Unmanned boat obstacle avoidance method, device, computer equipment and storage medium

Abstract

The present application relates to an unmanned boat obstacle avoidance method, device, computer equipment, storage medium and computer program product, wherein the method constructs a bow coordinate system encounter model based on the position information and obstacle information of the unmanned boat; and converts the obstacle information into the relative encounter parameters between the unmanned boat and the obstacle; and simultaneously determines the collision risk range between the unmanned boat and the obstacle; when the obstacle is located in the collision risk range, determines the collision risk value of the obstacle based on the relative encounter parameters; and performs obstacle avoidance control on the unmanned boat. The scheme of the present application constructs a bow coordinate system encounter model based on the position information and obstacle information of the unmanned boat, thereby performing calculations in the bow coordinate system encounter model to obtain relative encounter parameters, and based on the relative encounter parameters, identifies the collision risk range and calculates the collision risk value, and finally realizes the obstacle avoidance control of the unmanned boat, which can effectively improve the accuracy of the unmanned boat's obstacle avoidance and improve the safety of the unmanned boat.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an unmanned boat obstacle avoidance method, device, computer equipment, storage medium and computer program product. Background Art

[0002] With the development of computer technology and shipbuilding technology, the application scope of unmanned boats on the water is also expanding. Unmanned boats, also known as unmanned ships, are fully automatic surface robots that can navigate on the water according to preset tasks without remote control, relying on precise satellite positioning and self-sensing. They can be used in surveying and mapping, hydrology and water quality monitoring and other fields. Unmanned boats are prone to encounter obstacles during navigation, so obstacle avoidance algorithms are extremely important for unmanned boats.

[0003] At present, the traditional local obstacle avoidance algorithm of unmanned boats is to unify the information of obstacles and unmanned boats in the geodetic coordinate system for collision analysis, and to determine the risk of collision based on the relative position relationship between the unmanned boat and the obstacle. The obstacle avoidance decision will inevitably be judged based on the position relationship. The raw data that the obstacle detection module can obtain is the relative position, and the calculated speed and distance are also relative values, so it is impossible to effectively estimate the obstacle avoidance, which affects the accuracy of obstacle avoidance. Summary of the invention

[0004] Based on this, it is necessary to provide an unmanned boat obstacle avoidance method, device, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of unmanned boat obstacle avoidance in response to the above technical problems.

[0005] In a first aspect, the present application provides an unmanned boat obstacle avoidance method. The method comprises:

[0006] Constructing a bow coordinate system encounter model based on the position information of the unmanned boat and the obstacle information, wherein the obstacle information is detected by the obstacle detection module of the unmanned boat;

[0007] The obstacle information is converted into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model;

[0008] Determining a collision risk range between the unmanned boat and the obstacle based on the relative encounter parameter;

[0009] When the obstacle is located in the collision risk range, determining a collision risk value of the obstacle based on the relative encounter parameter;

[0010] Obstacle avoidance control is performed on the unmanned boat based on the collision risk value.

[0011] In one embodiment, the relative encounter parameters include a relative position angle, a relative speed angle, a relative distance, and a relative speed absolute value;

[0012] The step of converting the obstacle information into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model includes:

[0013] Based on the obstacle information, determining relative position information and relative speed information of the obstacle relative to the unmanned boat;

[0014] The relative position angle and the relative distance are determined based on the relative position information, and the relative speed angle and the relative speed absolute value are determined based on the relative speed information.

[0015] In one embodiment, determining the collision risk range between the unmanned boat and the obstacle based on the relative encounter parameter includes:

[0016] Determining an obstacle mirror point of the obstacle relative to the bow coordinate system based on the relative encounter parameter;

[0017] A rectangular area enclosed by the obstacle and the obstacle mirror point is determined as a collision risk range between the unmanned boat and the obstacle.

[0018] In one embodiment, the collision risk value includes an angle dimension collision risk value and a distance dimension collision risk value;

[0019] When the obstacle is located in the collision risk range, determining the collision risk value of the obstacle based on the relative encounter parameter includes:

[0020] When the obstacle is located in the collision risk range, identifying an obstacle avoidance risk area corresponding to the obstacle;

[0021] Based on the identified obstacle avoidance danger zone and the relative encounter parameter, a collision danger value in an angle dimension and a collision danger value in a distance dimension are determined.

