An unmanned ship dynamic obstacle avoidance system and method, and a storage medium

Abstract

The application relates to the technical field of unmanned ship dynamic obstacle avoidance, in particular to an unmanned ship dynamic obstacle avoidance system and method and a storage medium; the system comprises a dynamic obstacle avoidance early warning platform, a database, an obstacle avoidance planning unit, an obstacle division unit, a deviation obstacle avoidance interference unit, a dynamic obstacle avoidance unit and a driving management unit; the application carries out preliminary safety evaluation analysis from the perspective of optimal planning of an obstacle avoidance route, so as to reasonably select an optimal driving path, carries out obstacle identification, division, management analysis on obstacles on the optimal driving path through an information feedback mode, helps to improve the driving safety of the target unmanned ship, further discriminates the collision risk of the target unmanned ship according to actual driving environment information, so as to reasonably make obstacle avoidance operation, and analyzes whether the target obstacle and the target unmanned ship will collide from the perspective of driving interaction prediction, so as to realize the effect of efficient and safe obstacle avoidance through small changes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned ship dynamic obstacle avoidance, and particularly relates to an unmanned ship dynamic obstacle avoidance system and method and a storage medium. BACKGROUND

[0002] An unmanned ship is a small offshore platform with environmental perception, autonomous navigation capability and the ability to autonomously complete corresponding tasks, and is widely used in offshore scientific investigation, offshore search and rescue and offshore energy exploration in recent years. Because the task environment of the unmanned ship is very complex, it not only contains static obstacles, but also is affected by sea waves, currents and other dynamic obstacles. Therefore, collision avoidance is a key technical factor affecting the autonomous navigation of the unmanned ship.

[0003] The autonomous obstacle avoidance function is a prerequisite for ensuring the smooth completion of the task of the unmanned ship. The obstacle avoidance of the unmanned ship is mainly aimed at static and dynamic obstacles in the surrounding environment during navigation, and the planned route can be continued after the obstacle avoidance is completed. However, in the existing obstacle avoidance technology, it is impossible to reasonably distinguish and manage static or dynamic obstacles in the driving path, and the actual environmental parameters are not considered in the obstacle avoidance planning during the obstacle avoidance process, thereby increasing the collision risk of the unmanned ship. Moreover, the rationality of the obstacle avoidance route cannot be analyzed, thereby reducing the obstacle avoidance management efficiency of the unmanned ship.

[0004] In view of the above technical defects, a solution is proposed. SUMMARY

[0005] The present application aims to provide an unmanned ship dynamic obstacle avoidance system and method and a storage medium to solve the above technical defects. The present application performs preliminary safety evaluation and analysis from the perspective of optimal planning of the obstacle avoidance route, so as to reasonably analyze the safety of the planned driving route autonomously generated by the target unmanned ship, to reasonably select the best driving path, and to perform obstacle identification, division, management and analysis of the obstacles on the best driving path through information feedback, which helps to improve the driving safety of the target unmanned ship. Further, the actual driving environment information is analyzed for driving deviation interference supervision, so as to determine the collision risk of the target unmanned ship according to the actual driving environment information, to reasonably make obstacle avoidance operation, and to analyze whether the target obstacle and the target unmanned ship will collide from the perspective of driving interaction prediction, so as to perform route optimal matching analysis on the target unmanned ship with collision risk, to achieve efficient and safe obstacle avoidance through small changes, and to help improve the driving safety and obstacle avoidance management efficiency of the target unmanned ship.

[0006] The application can be achieved by the following technical scheme: an unmanned ship dynamic obstacle avoidance system, comprising a dynamic obstacle avoidance early warning platform, a database, an obstacle avoidance planning unit, an obstacle division unit, a deviation obstacle avoidance interference unit, a dynamic obstacle avoidance unit and a driving management unit;

[0007] The dynamic obstacle avoidance early warning platform retrieves the obstacle avoidance planning information of the target unmanned ship from the database and sends it to the obstacle avoidance planning unit.

