A performance testing method, system, device and storage medium for unmanned boat
By calculating the sense knowledge and path planning data during the operation of unmanned boats, the problem of single unmanned boat performance test dimensions in the existing technology is solved, and the accurate evaluation of the autonomous obstacle avoidance and path planning performance of unmanned boats is achieved, improving the The accuracy of the test was performed.
Patent Information
- Application Number
- CN202411009611.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing unmanned boat performance testing system is not perfect enough and the test dimension is single, so it has failed to effectively evaluate the autonomous obstacle avoidance and path planning performance of unmanned boats.
By obtaining the operation data of the unmanned boat, calculating the sensing knowledge parameters and the minimum distance between obstacles, calculating the detection and identification accuracy of obstacle avoidance path prediction trajectory, generating performance test results, and characterizing the autonomous obstacle avoidance ability of the unmanned boat.
It improves the accuracy of performance evaluation, truly reflects the obstacle avoidance performance and autonomous path planning performance of unmanned boats, and provides multi-dimensional performance test data.
Smart Images

Figure CN118529218B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of testing technology, and in particular to a performance testing method, system, equipment and storage medium for an unmanned boat. Background Art
[0002] As an intelligent marine motion platform, unmanned boats are widely used in hydrographic surveying, marine environment monitoring, marine search and rescue, scientific exploration and military survey activities. Since unmanned boats are intelligent remote unmanned operated equipment, the performance of unmanned boats is particularly important. Based on this, the accuracy of the test and evaluation of the performance of unmanned boats is particularly critical.
[0003] However, in the prior art, the system for testing the performance of unmanned boats is not perfect, and the existing performance testing dimensions of unmanned boats are relatively single (for example, there is no test for autonomous obstacle avoidance performance), resulting in inaccurate performance optimization of unmanned boats. Summary of the invention
[0004] The main purpose of the present invention is to provide a performance testing method, system, equipment and storage medium for an unmanned boat. By calculating the perception and recognition data and path planning data during the operation of the unmanned boat, the basic data of the unmanned boat for performance testing can be obtained. Since the data is calculated based on data of multiple dimensions during the operation of the unmanned boat, the accuracy of the performance evaluation is improved, and the obstacle avoidance performance and autonomous path planning performance of the unmanned boat are truly reflected.
[0005] In order to achieve the above objectives, the embodiments of the present application provide the following technical solutions:
[0006] According to a first aspect of an embodiment of the present application, a performance test method for an unmanned boat is provided, the method comprising:
[0007] Obtain operational data of the unmanned boat in pre-deployed test scenarios;
[0008] Calculating the perception and recognition parameters of the unmanned boat, the minimum distance between obstacles related to the operation of the unmanned boat, and the geographic data of the test scene based on the operation data;
[0009] Calculating the obstacle detection and recognition accuracy value of the unmanned boat according to the perception and recognition parameters and the minimum obstacle distance;
[0010] Calculating the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data;
[0011] A performance test result of the unmanned boat is generated according to the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat and the obstacle detection and recognition accuracy value, and the performance test result represents the autonomous obstacle avoidance capability of the unmanned boat.
[0012] Optionally, the calculating the obstacle detection and recognition accuracy value of the unmanned boat according to the perception and recognition parameter and the minimum obstacle distance includes:
[0013] Extracting obstacle recognition features from the perception recognition parameters and the minimum obstacle spacing;
[0014] Obtaining obstacle position features and path boundary features formed by the obstacle based on the obstacle recognition features;
[0015] The obstacle detection and recognition accuracy value of the unmanned boat is calculated according to the relationship between the minimum obstacle spacing and the obstacle position characteristics and the path boundary characteristics formed by the obstacles.
[0016] Optionally, the calculating the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data includes:
[0017] Constructing a two-dimensional coordinate system corresponding to the test scene;
[0018] Determine the position information of the obstacle in the two-dimensional coordinate system;
[0019] Calculating the obstacle avoidance path prediction trajectory of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the location information of the obstacles; and / or
[0020] An obstacle avoidance speed is calculated according to the perception and recognition parameters, the location information of the obstacle and the geographic data.
[0021] Optionally, the obstacle includes a static obstacle, and the position information of the static obstacle is the coordinates of the static obstacle in the two-dimensional coordinate system; and calculating the obstacle avoidance path prediction trajectory of the unmanned boat according to the perception and recognition parameter, the minimum obstacle spacing, and the position information of the obstacle includes:
[0022] Generate a static distance map based on the position information of several static obstacles;
[0023] According to the static distance map, the perception and recognition parameters of the unmanned boat, and the minimum distance between obstacles, a predicted trajectory of an obstacle avoidance path that will not collide with the obstacle is determined.
