Unmanned ship collision avoidance method based on multiple collision avoidance objects, terminal equipment and medium

Abstract

The invention relates to an unmanned ship collision avoidance method based on multiple collision avoidance objects, terminal equipment and a medium. The method comprises the following steps: collecting motion information of all moving objects in a sea area nearby an unmanned ship; clustering all moving objects to obtain a plurality of object clusters; calculating a collision avoidance area of each object cluster; when the unmanned ship travels to the collision avoidance waypoint, if more than one intersection point does not exist between the re-voyage route and the collision avoidance area, normal re-voyage is carried out; otherwise, according to the size of the course angle, the unmanned ship is controlled to keep the previous course to continue running or run according to the deflected route after deflecting rightwards, and the unmanned ship is re-navigated until more than one intersection point does not exist between the re-navigating route and the collision avoidance area. According to the method, the collision avoidance action can be safely completed on the multiple dynamic objects, meanwhile, the collision avoidance decision complexity is reduced, and the collision avoidance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned boat collision avoidance, and in particular to an unmanned boat collision avoidance method based on multiple collision avoidance targets, terminal equipment and a medium. Background Art

[0002] An unmanned surface vehicle (USV) is an unmanned watercraft that can perform specific tasks and has autonomous or semi-autonomous capabilities. It is widely used in military, scientific research, artificial intelligence and other fields because of its good concealment, strong maneuverability and small formation. When sailing in a complex marine environment, unmanned boats will be threatened by collisions with sailing ships (including merchant ships, fishing boats, etc.), so the study of USV autonomous collision avoidance technology has important practical significance.

[0003] USV autonomous collision avoidance technology refers to the ability of USV to quickly and effectively adjust its own course and speed according to the surrounding environment information, and autonomously avoid collisions with single or multiple static and dynamic objects encountered when sailing on the water. At present, domestic and foreign experts and scholars mainly use local path planning and intelligent algorithms to solve the collision avoidance planning problem of USV. Commonly used algorithms include speed barrier method, particle swarm algorithm, dynamic window method, artificial potential field method, reinforcement learning algorithm, deep learning algorithm and other intelligent algorithms and their improved algorithms. The existing methods can achieve good results in solving the avoidance problems of single ships, two ships and simple three ships, while the avoidance problem of multiple dynamic objects (such as unmanned boats, fishing boats and other large-scale clusters) is still a difficult problem in current research. At present, for the complex problem of USV collision avoidance with multiple dynamic objects, researchers have used the above methods to conduct relevant research based on the concept of ship priority and the strategy of avoiding collision with key ships. When dense traffic flow appears on the sea, the collision avoidance efficiency of these intelligent collision avoidance algorithms will be slow, and USV may fall into the dilemma of complex traffic flow and fail to obtain the optimal solution for collision avoidance, resulting in an increased risk of collision. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes an unmanned boat collision avoidance method based on multiple collision avoidance targets, terminal equipment and medium.

[0005] The specific plan is as follows:

[0006] A method for avoiding collision of an unmanned boat based on multiple collision avoidance objects comprises the following steps:

[0007] S1: Collect the motion information of all moving objects in the sea area near the unmanned boat;

[0008] S2: Cluster all moving objects based on the collected motion information to obtain multiple object clusters;

[0009] S3: Calculating the collision avoidance area of ​​each object cluster based on the current coordinates of each object cluster included in each object cluster;

[0010] S4: When the unmanned boat reaches a collision avoidance waypoint relative to a certain object cluster collision avoidance area, determine whether the unmanned boat's return route has more than one intersection with the collision avoidance area. If so, proceed to S5; otherwise, control the unmanned boat to return according to the return route.

[0011] S5: Determine the heading angle between the unmanned boat and the target cluster Is it satisfied? If yes, go to S6; otherwise, control the unmanned boat to keep the previous course and continue to travel until there is no more than one intersection between the unmanned boat's return route and the current collision avoidance area of ​​the object cluster, and then control the unmanned boat to return according to the return route; R represents the radius of the collision avoidance area of ​​the object cluster, The vertical component representing the relative distance between the target cluster and the unmanned boat;

[0012] S6: Control the unmanned boat to deflect to the right and make it travel along the deflected route until there is no more than one intersection between the unmanned boat's return route and the current collision avoidance area of ​​the object cluster, and then control the unmanned boat to return along the return route.

[0013] Furthermore, in step S2, all moving objects are clustered using an improved DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm; the improved DBSCAN algorithm adds speed difference constraints and heading difference constraints on the basis of the traditional DBSCAN algorithm, that is, the heading difference between any two objects in all objects belonging to the same object cluster is less than the heading difference threshold, and the speed difference between any two objects is less than the speed difference threshold.