[0008] The obstacle avoidance planning unit is used for optimal route selection and planning analysis of the received obstacle avoidance planning information, and the minimum value in the product value obtained by multiplying the obstacle avoidance times and the corresponding driving time of the planning driving route under the specified driving speed is set as the optimal driving path.

[0009] The obstacle division unit retrieves the optimal driving path and performs obstacle identification and division management analysis, compares the coordinates of the target obstacle and the marked obstacle, and obtains a marked planning signal or a dynamic obstacle avoidance signal.

[0010] The deviation obstacle avoidance interference unit is used to respond to the marked planning signal, collect the actual driving environment information of the target unmanned ship, and perform driving deviation interference supervision analysis on the actual driving environment information to obtain a safety signal or a control signal.

[0011] The dynamic obstacle avoidance unit is used to respond to the dynamic obstacle avoidance signal, collect the advance information of the target obstacle, and perform collision risk discrimination feedback analysis on the advance information to obtain a pass signal or a collision avoidance signal.

[0012] When the collision avoidance signal or the control signal is generated, route optimal matching analysis is performed, the minimum value of the obstacle avoidance recommendation evaluation coefficient T corresponding to the avoidance route is set as the optimal obstacle avoidance route and sent to the driving management unit.

[0013] Preferably, the obstacle avoidance planning unit has the following optimal route selection and planning analysis process:

[0014] The planning information, basic driving information of the target unmanned ship are obtained, the planning information includes the starting point coordinate and the ending point coordinate, a plurality of planning driving routes generated by the target unmanned ship from the starting point coordinate to the ending point coordinate are obtained, and the obstacle avoidance planning information of each planning driving route is obtained, the obstacle avoidance planning information includes the obstacle avoidance times of the planning driving route and the corresponding driving time of the planning driving route under the specified driving speed.

[0015] The minimum value in the product value obtained by multiplying the obstacle avoidance times and the corresponding driving time of the planning driving route under the specified driving speed is set as the optimal driving path.

[0016] Preferably, the obstacle identification and division management analysis process of the obstacle division unit is as follows:

[0017] The area surrounded by the circle drawn around the center of gravity of the target unmanned ship with R1 as the radius is set as the early warning area; when the target unmanned ship travels, the obstacles in the early warning area are monitored by the monitoring means, the monitored obstacles are set as target obstacles, and the obstacles in the best travel path of the target unmanned ship are set as marked obstacles; the target obstacles and the marked obstacles are compared and analyzed in coordinates to generate a marked planning signal or a dynamic obstacle avoidance signal.

[0018] Preferably, the travel deviation interference monitoring and analysis process of the deviation obstacle interference unit is as follows:

[0019] The minimum straight line distance between the marked obstacles and the target unmanned ship when the target unmanned ship travels on the best travel path is obtained; the actual travel environment information of the target unmanned ship is obtained, including the wind speed interference index and the water flow interference index;

[0020] The product value obtained by multiplying the corresponding values of the wind speed interference index and the water flow interference index is set as the actual yaw swing value, the set yaw swing value imported when the target unmanned ship is generated on the best travel path is obtained, and the actual yaw swing value and the set yaw swing value are compared and analyzed to generate a feedback signal.

[0021] Preferably, when the feedback signal is generated: the yaw swing value is compared and analyzed with the preset yaw swing value interval, and then the preset yaw swing value interval corresponding to the yaw swing value is obtained, and the unmanned ship yaw risk range value set by the preset yaw swing value interval corresponding to the yaw swing value is obtained;

[0022] When the target unmanned ship is in the state of the maximum value of the unmanned ship yaw risk range value, the minimum straight line distance between the marked obstacles and the target unmanned ship is obtained, and the minimum straight line distance is set as the collision risk peak value; the value obtained by subtracting the collision risk peak value from the minimum straight line distance between the marked obstacles and the target unmanned ship when the target unmanned ship travels on the best travel path is set as the emergency distance, and the emergency distance is judged: a safety signal is generated or a control signal is generated;

[0023] The wind speed interference index represents the maximum instantaneous wind speed in the travel environment of the target unmanned ship; and the water flow interference index represents the mean amplitude of the water flow in the travel environment of the target unmanned ship.