[0024] Optionally, the obstacles further include dynamic obstacles, and the position information of the dynamic obstacles is a trajectory of the dynamic obstacles in the two-dimensional coordinate system;
[0025] The step of calculating the obstacle avoidance path prediction trajectory of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the position information of the obstacles includes:
[0026] Obtain the real-time position and speed of several dynamic obstacles, and generate a trajectory map based on the position information of the dynamic obstacles;
[0027] Determine a real-time obstacle avoidance path prediction trajectory that will not collide with the obstacle based on the trajectory graph, the perception and recognition parameters of the unmanned boat, the real-time speed of the dynamic obstacle, and the minimum distance between the obstacles;
[0028] The calculating the obstacle avoidance speed according to the perception and recognition parameter, the position information of the obstacle and the geographic data includes:
[0029] Obtain the real-time position and speed of several dynamic obstacles, and generate a trajectory map based on the position information of the dynamic obstacles;
[0030] The obstacle avoidance speed of the unmanned boat to avoid each of the dynamic obstacles is calculated based on the trajectory diagram, the perception and recognition parameters of the unmanned boat, the real-time speed of the dynamic obstacles, and the minimum obstacle spacing.
[0031] Optionally, the calculating of the minimum distance between obstacles related to the operation of the unmanned boat includes:
[0032] When an obstacle is detected, the obstacle information and the real-time speed and center of gravity position of the unmanned boat are obtained; the center of gravity position is determined based on the force data of several preset force measuring points before the unmanned boat is started and when it is accelerated, and the positions of different force measuring points;
[0033] Determining an obstacle avoidance acceleration according to the center of gravity position of the unmanned boat;
[0034] Determining a deceleration distance of the unmanned boat according to the real-time speed of the unmanned boat and the obstacle avoidance acceleration;
[0035] The minimum obstacle spacing is determined according to the obstacle information, the deceleration distance and the perception time of the unmanned boat; the perception time of the unmanned boat is determined according to historical data.
[0036] Optionally, the calculating the perception recognition data of the unmanned boat includes:
[0037] Acquire detection data and real data detected by a plurality of detection points deployed by the perception system of the unmanned boat;
[0038] The perception recognition data is obtained according to the detection data and the real data of the plurality of detection points, and the perception recognition data includes at least one of a position error, a speed error and a heading error.
[0039] According to a second aspect of an embodiment of the present application, a performance test system for an unmanned boat is provided, the system comprising:
[0040] A data acquisition module, used to obtain the operating data of the unmanned boat in the pre-deployed test scenario;
[0041] A data calculation module, used for calculating the perception and recognition parameters of the unmanned boat, the minimum distance between obstacles related to the operation of the unmanned boat and the geographical data of the test scene based on the operation data;
[0042] An obstacle perception module, used to calculate the obstacle detection and recognition accuracy value of the unmanned boat according to the perception and recognition parameters and the minimum obstacle spacing;
[0043] An obstacle avoidance module, used to calculate the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data;
[0044] A performance test module is used to generate a performance test result of the unmanned boat according to the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat and the obstacle detection and recognition accuracy value, wherein the performance test result represents the ability of the unmanned boat to autonomously avoid obstacles.
[0045] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.
[0046] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. The computer-readable instructions can be executed by a processor to implement the method described in the first aspect above.
[0047] In summary, the embodiments of the present application provide a performance test method, system, device and storage medium for an unmanned boat, which obtains the operation data of the unmanned boat in a pre-deployed test scene; calculates the perception and recognition parameters of the unmanned boat, the minimum distance between obstacles related to the operation of the unmanned boat and the geographical data of the test scene based on the operation data; calculates the obstacle detection and recognition accuracy value of the unmanned boat according to the perception and recognition parameters and the minimum distance between obstacles; calculates the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum distance between obstacles and the geographical data; generates the performance test results of the unmanned boat according to the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat and the obstacle detection and recognition accuracy value, and the performance test results characterize the autonomous obstacle avoidance capability of the unmanned boat. By calculating the perception and recognition data and path planning data during the operation of the unmanned boat, the basic data for the performance test of the unmanned boat can be obtained. Since the data is calculated based on data of multiple dimensions during the operation of the unmanned boat, the accuracy of the performance evaluation is improved, and the obstacle avoidance performance and autonomous path planning performance of the unmanned boat are truly reflected. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.
[0049] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.
[0050] Figure 1 A schematic diagram of a performance testing method for an unmanned boat provided in an embodiment of the present application;
[0051] Figure 2 A schematic diagram of the autonomous evaluation parameters of the unmanned boat provided in the embodiment of the present application;
[0052] Figure 3 A block diagram of a performance test system for an unmanned boat provided in an embodiment of the present application;
[0053] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown;
[0054] Figure 5 A schematic diagram of a computer-readable storage medium provided in an embodiment of the present application is shown.
[0055] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0057] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.
[0058] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0059] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0060] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.