[0014] Furthermore, when clustering all moving objects by using the improved DBSCAN algorithm, a neighborhood radius constraint is included, that is, the neighborhood radius ε of any two objects in all objects belonging to the same object cluster should be less than or equal to 4 times the safety distance of the objects.

[0015] Furthermore, when step S6 controls the unmanned boat to deflect to the right, the calculation formula of the deflection angle is:

[0016]

[0017] Where θ represents the deflection angle, v U represents the speed of the unmanned boat, v C Indicates the speed of the object cluster.

[0018] An unmanned boat collision avoidance terminal device based on multiple collision avoidance objects includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method of the embodiment of the present invention are implemented.

[0019] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above in an embodiment of the present invention are implemented.

[0020] The present invention adopts the above technical solution, which can safely complete the collision avoidance action for multiple dynamic objects, while reducing the complexity of collision avoidance decision-making and improving the collision avoidance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Shown is a flow chart of a method according to a first embodiment of the present invention.

[0022] Figure 2 Shown is a schematic diagram of the clustering result in this embodiment.

[0023] Figure 3 Shown is a schematic diagram of the collision avoidance area in this embodiment.

[0024] Figure 4 Shown is a schematic diagram of the traditional geometric collision avoidance algorithm for avoiding a single target in this embodiment.

[0025] Figure 5 Shown is a schematic diagram of a cluster of objects avoided using a traditional geometric collision avoidance algorithm in this embodiment.

[0026] Figure 6 The diagram shown is a schematic diagram when the heading angle does not meet the conditions in this embodiment.

[0027] Figure 7 The diagram shown is a schematic diagram when the heading angle meets the conditions in this embodiment.

[0028] Figure 8 FIG. 1 is a schematic diagram of the distribution of objects in this embodiment.

[0029] Fig. 9 FIG. 4 is a schematic diagram of the object clustering result in this embodiment.

[0030] Fig.10 Shown is a schematic diagram of the USV collision avoidance process based on the traditional collision avoidance method in the encounter scenario in this embodiment.

[0031] Fig.11 The figure shows a schematic diagram of the USV collision avoidance process based on the method of this embodiment in the encounter scenario in this embodiment.

[0032] Fig.12Shown is a schematic diagram of the USV collision avoidance process based on the traditional collision avoidance method in the intersection encounter scenario in this embodiment.

[0033] Fig.13 The figure shows a schematic diagram of the USV collision avoidance process based on the method of this embodiment in the intersection encounter scenario in this embodiment.

[0034] Fig.14 Shown is a schematic diagram of the USV collision avoidance process based on the traditional collision avoidance method in the overtaking scenario in this embodiment.

[0035] Fig.15 The figure shows a schematic diagram of the USV collision avoidance process based on the method of this embodiment in the overtaking scenario in this embodiment.

[0036] Fig.16 Shown is a comparison diagram of USV collision avoidance paths of the two collision avoidance methods in three encounter scenarios in this embodiment.

[0037] Fig.17 Shown is a comparison diagram of collision avoidance efficiency in this embodiment.

[0038] Fig.18 Shown is a comparison diagram of the sum of closest encounter distances in this embodiment.

[0039] Fig.19 The diagram shown is a diagram of the variation of the encounter distance between the USV and the target object in this embodiment. DETAILED DESCRIPTION

[0040] To further illustrate various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementations and advantages of the present invention.

[0041] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.

[0042] Embodiment 1:

[0043] The embodiment of the present invention provides a method for avoiding collision of an unmanned boat based on multiple collision avoidance targets, such as Figure 1 As shown, the method comprises the following steps:

[0044] S1: Collect the motion information of each object in the sea area around the unmanned boat.

[0045] The landmarks may be merchant ships, fishing boats, etc. sailing on the sea.

[0046] The collected object motion information is the information needed in the subsequent steps, such as speed, heading, coordinates, etc.

[0047] S2: Cluster all moving objects based on the collected motion information to obtain multiple object clusters.

[0048] The DBSCAN algorithm is a density-based clustering algorithm. The neighborhood refers to the area where the distance to the selected object is less than ε, and the set of other members in the neighborhood is expressed as formula (1):

[0049] N ε (q)={p belong to D|dist(q,p)≤ε} (1)

[0050] In the formula, q is the selected object; D is the neighborhood of the selected object; ε is the neighborhood radius; and p is the object other than the selected object. In this algorithm, q is called a core object if it satisfies formula (2):

[0051] |N ε (q)|≥Minpts (2)

[0052] In the formula, |N ε (q)| is the number of members in the set; Minpts refers to the minimum number of neighborhood points required to define a core object. That is, in the ε neighborhood of the core object q, if the number of non-core objects p is greater than or equal to the minimum number of neighborhood points, then all objects p in the ε neighborhood are directly accessible from q, and eventually these objects are clustered into one cluster. The schematic diagram of object clustering based on the traditional DBSCAN algorithm is shown in Figure 2 shown.

