Modular unmanned ship control method and system for urban culvert detection

Abstract

The application provides a modular unmanned ship control method and system for urban culvert detection. The method comprises the following steps: acquiring characteristic parameters of a preset culvert, kinematic parameters of a target unmanned ship and detection task requirements, acquiring optimization target parameters, optimizing path planning of the target unmanned ship, monitoring operation state of the target unmanned ship in real time and judging whether there is an obstacle, if there is an obstacle, acquiring state parameters of the obstacle, judging the category of the obstacle and evaluating collision risk, and formulating a corresponding obstacle avoidance strategy according to the collision risk coefficient, so as to realize the technology of modular unmanned ship control for urban culvert detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of culvert detection, in particular to a modular unmanned ship control method and system for urban culvert detection. BACKGROUND

[0002] As an important underground drainage and transportation facility, the structural integrity and operating state of urban culverts are directly related to the normal operation of the city. At present, the detection of urban culverts is mostly carried out by manual inspection or traditional unmanned equipment detection. Manual inspection has the problems of low efficiency, high cost, high risk, etc., and it is difficult to cover comprehensively in complex culvert environments. Traditional unmanned equipment has deficiencies in adaptability of path planning and flexibility of obstacle handling, and it is difficult to meet the high-precision detection requirements in complex culvert environments.

[0003] The modular unmanned ship has broad application prospects in culvert detection due to its flexible configuration of modules according to detection tasks. However, the existing control method of modular unmanned ships lacks pertinence in path optimization and real-time obstacle avoidance, leading to problems such as unreasonable path and untimely obstacle avoidance during detection, affecting detection efficiency and safety.

[0004] In view of the above problems, there is an urgent need for effective technical solutions. SUMMARY

[0005] The purpose of the present application is to provide a modular unmanned ship control method and system for urban culvert detection, which can obtain the characteristic parameters of the preset culvert, the kinematic parameters of the target unmanned ship and the detection task requirements, obtain the optimization target parameters, optimize the path planning of the target unmanned ship, monitor the operation state of the target unmanned ship in real time and determine whether there are obstacles, if there are obstacles, obtain the state parameters of the obstacles, determine the type of the obstacles and evaluate the collision risk, and formulate the corresponding obstacle avoidance strategy according to the collision risk coefficient, thereby realizing the control technology of the modular unmanned ship for urban culvert detection.

[0006] The present application also provides a modular unmanned ship control method for urban culvert detection, comprising the following steps:

[0007] Obtaining the characteristic parameters of the preset culvert, the kinematic parameters of the target unmanned ship and the detection task requirements;

[0008] Obtaining the optimization target parameters and optimizing the path planning of the target unmanned ship;

[0009] Monitoring the operation state of the target unmanned ship in real time and determining whether there are obstacles;

[0010] If there are obstacles, obtaining the state parameters of the obstacles, determining the type of the obstacles and evaluating the collision risk;

[0011] According to the collision risk coefficient, a corresponding obstacle avoidance strategy is formulated.

[0012] Optionally, in the modular unmanned ship control method for urban culvert detection provided in the application, the characteristic parameters of the preset culvert, the kinematic parameters of the target unmanned ship, and the detection task requirements are obtained, including:

[0013] The characteristic parameters of the preset culvert include the length of the culvert, the number of detection points, the cross-sectional size, and the turning radius.

[0014] The kinematic parameters of the target unmanned ship include the minimum turning radius and the maximum speed.

[0015] The detection task requirements include the range of detection points to be covered and the detection accuracy.

[0016] Optionally, in the modular unmanned ship control method for urban culvert detection provided in the application, the optimization target parameters are obtained, and the path planning of the target unmanned ship is optimized, including:

[0017] According to the characteristic parameters of the culvert, the kinematic parameters of the target unmanned ship, and the detection task requirements, a plurality of single targets are extracted, including the shortest path length, the minimum curvature change, and the highest detection coverage.

[0018] The shortest path length, the minimum curvature change, and the highest detection coverage are weighted to obtain the optimization target parameters.

[0019] According to the optimization target parameters, the path planning of the target unmanned ship is optimized by a preset optimization algorithm.

[0020] Optionally, in the modular unmanned ship control method for urban culvert detection provided in the application, the operation state of the target unmanned ship is monitored in real time and whether there is an obstacle is determined, including:

[0021] The operation state of the target unmanned ship is monitored in real time, and operation state data is extracted, including real-time position, real-time motion speed, remaining power, detection module state, and communication signal.

[0022] Whether there is an obstacle is determined according to the laser radar, the visual sensor, and the sonar.

[0023] If at least two of the laser radar, the visual sensor, and the sonar determine that there is an obstacle, it is determined that there is an obstacle.

[0024] Otherwise, it is determined that there is no obstacle.

[0025] Optionally, in the modular unmanned ship control method for urban culvert detection provided in the present application, if there is an obstacle, the state parameters of the obstacle are acquired, the category of the obstacle is determined, and the collision risk is evaluated, including:

[0026] If there is an obstacle, the state parameters of the obstacle are acquired, including the size of the obstacle, the distance from the target unmanned ship, and the movement speed of the obstacle;

[0027] The category of the obstacle is determined according to the movement speed of the obstacle, including a fixed obstacle and a moving obstacle;

[0028] According to the size of the obstacle, the distance from the target unmanned ship, and the movement speed of the obstacle, and in combination with the real-time movement speed of the target unmanned ship, a preset collision risk evaluation model is processed to obtain a collision risk coefficient.