[0022] In one embodiment, the relative encounter parameters include a relative position angle, a relative speed angle, a relative distance, and a relative speed absolute value;

[0023] The determining of the collision risk value in the angle dimension and the collision risk value in the distance dimension based on the obstacle avoidance danger zone and the relative encounter parameter comprises:

[0024] Determine the angle dimension collision risk value formula and the distance dimension collision risk value formula corresponding to the identified obstacle avoidance danger zone;

[0025] Determine an angle dimension collision risk value based on the relative position angle, the relative speed angle and the angle dimension collision risk value formula;

[0026] The distance dimension collision risk value is determined based on the relative position angle, the relative speed angle, the relative distance, the absolute value of the relative speed and the distance dimension collision risk value formula.

[0027] In one embodiment, the performing obstacle avoidance control processing on the unmanned boat based on the collision risk value includes:

[0028] Determining an obstacle avoidance angular velocity control amount based on the maximum angular velocity value of the unmanned boat and the angular dimension collision risk value;

[0029] Determining an obstacle avoidance acceleration control amount based on the maximum acceleration value of the unmanned boat and the distance dimension collision risk value;

[0030] Obstacle avoidance control processing is performed on the unmanned boat based on the obstacle avoidance angular velocity control amount and the obstacle avoidance acceleration control amount.

[0031] In a second aspect, the present application also provides an unmanned boat obstacle avoidance device. The device comprises:

[0032] A model building module, used to build a bow coordinate system encounter model based on the position information of the unmanned boat and the obstacle information, wherein the obstacle information is detected by the obstacle detection module of the unmanned boat;

[0033] A parameter conversion module, used to convert the obstacle information into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model;

[0034] A range identification module, used to determine a collision risk range between the unmanned boat and the obstacle based on the relative encounter parameter;

[0035] a risk value identification module, configured to determine a collision risk value of the obstacle based on the relative encounter parameter when the obstacle is located in the collision risk range;

[0036] The obstacle avoidance control module is used to perform obstacle avoidance control processing on the unmanned boat based on the collision risk value.

[0037] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0038] Constructing a bow coordinate system encounter model based on the position information of the unmanned boat and the obstacle information, wherein the obstacle information is detected by the obstacle detection module of the unmanned boat;

[0039] The obstacle information is converted into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model;

[0040] Determining a collision risk range between the unmanned boat and the obstacle based on the relative encounter parameter;

[0041] When the obstacle is located in the collision risk range, determining a collision risk value of the obstacle based on the relative encounter parameter;

[0042] Obstacle avoidance control is performed on the unmanned boat based on the collision risk value.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0044] Constructing a bow coordinate system encounter model based on the position information of the unmanned boat and the obstacle information, wherein the obstacle information is detected by the obstacle detection module of the unmanned boat;

[0045] The obstacle information is converted into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model;

[0046] Determining a collision risk range between the unmanned boat and the obstacle based on the relative encounter parameter;

[0047] When the obstacle is located in the collision risk range, determining a collision risk value of the obstacle based on the relative encounter parameter;

[0048] Obstacle avoidance control is performed on the unmanned boat based on the collision risk value.

[0049] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0050] Constructing a bow coordinate system encounter model based on the position information of the unmanned boat and the obstacle information, wherein the obstacle information is detected by the obstacle detection module of the unmanned boat;

[0051] The obstacle information is converted into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model;

[0052] Determining a collision risk range between the unmanned boat and the obstacle based on the relative encounter parameter;

[0053] When the obstacle is located in the collision risk range, determining a collision risk value of the obstacle based on the relative encounter parameter;

[0054] Obstacle avoidance control is performed on the unmanned boat based on the collision risk value.