[0053] When the intervals between multiple objects are large, so large that the USV can safely avoid collisions between them, it is obvious that they should not be avoided as a cluster. Therefore, when clustering objects, the value of the neighborhood radius ε should be determined. The selection of the neighborhood radius ε parameter during clustering is closely related to the safe distance (SD) of the object. Usually, under good visibility conditions, the safe distance of ships above 10,000 tons should not be less than 1nm; the safe distance SD of USV can be calculated by formula (3):

[0054] SD=R U +R T +d s (3)

[0055] In the formula, R U Half the length of the USV, R T Half of the length of the object; d s is the safety margin, and the value is calculated as follows:

[0056] d s =v R ·t+L x (4)

[0057] Where t is the time step; L x It is the longitudinal movement distance of the ship when the heading changes by 90° for the party with poor maneuverability.

[0058] When the USV can avoid collision between any two objects at a distance greater than 2 times the SD, it can be considered that the USV has a sufficiently safe collision avoidance distance. Therefore, when clustering dynamic objects, the neighborhood radius ε should be less than or equal to 4 times the SD.

[0059] When the heading difference between members of a cluster is too large, the USV may encounter multiple situations with members of the cluster. At this time, it is obviously not appropriate to avoid collision with them as a whole. If the speed difference between members of a cluster is too large, the distance between members of the cluster will gradually increase over time, and individual cluster members may break away from the cluster in the process of forming a collision situation. Obviously, the cluster collision avoidance model cannot be used for avoidance at this time. To this end, this embodiment imposes the following constraints on the neighborhood radius ε and the motion situation of cluster members during dynamic clustering of objects:

[0060] ε≤4SD (5)

[0061]

[0062] In the formula, and are the headings of the i-th object and the j-th object respectively; and are the speed of the i-th object and the speed of the j-th object respectively; E c is the heading difference threshold, E v is the speed difference threshold; Formula (5) indicates that the neighborhood radius ε should be less than or equal to 4 times the safety distance SD; Formula (6) indicates that the heading difference between any two members in the object cluster should be less than or equal to E c ; Formula (7) indicates that the speed difference between any two members of the object cluster should be less than or equal to E v .

[0063] Among them, E c and E v The value of is not fixed and can have different values ​​in different encounter situations. In navigation practice, the avoidance timing can be determined by considering both the distance of closest point of approach (DCPA) and the distance between the two parties when taking collision avoidance action (Distance, D). When the relationship between them satisfies equation (8), avoidance action should be taken.

[0064] DCPA / D<0.5 (8)

[0065] When avoiding a 10,000-ton ship cluster, the DCPA required to be maintained is relatively large. When the relative distance D between the two is large under the condition of satisfying equation (8), the collision avoidance process is relatively long. In order to prevent the target cluster from being too discrete, E c and E v The value of can be smaller. In the existing research literature, E is used to avoid collision with 10,000-ton ships. c Take 1°, E v The DCPA required for USV collision avoidance is relatively small, so the entire collision avoidance process is faster and the discrete change amplitude of the object cluster is relatively small. Therefore, it can be appropriately increased. After a large number of experimental analyses, E is set as follows in this embodiment: c Take 5°, E v Take 2kn.

[0066] Based on the constraints of the above dynamic object clustering, this embodiment improves the traditional DBSCAN algorithm and introduces a heading difference threshold E c and speed difference threshold E v The two parameters are used to detect the heading difference and speed difference between members in each cluster after clustering. If the heading difference and speed difference between members in the same cluster are both less than the set threshold, they are density-reachable and will be clustered into one cluster. The set of all objects in the same cluster can be expressed by formula (9):

[0067]

[0068] In the formula, represents the heading of the ith object, represents the heading of the jth object, represents the speed of the i-th object, Represents the speed of the jth object. Based on the improved DBSCAN algorithm, the object clusters that are clustered into the same cluster can be used to avoid collision as a whole using the cluster collision avoidance model.

[0069] S3: Calculate the collision avoidance area of ​​each object cluster based on the current coordinates of each object cluster.

[0070] The collision avoidance area of ​​the object cluster is to determine the avoidance range of the object cluster. In this embodiment, the calculation of the collision avoidance area is implemented using an existing algorithm.