[0061] At present, the autonomous navigation technology of unmanned boats is still in the early stages of development. In order to ensure the effectiveness and feasibility of autonomous navigation technology, it must be rigorously tested and evaluated during the research process. Through testing and evaluation, we can gain an in-depth understanding of the advantages and disadvantages of the technology, so as to make targeted improvements and optimizations. In order to promote the development of autonomous navigation technology for unmanned boats, it is particularly important to build a complete test and verification technology system. This system needs to achieve virtual-real integration and progressive progress to ensure the quality and efficiency of the test, while ensuring the safety and reliability of the test process. For the current various new unmanned boats, it is urgent to study and establish a reasonable data system to support the autonomous evaluation of unmanned boats.
[0062] Figure 1 A performance test method for an unmanned boat provided by an embodiment of the present application is shown. By calculating the perception recognition data and path planning data during the operation of the unmanned boat, the basic data for the performance test of the unmanned boat can be obtained. Since the data is calculated based on data of multiple dimensions during the operation of the unmanned boat, the accuracy of the performance evaluation is improved, and the obstacle avoidance performance and autonomous path planning performance of the unmanned boat are truly reflected. The method includes:
[0063] Step 101: Acquire the operation data of the unmanned boat in the pre-deployed test scenario;
[0064] Step 102: Calculate the perception and recognition parameters of the unmanned boat, the minimum distance between obstacles related to the operation of the unmanned boat, and the geographic data of the test scene based on the operation data;
[0065] Step 103: Calculating the obstacle detection and recognition accuracy value of the unmanned boat according to the perception and recognition parameters and the minimum obstacle distance;
[0066] Step 104: Calculating the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data;
[0067] Step 105: Generate a performance test result of the unmanned boat according to the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat and the obstacle detection and recognition accuracy value, wherein the performance test result represents the autonomous obstacle avoidance capability of the unmanned boat.
[0068] In a possible implementation, in step 103, the calculating the obstacle detection and recognition accuracy value of the unmanned boat according to the perception and recognition parameter and the minimum obstacle distance includes:
[0069] Obstacle recognition features are extracted from the perception and recognition parameters and the minimum obstacle spacing; obstacle position features and path boundary features formed by the obstacle are obtained from the obstacle recognition features; and the obstacle detection and recognition accuracy value of the unmanned boat is calculated based on the relationship between the minimum obstacle spacing and the obstacle position features and the path boundary features formed by the obstacle.
[0070] In a possible implementation, the calculating the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data includes:
[0071] Construct a two-dimensional coordinate system corresponding to the test scene; determine the position information of the obstacle in the two-dimensional coordinate system; calculate the obstacle avoidance path prediction trajectory of the unmanned boat according to the perception and recognition parameters, the minimum distance between the obstacles, and the position information of the obstacles; and / or calculate the obstacle avoidance speed according to the perception and recognition parameters, the position information of the obstacles and the geographic data.
[0072] In a possible implementation, the obstacle includes a static obstacle, and the position information of the static obstacle is the coordinates of the static obstacle in the two-dimensional coordinate system; and calculating the obstacle avoidance path prediction trajectory of the unmanned boat according to the perception and recognition parameter, the minimum obstacle spacing, and the position information of the obstacle includes:
[0073] A static distance map is generated according to the position information of a plurality of static obstacles; and a predicted obstacle avoidance path trajectory that will not collide with the obstacles is determined according to the static distance map, the perception and recognition parameters of the unmanned boat, and the minimum distance between the obstacles.
[0074] In a possible implementation, the obstacles further include dynamic obstacles, and the position information of the dynamic obstacles is the trajectory of the dynamic obstacles in the two-dimensional coordinate system; the step of calculating the obstacle avoidance path prediction trajectory of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the position information of the obstacles includes: obtaining the real-time positions and real-time speeds of a plurality of dynamic obstacles, and generating a trajectory map according to the position information of the dynamic obstacles;
[0075] In a possible implementation, a real-time obstacle avoidance path prediction trajectory that will not collide with the obstacle is determined based on the trajectory graph, the perception and recognition parameters of the unmanned boat, the real-time speed of the dynamic obstacle, and the minimum distance between the obstacles;
[0076] The calculating the obstacle avoidance speed according to the perception and recognition parameter, the position information of the obstacle and the geographic data includes:
[0077] The real-time positions and real-time speeds of several dynamic obstacles are obtained, and a trajectory diagram is generated according to the position information of the dynamic obstacles; based on the trajectory diagram, the perception and recognition parameters of the unmanned boat, the real-time speed of the dynamic obstacles, and the minimum obstacle spacing, the obstacle avoidance speed of the unmanned boat to avoid each of the dynamic obstacles is calculated.