[0055] The above-mentioned unmanned boat obstacle avoidance method, device, computer equipment, storage medium and computer program product, wherein the method constructs a bow coordinate system encounter model based on the position information and obstacle information of the unmanned boat, and the obstacle information is detected by the obstacle detection module of the unmanned boat; through the bow coordinate system encounter model, the obstacle information is converted into the relative encounter parameter between the unmanned boat and the obstacle; the collision risk range between the unmanned boat and the obstacle is determined based on the relative encounter parameter; when the obstacle is located in the collision risk range, the collision risk value of the obstacle is determined based on the relative encounter parameter; the unmanned boat is subjected to obstacle avoidance control processing based on the collision risk value. The scheme of the present application constructs a bow coordinate system encounter model based on the position information and obstacle information of the unmanned boat during the obstacle avoidance control process, thereby calculating the relative encounter process between the unmanned boat and the obstacle in the bow coordinate system encounter model, obtaining the relative encounter parameter, and identifying the collision risk range and calculating the collision risk value based on the relative encounter parameter, and finally controlling the unmanned boat to avoid the obstacle based on the determined collision risk value, which can effectively improve the accuracy of the unmanned boat's obstacle avoidance and improve the safety of the unmanned boat. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 A diagram showing an application environment of an unmanned boat obstacle avoidance method in one embodiment;

[0058] Figure 2 A schematic diagram of a flow chart of an unmanned boat obstacle avoidance method in one embodiment;

[0059] Figure 3 A schematic diagram of a model of an unmanned boat encountering an obstacle in one embodiment;

[0060] Figure 4 is a schematic diagram of an obstacle avoidance danger range in one embodiment;

[0061] Figure 5 A schematic diagram of dividing an obstacle avoidance danger zone in one embodiment;

[0062] Figure 6is a schematic diagram of a possible collision model of area 1 in one embodiment;

[0063] Figure 7 is a schematic diagram of a possible collision model of area 2 in one embodiment;

[0064] Figure 8 is a schematic diagram of a possible collision model of area 3 in one embodiment;

[0065] Fig. 9 is a schematic diagram of a possible collision model of area 4 in one embodiment;

[0066] Fig.10 is a structural block diagram of an unmanned boat obstacle avoidance device in one embodiment;

[0067] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] The unmanned boat obstacle avoidance method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the unmanned boat controller 102 communicates with the server 104 through the network. The data storage system can store the data required by the server 104 for obstacle avoidance control. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The unmanned boat controller 102 can send the position information and obstacle information of the unmanned boat to the server 104 to perform obstacle avoidance control through the server 104. After receiving the position information and obstacle information of the unmanned boat, the server 104 will construct a bow coordinate system encounter model based on the position information and obstacle information of the unmanned boat, and the obstacle information is detected by the obstacle detection module of the unmanned boat; through the bow coordinate system encounter model, the obstacle information is converted into the relative encounter parameters of the unmanned boat and the obstacle; based on the relative encounter parameters, the collision risk range of the unmanned boat and the obstacle is determined; when the obstacle is in the collision risk range, the collision risk value of the obstacle is determined based on the relative encounter parameters; based on the collision risk value, the unmanned boat is subjected to obstacle avoidance control. Among them, the server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0070] In an exemplary embodiment, Figure 2 As shown, a method for avoiding obstacles in an unmanned boat is provided. Figure 1The server 104 in the example is used for explanation. Of course, the obstacle avoidance method of the unmanned boat can also be directly applied to the unmanned boat controller on the unmanned boat, and the obstacle avoidance control processing is realized by the unmanned boat itself. When the obstacle avoidance method is realized by the server 104, the following steps are included:

[0071] Step 201: construct a bow coordinate system encounter model based on the position information of the unmanned boat and the obstacle information, where the obstacle information is detected by the obstacle detection module of the unmanned boat.

[0072] Among them, the position information of the unmanned boat refers to the location of the unmanned boat itself, which can be identified by the positioning module of the unmanned boat, and the obstacle information is detected by the relevant sensors on the obstacle detection module of the unmanned boat, including the relative position information and relative speed information of the obstacle. The bow coordinate system encounter model is a coordinate system established by considering the relative relationship parameters between the unmanned boat and the obstacle in the same coordinate system.