[0071] In this embodiment, each object is first puffed to construct an object avoidance region model, and then the dense multiple object avoidance regions are covered with circular envelopes based on the circular envelope algorithm to determine the collision avoidance region of the object cluster, such as Figure 3 As shown, the dotted circle represents the avoidance range of the individual object, and the solid circle represents the cluster avoidance area after the circular envelope is covered, which is used as the collision avoidance area of ​​the object cluster.

[0072] When the USV avoids a cluster of objects, their position relationship should satisfy equation (10):

[0073] (x U -x C ) 2 +(y U -y C ) 2 ≥R C 2 (10)

[0074] In the formula, x U and U are the horizontal and vertical coordinates of the USV position respectively; x C and C are the horizontal and vertical coordinates of the center of the cluster security area; R C is the radius of the cluster security area, and its value can be calculated by formula (11).

[0075]

[0076] In the formula, x O and O are the horizontal and vertical coordinates of the target object respectively; SD is the safety distance.

[0077] S4: When the unmanned boat reaches a collision avoidance waypoint relative to a certain object cluster collision avoidance area, determine whether the unmanned boat's return route has more than one intersection with the collision avoidance area. If so, enter S5; otherwise, control the unmanned boat to return according to the return route.

[0078] S5: Determine the heading angle between the unmanned boat and the target cluster Is it satisfied? If yes, go to S6; otherwise, control the unmanned boat to keep the previous course and continue to travel until there is no more than one intersection between the unmanned boat's return route and the current collision avoidance area of ​​the object cluster, and then control the unmanned boat to return according to the return route; R represents the radius of the collision avoidance area of ​​the object cluster, The vertical component of the relative distance between the object cluster and the unmanned boat is represented. In this embodiment, the vertical component of the relative distance between the center point of the object cluster and the unmanned boat is used.

[0079] S6: Control the unmanned boat to deflect to the right and make it travel along the deflected route until there is no more than one intersection between the unmanned boat's return route and the current collision avoidance area of ​​the object cluster, and then control the unmanned boat to return along the return route.

[0080] The calculation formula of the deflection angle in this embodiment is:

[0081]

[0082] Where θ represents the deflection angle, v U represents the speed of the unmanned boat, v C Indicates the speed of the object cluster.

[0083] The traditional geometric collision avoidance algorithm determines the safe course of the unmanned boat to avoid the oncoming ship through geometric drawing based on the current position, heading, speed and other motion information of the unmanned boat and the oncoming ship. When using the traditional geometric collision avoidance algorithm to avoid a single target ship, the unmanned boat can calculate the collision avoidance waypoints between the unmanned boat and the target ship in the future (usually the right tangent point of the target ship's collision avoidance area) based on its own and the target ship's position, heading, speed and other motion information. When the unmanned boat reaches the collision avoidance waypoint, it completes the safe avoidance of the oncoming ship and then resumes sailing to the destination. Figure 4 As shown, the re-route route is the line connecting the initial position and the destination when re-route.

[0084] However, when using the geometric collision avoidance algorithm to avoid the cluster of objects, the unmanned boat uses the center of the cluster as the reference point for geometric construction to obtain relevant motion parameters, and uses it as a reference for judging collision risk and avoiding collision. Since there are multiple target ship members in the cluster of objects, if the unmanned boat has no collision risk with the center of the cluster of objects, it will resume the original route and continue to travel to the destination. Figure 5 As shown in the figure, the unmanned boat may pass through the middle of the object cluster and collide with some members of the object cluster. Therefore, when the unmanned boat uses the traditional geometric collision avoidance algorithm to avoid the object cluster, there are certain defects and it cannot meet the requirements of safe collision avoidance of the object cluster, so it should be improved.

[0085] This embodiment introduces a method for detecting the risk of re-navigation based on the navigation line of sight of the unmanned boat, that is, whether there is a risk of re-navigation collision between the unmanned boat and the object cluster according to whether there is more than one intersection between the ray of the unmanned boat's heading and the collision avoidance area of ​​the object cluster. When the unmanned boat travels to the collision avoidance waypoint and is ready to re-navigate, the intersection of the unmanned boat's re-navigation route and the collision avoidance area is determined. If there is only one intersection, the unmanned boat is tangent to the object cluster, the unmanned boat will not cross the collision avoidance area of ​​the object cluster, and the unmanned boat can safely re-navigate; if there are two intersections, the unmanned boat will cross the collision avoidance area of ​​the object cluster. At this time, the unmanned boat may be at risk of re-navigation collision, and the unmanned boat should not re-navigate immediately, but should be based on the heading angle between the unmanned boat and the object cluster. (The angle between the heading of the unmanned boat and the heading of the object cluster, the heading of the object cluster is the average of the headings of all the objects in the object cluster) to further determine which method to use. When it is detected that the unmanned boat and the object cluster have a risk of collision, if the unmanned boat continues to drive on the original heading, passes the object cluster, and has no intersection with the collision avoidance area of ​​the object cluster, the unmanned boat will continue to drive on the original heading; if the unmanned boat continues to drive on the original heading, it will inevitably enter the collision avoidance area of ​​the object cluster, and the unmanned boat will turn right to avoid entering the collision avoidance area of ​​the object cluster.