[0078] In a possible implementation manner, the calculating the minimum distance between obstacles related to the operation of the unmanned boat includes:
[0079] When an obstacle is detected, the obstacle information and the real-time speed and center of gravity position of the unmanned boat are obtained; the center of gravity position is determined based on the force data of several preset force measuring points before the unmanned boat is started and when it is accelerated, and the positions of different force measuring points; the obstacle avoidance acceleration is determined according to the center of gravity position of the unmanned boat; the deceleration distance of the unmanned boat is determined according to the real-time speed of the unmanned boat and the obstacle avoidance acceleration; the minimum obstacle spacing is determined according to the obstacle information, the deceleration distance and the perception time of the unmanned boat; the perception time of the unmanned boat is determined according to historical data.
[0080] In a possible implementation, the calculating the perception recognition data of the unmanned boat includes:
[0081] Acquire detection data and real data detected by several detection points deployed by the perception system of the unmanned boat; obtain perception recognition data based on the detection data and real data of the several detection points, and the perception recognition data includes at least one of position error, speed error and heading error.
[0082] With the goal of improving the intelligence level of unmanned boat equipment systems and enhancing their autonomy in complex marine environments, this study takes unmanned boats as the core research object. On this basis, a comprehensive unmanned boat evaluation data system is designed, which aims to evaluate the performance of unmanned boats from all aspects and angles. An evaluation method for the autonomy of unmanned boats is proposed, aiming to provide a new and feasible path for unmanned boat equipment systems to move towards a higher level of intelligence.
[0083] First aspect: Construction of autonomous test data system for unmanned boats:
[0084] The testing and verification of unmanned boat equipment requires the construction of a scientific and reasonable data system. This system needs to accurately capture and evaluate various data of unmanned boat equipment during the testing and verification process. Taking autonomous navigation tasks as the core application scenario, this study designed a set of standardized data systems for the perception and recognition and path planning functions of intelligent unmanned boats.
[0085] The function realization of the unmanned boat's autonomy includes the perception and recognition function and the action control function of the unmanned boat. The corresponding autonomy evaluation data system is constructed for the perception and recognition function, path planning function and action control function of the unmanned boat. Finally, the unmanned boat autonomy evaluation data system structure is obtained as shown in Table 1.
[0086] Table 1 Data system structure of autonomous evaluation of unmanned boat
[0087]
[0088] Combine the following Figure 2 A detailed explanation is given to each evaluation data.
[0089] 1. Average Position Error in Perception and Recognition:
[0090] It is a data that measures the accuracy of the perception system and is usually used to evaluate the performance of the perception module in tasks such as target detection and target tracking. It measures the average distance error between the target position detected by the perception system and its true position. The average position error (APE) is defined as the average of the differences between the target position detected by the perception system and its true position. Specifically, it is the average of the position errors of multiple measurement points. The general formula for calculating the average position error is as follows:
[0091]
[0092] in, N is the number of measurement points, and the predicted position i is the i The detected position of the measurement point i, and the true position i is i The actual position of the measurement point.
[0093] 2. Average Velocity Error is a measure of the accuracy of the perception system's prediction of the target's velocity. It is used to evaluate the accuracy of the perception system in estimating and predicting the target's velocity. In autonomous navigation systems such as unmanned boats, drones, and driverless cars, accurately estimating the target's velocity is crucial for avoiding collisions, planning paths, and conducting effective tracking.
[0094] The general formula for calculating the average speed error is as follows:
[0095]
[0096] Where N is the number of measurement points, predicted speed i is the predicted speed at the i-th measurement point, and true speed i is the actual speed at the i-th measurement point.
[0097] 3. Average Heading Error is a data used to measure the accuracy of the perception system's prediction of the target heading (direction). The general formula for calculating the average heading error is as follows:
[0098]
[0099] Heading is usually expressed in degrees, where N is the number of measurement points, predicted heading i is the predicted heading of the ith measurement point, and true heading i is the actual heading of the ith measurement point. Note that the heading angle may need to be normalized to avoid errors due to angles exceeding 360 degrees.
[0100] 4. Recall, also known as recall rate or sensitivity, is one of the data used to measure the accuracy of a classification model in identifying a certain category. It indicates the proportion of positive examples (True Positive, true positive) successfully identified by the model to all positive examples. The calculation formula of recall rate is as follows:
[0101]
[0102] Among them: TP (True Positive) is the number of positive examples correctly identified by the model; FN (False Negative) is the number of positive examples that the model failed to identify.
[0103] 5. In path planning, it is often crucial to calculate the minimum safe distance from obstacles to ensure that the planned path avoids obstacles and remains safe. When calculating the minimum safe distance, it is necessary to take into account the motion dynamics of the unmanned boat, the performance of the perception system, and the reaction time required in an emergency. A common method is to calculate the minimum safe distance based on the motion dynamics of the unmanned boat. A commonly used formula is based on the formula of velocity and acceleration, as shown below:
[0104]
[0105] Reaction time is the time from detecting an obstacle to taking action; acceleration is usually a negative value. It should be noted that this formula is a simplified model and the actual situation may be more complicated. For example, the acceleration of the unmanned boat may not be constant, the performance of the perception system may be affected by environmental factors, and external factors such as water flow and wind speed may also need to be considered.