[0024] Preferably, the collision risk judgment feedback analysis process of the dynamic obstacle avoidance unit is as follows:

[0025] The advancing information of the target obstacle and the basic driving information of the target unmanned ship are acquired, and then the intersection point of the advancing route of the target obstacle and the remaining optimal driving path of the target unmanned ship is acquired;

[0026] The predicted time length of the target obstacle to the intersection point is acquired, and the predicted time length of the target unmanned ship to the intersection point is acquired, the difference between the predicted time length of the target obstacle to the intersection point and the predicted time length of the target unmanned ship to the intersection point is acquired, and the difference is set as the interactive collision time length;

[0027] The interactive collision time length is compared and analyzed with the preset interactive collision time length threshold value recorded and stored in the inside, and a pass signal or a collision avoidance signal is generated.

[0028] Preferably, when the collision avoidance signal or the control signal is generated:

[0029] A plurality of avoidance routes autonomously generated by the target unmanned ship are acquired, and the basic route information of each avoidance route is acquired, the basic route information including an energy consumption value, a turning angle and a region evaluation value, the energy consumption value, the turning angle and the region evaluation value are respectively labeled as NH, ZJ and QP, and the energy consumption value NH, the turning angle ZJ and the region evaluation value QP are substituted into a formula to obtain an obstacle avoidance recommendation evaluation coefficient T;

[0030] The minimum value of the obstacle avoidance recommendation evaluation coefficient T is acquired, and the avoidance route corresponding to the minimum value of the obstacle avoidance recommendation evaluation coefficient T is set as the optimal obstacle avoidance route;

[0031] The region evaluation value represents the area size of the region surrounded by the avoidance route and the optimal driving path.

[0032] The beneficial effects of the present application are as follows:

[0033] The present application preliminarily evaluates and analyzes from the perspective of optimal planning of obstacle avoidance route, so as to reasonably analyze the safety of the planning driving route autonomously generated by the target unmanned ship, so as to reasonably select the optimal driving path, and the obstacles on the optimal driving path are identified, classified, managed and analyzed through the information feedback mode, which is helpful for distinguishing the types of obstacles and improving the driving safety of the target unmanned ship;

[0034] The application further analyzes the actual driving environment information for driving deviation interference supervision, so as to understand the deviation between the actual driving environment information of the target unmanned ship and the set value when the optimal driving path is generated, so as to determine the collision risk of the target unmanned ship according to the actual driving environment information, so as to reasonably make obstacle avoidance operation, and analyze whether the target obstacle and the target unmanned ship will collide from the driving interaction prediction angle, so as to perform route optimization matching analysis on the target unmanned ship with collision risk, so as to realize efficient and safe obstacle avoidance through small changes, and help to improve the driving safety and obstacle avoidance management efficiency of the target unmanned ship. BRIEF DESCRIPTION OF DRAWINGS

[0035] The application will be further described below with reference to the drawings;

[0036] Fig. 1 is a system flow block diagram of the application;

[0037] Fig. 2 is a method reference diagram of the application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application. EMBODIMENT

[0039] Please refer to Figs. 1-2 As shown in the figure, the application is an unmanned ship dynamic obstacle avoidance system, which comprises a dynamic obstacle avoidance early warning platform, a database, an obstacle avoidance planning unit, an obstacle division unit, a deviation obstacle avoidance interference unit, a dynamic obstacle avoidance unit and a driving management unit. The database is in one-way communication connection with the dynamic obstacle avoidance early warning platform. The dynamic obstacle avoidance early warning platform is in two-way communication connection with the obstacle avoidance planning unit. The dynamic obstacle avoidance early warning platform is in one-way communication connection with the obstacle division unit. The obstacle division unit is in one-way communication connection with the deviation obstacle avoidance interference unit and the dynamic obstacle avoidance unit. The deviation obstacle avoidance interference unit and the dynamic obstacle avoidance unit are in one-way communication connection with the driving management unit.