[0029] Optionally, in the modular unmanned ship control method for urban culvert detection provided in the present application, the corresponding obstacle avoidance strategy is formulated according to the collision risk coefficient, including:

[0030] A set of preset obstacle avoidance condition thresholds is acquired, including an obstacle size threshold and a collision risk threshold;

[0031] According to the size of the obstacle and the collision risk coefficient, a threshold comparison is performed with two thresholds of the set of preset obstacle avoidance condition thresholds;

[0032] If the results of the two threshold comparisons are not both less than the corresponding thresholds of the set of preset obstacle avoidance condition thresholds, an obstacle avoidance mechanism needs to be executed;

[0033] Otherwise, the obstacle avoidance mechanism does not need to be executed, and the operation state of the target unmanned ship continues to be monitored.

[0034] In a second aspect, the present application provides a modular unmanned ship control system for urban culvert detection, which includes a memory and a processor, the memory includes a program of a modular unmanned ship control method for urban culvert detection, and the program of the modular unmanned ship control method for urban culvert detection is executed by the processor to realize the following steps:

[0035] The characteristic parameters of a preset culvert, the kinematic parameters of a target unmanned ship, and the detection task requirements are acquired;

[0036] Optimized target parameters are acquired, and the path planning of the target unmanned ship is optimized;

[0037] The operation state of the target unmanned ship is monitored in real time, and it is determined whether there is an obstacle;

[0038] If there is an obstacle, the state parameters of the obstacle are acquired, the category of the obstacle is determined, and the collision risk is evaluated;

[0039] According to the collision risk coefficient, a corresponding obstacle avoidance strategy is formulated.

[0040] Optionally, in the modular unmanned ship control system for urban culvert detection provided in the present application, the feature parameters of the preset culvert, the kinematic parameters of the target unmanned ship, and the detection task requirements are obtained, including:

[0041] The feature parameters of the preset culvert include the length of the culvert, the number of detection points, the cross-sectional size, and the turning radius.

[0042] The kinematic parameters of the target unmanned ship include the minimum turning radius and the maximum speed.

[0043] The detection task requirements include the range of detection points to be covered and the detection accuracy.

[0044] Optionally, in the modular unmanned ship control system for urban culvert detection provided in the present application, the optimization target parameters are obtained, and the path planning of the target unmanned ship is optimized, including:

[0045] According to the feature parameters of the culvert, the kinematic parameters of the target unmanned ship, and the detection task requirements, a plurality of single targets are extracted, including the shortest path length, the minimum curvature change, and the highest detection coverage rate.

[0046] The shortest path length, the minimum curvature change, and the highest detection coverage rate are weighted to obtain the optimization target parameters.

[0047] According to the optimization target parameters, the path planning of the target unmanned ship is optimized through a preset optimization algorithm.

[0048] Optionally, in the modular unmanned ship control system for urban culvert detection provided in the present application, the operation state of the target unmanned ship is monitored in real time and whether there is an obstacle is determined, including:

[0049] The operation state of the target unmanned ship is monitored in real time, and operation state data is extracted, including real-time position, real-time motion speed, remaining power, detection module state, and communication signal.

[0050] Whether there is an obstacle is determined according to the laser radar, the visual sensor, and the sonar.

[0051] If at least two of the laser radar, the visual sensor, and the sonar determine that there is an obstacle, it is determined that there is an obstacle.

[0052] Otherwise, it is determined that there is no obstacle.

[0053] From the above, the city culvert detection module unmanned ship control method and system provided by the application, by obtaining the characteristic parameters of the preset culvert, the kinematics parameters of the target unmanned ship and the detection task requirements, obtaining the optimization target parameters, optimizing the path planning of the target unmanned ship, real-time monitoring the operation state of the target unmanned ship and judging whether there is an obstacle, if there is an obstacle, obtaining the state parameters of the obstacle, judging the category of the obstacle and evaluating the collision risk, according to the collision risk coefficient, formulating the corresponding obstacle avoidance strategy, so as to realize the control of the city culvert detection module unmanned ship.

[0054] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, therefore should not be regarded as a limitation to the scope, for those skilled in the art, without paying creative labor, other related drawings can also be obtained according to these drawings.

[0056] Figure 1 The flow chart of the city culvert detection module unmanned ship control method provided by the embodiments of the present application;

[0057] Figure 2 The flow chart of the city culvert detection module unmanned ship control method provided by the embodiments of the present application;

[0058] Figure 3 The flow chart of the city culvert detection module unmanned ship control method provided by the embodiments of the present application;

[0059] Figure 4 The flow chart of the city culvert detection module unmanned ship control method provided by the embodiments of the present application; DETAILED DESCRIPTION

[0060] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0061] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0062] Please refer to Figure 1 , Figure 1 This is a flowchart of a modular unmanned surface vessel (USV) control method for urban culvert detection, as described in some embodiments of this application. This modular USV control method for urban culvert detection is used in terminal devices, such as computers and mobile terminals. The modular USV control method for urban culvert detection includes the following steps:

[0063] S11. Obtain the feature parameters of the preset culvert, the kinematic parameters of the target unmanned vessel, and the detection task requirements;

[0064] S12. Obtain the target parameters for optimization and optimize the path planning of the target unmanned vessel;

[0065] S13. Monitor the operational status of the target unmanned vessel in real time and determine whether there are obstacles;

[0066] S14. If there is an obstacle, obtain the state parameters of the obstacle, determine the category of the obstacle, and assess the collision risk.

[0067] S15. Formulate a corresponding obstacle avoidance strategy based on the collision risk coefficient.