[0073] Specifically, the unmanned boat includes a positioning module and an obstacle detection module, wherein the positioning module is used to locate the position of the unmanned boat and report it to the server 104, while the obstacle detection module is used to detect various obstacles encountered by the unmanned boat during navigation through sensors. After the unmanned boat detects the obstacle information, the current position information of the unmanned boat and the obstacle information can be sent to the server 104 together, so that the server 104 can perform unmanned obstacle avoidance calculations to achieve obstacle avoidance. When the server 104 receives the position information and obstacle information of the unmanned boat, since the obstacle information output by the obstacle detection module is three-dimensional space information, in order to describe the obstacle as realistically as possible and facilitate the analysis of local obstacle avoidance decisions, the unmanned boat and the obstacle are projected onto a two-dimensional plane for description. At the same time, in the process of local collision avoidance, the relative relationship between the unmanned boat and the obstacle will change all the time. To analyze the local obstacle avoidance problem of the unmanned boat, it is necessary to consider the relative relationship parameters between the unmanned boat and the obstacle in the same coordinate system. Therefore, it is possible to establish the following Figure 3 The bow coordinate system shown in the figure meets the model, where the position of the unmanned boat is the origin. Obtain the relative position information S of the obstacle through the obstacle detection module o (X o ,y o ) and relative speed information and and is the length and width of the obstacle and the unmanned boat in the two-dimensional plane.

[0074] Step 203: The obstacle information is converted into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model.

[0075] Among them, the relative encounter parameters between the unmanned boat and the obstacle refer to various parameter information involved in the unmanned boat's obstacle encounter process, which may include relative position angle, relative speed angle, relative distance and relative speed absolute value, etc.

[0076] Specifically, after establishing the encounter model of the bow coordinate system, the obstacle information relative to the unmanned boat can be converted into the relative encounter parameters between the unmanned boat and the obstacle based on the constructed encounter model of the bow coordinate system. The relative encounter parameters specifically include the relative speed parameters of the obstacle and the relative position parameters of the obstacle. The detected obstacle information can be directly converted into the relative encounter parameters between the unmanned boat and the obstacle through the corresponding calculation formula, so as to perform the subsequent unmanned boat obstacle avoidance calculation.

[0077] Step 205: determine the collision risk range between the unmanned boat and the obstacle based on the relative encounter parameter.

[0078] Specifically, various relative encounter parameters will affect the collision risk of the unmanned boat. For example, the relative position angle θ in the relative encounter parameters represents the relative position direction relationship between the obstacle and the unmanned boat at the current moment. The constructed encounter model is based on the bow coordinate system, so the bow direction is not necessarily the actual navigation direction of the unmanned boat. As long as the obstacle is not on the originally planned global route, the relative position angle θ does not directly affect the collision safety of the unmanned boat. However, the local obstacle avoidance of the unmanned boat is achieved by changing the bow direction, so θ can also represent the change in the heading angle under the obstacle avoidance decision. And the relative speed angle It represents the relative motion direction of the obstacle and the unmanned boat at the current moment. When its value is ±π / 2, the obstacle may pass infinitely far from the head or tail of the unmanned boat; when its value is π or 0, it indicates that the obstacle and the unmanned boat are in a relatively parallel motion state. When the unmanned boat maintains these two states, it will definitely not collide with the obstacle. The safety of the unmanned boat is the highest in these two cases. When , it indicates the relative speed angle of the obstacle Pointing to the center of mass of the unmanned boat, at this time, the unmanned boat and the obstacle are in a relative motion relationship. If the unmanned boat maintains the current running state, it will inevitably collide with the obstacle at a certain moment in the future. The collision risk of the unmanned boat is the greatest in this case. As for the relative distance d, the relative distance is a very intuitive state quantity for evaluating the collision risk, and its value often determines whether the unmanned boat has a collision risk. The safety of the unmanned boat is certainly proportional to the d value to a certain extent, that is, the larger the D value, the stronger the safety of the unmanned boat, but this does not mean that the unmanned boat is unsafe when the D value is very small. When the running trajectory of the obstacle is parallel to the running trajectory of the unmanned boat, the two will still not collide. Therefore, the risk assessment in the distance dimension still needs to refer to the angle and the rate of change of the angle. As for the absolute value of the relative speed D′, it represents the speed of the obstacle relative to the unmanned boat. Its numerical value does not determine whether the unmanned boat has a collision risk, but it affects the time of encounter. It can be used as a reference for global constraints to avoid the algorithm from falling into a local optimal solution. Therefore, the impact of each parameter value on the collision risk of the unmanned boat can be considered, and a universal collision risk range can be established after comprehensive consideration to estimate the collision risk range.