[0040] The dynamic obstacle avoidance early warning platform retrieves the obstacle avoidance planning information of the target unmanned ship from the database and sends it to the obstacle avoidance planning unit.

[0041] The obstacle avoidance planning unit is used for obstacle avoidance route optimization planning analysis on the received obstacle avoidance planning information, so as to reasonably analyze the rationality and safety of the planning driving route autonomously generated by the target unmanned ship, so as to reasonably select the optimal driving path. The specific obstacle avoidance route optimization planning analysis process is as follows:

[0042] The planning information, basic driving information, etc. of the target unmanned ship are acquired, the planning information includes the start point position coordinates and the end point position coordinates, a plurality of planning driving routes autonomously generated by the target unmanned ship from the start point position coordinates to the end point position coordinates are acquired, and the obstacle avoidance planning information of each planning driving route is acquired, the obstacle avoidance planning information includes the obstacle avoidance times of the planning driving route and the driving time length corresponding to the planning driving route under the specified driving speed;

[0043] In the embodiment of the application, the basic driving information includes driving speed, acceleration, etc.

[0044] The best driving path is obtained based on the quantitative analysis of the obstacle avoidance times and the driving time length corresponding to the planning driving route under the specified driving speed, and the best driving path is sent to the dynamic obstacle avoidance warning platform.

[0045] In the embodiment of the application, the quantitative analysis process of the obstacle avoidance times and the driving time length corresponding to the planning driving route under the specified driving speed is as follows:

[0046] The planning driving route corresponding to the minimum value in the product value obtained by multiplying the values corresponding to the obstacle avoidance times and the driving time length corresponding to the planning driving route under the specified driving speed is set as the best driving path.

[0047] The obstacle division unit calls the monitoring best driving path and performs obstacle identification division management analysis, which is helpful for distinguishing the types of obstacles and improving the driving safety of the target unmanned ship, and the specific obstacle identification division management analysis process is as follows:

[0048] Taking the center of gravity of the target unmanned ship as the center and R1 as the radius, the area surrounded by the circle drawn around the center of gravity of the target unmanned ship is set as the warning area.

[0049] When the target unmanned ship drives through the monitoring means to perform obstacle warning on the warning area, the monitored obstacle is set as the target obstacle, and the obstacle in the best driving path of the target unmanned ship is set as the marked obstacle.

[0050] In the embodiment of the application, the monitoring means includes a millimeter wave radar, satellite positioning, etc.

[0051] The target obstacle and the marked obstacle are compared and analyzed in coordinates:

[0052] If the corresponding coordinates of the target obstacle and the marked obstacle are one-to-one, a marked planning signal is generated.

[0053] If the corresponding coordinates of the target obstacle and the marked obstacle are not one-to-one, a dynamic obstacle avoidance signal is generated. Embodiment

[0054] When the marking planning signal is generated, the deviation obstacle avoidance interference unit is used to respond to the marking planning signal, collect the actual running environment information of the target unmanned ship, and perform running deviation interference supervision analysis on the actual running environment information to understand the deviation between the actual running environment information of the target unmanned ship and the set value when the best running path is generated, so as to judge the collision risk of the target unmanned ship according to the actual running environment information, so as to reasonably make obstacle avoidance operation. The specific running deviation interference supervision analysis process is as follows:

[0055] The minimum straight line distance between the target unmanned ship and the marked obstacle when the target unmanned ship runs on the best running path is obtained;

[0056] The actual running environment information of the target unmanned ship is obtained, and the actual running environment information includes the wind speed interference index and the water flow interference index;

[0057] The product value obtained by multiplying the corresponding values of the wind speed interference index and the water flow interference index is set as the actual yaw swing value, the set yaw swing value imported when the best running path of the target unmanned ship is generated is obtained, and the actual yaw swing value and the set yaw swing value are compared and analyzed:

[0058] If the actual yaw swing value is less than or equal to the set yaw swing value, no signal is generated;

[0059] If the actual yaw swing value is greater than the set yaw swing value, a feedback signal is generated, and when the feedback signal is generated, the yaw swing value is compared and analyzed with the preset yaw swing value interval, and then the preset yaw swing value interval corresponding to the yaw swing value is obtained. The unmanned ship yaw risk range value set by the preset yaw swing value interval corresponding to the yaw swing value is obtained;

[0060] When the target unmanned ship is in the state of the maximum value of the unmanned ship yaw risk range value, the minimum straight line distance between the target unmanned ship and the marked obstacle is set as the collision risk peak value, and the value obtained by subtracting the collision risk peak value from the minimum straight line distance between the target unmanned ship and the marked obstacle when the target unmanned ship runs on the best running path is set as the emergency distance, and the emergency distance is judged:

[0061] If the emergency distance is greater than the preset emergency distance threshold, a safety signal is generated, and the safety signal is sent to the running management unit. After receiving the safety signal, the running management unit immediately makes the preset warning operation corresponding to the safety signal, that is, the preset warning operation corresponding to the safety signal is to continue to advance according to the set best running path;

[0062] If the emergency distance is less than or equal to the preset emergency distance threshold, a control signal is generated;

[0063] In the embodiment of the present application, the wind speed interference index represents the maximum value of the instantaneous wind speed in the target unmanned ship running environment.

[0064] In the embodiment of the present application, the water flow interference index represents the mean value of the wave amplitude of the water flow in the target unmanned ship running environment, and the greater the water flow interference index, the greater the swing of the target unmanned ship, which leads to more intense swing of the target unmanned ship, greater risk of deviation, and smaller minimum straight-line distance between the marked obstacle and the target unmanned ship. Embodiment

[0065] When the dynamic obstacle avoidance signal is generated, the dynamic obstacle avoidance unit is used to respond to the dynamic obstacle avoidance signal, collect the advance information of the target obstacle, and perform collision risk judgment feedback analysis on the advance information to determine whether the target obstacle and the target unmanned ship will collide, so as to perform a reasonable obstacle avoidance control analysis process under the condition of collision risk. The specific collision risk judgment feedback analysis process is as follows:

[0066] The advance information of the target obstacle and the basic running information of the target unmanned ship are obtained, and then the intersection point of the advance route of the target obstacle and the remaining optimal running path of the target unmanned ship is obtained.

[0067] The predicted time length of the target obstacle to the intersection point is obtained, and the predicted time length of the target unmanned ship to the intersection point is also obtained. The difference between the predicted time length of the target obstacle to the intersection point and the predicted time length of the target unmanned ship to the intersection point is obtained, and the difference between the predicted time length of the target obstacle to the intersection point and the predicted time length of the target unmanned ship to the intersection point is set as the interactive collision time length.

[0068] The interactive collision time length is compared and analyzed with the preset interactive collision time length threshold value recorded and stored in it:

[0069] If the interactive collision time length is greater than or equal to the preset interactive collision time length threshold value, a pass signal is generated.

[0070] If the interactive collision time length is less than the preset interactive collision time length threshold value, a collision avoidance signal is generated.

[0071] In the embodiment of the present application, the advance information includes advance speed, advance route, etc.

[0072] When the collision avoidance signal or the control signal is generated:

[0073] The target unmanned ship autonomously generates multiple avoidance routes, and basic route information of each avoidance route is obtained, including energy consumption value, turning angle and area evaluation value, and the energy consumption value, turning angle and area evaluation value are respectively labeled as NH, ZJ and QP, and the energy consumption value NH, turning angle ZJ and area evaluation value QP are substituted into the formula T=(NH*a1+ZJ*a2+QP*a3)*a4 to obtain an obstacle avoidance recommendation evaluation coefficient, wherein a1, a2 and a3 are respectively preset weight factor coefficients of the energy consumption value, the turning angle and the area evaluation value, a4 is a preset error correction factor, a1, a2, a3 and a4 are all greater than zero, and T is the obstacle avoidance recommendation evaluation coefficient.