[0106] In addition, in order to improve the accuracy and safety of path planning, other sensor data and advanced algorithms, such as machine learning and artificial intelligence methods, can be combined to optimize path planning and calculation of safe distances. Through these methods, the trajectory of the unmanned boat can be predicted more accurately and obstacles can be avoided more effectively, thereby improving the safety and reliability of the unmanned boat.
[0107] 6. The calculation formula for the total distance of a voyage can be defined based on the discrete nature of the path. The calculation formula for the total distance of a voyage can be defined based on the discrete nature of the path. There are usually several different ways to calculate or estimate the total distance of a path. The following are some common calculation methods:
[0108] Straight-line distance: If the path is considered to be composed of a series of straight-line segments, each connecting two consecutive points, then the total distance can be simply calculated by summing the distances of each straight-line segment. For the straight-line distance between two points, the Euclidean distance formula can be used:
[0109]
[0110] is the sum of all straight line segment distances.
[0111] Discrete point interpolation: For a complex path consisting of discrete points, you can use interpolation methods (such as linear interpolation, spline interpolation) to approximate the path, and then calculate the total length of the interpolated path.
[0112] 7. The time of path planning usually refers to the time required to go through the planned path from the starting point to the end point. This time depends on factors such as the length of the path, the speed of the unmanned boat, and possible traffic conditions. The basic calculation formula can be obtained by dividing the length of the path by the speed of the unmanned boat, that is:
[0113]
[0114] The second aspect: unmanned boat autonomy test items.
[0115] The five test items for representative unmanned boat autonomy testing are shown in the table, including all test items and scenario composition samples.
[0116] Table 2 Representative unmanned boat autonomy test items
[0117]
[0118] In the navigation system of unmanned boats, obstacle detection is one of the key technologies to ensure safe driving. In order to evaluate the performance of the obstacle detection system of unmanned boats, a series of tests can be performed, including obstacle detection accuracy test, obstacle detection recognition rate test, static obstacle test, dynamic obstacle encounter test and dynamic obstacle intersection test. The following is a detailed introduction to these tests:
[0119] 1. Obstacle detection accuracy test:
[0120] This test is designed to evaluate the obstacle detection system's accuracy in identifying the location of obstacles. By placing obstacles at known locations and recording the locations reported by the UAV detection system, the position deviation can be calculated. The accuracy test can be repeated multiple times and the average deviation calculated to improve the reliability of the results. A high-precision detection system can more accurately predict the location of obstacles, thereby improving the safety and obstacle avoidance capabilities of the UAV.
[0121] 2. Obstacle detection recognition rate test:
[0122] The recognition rate test focuses on the system's ability to correctly identify obstacles. In this test, various types of obstacles can be placed in the path of the unmanned boat, and the number of obstacles successfully identified and classified by the system is recorded. Systems with high recognition rates can better understand the surrounding environment and provide more accurate obstacle avoidance strategies for the unmanned boat.
[0123] 3. Static obstacle test:
[0124] The static obstacle test mainly evaluates the unmanned boat's ability to detect static obstacles. In the test, obstacles are placed in fixed positions, and the unmanned boat needs to be able to detect these obstacles when approaching and take appropriate obstacle avoidance measures. This test is particularly important for evaluating the unmanned boat's navigation ability in environments such as ports and narrow waterways.
[0125] 4. Dynamic obstacle encounter test:
[0126] In the dynamic obstacle encounter test, the unmanned boat needs to detect and respond to dynamic obstacles moving towards it. This test simulates the situation of a ship encounter that may be encountered in open water. The navigation system of the unmanned boat must be able to identify the oncoming ship in time and calculate a safe avoidance path.
[0127] 5. Dynamic obstacle crossing test:
[0128] The crossing test focuses on the obstacle detection capability of the unmanned boat when crossing with other ships. In this case, the unmanned boat needs to evaluate the trajectory of other ships and predict possible crossing points. The navigation system must be able to accurately determine when and where to avoid potential collision risks.
[0129] Through these tests, the performance of the obstacle detection system of the unmanned boat can be fully evaluated to ensure that it can work reliably in various complex environments. This is of great significance for improving the autonomous navigation capability of the unmanned boat and ensuring navigation safety.
[0130] The third aspect: Unmanned boat autonomy evaluation method.
[0131] At present, there is a lack of a test and evaluation method for the autonomy of unmanned boats that is generally applicable to different mission scenarios, which limits the comprehensive evaluation of the autonomy of unmanned boats. To meet this challenge, the Analytic Hierarchy Process (AHP) is introduced as a means to construct an evaluation method for the autonomy of unmanned boats.