[0086] like Figure 6 The heading angle is shown If the above conditions are not met, the unmanned boat will continue to travel in the original direction after reaching the collision avoidance waypoint until the unmanned boat's return route has no more than one intersection with the current collision avoidance area of ​​the object cluster. Figure 7 The heading angle is shown When the above conditions are met, after the unmanned boat reaches the collision avoidance waypoint, if it continues to maintain the original course, it will inevitably enter the collision avoidance area of ​​the object cluster. At this time, the unmanned boat will deflect to the right according to the calculated right deflection angle to avoid entering the collision avoidance area of ​​the object cluster, thereby avoiding the risk of collision. The improved geometric collision avoidance algorithm effectively solves the problem of the unmanned boat returning to the collision avoidance waypoint after reaching the collision avoidance waypoint and colliding with individual members of the object cluster, and can be applied to the cluster collision avoidance problem occupying a large water space.

[0087] Simulation Analysis

[0088] 1. Dynamic object clustering simulation based on improved DBSCAN

[0089] To verify the effectiveness of the improved DBSCAN algorithm, this embodiment selects the distribution of ships near latitude 32°26′N and longitude 123°23′E at 1514 on August 12, 2024, as shown in Figure 8 As shown in Figure 1 (pictures and data are from Ship News Network), the specific motion status data of the ship is shown in Table 1. Based on the improved DBSCAN algorithm, a clustering simulation experiment is carried out on multiple dynamic objects in the red circle in the figure.

[0090] Table 1

[0091]

[0092] Based on the existing related research and the above analysis, this embodiment sets the heading difference threshold E c Take 5°, speed difference threshold E vSince any two objects with similar motion and location can be clustered into one object cluster, the avoidance complexity can be reduced when avoiding them. Therefore, Minpts is set to 2. The dynamic object clustering results based on the improved DBSCAN algorithm are as follows: Fig. 9 shown.

[0093] like Fig. 9 As shown in the first figure, when the neighborhood radius ε = 400m, since the distance between object 1, object 2 and object 3 is less than 400m, and the heading difference and speed difference between them do not exceed the limit value, they are clustered into one category. When avoiding collision, these three dynamic objects can be regarded as a cluster of objects for overall unified collision avoidance. As shown in the second figure, when the neighborhood radius ε = 500m, since the distance relationship between object 6, object 7 and object 8 is also satisfied and the heading difference and speed difference between them are less than the set threshold, they are clustered into one category and regarded as an object cluster. Fig. 9 As shown in the third figure, when the neighborhood radius ε = 800m, although the distance between objects 1, 2, 3, 4, and 5 is less than 800m, the speed difference between object 4 and other objects in the cluster exceeds the speed difference threshold E. v Therefore, it does not meet the clustering constraints and cannot be clustered into one category by the improved DBSCAN algorithm, so the cluster overall avoidance method cannot be used when avoiding collisions. Fig. 9 As shown in the fourth figure, when the neighborhood radius ε = 1000m, the relative distances of all objects except object 9 are less than 1000m. However, the speed differences between these objects also exceed E. v Therefore, it cannot be clustered into object clusters.

[0094] Through the simulation results, it can be found that the improved DBSCAN algorithm proposed in this embodiment can effectively cluster multiple objects with similar motion and positions into object clusters. When the unmanned boat encounters an object cluster, it can use the overall avoidance strategy to avoid it, so as to reduce the difficulty of collision avoidance decision-making.

[0095] 2. Object cluster collision avoidance simulation

[0096] For multiple dynamic objects that can be clustered into object clusters, this embodiment uses the MATLAB platform and combines the three encounter situations of head-on encounter, cross encounter, and overtaking to conduct comparative simulation verification on the traditional collision avoidance key ship method and the method proposed in this embodiment. The basic parameters of the unmanned boat prototype used in the simulation are shown in Table 2. In the simulation experiment, the safety distance SD of the object is taken as 100m, and the neighborhood radius ε is taken as 400m. Minpts Take 2, heading difference threshold E c Take 5°, speed difference threshold E v To take 2kn.

[0097] Table 2

[0098]

[0099] (1) Simulation verification of the encounter situation

[0100] A situation in which a USV and multiple objects meet each other is designed. Simulation experiments are carried out on the USV using the traditional key ship collision avoidance method and the embodiment of the present invention to avoid collision with dense multiple objects. The simulation data are shown in Table 3.