[0079] Step 207: When the obstacle is located in the collision risk range, a collision risk value of the obstacle is determined based on the relative encounter parameter.

[0080] Step 209: performing obstacle avoidance control on the unmanned boat based on the collision risk value.

[0081] Among them, the collision risk value in the angle dimension represents the ideal weight for the unmanned boat to achieve obstacle avoidance by simply changing the heading angle while maintaining the current speed. The collision risk value in the distance dimension represents the ideal weight for achieving obstacle avoidance by changing the speed of the unmanned boat while maintaining the current heading.

[0082] Specifically, in order to directly control the obstacle avoidance action of the unmanned boat, the angular velocity and acceleration that control the local obstacle avoidance of the unmanned boat are mapped to the collision risk values ​​of the angle dimension and the distance dimension respectively. The obstacle avoidance strategy is combined with the collision risk value, and the obstacle collision risk values ​​of the two dimensions are quantified within the collision risk range, thereby obtaining the optimal obstacle avoidance output value. When it is determined that the obstacle is still within the collision risk range during the obstacle avoidance process, the collision risk value of the obstacle can be determined based on the relative encounter parameters, and then the obstacle avoidance control parameters of the unmanned boat during the obstacle avoidance process are determined by the collision risk value to complete the obstacle avoidance control processing of the unmanned boat.

[0083] The above-mentioned unmanned boat obstacle avoidance method, wherein the method constructs a bow coordinate system encounter model based on the position information and obstacle information of the unmanned boat, and the obstacle information is detected by the obstacle detection module of the unmanned boat; through the bow coordinate system encounter model, the obstacle information is converted into the relative encounter parameters of the unmanned boat and the obstacle; the collision risk range of the unmanned boat and the obstacle is determined based on the relative encounter parameters; when the obstacle is located in the collision risk range, the collision risk value of the obstacle is determined based on the relative encounter parameters; the unmanned boat is subjected to obstacle avoidance control based on the collision risk value. The scheme of the present application constructs a bow coordinate system encounter model based on the position information and obstacle information of the unmanned boat during the obstacle avoidance control process, thereby calculating the relative encounter process of the unmanned boat and the obstacle in the bow coordinate system encounter model, obtaining the relative encounter parameters, and identifying the collision risk range and calculating the collision risk value based on the relative encounter parameters, and finally controlling the unmanned boat to avoid obstacles based on the determined collision risk value, which can effectively improve the accuracy of the unmanned boat's obstacle avoidance and improve the safety of the unmanned boat.

[0084] In an exemplary embodiment, the relative encounter parameters include a relative position angle, a relative speed angle, a relative distance, and a relative speed absolute value. Step 203 includes: determining the relative position information and relative speed information of the obstacle relative to the unmanned boat based on the obstacle information; determining the relative position angle and relative distance based on the relative position information, and determining the relative speed angle and relative speed absolute value based on the relative speed information.

[0085] For example, after the obstacle information is determined, the obstacle information can be analyzed to obtain the relative position information S of the currently detected obstacle relative to the unmanned boat. o (X o ,y o ) and relative speed information After determining the relative position information and relative speed information, various relative encounter parameters can be calculated based on the relative position information. Figure 3 The bow coordinate system shown in the figure encounters the model, and the relative velocity parameters of the obstacle are and d′ respectively represent the relative velocity angle and absolute value of the relative velocity of the obstacle. The specific calculation formula is:

[0086]

[0087]

[0088] The relative position parameters of the obstacle (θ, d), θ and d represent the relative position angle of the obstacle and the encounter distance between the obstacle and the unmanned boat, respectively. The specific calculation formula is:

[0089] θ=atan2(yo ,x o )

[0090]

[0091] in, and is the length and width of the obstacle and the unmanned boat in the two-dimensional plane. The relative position angle θ has a great impact on the navigation safety of the unmanned boat, especially when the obstacle is located in front of the unmanned boat. Here, θ also needs to determine whether the obstacle frame occupies the Y axis of the bow coordinate system. When it occupies, θ is equal to 0. In this embodiment, by determining the relative position information and relative speed information of the obstacle relative to the unmanned boat, and then calculating various relative encounter parameters, the accuracy of the relative encounter parameter calculation can be effectively guaranteed.