[0068] It should be noted that the existing pipeline endoscopic detection equipment (pipeline periscope, pipeline detection robot) has some limitations in actual application, and the operation difficulty is significantly increased in the face of complex environments with long detection distance, large water storage capacity and fast flow rate. Therefore, in order to solve these problems, first, the characteristic parameters of the preset culvert, including the length of the culvert, the number of detection points, the cross-sectional size and the turning radius, the kinematic parameters of the target unmanned ship, including the minimum turning radius and the maximum speed, and the detection task requirements, including the range of detection points to be covered and the detection accuracy, are obtained; then, the target unmanned ship path planning is optimized, the operation state of the target unmanned ship is monitored in real time, and whether there is an obstacle is judged according to the laser radar, visual sensor and sonar, if there is an obstacle, the state parameters of the obstacle, including the size of the obstacle, the distance from the target unmanned ship and the movement speed of the obstacle, are obtained, the type of the obstacle is judged and the collision risk is evaluated, and the corresponding obstacle avoidance strategy is formulated according to the collision risk coefficient, so as to realize the technology of modular unmanned ship control for urban culvert detection.

[0069] According to the embodiment of the application, the characteristic parameters of the preset culvert, the kinematic parameters of the target unmanned ship and the detection task requirements are obtained, including:

[0070] The characteristic parameters of the preset culvert, including the length of the culvert, the number of detection points, the cross-sectional size and the turning radius, are obtained.

[0071] The kinematic parameters of the target unmanned ship, including the minimum turning radius and the maximum speed, are obtained.

[0072] The detection task requirements, including the range of detection points to be covered and the detection accuracy, are obtained.

[0073] It should be noted that before carrying out the culvert detection operation, three types of key parameters need to be collected systematically to ensure accurate task execution; first, the characteristic parameters of the preset culvert, which include the actual length of the culvert, directly determine the total mileage of the detection path; the number of detection points needs to be reasonably arranged in combination with the complexity of the culvert structure to ensure that key monitoring areas are covered; the cross-sectional size covers the height and width, which is the core basis for planning the unmanned ship navigation channel; if the culvert has a curve, the turning radius data will affect the development of the unmanned ship turning strategy; secondly, the kinematic parameters of the target unmanned ship are obtained, wherein the minimum turning radius determines whether the unmanned ship can smoothly pass through the curved part of the culvert and needs to be adapted to the culvert turning radius; the maximum speed is related to the detection efficiency and needs to be reasonably set on the premise of meeting the detection accuracy to avoid data collection distortion due to excessive speed; finally, the detection task requirements need to be clarified, the range of detection points to be covered needs to be accurate to specific coordinates or sections to ensure that there is no monitoring blind area; the detection accuracy specifies the error threshold of data collection, for example, the position measurement deviation should not exceed a certain value, which is an important standard for judging whether the detection result is qualified or not.

[0074] According to the embodiment of the present application, the obtaining of the optimization target parameter optimizes the path planning of the target unmanned ship, comprising:

[0075] According to the characteristic parameters of the hidden culvert, the kinematic parameters of the target unmanned ship and the detection task requirements, a plurality of single targets are extracted, including the shortest path length, the minimum curvature change and the highest detection coverage rate;

[0076] According to the shortest path length, the minimum curvature change and the highest detection coverage rate, a weighted processing is performed to obtain the optimization target parameter;

[0077] According to the optimization target parameter, a preset optimization algorithm is used to optimize the path planning of the target unmanned ship.

[0078] It should be noted that in the path planning of the unmanned ship culvert detection, a key single optimization target needs to be extracted based on various basic parameters. Specifically, the extraction of the shortest path length needs to comprehensively consider the culvert length, the number of detection points, and the maximum speed of the unmanned ship: the culvert length determines the overall framework of the path, the number of detection points affects the node distribution of the path, and the maximum speed sets an efficiency boundary for the path length. By reasonably connecting the detection points, the total distance is shortened under the premise of meeting the coverage demand, which can effectively improve the detection efficiency; the determination of the minimum curvature change is closely related to the turning radius of the culvert, the cross-sectional size of the culvert, and the minimum turning radius of the unmanned ship; the turning radius of the culvert directly limits the degree of bending of the path, the cross-sectional size determines the safety space when turning, and the minimum turning radius of the unmanned ship is the bottom line of its physical performance. The combination of the three can ensure smooth turning of the path and avoid unmanned ship out of control or collision with the inner wall of the culvert due to sudden change of curvature; the highest detection coverage rate needs to match the detection point range that needs to be covered and the detection accuracy requirement; the detection point range that needs to be covered determines the area that the path must reach, and the detection accuracy requirement specifies the upper limit of the error when the path passes through the detection point. By accurately planning the trajectory of the path passing through each detection point, it can be ensured that all key areas are effectively detected; next, the three targets are weighted to obtain the optimization target parameters, and the weight distribution needs to be adjusted according to the actual detection scene: if the culvert structure is complex and has many turns, the weight of the minimum curvature change can be increased to ensure safe navigation; if the detection task is urgent, the weight of the shortest path length can be increased; if the requirement for the integrity of the detection data is very high, the weight of the highest detection coverage rate needs to be increased accordingly; by scientifically distributing the weights, the optimization target parameters can comprehensively reflect the priority of various requirements; finally, the optimization target parameters are input into a preset optimization algorithm (such as genetic algorithm, A* algorithm, etc.) to optimize the path planning of the unmanned ship; the algorithm will iteratively search for the optimal path under the premise of meeting various constraint conditions according to the optimization target parameters; by simulating the navigation effect of different path schemes and comparing their performances in path length, curvature change, and detection coverage, the optimal path planning scheme that takes into account efficiency, safety, and detection quality is finally selected, providing accurate guidance for the culvert detection operation of the unmanned ship.