[0074] The minimum value of the obstacle avoidance recommendation evaluation coefficient T is obtained, and the avoidance route corresponding to the minimum value of the obstacle avoidance recommendation evaluation coefficient T is set as the optimal obstacle avoidance route, and the optimal obstacle avoidance route is sent to the driving management unit, and the driving management unit drives according to the optimal obstacle avoidance route after receiving the optimal obstacle avoidance route, which helps to achieve efficient and safe obstacle avoidance with small changes, and helps to improve the driving safety and obstacle avoidance management efficiency of the target unmanned ship.

[0075] In the embodiment of the application, the area evaluation value represents the area size of the area surrounded by the avoidance route and the optimal driving path, and it should be noted that the smaller the area evaluation value, the smaller the yaw change of the target unmanned ship under the premise of obstacle avoidance safety, and the faster the recovery of navigation. Embodiment

[0076] An unmanned ship dynamic obstacle avoidance method, comprising the following steps:

[0077] Step one: collect obstacle avoidance planning information for optimal planning analysis of obstacle avoidance route, and set the planning driving route corresponding to the minimum value of the product of the avoidance times and the driving time corresponding to the driving speed as the optimal driving path;

[0078] Step two: obstacle identification and division management analysis based on the optimal driving path, coordinate comparison of the target obstacle and the marked obstacle, if the marked planning signal is obtained, step three is entered, if the dynamic obstacle avoidance signal is obtained, step four is entered:

[0079] Step three: driving yaw disturbance supervision analysis based on actual driving environment information under information feedback, judge the collision risk of the target unmanned ship, and judge the obtained emergency response distance, if the safety signal is obtained, output feedback, if the control signal is obtained, step five is entered;

[0080] Step four: collision risk discrimination feedback analysis is carried out through information feedback to determine whether the target obstacle and the target unmanned ship will collide, and the obtained interactive collision time is compared and analyzed, if the pass signal is obtained, the feedback is output, and if the collision avoidance signal is obtained, step five is entered;

[0081] Step five: the optimal obstacle avoidance route is set as the optimal obstacle avoidance route by layer-by-layer progressive route optimization matching analysis of the minimum value of the obtained obstacle avoidance recommendation evaluation coefficient T, and the optimal obstacle avoidance route is output feedback;

[0082] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method described above;

[0083] In summary, the application preliminarily evaluates and analyzes from the perspective of optimal obstacle avoidance route planning, so as to reasonably analyze the safety of the planning driving route generated by the target unmanned ship, so as to reasonably select the best driving path, and the obstacles on the best driving path are identified, classified and managed by information feedback, which helps to distinguish the types of obstacles and improve the driving safety of the target unmanned ship. Further, the actual driving environment information is analyzed for drift interference supervision, so as to understand the deviation between the actual driving environment information of the target unmanned ship and the set value when the best driving path is generated, so as to reasonably determine the collision risk of the target unmanned ship according to the actual driving environment information, so as to reasonably make obstacle avoidance operation, and analyze whether the target obstacle and the target unmanned ship will collide from the perspective of driving interaction prediction, so as to analyze the optimal route matching of the target unmanned ship with collision risk, so as to realize efficient and safe obstacle avoidance through small changes, and improve the driving safety and obstacle management efficiency of the target unmanned ship.

[0084] The size of the threshold is set for comparison, and the size of the threshold depends on the amount of sample data and the base number set by the person skilled in the art for each group of sample data; as long as it does not affect the proportional relationship between the parameters and the quantized values.

[0085] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value, and the coefficients in the formula are set by the person skilled in the art according to the actual situation. The above is only a preferred specific embodiment of the application, but the protection scope of the application is not limited thereto. Any person skilled in the art can make equivalent replacement or change according to the technical solution and the inventive concept of the application within the technical range disclosed by the application, which should be covered within the protection scope of the application.