[0092] In an exemplary embodiment, step 205 includes: determining the obstacle mirror point of the obstacle relative to the bow coordinate system based on the relative encounter parameter; and determining the rectangular area enclosed by the obstacle and the obstacle mirror point as the collision risk range between the unmanned boat and the obstacle.

[0093] Among them, the obstacle mirror point relative to the bow coordinate system specifically includes the obstacle mirror point relative to the X-axis of the bow coordinate system, the obstacle mirror point relative to the Y-axis of the bow coordinate system, and the obstacle mirror point relative to the origin of the bow coordinate system. Through these three mirror points and the original obstacle point, a rectangular area can be enclosed, which is the collision risk range between the unmanned boat and the obstacle.

[0094] For example, considering that unmanned boats are often in a state of uniform motion for a long time during operation, as long as an obstacle is found to be in a collision situation with the unmanned boat, regardless of the relative distance, it means that the risk of collision is the greatest at this moment. The unmanned boat should immediately respond to avoid the obstacle, adjust the course and speed, and prompt Deflection is performed in the direction of 0, π or ±π / 2. Therefore, the rectangular range drawn by the obstacle and its mirror image relative to the coordinate axis is the collision risk range. If it exceeds this range, it means that the obstacle does not pose a threat to the navigation of the unmanned boat, such as Figure 4 As shown in the figure, the obstacle is within the collision risk range, which means that the relative velocity angle of the obstacle The relative position angle θ satisfies the following formula in the quadrant corresponding to the mirror image of the origin:

[0095]

[0096] However, the collision risk range of each obstacle is different, and the four vertices represent the possible relative positions of the obstacles. Figure 4The two diagonal lines in represent the situation with the highest collision risk, that is, the obstacle and the unmanned boat are in a situation of encountering each other. In this embodiment, the rectangular area surrounded by the obstacle and the obstacle mirror point is the collision risk range, so that the unmanned boat is controlled within the collision risk range.

[0097] In one embodiment, the collision risk value includes an angle dimension collision risk value and a distance dimension collision risk value. Step 207 includes: when the obstacle is within the collision risk range, identifying the obstacle avoidance risk area corresponding to the obstacle; and determining the angle dimension collision risk value and the distance dimension collision risk value based on the identified obstacle avoidance risk area and the relative encounter parameter.

[0098] Among them, the collision risk value in the angle dimension represents the ideal weight for the unmanned boat to achieve obstacle avoidance by simply changing the bow angle while maintaining the current speed. The collision risk value in the distance dimension represents the ideal weight for obstacle avoidance by changing the speed of the unmanned boat while maintaining the current heading. The obstacle avoidance danger zone refers to dividing the complete collision risk range into multiple different obstacle avoidance danger zones according to the difference in obstacle avoidance directions. After the split, different obstacle avoidance danger zones correspond to different obstacle avoidance directions, so the collision risk values ​​in the angle dimension and the collision risk values ​​in the distance dimension will also be different.

[0099] For example, during the research process, the applicant found that different areas where obstacles are within the collision range have different effects on the obstacle avoidance strategy of the unmanned boat, that is, the areas on both sides of the diagonal represent different obstacle avoidance directions. Therefore, in order to better quantify the collision risk value of the obstacle so that its value can directly reflect the obstacle avoidance direction and speed of the unmanned boat, the collision risk value in the angle dimension and the collision risk value in the distance dimension are determined based on the identified obstacle avoidance risk area and relative encounter parameters. In one embodiment. As Figure 5 As shown, the collision risk area can be divided into 8 sub-areas with rectangular coordinate axes and diagonals as boundaries. Then, the calculation of the collision risk value of the angle dimension and the collision risk value of the distance dimension is realized in the sub-area. In this embodiment, by identifying the obstacle avoidance risk area corresponding to the obstacle and then calculating the collision risk value, the accuracy and efficiency of the risk value calculation can be effectively guaranteed, thereby improving the obstacle avoidance effect of the unmanned boat.