[0079] Please refer to Figure 2 , Figure 2 is a flowchart of a method for judging whether there is an obstacle in the control method of the modular unmanned ship for urban culvert detection in some embodiments of the present application. According to the embodiment of the present application, the real-time monitoring of the operation state of the target unmanned ship and the judgment of whether there is an obstacle include:

[0080] S21, real-time monitoring of the operation state of the target unmanned ship, and extracting operation state data including real-time position, real-time motion speed, remaining power, detection module state, and communication signal;

[0081] S22, judging whether there is an obstacle according to the laser radar, the visual sensor and the sonar;

[0082] S23, if at least two sensors of the laser radar, the visual sensor and the sonar judge that there is an obstacle, judging that there is an obstacle;

[0083] S24, otherwise, judging that there is no obstacle.

[0084] It should be noted that when the target unmanned ship performs the culvert detection task, the operation state thereof needs to be monitored in real time and key data needs to be extracted synchronously; the key data includes the real-time position of the unmanned ship, which can be accurately acquired through a positioning system and is used to judge whether the planned path is deviated; the real-time motion speed can reflect the navigation efficiency and needs to be compared with a preset speed to ensure the detection rhythm; the remaining power is directly related to the task endurance and is an important basis for judging whether the unmanned ship needs to return to the home base for charging halfway; the detection module state needs to be monitored in real time to ensure that the sensors, data acquisition equipment and the like are normally operated; the communication signal strength affects the data transmission stability and avoids command delay or data loss caused by signal interruption; at the same time, the laser radar, the visual sensor and the sonar are used for obstacle detection; the laser radar can quickly acquire the distance and contour information of the obstacle by emitting a laser beam to scan the surrounding environment; the visual sensor can identify the shape and color features of the obstacle by using a camera to capture images; the sonar can play a detection advantage in the culvert environment of turbidity or insufficient light through the principle of sound wave reflection; when at least two of the three sensors judge that there is an obstacle, the system confirms that there is an obstacle; the multi-sensor cross verification mechanism can reduce the risk of false judgment of a single device; if less than two sensors detect an obstacle, it is judged that there is no obstacle, so as to ensure the accuracy of obstacle judgment and provide a reliable basis for the unmanned ship to adjust the path in time.

[0085] Please refer to Figure 3 , Figure 3 is a flowchart for evaluating collision risk of the modular unmanned ship control method for urban culvert detection in some embodiments of the present application. According to the embodiment of the present application, if there is an obstacle, the state parameters of the obstacle are acquired, the category of the obstacle is judged and the collision risk is evaluated, which comprises:

[0086] S31, if there is an obstacle, the state parameters of the obstacle are acquired, including the obstacle size, the distance from the target unmanned ship and the obstacle motion speed;

[0087] S32, judging the obstacle category according to the obstacle motion speed, including a fixed obstacle and a moving obstacle;

[0088] S33, according to the obstacle size, the distance from the target unmanned ship and the obstacle movement speed, combined with the real-time movement speed of the target unmanned ship, a preset collision risk evaluation model is processed to obtain a collision risk coefficient.

[0089] It should be noted that when it is determined that there is an obstacle, the core state parameters of the obstacle need to be quickly obtained: the obstacle size (including length, width and height) is used to evaluate the space requirement for avoidance; the real-time distance from the target unmanned ship can be updated by real-time ranging of the sensor, reflecting the collision warning time; the obstacle movement speed needs to be accurately captured to provide data support for dynamic avoidance; based on the obstacle movement speed, the obstacle can be classified: if the movement speed is continuously zero or within a small error range, it is determined to be a fixed obstacle (such as a pipe protruding from a hidden culvert or a deposited stone); if a significant speed change is detected and the trajectory has displacement, it is classified as a moving obstacle (such as floating debris or other navigation bodies); then, the obstacle size, real-time distance, movement speed and real-time movement speed of the unmanned ship (such as the current speed of 2 m / s) are input into a preset collision risk evaluation model; the model first calculates the relative velocity vector of the two, if the moving obstacle and the unmanned ship move in the same direction, the speed difference needs to be considered to bring the collision window period; then, combined with the obstacle size and the channel width, the minimum avoidance radius is calculated - if the obstacle transverse size accounts for 60% of the channel, a larger turning space needs to be reserved; finally, the collision risk coefficient is obtained through the time window algorithm.

[0090] Please refer to Figure 4 , Figure 4 is the flowchart of the corresponding obstacle avoidance strategy formulated by the modular unmanned ship control method for urban culvert detection in some embodiments of the present application. According to the embodiment of the present application, the corresponding obstacle avoidance strategy is formulated according to the collision risk coefficient, which comprises:

[0091] S41, a set of preset obstacle avoidance condition thresholds is obtained, including an obstacle size threshold and a collision risk threshold;

[0092] S42, according to the obstacle size and the collision risk coefficient, the two threshold values are compared with the corresponding threshold values of the set of preset obstacle avoidance condition thresholds;

[0093] S43, if the comparison results of the two threshold values are not all less than the corresponding threshold values of the set of preset obstacle avoidance condition thresholds, the obstacle avoidance mechanism needs to be executed;

[0094] S44, otherwise, the obstacle avoidance mechanism does not need to be executed, and the operation state of the target unmanned ship continues to be monitored.