[0101] Table 3

[0102]

[0103] (a) USV collision avoidance simulation results based on the traditional collision avoidance key ship method in the encounter situation are shown in the figure. Fig.10 shown. Fig.10 During the navigation process, the USV will encounter multiple objects. It uses the geometric collision avoidance algorithm to avoid collisions with object 1, object 2, and object 3 in turn, and then drives to the destination. Fig.10 As shown in the first figure, the USV and object 1 are facing each other, and the USV turns right to avoid it. However, during the collision avoidance process, the USV is too close to object 5 and has invaded the safety area of ​​object 5. Fig.10 As shown in the second picture, when the USV resumed its flight, it encountered object 2 again and the USV turned right again to avoid collision with it. Fig.10 As shown in the third figure, after the USV completed the collision avoidance with object 2, it encountered object 3 again during the re-entry. The USV turned right again to avoid it, and then continued to sail towards the destination. During the entire navigation process, the USV completed three collision avoidance actions in succession, but the safety distance margin between the USV and object 1 was too small during the collision avoidance process, with the closest encounter distance being only 77m. The closest encounter distances between the USV and objects 2 and 3 were also less than the safe encounter distance of 100m, indicating that the USV could not safely avoid multiple objects during the collision avoidance process.

[0104] (b) The USV collision avoidance simulation results obtained based on the method of this embodiment in the case of a head-on encounter are as follows: Fig.11 shown. Fig.11 The USV clustered multiple objects into one object cluster based on the improved DBSCAN algorithm and avoided it as a whole. Fig.11 At the moment shown in the first figure, the USV detects a collision risk with the object cluster and turns right according to COLREGs to avoid the collision. Fig.11 At the moment shown in the second figure, the USV detects that there is a risk of collision if it resumes its flight at this time, so the USV turns to avoid it again until there is no risk of collision and resumes its flight towards the destination. When the collision avoidance model proposed in this embodiment is adopted, the closest encounter distance between the USV and each object is maintained at more than 100m, and the collision avoidance action of the USV is safer.

[0105] (2) Simulation verification of intersection encounter

[0106] A situation in which the USV and multiple objects meet each other is designed. Simulation experiments are carried out on the USV using the traditional key ship collision avoidance method and the embodiment of the present invention to avoid collision with dense multiple objects. The simulation data are shown in Table 4.

[0107] Table 4

[0108]

[0109] (a) USV collision avoidance simulation results based on the traditional collision avoidance key ship method in the case of crossing encounter Fig.12 shown. Fig.12 In the video, the USV successively formed a right crossing situation with object 6, object 2, object 3, and object 1. The USV made four turns to avoid the collision according to the collision avoidance rules. When sailing at sea, continuous and multiple avoidances may affect the difficulty of collision avoidance prediction for other objects and increase navigation risks.

[0110] (b) The USV collision avoidance simulation results based on the method of this embodiment in the case of crossing encounter are as follows: Fig.13 shown. Fig.13 In the simulation, the USV completed the overall avoidance of the cluster of objects with only one turn, avoiding the problem that the USV might cross and avoid between multiple dynamic objects and could not avoid them at a sufficiently safe distance, reducing the complexity of collision avoidance decision-making and improving collision avoidance efficiency.

[0111] (3) Simulation verification of overtaking situation

[0112] The USV is designed to overtake multiple dynamic objects during navigation. The simulation data is shown in Table 5.

[0113] Table 5

[0114]

[0115] (a) USV collision avoidance simulation results based on the traditional collision avoidance key ship method in the overtaking situation are shown in the figure. Fig.14 shown. Fig.14 In the figure, the USV overtook object 5. As the overtaking party, the USV turned left to give way to object 5 and passed through multiple objects. Then the USV overtook object 3 and turned left again to avoid it. Finally, the USV overtook object 1 again and turned left again to avoid it. The USV completed three collision avoidance actions and then continued to drive to the end.

[0116] (b) The USV collision avoidance simulation results based on the collision avoidance model of this embodiment in the overtaking situation are as follows: Fig.15 shown. Fig.15In the example, the USV detected that it was overtaking the cluster of objects. Since the collision avoidance path was shorter when the USV overtook the cluster of objects, the USV chose to turn right to avoid the cluster of objects. The USV only performed one collision avoidance operation to avoid the entire cluster of objects, which reduced the complexity of collision avoidance decision-making and improved the collision avoidance efficiency. The collision avoidance distance of the USV was greatly shortened, and the safe distance between the USV and the objects was also increased.