[0132] The AHP method is a multi-objective decision analysis method that combines qualitative and quantitative analysis and has a wide range of applications in the field of operations research. Through numerical evaluation, the experience of decision makers or experts is converted into computable quantitative data, which is particularly suitable for dealing with problems with complex target structures. Therefore, the use of the AHP method to construct an autonomous evaluation system for unmanned boats is expected to provide a more comprehensive, objective and practical means for the autonomous evaluation of unmanned boats.
[0133] The relative importance of different factors can be determined by using the Analytic Hierarchy Process (AHP). The AHP is a multi-criteria decision-making method that helps decision makers make decisions by constructing a judgment matrix, calculating weight vectors, and performing consistency checks.
[0134] The calculation formula of AHP mainly involves two aspects: one is to calculate the weight of each level, and the other is to conduct consistency test.
[0135] 1. Calculate the weight of each level
[0136] For each level of factors, it is necessary to compare them two by two, and then build a judgment matrix based on the comparison results. Then, the judgment matrix is processed using the eigenvalue method or other solution methods to obtain the weight vector of each factor.
[0137]
[0138] First, all the key factors that affect the path planning time need to be identified, such as path length, UAV speed, traffic conditions, water and wind speed, obstacles, etc. Then, these factors are compared pairwise and scored according to their relative importance in affecting the path planning time.
[0139] After constructing the judgment matrix, it needs to be processed to obtain the weight of each factor. The processing steps are as follows:
[0140] Step 1: Calculate the sum of each column of the judgment matrix.
[0141] Step 2: Divide the sum of each column by the number of rows in the matrix to get the relative weight of each factor.
[0142] Step 3: Normalize the relative weights obtained, that is, divide them by the sum of all weights to obtain the final weight vector.
[0143] 2. Consistency Test
[0144] In order to ensure that the comparison results in the judgment matrix are consistent, it is necessary to check the consistency of the comparisons when making pairwise comparisons. Consistency Index (CI) and Random Index (RI) are used in AHP to perform consistency checks.
[0145]
[0146] in, λ max is the maximum eigenvalue of the judgment matrix, and n is the order of the judgment matrix. If CI is less than or close to RI, it means that the comparison results are consistent; if CI is much larger than RI, the comparison results need to be reconsidered. If CI is less than 0.1, the judgment matrix is considered to have satisfactory consistency; if CI is greater than 0.1, the judgment matrix needs to be readjusted until the consistency requirements are met.
[0147] Through the above steps, a weight vector can be obtained, which represents the relative importance of each factor in the path planning time evaluation. This weight vector can be used to evaluate and compare different path planning schemes, so as to select the optimal path planning scheme. The analytic hierarchy process is a systematic and structured method that can help decision makers make more reasonable and scientific decisions in a complex decision-making environment. In general, the calculation formula of AHP can be summarized into the following steps: construct a judgment matrix and make pairwise comparisons; process the judgment matrix to solve the weight vector of each factor; and perform consistency checks to ensure that the comparison results are consistent.
[0148] The autonomous navigation system is the most important system to ensure the navigation safety and combat mission execution capability of unmanned boats. In order to ensure navigation safety, achieve high reliability and reduce development costs, the autonomous navigation of intelligent unmanned boats must undergo comprehensive testing and verification from development to application. Therefore, building a testing and verification technology system is an important guarantee for the development of unmanned boats.
[0149] In summary, the embodiment of the present application constructs a test data system for the autonomy of unmanned boats and realizes the evaluation of the autonomy of unmanned boats. The establishment of this data system provides a more clear and quantifiable evaluation standard for the autonomy test of unmanned boats, which helps to promote the further development and application of unmanned boat technology. Unmanned boat autonomy test items. Five test items were proposed, and this achievement supported the representative unmanned boat autonomy test. Unmanned boat autonomy evaluation data system and evaluation method based on the hierarchical analysis method, on which evaluation data and test methods suitable for the autonomy of unmanned boats are formed based on the test data.
[0150] In summary, the embodiment of the present application provides a performance test method for an unmanned boat, by acquiring the operation data of the unmanned boat in a pre-deployed test scene; calculating the perception and recognition parameters of the unmanned boat, the minimum distance between obstacles related to the operation of the unmanned boat, and the geographic data of the test scene based on the operation data; calculating the obstacle detection and recognition accuracy value of the unmanned boat according to the perception and recognition parameters and the minimum distance between obstacles; calculating the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum distance between obstacles, and the geographic data; generating the performance test result of the unmanned boat according to the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat and the obstacle detection and recognition accuracy value, and the performance test result characterizes the autonomous obstacle avoidance capability of the unmanned boat. By calculating the perception and recognition data and path planning data during the operation of the unmanned boat, the basic data for the performance test of the unmanned boat can be obtained. Since the data is calculated based on data of multiple dimensions during the operation of the unmanned boat, the accuracy of the performance evaluation is improved, and the obstacle avoidance performance and autonomous path planning performance of the unmanned boat are truly reflected.