[0095] It should be noted that in the decision-making link of the unmanned ship obstacle avoidance, the preset obstacle avoidance condition threshold set needs to be acquired first, wherein the obstacle size limiting threshold is used to clearly define the size standard of the obstacle to be avoided (such as the transverse width exceeding 1 / 3 of the channel), and the collision risk limiting threshold is used to define the risk level critical value (such as 0.5); then, the real-time collected obstacle size is compared with the size limiting threshold, and the collision risk coefficient is compared with the risk limiting threshold; the two comparisons need to be performed synchronously and cannot be omitted; if any result is not less than the corresponding threshold, such as the obstacle size exceeding the standard or the collision risk coefficient reaching 0.6 (exceeding the threshold value of 0.5), it is determined that the obstacle avoidance mechanism needs to be immediately executed, and the sailing around, speed reduction and other operations are started; if both results are less than the threshold value, it is indicated that the current state is safe, and the obstacle avoidance is not needed, and the system continues to monitor the real-time position, speed and other operation states of the unmanned ship to ensure the subsequent stable sailing.

[0096] According to the embodiment of the application, the method further comprises:

[0097] The real-time position, the real-time motion speed, the remaining power, the detection module state and the communication signal are compared with corresponding threshold values in a preset threshold value rule base;

[0098] The state of the target unmanned ship is determined according to the threshold value comparison result, including normal, abnormal and dangerous;

[0099] A corresponding processing strategy is automatically responded according to the state.

[0100] It should be noted that in the running process of the target unmanned ship, the real-time operation data thereof needs to be comprehensively compared with the preset threshold value rule base; specifically, the real-time position needs to be compared with the planned path deviation threshold value, the real-time motion speed needs to be compared with the safe sailing speed range threshold value, the remaining power needs to be compared with the low power warning threshold value, the detection module state needs to be compared with the normal working parameter threshold value, and the communication signal needs to be compared with the stable transmission strength threshold value; according to the comparison results of these threshold values, the state of the unmanned ship can be accurately determined: if all data are within the threshold value range, it is determined as a normal state; if a certain data slightly exceeds the threshold value (such as a slight deviation in the position but can be corrected), it is classified as an abnormal state; if a key data seriously exceeds the threshold value (such as the remaining power being lower than the emergency return threshold value or the communication signal being interrupted), it is determined as a dangerous state; for different states, the system will automatically respond to the corresponding processing strategy; in the normal state, the original path is maintained to continue the work; in the abnormal state, the fine tuning mechanism is started, such as correcting the heading and adjusting the sailing speed; in the dangerous state, the emergency measures are triggered, including immediately stopping sailing, starting the standby communication, planning the return route and the like, so as to ensure the safety of the unmanned ship and the detection task.

[0101] In a second aspect, the present application further discloses a modular unmanned ship control system for urban culvert detection, comprising a memory and a processor, wherein the memory comprises a modular unmanned ship control method program for urban culvert detection, and the modular unmanned ship control method program for urban culvert detection is executed by the processor to realize the following steps:

[0102] obtaining characteristic parameters of a preset culvert, kinematic parameters of a target unmanned ship and detection task requirements;

[0103] obtaining optimization target parameters to optimize path planning of the target unmanned ship;

[0104] real-time monitoring of an operation state of the target unmanned ship and determination of whether there is an obstacle;

[0105] if there is an obstacle, obtaining state parameters of the obstacle, determining a type of the obstacle and evaluating a collision risk;

[0106] formulating a corresponding obstacle avoidance strategy according to the collision risk coefficient.

[0107] It should be noted that existing pipeline endoscopic detection equipment (pipeline periscope, pipeline detection robot) has some limitations in actual application. In the face of complex environments with long detection distance, large water storage capacity and fast flow rate, the operation difficulty is significantly increased. Therefore, in order to solve these problems, firstly, the characteristic parameters of the preset culvert, including the length of the culvert, the number of detection points, the cross-sectional size and the turning radius, the kinematic parameters of the target unmanned ship, including the minimum turning radius and the maximum speed, and the detection task requirements, including the range of detection points to be covered and the detection accuracy, are obtained; then, the optimization target parameters are obtained to optimize the path planning of the target unmanned ship, the operation state of the target unmanned ship is monitored in real time, and whether there is an obstacle is determined according to the laser radar, the visual sensor and the sonar, if there is an obstacle, the state parameters of the obstacle, including the size of the obstacle, the distance from the target unmanned ship and the movement speed of the obstacle, are obtained, the type of the obstacle is determined and the collision risk is evaluated, and the corresponding obstacle avoidance strategy is formulated according to the collision risk coefficient, so as to realize the control technology of the modular unmanned ship for urban culvert detection.

[0108] According to the embodiment of the present application, the obtaining of the characteristic parameters of the preset culvert, the kinematic parameters of the target unmanned ship and the detection task requirements comprises:

[0109] obtaining the characteristic parameters of the preset culvert, including the length of the culvert, the number of detection points, the cross-sectional size and the turning radius;

[0110] obtaining the kinematic parameters of the target unmanned ship, including the minimum turning radius and the maximum speed;

[0111] Obtain detection task requirements, including the range of detection points to be covered and detection accuracy.