[0117] By sorting out the distance change diagrams between USV and dynamic objects in three encounter scenarios, we found that Fig.16 As shown, the three figures on the left are USV collision avoidance path diagrams based on the traditional collision avoidance key ship method, and the three figures on the right are USV collision avoidance path diagrams based on the collision avoidance model of this embodiment. By comparison, it is found that when the USV is approaching dense multi-object targets in a collision avoidance navigation situation, the traditional collision avoidance key ship method is adopted. In order to avoid collision, the USV may cross multiple targets multiple times and turn to avoid at close range. However, when avoiding collision based on the method of this embodiment, in three different encounter scenarios, the number of USV collision avoidance decisions is significantly reduced, and the length of the collision avoidance path is reduced. The collision avoidance path and collision avoidance time of the USV are calculated and counted, and it is found that Fig.17 As shown, the collision avoidance path and collision avoidance time of the USV based on the method of this embodiment (CCAMDG in the figure) in the three scenarios are shorter than those when the traditional collision avoidance method is used. It can be seen that the collision avoidance efficiency of the USV is higher when the method of this embodiment is used to avoid dense multiple objects with close navigation status.

[0118] In order to quantify the collision avoidance safety of the two collision avoidance methods, the changes in the encounter distances between the USV and each object in the three encounter scenarios were sorted out, such as Fig.19 As shown, the three figures on the left are the distance change diagrams between the USV and each object in three encounter scenarios based on the traditional collision avoidance key ship method, and the three figures on the right are the distance change diagrams between the USV and each object in three encounter scenarios based on the method of this embodiment. By comparison, it is found that when the USV avoids collision with dense multiple objects based on the traditional collision avoidance key ship method, in the three encounter scenarios, the closest encounter distance between the USV and individual objects is less than 100m, indicating that the USV cannot avoid the objects safely enough. When the method of this embodiment is used, the closest encounter distance between the USV and each object is greater than 100m, and the collision avoidance action of the USV is safer.

[0119] By calculating and sorting the sum of the closest encounter distances between the USV and each object, such as Fig.18 As shown, by comparison, it is found that the sum of the closest encounter distances between the USV based on the method of this embodiment and each target object in the three encounter scenarios is greater than the sum of the closest encounter distances based on the traditional collision avoidance key ship method, which shows that the collision avoidance safety of the USV using the collision avoidance model of this embodiment is improved.

[0120] Based on the simulation experimental results of dense multi-object collision avoidance in the above three different encounter scenarios, the following conclusions can be drawn:

[0121] (1) In the three different encounter scenarios, based on the traditional collision avoidance method, the USV may pass through multiple objects and needs to make multiple collision avoidance decisions. However, when the method of this embodiment is adopted, the USV treats the dense objects with close navigation status as a cluster of objects and avoids them as a whole, thus avoiding passing through multiple ships at close range. Fig.11 , Fig.13 and Fig.15 As shown in the figure, the number of collision avoidance decisions of USV is reduced, thereby improving navigation efficiency.

[0122] (2) Compared with the traditional collision avoidance method, the USV collision avoidance path length and collision avoidance time based on the method of this embodiment are reduced in the three encounter scenarios, such as Fig.17 As shown in the figure, in the encounter, cross encounter and overtaking scenarios, the USV collision avoidance path was reduced by 13.2%, 30.3% and 23.0% respectively, and the collision avoidance time was reduced by 13.8%, 29.8% and 22.9% respectively. It can be seen that the collision avoidance efficiency of the USV is improved when avoiding dense multiple objects with close navigation status based on the method of this embodiment.

[0123] (3) In the three encounter scenarios, based on the traditional collision avoidance method, the closest encounter distance between the USV and the target object is less than 100m, which is lower than the minimum safe encounter distance. However, when the collision avoidance model in the method of this embodiment is used, the closest encounter distance between the USV and each target object is greater than 100m, and the sum of the closest encounter distances with all targets is greater, such as Fig.18 In the encounter, cross encounter and overtaking scenarios, the sum of the closest encounter distances between the USV and the target object increased by 142.5%, 231.0% and 181.5% respectively. Therefore, the collision avoidance model in the embodiment method proposed in this paper has better collision avoidance safety for the USV when solving the collision avoidance problem of dense multi-target objects with close navigation status.

[0124] Based on all the above analysis, it can be concluded that, by using the method of this embodiment, for the collision avoidance problem of multiple dynamic objects with close and dense motion situations, the USV can safely complete the collision avoidance action for multiple dynamic objects, effectively reducing the complexity of collision avoidance decision-making, and the USV has higher collision avoidance efficiency and better safety.

