path deviation, heading deviation, ocean current data, environmental data, battery data and the global optimal path as the input of the path tracking model to obtain the control parameters of the unmanned ship thruster; perform real-time adjustment according to the control parameters of the unmanned ship thruster to achieve path tracking control.

[0130] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0131] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An adaptive path tracking control method for an unmanned ship, characterized in that, It includes the following steps: Collect the position data of the unmanned ship, and based on the boundary judgment algorithm, judge whether the unmanned ship exceeds the preset boundary according to the position data of the unmanned ship. If it exceeds, proceed to the next step; otherwise, continue to judge. Collect and analyze the ocean current data, environmental data, and unmanned ship data corresponding to the position data to obtain the predicted drifting trajectory of the unmanned ship; collect and analyze the radiation data corresponding to the position data to obtain the charging area; collect and analyze the battery data to obtain the predicted remaining endurance time. Construct a path planning objective based on the predicted drifting trajectory, charging area, and predicted remaining endurance time, and use the path planning algorithm to perform dynamic path search to obtain the globally optimal path. Preset multiple levels of power thresholds, and when the current remaining battery power in the battery data is lower than different thresholds, activate the corresponding loss reduction strategy. Calculate the path deviation and heading deviation based on the position data and the globally optimal path, and use the path deviation, heading deviation, ocean current data, environmental data, battery data, and globally optimal path as the input of the path tracking model to obtain the control parameters of the unmanned ship thruster; perform real-time adjustment according to the control parameters of the unmanned ship thruster to achieve path tracking control.

2. The adaptive path tracking control method for an unmanned ship according to claim 1, wherein The method for obtaining the predicted drifting trajectory of the unmanned ship includes: According to the ocean current data, environmental data, and unmanned ship data corresponding to the position data, based on Newton's laws of motion and hydrodynamics, combined with the ocean current data, environmental data, and unmanned ship data corresponding to the position data, establish the motion equation of the unmanned ship under external forces, extract the acceleration of the unmanned ship from the unmanned ship data, and calculate the position and velocity of the unmanned ship at the next time step by combining the velocity-acceleration formula and the displacement-velocity formula; obtain the position sequence within the preset trajectory period through iterative calculation, and use the position sequence as the predicted drifting trajectory of the unmanned ship.

3. The adaptive path tracking control method for an unmanned ship according to claim 1, wherein The method for obtaining the charging area includes: Obtain the UTC time corresponding to the position data of the collected unmanned ship, convert the UTC time to the Julian day, calculate the Greenwich sidereal time based on the Julian day, and calculate the local sidereal time according to the Greenwich sidereal time. Calculate the mean anomaly and the correction term of the Earth's orbital eccentricity according to the Julian day, calculate the solar longitude according to the mean anomaly and the correction term of the Earth's orbital eccentricity, calculate the solar right ascension according to the solar longitude, and calculate the hour angle according to the local sidereal time and the solar right ascension. Calculate the solar declination angle through the obliquity of the ecliptic and the solar longitude. Based on the longitude and latitude coordinates of the unmanned ship, combined with the hour angle and the solar declination angle, calculate the corresponding solar altitude angle, and obtain the solar altitude angle sequence within the preset future period through iterative calculation. Select the period with the solar altitude angle greater than the preset altitude angle threshold in the solar altitude angle sequence as the daily best charging period. Collect the illumination data at the position of the solar panel on the unmanned ship. The illumination data includes the illumination sequence and cloud movement speed within the preset period, and use the illumination data as the input of the short-term prediction model to obtain the predicted illumination intensity within the preset future period. Obtain the satellite image in the radiation data, identify the cloud pixels in the image through threshold segmentation, calculate the proportion of the cloud area in the preset sea area, and mark it as the cloud cover rate. Obtain the cloud movement speed in the light data, use the cloud coverage rate and the cloud movement speed as the input of the cloud prediction model, and obtain the cloud coverage rate sequence within a preset future time period; If the predicted light intensity is greater than the preset light intensity threshold and the cloud coverage rate within the preset future time period is lower than the preset coverage rate threshold, mark the corresponding solar panel position as the charging area and mark the daily best charging time period on the charging area.

4. The adaptive path tracking control method for an unmanned ship according to claim 1, characterized in that The method for obtaining the predicted remaining endurance time includes: Obtain the current remaining battery power in the battery data, obtain the thruster power and the power consumption of the mission equipment, correct the thruster power according to the ocean current speed and the unmanned ship speed to obtain the corrected thruster power value, and calculate the total energy consumption based on the corrected thruster power value and the power consumption of the mission equipment; Obtain the output electric power, incident light power and panel area of the solar panel to obtain the conversion efficiency of the solar panel; Calculate the charging amount corresponding to the current moment according to the light intensity and the conversion efficiency of the solar panel, calculate the charging amounts at different moments according to the predicted light intensity and the conversion efficiency of the solar panel within the preset future time period, and accumulate the charging amounts at different moments within the preset future time period to obtain the charging amount within the preset future time period; Calculate the remaining endurance time based on the current remaining battery power, the charging amount within the preset future time period and the total energy consumption.