[0112] It should be noted that before carrying out the culvert detection operation, three types of key parameters need to be collected to ensure accurate execution of the task; first, the characteristic parameters of the preset culvert, including the actual length of the culvert, which directly determines the total mileage of the detection path; the number of detection points needs to be reasonably arranged in combination with the complexity of the culvert structure to ensure coverage of key monitoring areas; the cross-sectional size, including height and width, is the core basis for planning the unmanned ship's navigation channel; if the culvert has a curve, the turning radius data will affect the development of the unmanned ship turning strategy; secondly, the kinematic parameters of the target unmanned ship need to be obtained, among which the minimum turning radius determines whether the unmanned ship can successfully pass through the curved part of the culvert and needs to be adapted to the culvert turning radius; the maximum speed is related to the detection efficiency and needs to be reasonably set under the premise of meeting the detection accuracy to avoid data collection distortion due to excessive speed; finally, the detection task requirements need to be clarified, the range of detection points to be covered needs to be accurate to specific coordinates or sections to ensure no monitoring blind area; the detection accuracy specifies the error threshold of data collection, for example, the position measurement deviation should not exceed a certain value, which is an important standard for judging the qualification of detection results.

[0113] According to the embodiment of the present application, the acquisition of the optimization target parameter optimizes the path planning of the target unmanned ship, including:

[0114] According to the characteristic parameters of the culvert, the kinematic parameters of the target unmanned ship and the detection task requirements, a plurality of single targets are extracted, including the shortest path length, the minimum curvature change and the highest detection coverage rate;

[0115] According to the shortest path length, the minimum curvature change and the highest detection coverage rate, weighted processing is performed to obtain the optimization target parameter;

[0116] According to the optimization target parameter, the path planning of the target unmanned ship is optimized through a preset optimization algorithm.

[0117] It should be noted that in the path planning of the unmanned ship culvert detection, a key single optimization target needs to be extracted based on various basic parameters. Specifically, the extraction of the shortest path length needs to comprehensively consider the culvert length, the number of detection points and the maximum speed of the unmanned ship: the culvert length determines the overall framework of the path, the number of detection points affects the node distribution of the path, and the maximum speed sets an efficiency boundary for the path length. By reasonably connecting each detection point, the total distance is shortened under the premise of meeting the coverage requirement, which can effectively improve the detection efficiency; the determination of the minimum curvature change is closely related to the turning radius of the culvert, the cross-sectional size of the culvert and the minimum turning radius of the unmanned ship; the turning radius of the culvert directly limits the bending degree of the path, the cross-sectional size determines the safety space when turning, and the minimum turning radius of the unmanned ship is the bottom line of its physical performance. The combination of the three can ensure that the path turns smoothly and avoids the unmanned ship out of control or colliding with the inner wall of the culvert due to sudden change of curvature; the highest detection coverage rate needs to match the detection point range to be covered and the detection accuracy requirement; the detection point range to be covered determines the area that the path must reach, and the detection accuracy requirement specifies the upper limit of the error when the path passes through the detection point. By accurately planning the trajectory of the path passing through each detection point, it can be ensured that all key areas are effectively detected; next, the three targets are weighted to obtain the optimization target parameters, and the weight distribution needs to be adjusted according to the actual detection scene: if the culvert structure is complex and has many turns, the weight of the minimum curvature change can be increased to ensure the safety of navigation; if the detection task is urgent, the weight of the shortest path length can be increased; if the requirement for the integrity of the detection data is very high, the weight of the highest detection coverage rate needs to be increased accordingly; by scientifically distributing the weights, the optimization target parameters can comprehensively reflect the priority of various requirements; finally, the optimization target parameters are input into a preset optimization algorithm (such as genetic algorithm, A* algorithm, etc.) to optimize the path planning of the unmanned ship; the algorithm will iteratively search for the optimal path under the premise of meeting various constraint conditions according to the optimization target parameters; by simulating the navigation effect of different path schemes and comparing their performances in path length, curvature change and detection coverage rate, the optimal path planning scheme that takes into account efficiency, safety and detection quality is finally selected, providing accurate guidance for the culvert detection operation of the unmanned ship.

[0118] According to the embodiment of the present application, the operation state of the target unmanned ship is monitored in real time, and it is judged whether there is an obstacle, comprising:

[0119] The operation state of the target unmanned ship is monitored in real time, and operation state data is extracted, including real-time position, real-time motion speed, remaining power, detection module state and communication signal;

[0120] Whether there is an obstacle is judged according to the laser radar, visual sensor and sonar;

[0121] If at least two of the laser radar, visual sensor and sonar determine that there is an obstacle, it is determined that there is an obstacle;

[0122] Otherwise, it is determined that there is no obstacle.

[0123] It should be noted that when the target unmanned ship performs the culvert detection task, the operation state thereof needs to be monitored in real time and key data needs to be extracted synchronously; these data include the real-time position of the unmanned ship, which can be accurately acquired through a positioning system and is used to determine whether the planned path is deviated; the real-time motion speed can reflect the navigation efficiency and needs to be compared with a preset speed to ensure the detection rhythm; the remaining power is directly related to the task endurance capability and is an important basis for determining whether to return halfway for charging; the detection module state needs to be monitored in real time to ensure that sensors, data acquisition equipment and the like are normally operated; the communication signal strength affects the data transmission stability and avoids command delay or data loss caused by signal interruption; at the same time, three devices of a laser radar, a visual sensor and a sonar are used for obstacle detection; the laser radar can quickly acquire distance and contour information of an obstacle by emitting a laser beam to scan the surrounding environment; the visual sensor can identify shape and color features of an obstacle by using a camera to capture images; the sonar plays a detection advantage in a culvert environment of turbidity or insufficient light through the principle of sound wave reflection; when at least two of the three sensors determine that there is an obstacle, the system confirms that there is an obstacle, and such a multi-sensor cross verification mechanism can reduce the risk of false judgment of a single device; if less than two sensors detect an obstacle, it is determined that there is no obstacle, so as to ensure the accuracy of obstacle judgment and provide a reliable basis for the unmanned ship to adjust the path in time.