[0125] The embodiment of the present invention introduces heading difference threshold and speed difference threshold parameters into the classic DBSCAN algorithm, clusters the dense dynamic objects around the unmanned boat that meet the clustering conditions into object clusters that need to be avoided, and uses the circular envelope algorithm to establish the collision avoidance area of ​​the object cluster; introduces the line-of-sight-based collision detection method into the geometric collision avoidance algorithm to achieve safe collision avoidance of the unmanned boat with the object cluster. Experiments show that the method of this embodiment can safely complete collision avoidance actions for multiple dynamic objects, while reducing the complexity of collision avoidance decisions and improving collision avoidance efficiency. It can be applied to avoidance decisions in dense traffic flow scenarios such as avoiding formation clusters and fishing boat clusters at sea.

[0126] Embodiment 2:

[0127] The present invention also provides an unmanned boat collision avoidance terminal device based on multiple collision avoidance objects, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiment of embodiment 1 of the present invention are implemented.

[0128] Further, as an executable solution, the unmanned boat collision avoidance terminal device based on multiple collision avoidance markers can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The unmanned boat collision avoidance terminal device based on multiple collision avoidance markers may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the composition structure of the unmanned boat collision avoidance terminal device based on multiple collision avoidance markers is only an example of an unmanned boat collision avoidance terminal device based on multiple collision avoidance markers, and does not constitute a limitation on the unmanned boat collision avoidance terminal device based on multiple collision avoidance markers. It may include more or less components than the above, or a combination of certain components, or different components. For example, the unmanned boat collision avoidance terminal device based on multiple collision avoidance markers may also include input and output devices, network access devices, buses, etc., and the embodiments of the present invention do not limit this.

[0129] Further, as an executable solution, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the unmanned boat collision avoidance terminal device based on multiple collision avoidance objects, and uses various interfaces and lines to connect various parts of the unmanned boat collision avoidance terminal device based on multiple collision avoidance objects.

[0130] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the unmanned boat collision avoidance terminal device based on multiple collision avoidance objects by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and an application required for at least one function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0131] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method in the embodiment of the present invention are implemented.

[0132] If the module / unit integrated in the unmanned boat collision avoidance terminal device based on multiple collision avoidance objects is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory) and software distribution medium, etc.

[0133] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.

Claims

1. A collision avoidance method for an unmanned boat based on multiple collision avoidance targets, characterized in that: The following steps are involved: S1: Collect the motion information of all moving objects in the sea area near the unmanned boat; S2: Cluster all moving objects based on the collected motion information to obtain multiple object clusters; S3: Calculating the collision avoidance area of ​​each object cluster based on the current coordinates of each object cluster included in each object cluster; S4: When the unmanned boat reaches a collision avoidance waypoint relative to a certain object cluster collision avoidance area, determine whether the unmanned boat's return route has more than one intersection with the collision avoidance area. If so, proceed to S5; otherwise, control the unmanned boat to return according to the return route. S5: Determine the heading angle between the unmanned boat and the target cluster Is it satisfied? If yes, go to S6; otherwise, control the unmanned boat to keep the previous course and continue to travel until there is no more than one intersection between the unmanned boat's return route and the current collision avoidance area of ​​the object cluster, and then control the unmanned boat to return according to the return route; R represents the radius of the collision avoidance area of ​​the object cluster, The vertical component representing the relative distance between the target cluster and the unmanned boat; S6: Control the unmanned boat to deflect to the right and make it travel along the deflected route until there is no more than one intersection between the unmanned boat's return route and the current collision avoidance area of ​​the object cluster, and then control the unmanned boat to return along the return route.

2. The unmanned boat collision avoidance method based on multiple collision avoidance targets according to claim 1 is characterized in that: In step S2, all moving objects are clustered using the improved DBSCAN algorithm; the improved DBSCAN algorithm adds speed difference constraints and heading difference constraints on the basis of the traditional DBSCAN algorithm, that is, the heading difference between any two objects in all objects belonging to the same object cluster is less than the heading difference threshold, and the speed difference between any two objects is less than the speed difference threshold.

3. The unmanned boat collision avoidance method based on multiple collision avoidance targets according to claim 1 is characterized in that: When clustering all moving objects using the improved DBSCAN algorithm, a neighborhood radius constraint is included, that is, the neighborhood radius ε of any two objects in the same object cluster should be less than or equal to 4 times the safety distance of the objects.

4. The unmanned boat collision avoidance method based on multiple collision avoidance targets according to claim 1 is characterized in that: When step S6 controls the unmanned boat to deflect to the right, the calculation formula of the deflection angle is: Where θ represents the deflection angle, v U represents the speed of the unmanned boat, v C Indicates the speed of the object cluster.

5. An unmanned boat collision avoidance terminal device based on multiple collision avoidance markers, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 4 when executing the computer program.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images