5. The adaptive path tracking control method for an unmanned ship according to claim 1, characterized in that The method for obtaining the globally optimal path includes: Obtain the charging area, the drifting risk area, the endurance forbidden area, and the preset optimization objectives; The drifting risk area is the area where the predicted ocean current speed is greater than the preset ocean current speed threshold, and the endurance forbidden area is the area where the total path time is greater than the remaining endurance time; the preset optimization objectives include minimizing the total energy consumption, maximizing the charging benefit and the total path time being lower than the remaining endurance time; Calculate the Euclidean distance between the position data and the charging area; calculate the ratio of the electric energy finally stored in the battery to the total incident light energy to obtain the energy conversion efficiency; calculate the product of the light intensity, the effective area of the solar panel and the nominal efficiency of the solar panel to obtain the input power of the solar panel; calculate the product of the energy conversion efficiency, the input power of the solar panel and the effective charging time to obtain the charging benefit; weight the Euclidean distance, the energy conversion efficiency and the charging benefit and calculate to obtain the cost function; Construct a heuristic function based on the weighted Euclidean distance and the charging area attraction, where the weight of the charging area attraction is negative. By minimizing the cost function and combining the heuristic function for node expansion, obtain the globally optimal path.

6. The unmanned ship adaptive path tracking control method according to claim 5, characterized in that The charging area attraction is obtained by summing the attractions of all charging areas, and the attraction is the ratio of the light intensity corresponding to the charging area to the Euclidean distance.

7. The adaptive path tracking control method for an unmanned ship according to claim 5, characterized in that, In the method for obtaining the globally optimal path, a trigger condition for dynamic path adjustment is also preset. When the trigger condition is reached, re-plan the globally optimal path; the trigger conditions include: the deviation value between the actual drifting trajectory and the predicted drifting trajectory is greater than the preset deviation threshold; the predicted remaining endurance time is lower than the preset endurance safety threshold.

8. The unmanned ship adaptive path tracking control method according to claim 1, characterized in that The method for judging whether the unmanned ship exceeds the preset boundary based on the boundary judgment algorithm according to the position data of the unmanned ship includes: Preset the boundary of the observation area, and pre-calibrate the boundary coordinates of the observation area through GIS; Obtain the current longitude and latitude coordinates of the unmanned ship through GIS, and calculate the Euclidean distance between the current longitude and latitude coordinates of the unmanned ship and the boundary coordinates in real time. If the Euclidean distance exceeds the preset distance threshold, immediately trigger path replanning.

9. The unmanned ship adaptive path tracking control method according to claim 1, characterized in that The method for starting the corresponding loss reduction strategy includes: Preset the first threshold, the second threshold and the third threshold. When the power is lower than the first threshold, suspend the preset secondary tasks. When the power is lower than the second threshold, only retain the preset core tasks. When the power is lower than the third threshold, force the return voyage or enter the sleep mode, and the return path planning preferentially points to the charging area; Take the path deviation, heading deviation, ocean current data, environmental data, battery data and the global optimal path as the input of the path tracking model to obtain the control parameters of the unmanned ship thruster; perform real-time adjustment according to the control parameters of the unmanned ship thruster to achieve path tracking control.

10. The unmanned ship adaptive path tracking control method according to claim 1, characterized in that, The method for achieving path tracking control includes: According to the position data of the unmanned ship, calculate the difference between the actual position and the nearest point on the preset path to obtain the path deviation; calculate the difference between the current heading and the preset heading to obtain the heading deviation; Take the path deviation, heading deviation, ocean current data, environmental data, battery data and the global optimal path as the input of the path tracking model to obtain the control parameters of the unmanned ship thruster; perform real-time adjustment according to the control parameters of the unmanned ship thruster to achieve path tracking control.

11. An adaptive path tracking control device for an unmanned ship, which implements the adaptive path tracking control method for an unmanned ship according to any one of claims 1-10, characterized in that, It includes: Boundary judgment module: Collect the position data of the unmanned ship, and judge whether the unmanned ship exceeds the preset boundary based on the boundary judgment algorithm according to the position data of the unmanned ship. If it exceeds, continue to the next step, otherwise continue to judge; Path planning module: Collect and analyze the ocean current data, environmental data and unmanned ship data corresponding to the position data to obtain the predicted drift trajectory of the unmanned ship; collect and analyze the radiation data corresponding to the position data to obtain the charging area; collect and analyze the battery data to obtain the predicted remaining endurance time; Construct a path planning target based on the predicted drift trajectory, charging area and predicted remaining endurance time, and use the path planning algorithm to perform dynamic path search to obtain the global optimal path; Adaptive loss reduction module: Preset multiple levels of power thresholds, and start the corresponding loss reduction strategy when the current remaining battery power in the battery data is lower than different thresholds; Path tracking module: Calculate the path deviation and heading deviation according to the position data and the global optimal path, take the path deviation, heading deviation, ocean current data, environmental data, battery data and the global optimal path as the input of the path tracking model to obtain the control parameters of the unmanned ship thruster; perform real-time adjustment according to the control parameters of the unmanned ship thruster to achieve path tracking control.

Images