Claims

1. A dynamic obstacle avoidance system for unmanned surface vessels, characterized in that, It includes a dynamic obstacle avoidance early warning platform, a database, an obstacle avoidance planning unit, an obstacle classification unit, a deviation obstacle avoidance interference unit, a dynamic obstacle avoidance unit, and a driving management unit; The dynamic obstacle avoidance early warning platform retrieves the obstacle avoidance planning information of the target unmanned surface vessel from the database and sends it to the obstacle avoidance planning unit; The obstacle avoidance planning unit is used to perform obstacle avoidance route optimization analysis on the received obstacle avoidance planning information. The minimum value of the product obtained by multiplying the number of obstacle avoidances and the corresponding travel time of the planned travel route at the specified travel speed is set as the optimal travel route. The obstacle classification unit retrieves the best driving path from the monitoring system and performs obstacle identification, classification, management, and analysis. It then compares the coordinates of the target obstacles with those of the marked obstacles to obtain marking planning signals or dynamic obstacle avoidance signals. The deviation obstacle avoidance interference unit is used to respond to the marker planning signal, collect the actual driving environment information of the target unmanned surface vessel, and perform driving yaw interference monitoring and analysis on the actual driving environment information to obtain safety signals or control signals; The dynamic obstacle avoidance unit is used to respond to dynamic obstacle avoidance signals, collect the forward information of the target obstacle, and perform collision risk judgment feedback analysis on the forward information to obtain a pass signal or a collision avoidance signal. When a collision avoidance signal or control signal is generated, a route selection matching analysis is performed. The avoidance route corresponding to the minimum value of the obstacle avoidance recommendation evaluation coefficient T is set as the optimal obstacle avoidance route and sent to the driving management unit. The obstacle avoidance planning unit's optimal obstacle avoidance route planning analysis process is as follows: The system obtains the planning information and basic driving information of the target unmanned surface vessel (USV). The planning information includes the coordinates of the starting point and the ending point. The system obtains multiple planned driving routes that the USV autonomously generates from the starting point to the ending point. The system obtains the obstacle avoidance planning information for each planned driving route. The obstacle avoidance planning information includes the number of obstacle avoidances for the planned driving route and the driving time corresponding to the planned driving route at the specified driving speed. The minimum value of the product of the number of obstacle avoidance attempts and the driving time corresponding to the planned driving route at the specified driving speed is set as the optimal driving route. The obstacle identification, classification, management, and analysis process of the obstacle classification unit is as follows: Using the center of gravity of the target unmanned surface vessel (USV) as the center and R1 as the radius, the area enclosed by a circle drawn around the center of gravity of the USV is set as the warning zone. When the USV issues an obstacle warning in the warning zone through monitoring during its operation, the detected obstacle is set as the target obstacle, and the obstacle in the USV's optimal travel path is set as the marked obstacle. The coordinates of the target obstacle and the marked obstacle are compared and analyzed to generate a marking planning signal or a dynamic obstacle avoidance signal. The monitoring and analysis process of the driving yaw interference of the deviation obstacle avoidance interference unit is as follows: The minimum straight-line distance between the target unmanned surface vessel (USV) and the marked obstacle is obtained when the USV travels along the optimal driving path; the actual driving environment information of the USV is obtained, including wind speed interference index and water flow interference index. The product of the corresponding values ​​of wind speed interference index and water flow interference index is set as the actual yaw swing value. The set yaw swing value imported when the target unmanned surface vessel generates the optimal driving path is obtained. The actual yaw swing value is compared and analyzed with the set yaw swing value to generate a feedback signal. When a feedback signal is generated: the yaw swing value is compared and analyzed with the preset yaw swing value range, and then the preset yaw swing value range corresponding to the yaw swing value is obtained, and the yaw risk range value of the unmanned surface vessel is set by the preset yaw swing value range corresponding to the yaw swing value. When the target unmanned surface vessel (USV) is in the state where the maximum value of the USV yaw risk range is located, the minimum straight-line distance between the obstacle and the target USV is marked and set as the collision risk peak value. The value obtained by subtracting the collision risk peak value from the minimum straight-line distance between the marked obstacle and the target USV when the target USV is traveling on the optimal driving path is set as the emergency response distance. The emergency response distance is then processed to generate a safety signal or a control signal. The wind speed interference index represents the maximum instantaneous wind speed in the environment in which the target unmanned surface vessel is operating; the water flow interference index represents the average amplitude of the water flow in the environment in which the target unmanned surface vessel is operating.