[0151] Based on the same technical concept, the embodiment of the present application also provides a performance test system for an unmanned boat, such as Figure 3 As shown, the system comprises:
[0152] The data acquisition module 301 is used to acquire the operation data of the unmanned boat in the pre-deployed test scenario;
[0153] A data calculation module 302 is used to calculate the perception and recognition parameters of the unmanned boat, the minimum distance between obstacles related to the operation of the unmanned boat, and the geographical data of the test scene based on the operation data;
[0154] The obstacle sensing module 303 is used to calculate the obstacle detection and recognition accuracy value of the unmanned boat according to the sensing and recognition parameters and the minimum obstacle distance;
[0155] The obstacle avoidance module 304 is used to calculate the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data;
[0156] The performance test module 305 is used to generate a performance test result of the unmanned boat according to the obstacle avoidance path prediction trajectory and / or obstacle avoidance speed of the unmanned boat and the obstacle detection and recognition accuracy value, and the performance test result represents the autonomous obstacle avoidance capability of the unmanned boat.
[0157] The present application also provides an electronic device corresponding to the method provided in the above embodiment. Figure 4 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. The electronic device 20 may include: a processor 200, a memory 201, a bus 202 and a communication interface 203, wherein the processor 200, the communication interface 203 and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and the processor 200 executes the method provided by any of the aforementioned embodiments of the present application when running the computer program.
[0158] The memory 201 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one physical port 203 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.
[0159] The bus 202 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs, and the processor 200 executes the programs after receiving execution instructions. The method disclosed in any implementation of the aforementioned embodiment of the present application may be applied to the processor 200, or implemented by the processor 200.
[0160] The processor 200 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 200. The above processor 200 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and completes the steps of the above method in combination with its hardware.
[0161] The electronic device provided in the embodiment of the present application and the method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, operated or implemented by them.
[0162] The present application also provides a computer-readable storage medium corresponding to the method provided in the above embodiment. Figure 5 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, the method provided in any of the aforementioned embodiments is executed.
[0163] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.
[0164] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.
[0165] It should be noted that:
[0166] The algorithm and display provided herein are not inherently related to any particular computer, virtual device or other equipment. Various general purpose devices can also be used together with the teachings based on this. According to the above description, it is obvious to construct the structure required for this type of device. In addition, the application is not directed to any specific programming language. It should be understood that the content of the application described herein can be realized using various programming languages, and the description of the specific language above is to disclose the best mode of implementation of the application.
[0167] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.
[0168] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the claims below, the inventive aspects are less than all the features of the single embodiment disclosed above. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.
[0169] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.
[0170] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.
[0171] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the creation device of the virtual machine according to the embodiment of the present application. The present application can also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.
[0172] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.
[0173] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
[0174] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.
Claims
1. A performance test method for an unmanned boat, characterized in that: The method comprises: Obtain operational data of the unmanned boat in pre-deployed test scenarios; Calculating the perception and recognition parameters of the unmanned boat, the minimum distance between obstacles related to the operation of the unmanned boat, and the geographic data of the test scene based on the operation data; Extracting obstacle recognition features from the perception recognition parameters and the minimum obstacle spacing; obtaining obstacle position features and path boundary features formed by the obstacle from the obstacle recognition features; and calculating the obstacle detection and recognition accuracy value of the unmanned boat according to the relationship between the minimum obstacle spacing and the obstacle position features and the path boundary features formed by the obstacle; Calculating the obstacle avoidance path prediction trajectory and obstacle avoidance speed, or obstacle avoidance speed, of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data; Generating a performance test result of the unmanned boat according to the obstacle avoidance path prediction trajectory and obstacle avoidance speed, or obstacle avoidance speed, of the unmanned boat, and the obstacle detection and recognition accuracy value, wherein the performance test result represents the ability of the unmanned boat to autonomously avoid obstacles; The obstacles also include dynamic obstacles, and the position information of the dynamic obstacles is the trajectory of the dynamic obstacles in a two-dimensional coordinate system; The obstacle avoidance path prediction trajectory of the unmanned boat is calculated according to the perception and recognition parameters, the minimum distance between obstacles, and the geographic data, including: obtaining the real-time positions and real-time speeds of a plurality of dynamic obstacles, and generating a trajectory map according to the position information of the dynamic obstacles; determining the real-time obstacle avoidance path prediction trajectory that will not collide with the obstacles based on the trajectory map, the perception and recognition parameters of the unmanned boat, the real-time speed of the dynamic obstacles, and the minimum distance between obstacles; The method of calculating the obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data includes: obtaining the real-time positions and real-time speeds of a plurality of dynamic obstacles, and generating a trajectory map according to the position information of the dynamic obstacles; and calculating the obstacle avoidance speed of the unmanned boat to avoid each of the dynamic obstacles based on the trajectory map, the perception and recognition parameters of the unmanned boat, the real-time speed of the dynamic obstacles, and the minimum obstacle spacing.