[0124] According to the embodiment of the present application, if there is an obstacle, the state parameters of the obstacle are acquired, the category of the obstacle is determined and the collision risk is evaluated, including:

[0125] If there is an obstacle, the state parameters of the obstacle are acquired, including the size of the obstacle, the distance from the target unmanned ship and the motion speed of the obstacle;

[0126] According to the motion speed of the obstacle, the category of the obstacle is determined, including a fixed obstacle and a mobile obstacle;

[0127] According to the size of the obstacle, the distance from the target unmanned ship and the motion speed of the obstacle, the real-time motion speed of the target unmanned ship is combined to process through a preset collision risk evaluation model to obtain a collision risk coefficient.

[0128] It should be noted that when it is determined that there is an obstacle, the core state parameters of the obstacle need to be quickly obtained: the size of the obstacle (including length, width and height) is used to evaluate the space requirement for avoidance; the real-time distance from the target unmanned ship can be updated by real-time ranging of the sensor, reflecting the collision warning time; the motion speed of the obstacle needs to be accurately captured to provide data support for dynamic avoidance; based on the motion speed of the obstacle, its category can be divided: if the motion speed is continuously zero or within a very small error range, it is determined to be a fixed obstacle (such as a pipe protruding in a dark culvert or a deposited stone); if a significant speed change is detected and the trajectory has displacement, it is classified as a moving obstacle (such as floating debris or other navigation bodies); then, the size of the obstacle, the real-time distance, the motion speed and the real-time motion speed of the unmanned ship (such as the current speed of 2 m / s) are input into a preset collision risk assessment model; the model first calculates the relative velocity vector of the two, if the moving obstacle and the unmanned ship move in the same direction, the collision window period caused by the speed difference needs to be considered; then, the size of the obstacle and the width of the channel are combined to calculate the minimum avoidance radius - if the lateral size of the obstacle accounts for 60% of the channel, a larger turning space needs to be reserved; finally, the collision risk coefficient is obtained through the time window algorithm.

[0129] According to the embodiment of the application, the corresponding obstacle avoidance strategy is formulated according to the collision risk coefficient, comprising:

[0130] A set of preset obstacle avoidance condition thresholds is obtained, including an obstacle size threshold and a collision risk threshold;

[0131] The two thresholds corresponding to the obstacle size and the collision risk coefficient are compared with the set of preset obstacle avoidance condition thresholds;

[0132] If the comparison results of the two thresholds are not all less than the corresponding thresholds of the set of preset obstacle avoidance condition thresholds, the obstacle avoidance mechanism needs to be executed;

[0133] Otherwise, the obstacle avoidance mechanism does not need to be executed, and the operation state of the target unmanned ship continues to be monitored.

[0134] It should be noted that in the decision-making link of the unmanned ship obstacle avoidance, the preset obstacle avoidance condition threshold set needs to be obtained first, wherein the obstacle size limiting threshold is used to clearly define the size standard of the obstacle to be avoided (such as the transverse width exceeding 1 / 3 of the channel), and the collision risk limiting threshold is used to define the risk level critical value (such as 0.5); then, the real-time collected obstacle size is compared with the size limiting threshold, and the collision risk coefficient is compared with the risk limiting threshold; the two comparisons need to be performed synchronously and cannot be omitted; if either result is not less than the corresponding threshold value, such as the obstacle size is out of limit or the collision risk coefficient reaches 0.6 (exceeding the threshold value of 0.5), it is determined that the obstacle avoidance mechanism needs to be immediately executed, and the sailing around, speed reduction and other operations are started; if both results are less than the threshold value, it is indicated that the current state is safe, and the obstacle avoidance is not needed, and the system continues to monitor the real-time position, speed and other operation states of the unmanned ship to ensure the subsequent stable sailing; the double threshold value checking mechanism can ensure safety while reducing unnecessary obstacle avoidance operations and improving detection efficiency.

[0135] According to the embodiment of the application, the method further comprises:

[0136] The real-time position, real-time motion speed, remaining power, detection module state and communication signal are compared with corresponding threshold values in a preset threshold value rule base;

[0137] The state of the target unmanned ship is determined according to the threshold value comparison result, including normal, abnormal and dangerous;

[0138] A corresponding processing strategy is automatically responded according to the state.

[0139] It should be noted that in the running process of the target unmanned ship, the real-time operation data thereof needs to be comprehensively compared with the preset threshold value rule base; specifically, the real-time position needs to be compared with the planned path deviation threshold value, the real-time motion speed needs to be compared with the safe sailing speed range threshold value, the remaining power needs to be compared with the low power warning threshold value, the detection module state needs to be compared with the normal working parameter threshold value, and the communication signal needs to be compared with the stable transmission strength threshold value; according to the comparison results of these threshold values, the state of the unmanned ship can be accurately determined: if all data are within the threshold value range, it is determined as a normal state; if a certain data slightly exceeds the threshold value (such as a slight deviation in the position but can be corrected), it is classified as an abnormal state; if a key data seriously exceeds the threshold value (such as the remaining power being lower than the emergency return threshold value or the communication signal being interrupted), it is determined as a dangerous state; for different states, the system will automatically respond to the corresponding processing strategy; in the normal state, the original path is maintained to continue the work; in the abnormal state, the fine tuning mechanism is started, such as correcting the heading and adjusting the sailing speed; in the dangerous state, the emergency measures are triggered, including immediately stopping sailing, starting the standby communication, planning the return route and the like, so as to ensure the safety of the unmanned ship and the detection task.

[0140] The application discloses a modular unmanned ship control method and system for urban culvert detection.