2. The unmanned surface vessel dynamic obstacle avoidance system according to claim 1, characterized in that, The collision risk judgment and feedback analysis process of the dynamic obstacle avoidance unit is as follows: The system obtains the forward movement information of the target obstacle and the basic driving information of the target unmanned surface vessel, and then obtains the intersection point of the forward movement route of the target obstacle and the remaining optimal driving path of the target unmanned surface vessel. The predicted time from the target obstacle to the intersection point is obtained, as is the predicted time from the target unmanned surface vessel to the intersection point. The difference between the predicted time from the target obstacle to the intersection point and the predicted time from the target unmanned surface vessel to the intersection point is obtained and set as the interaction collision time. The interaction collision duration is compared and analyzed with the preset interaction collision duration threshold recorded and stored internally, and a pass signal or a collision avoidance signal is generated.

3. The unmanned surface vessel dynamic obstacle avoidance system according to claim 2, characterized in that, When a collision avoidance signal or control signal is generated: Multiple obstacle avoidance routes autonomously generated by the target unmanned surface vessel are obtained, and the basic route information of each obstacle avoidance route is obtained. The basic route information includes energy consumption value, turning angle and area assessment value. The energy consumption value, turning angle and area assessment value are labeled as NH, ZJ and QP respectively. The energy consumption value NH, turning angle ZJ and area assessment value QP are substituted into the formula to obtain the obstacle avoidance recommendation assessment coefficient T. The minimum value of the obstacle avoidance recommendation evaluation coefficient T is obtained, and the corresponding avoidance route is set as the optimal obstacle avoidance route; the area evaluation value represents the size of the area enclosed by the avoidance route and the optimal driving path.

4. A dynamic obstacle avoidance method for unmanned surface vessels (USVs), wherein the method is applied to the dynamic obstacle avoidance system for USVs as described in claim 3, characterized in that, Includes the following steps: Step 1: Collect obstacle avoidance planning information and conduct obstacle avoidance route optimization analysis. The minimum value of the product obtained by multiplying the number of obstacle avoidance attempts and the corresponding travel time of the planned travel route at the specified travel speed is set as the optimal travel route. Step Two: Obstacle identification, classification, and management analysis based on the optimal driving path. Compare the coordinates of the target obstacle with the marked obstacle. If a marking planning signal is obtained, proceed to Step Three; if a dynamic obstacle avoidance signal is obtained, proceed to Step Four. Step 3: Based on the actual driving environment information under the feedback, conduct driving yaw interference monitoring and analysis, determine the collision risk of the target unmanned surface vessel, process the obtained emergency response distance, output feedback if a safety signal is obtained, and proceed to step 5 if a control signal is obtained. Step 4: Conduct collision risk assessment and feedback analysis through information feedback to determine whether the target obstacle and the target unmanned vessel will collide. Compare and analyze the obtained interaction collision duration. If a pass signal is obtained, output feedback. If a collision avoidance signal is obtained, proceed to step 5. Step 5: Perform route selection and matching analysis in a progressive manner, set the obstacle avoidance route corresponding to the minimum value of the obtained obstacle avoidance recommendation evaluation coefficient T as the optimal obstacle avoidance route, and output the optimal obstacle avoidance route as feedback.

5. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method as described in claim 4.

Images