2. The method according to claim 1, characterized in that The step of calculating the obstacle avoidance path prediction trajectory and obstacle avoidance speed of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data includes: Constructing a two-dimensional coordinate system corresponding to the test scene; Determine the position information of the obstacle in the two-dimensional coordinate system; Calculating the obstacle avoidance path prediction trajectory of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the position information of the obstacles; An obstacle avoidance speed is calculated according to the perception and recognition parameters, the location information of the obstacle and the geographic data.
3. The method according to claim 2, characterized in that The obstacle includes a static obstacle, and the position information of the static obstacle is the coordinate of the static obstacle in the two-dimensional coordinate system; the calculating the obstacle avoidance path prediction trajectory of the unmanned boat according to the perception and recognition parameter, the minimum distance between obstacles, and the position information of the obstacles includes: Generate a static distance map based on the position information of several static obstacles; According to the static distance map, the perception and recognition parameters of the unmanned boat, and the minimum distance between obstacles, a predicted trajectory of an obstacle avoidance path that will not collide with the obstacle is determined.
4. The method according to claim 1, characterized in that The calculating of the minimum distance between obstacles related to the operation of the unmanned boat includes: When an obstacle is detected, the obstacle information and the real-time speed and center of gravity position of the unmanned boat are obtained; the center of gravity position is determined based on the force data of several preset force measuring points before the unmanned boat is started and when it is accelerated, and the positions of different force measuring points; Determining an obstacle avoidance acceleration according to the center of gravity position of the unmanned boat; Determining a deceleration distance of the unmanned boat according to the real-time speed of the unmanned boat and the obstacle avoidance acceleration; The minimum obstacle spacing is determined according to the obstacle information, the deceleration distance and the perception time of the unmanned boat; the perception time of the unmanned boat is determined according to historical data.
5. The method according to claim 1, characterized in that The calculating the perception and recognition parameters of the unmanned boat includes: Acquire detection data and real data detected by a plurality of detection points deployed by the perception system of the unmanned boat; A perception identification parameter is obtained according to the detection data and the real data of the plurality of detection points, and the perception identification parameter includes at least one of a position error, a speed error and a heading error.
6. A performance test system for an unmanned boat, characterized in that: The system comprises: A data acquisition module, used to obtain the operating data of the unmanned boat in the pre-deployed test scenario; A data calculation module, used for calculating the perception and recognition parameters of the unmanned boat, the minimum distance between obstacles related to the operation of the unmanned boat and the geographical data of the test scene based on the operation data; The obstacle perception module is used to extract obstacle recognition features from the perception recognition parameters and the minimum obstacle spacing; obtain obstacle position features and path boundary features formed by the obstacle from the obstacle recognition features; calculate the obstacle detection and recognition accuracy value of the unmanned boat according to the relationship between the minimum obstacle spacing and the obstacle position features and the path boundary features formed by the obstacle; the obstacles also include dynamic obstacles, and the position information of the dynamic obstacles is the trajectory of the dynamic obstacles in a two-dimensional coordinate system; An obstacle avoidance module, used to calculate the obstacle avoidance path prediction trajectory and obstacle avoidance speed, or obstacle avoidance speed, of the unmanned boat according to the perception and recognition parameters, the minimum obstacle spacing, and the geographic data; A performance test module, used to generate a performance test result of the unmanned boat according to the obstacle avoidance path prediction trajectory and obstacle avoidance speed, or obstacle avoidance speed, and the obstacle detection and recognition accuracy value of the unmanned boat, wherein the performance test result represents the autonomous obstacle avoidance capability of the unmanned boat; The obstacle avoidance module is specifically used to obtain the real-time positions and real-time speeds of several dynamic obstacles, and generate a trajectory map according to the position information of the dynamic obstacles; determine a real-time obstacle avoidance path prediction trajectory that will not collide with the obstacles based on the trajectory map, the perception and recognition parameters of the unmanned boat, the real-time speed of the dynamic obstacles, and the minimum obstacle spacing; and is also used to obtain the real-time positions and real-time speeds of several dynamic obstacles, and generate a trajectory map according to the position information of the dynamic obstacles; calculate the obstacle avoidance speed of the unmanned boat to avoid each of the dynamic obstacles based on the trajectory map, the perception and recognition parameters of the unmanned boat, the real-time speed of the dynamic obstacles, and the minimum obstacle spacing.
7. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that: Computer-readable instructions are stored thereon, and the computer-readable instructions can be executed by a processor to implement the method according to any one of claims 1-5.
Citation Information
Patent Citations
Vehicle obstacle avoidance method and device and vehicle
CN109808686A
Autonomous capacity test device and test method for robot platform based on tasks
CN111618908A
Real-time obstacle avoidance method and system for unmanned ship
CN114326720A
Unmanned ship obstacle avoidance control method and device
CN115629603A
Device and method for simulating and testing obstacle avoidance performance of robot and readable storage medium
CN115657651A