[0141] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are merely schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, or direct coupling or communication connection between the various components can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0142] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0143] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0144] Those of ordinary skill in the art can understand that all or part of the steps of the above method embodiments can be completed by program instruction related hardware, and the foregoing program can be stored in a readable storage medium, and the program executes the steps of the above method embodiments when executed; and the foregoing storage medium includes mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks or optical disks, and various media that can store program codes.

[0145] Alternatively, the above-mentioned integrated unit of the present application, if realized in the form of a software function module and sold or used as an independent product, can also be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium, includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: mobile storage devices, ROM, RAM, magnetic or optical disks, and various media that can store program codes.

Claims

1. A modular unmanned surface vessel control method for urban culvert inspection, characterized in that, Includes the following steps: Obtain the feature parameters of the preset culvert, including the length of the culvert, the number of detection points, the cross-sectional dimensions, and the turning radius; Obtain the kinematic parameters of the target unmanned vessel, including the minimum turning radius and maximum speed; Obtain the requirements for the testing task, including the range of testing points to be covered and the testing accuracy; Based on the feature parameters of the culvert, the kinematic parameters of the target unmanned vessel, and the detection task requirements, multiple single targets are extracted, including the shortest path length, the minimum curvature change, and the highest detection coverage. The optimization target parameters are obtained by weighting the shortest path length, minimum curvature change, and highest detection coverage. The path planning of the target unmanned vessel is optimized using a preset optimization algorithm based on the optimization target parameters. The system monitors the operational status of the target unmanned vessel in real time and determines whether there are any obstacles. If an obstacle exists, obtain the state parameters of the obstacle, determine the category of the obstacle, and assess the collision risk; Develop corresponding obstacle avoidance strategies based on the collision risk coefficient.

2. The modular unmanned surface vessel control method for urban culvert detection according to claim 1, characterized in that, The real-time monitoring of the target unmanned vessel's operational status and determination of the presence of obstacles includes: The system monitors the operational status of the target unmanned vessel in real time and extracts operational status data, including real-time location, real-time speed, remaining battery power, detection module status, and communication signals. The presence of obstacles is determined using lidar, visual sensors, and sonar. If at least two of the aforementioned LiDAR, visual sensor, and sonar sensors determine that an obstacle exists, then an obstacle is determined to exist. Otherwise, it is determined that there is no obstacle.

3. The modular unmanned surface vessel control method for urban culvert detection according to claim 2, characterized in that, If an obstacle exists, the process of acquiring the obstacle's state parameters, determining the obstacle's category, and assessing the collision risk includes: If an obstacle exists, obtain the obstacle's state parameters, including the obstacle's size, distance from the target unmanned vessel, and the obstacle's speed. The obstacle category is determined based on its speed of movement, including fixed obstacles and moving obstacles; Based on the obstacle's size, distance from the target unmanned vessel, and obstacle's speed, combined with the target unmanned vessel's real-time speed, a collision risk assessment model is used to obtain a collision risk coefficient.

4. The modular unmanned surface vessel control method for urban culvert detection according to claim 3, characterized in that, The step of formulating a corresponding obstacle avoidance strategy based on the collision risk coefficient includes: Obtain a preset obstacle avoidance condition threshold set, including obstacle size definition threshold and collision risk limit threshold; The thresholds are compared based on the obstacle size and collision risk coefficient with two thresholds in the preset obstacle avoidance condition threshold set. If the comparison results of the two thresholds are not both less than the corresponding threshold of the preset obstacle avoidance condition threshold set, then the obstacle avoidance mechanism needs to be executed. Otherwise, there is no need to implement the obstacle avoidance mechanism, and the operational status of the target unmanned vessel will continue to be monitored.

5. A modular unmanned surface vessel control system for urban culvert inspection, characterized in that: The system includes a memory and a processor. The memory contains a program for a modular unmanned surface vessel (USV) control method for urban culvert detection. When the processor executes the program for the modular USV control method for urban culvert detection, it performs the following steps: Obtain the feature parameters of the preset culvert, including the length of the culvert, the number of detection points, the cross-sectional dimensions, and the turning radius; Obtain the kinematic parameters of the target unmanned vessel, including the minimum turning radius and maximum speed; Obtain the requirements for the testing task, including the range of testing points to be covered and the testing accuracy; Based on the feature parameters of the culvert, the kinematic parameters of the target unmanned vessel, and the detection task requirements, multiple single targets are extracted, including the shortest path length, the minimum curvature change, and the highest detection coverage. The optimization target parameters are obtained by weighting the shortest path length, minimum curvature change, and highest detection coverage. The path planning of the target unmanned vessel is optimized using a preset optimization algorithm based on the optimization target parameters. The system monitors the operational status of the target unmanned vessel in real time and determines whether there are any obstacles. If an obstacle exists, obtain the state parameters of the obstacle, determine the category of the obstacle, and assess the collision risk; Develop corresponding obstacle avoidance strategies based on the collision risk coefficient.

6. The modular unmanned surface vessel control system for urban culvert detection according to claim 5, characterized in that, The real-time monitoring of the target unmanned vessel's operational status and determination of the presence of obstacles includes: The system monitors the operational status of the target unmanned vessel in real time and extracts operational status data, including real-time location, real-time speed, remaining battery power, detection module status, and communication signals. The presence of obstacles is determined using lidar, visual sensors, and sonar. If at least two of the aforementioned LiDAR, visual sensor, and sonar sensors determine that an obstacle exists, then an obstacle is determined to exist. Otherwise, it is determined that there is no obstacle.

Images