[0100] In an exemplary embodiment, the relative encounter parameters include a relative position angle, a relative speed angle, a relative distance, and a relative speed absolute value. Based on the obstacle avoidance danger zone and the relative encounter parameters, determining the angle dimension collision risk value and the distance dimension collision risk value includes: determining the angle dimension collision risk value formula and the distance dimension collision risk value formula corresponding to the identified obstacle avoidance danger zone; determining the angle dimension collision risk value based on the relative position angle, the relative speed angle, and the angle dimension collision risk value formula; determining the distance dimension collision risk value based on the relative position angle, the relative speed angle, the relative distance, the relative speed absolute value, and the distance dimension collision risk value formula.

[0101] Exemplarily, different angle dimension collision hazard value formulas and distance dimension collision hazard value formulas correspond to different obstacle avoidance danger zones. Therefore, when calculating the hazard value, the angle dimension collision hazard value formula and the distance dimension collision hazard value formula corresponding to the identified obstacle avoidance danger zone can be determined first. Then, the hazard values ​​of two different dimensions are determined separately, that is, the angle dimension collision hazard value is determined based on the relative position angle, the relative speed angle, and the angle dimension collision hazard value formula; the distance dimension collision hazard value is determined based on the relative position angle, the relative speed angle, the relative distance, the absolute value of the relative speed, and the distance dimension collision hazard value formula.

[0102] In one embodiment, for Figure 5 The obstacle avoidance danger range division scheme shown in the figure, when the relative position angle θ∈(-π / 2,0] of the obstacle appears in the fourth quadrant within the collision danger range, its relative speed angle May point to area 1 or area 2. When the value belongs to area 1, it means that the obstacle will pass in front of the bow of the unmanned boat. Since the tail of the obstacle may be blocked and cannot be detected completely, and the unmanned boat cannot predict whether the obstacle will move away from the unmanned boat, the unmanned boat is not in an absolutely safe state at this time, and there is a possibility of collision with the obstacle. Figure 6 As shown, in order to ensure the navigation safety of the unmanned boat, the unmanned boat should slow down to the left to avoid obstacles. Deflect in the direction of π / 2, and finally bypass the tail of the obstacle. At this time, the possibility of the tail of the obstacle colliding with the bow of the boat is considered. First, the distance and speed parallel to the bow direction are used to evaluate the encounter time, that is:

[0103]

[0104] In the current situation, the optimal obstacle avoidance strategy for the unmanned boat is to turn left, so the collision risk value in the angle dimension is mapped to the (-1, 0) interval, as shown in the following formula:

[0105]

[0106] In the formula, C θ1 is the collision risk value of the 1-area angle dimension, and its positive and negative signs represent the obstacle avoidance direction of the unmanned boat, that is, C θ1 When it is greater than 0, it means the unmanned boat turns right. θ1 When it is less than 0, it means that the unmanned boat turns left. The speed increase and decrease is mapped to the collision risk in the distance dimension. According to the collision analysis, the evaluation of the distance dimension needs to consider the influence of distance and angle parameters on the acceleration control of the unmanned boat. Changing the speed as the control purpose can help understand the control of the unmanned boat to drive obstacles. The direction is away from the direction pointing to the center of mass of the unmanned boat, and does not directly change d or d′. When the relative velocity vector of the obstacle is in area 1, the distance dimension collision risk value when the encounter time t1 is 0 can be mapped to -1, and the distance dimension collision risk value when t1 is infinite can be mapped to 0, which is defined by the following formula:

[0107]

[0108] In the formula, C T1 is the collision risk value of the distance dimension of the 1 area, and its positive and negative signs represent the addition and subtraction of the speed of the unmanned boat, that is, C T1 When it is less than 0, it means the speed of the unmanned boat is decreasing, that is, the deceleration; C T1 When it is greater than 0, it represents the speed increment of the unmanned boat, that is, the acceleration. The actual obstacle avoidance trajectory of the unmanned boat is corrected by the local obstacle avoidance system, so that the relative position of the obstacle is transferred from the fourth quadrant to the first quadrant. When the obstacle leaves the defined collision danger zone, the navigation control module of the unmanned boat will take over the control and drive the unmanned boat to deflect towards the predetermined route.

[0109] Similarly, when the relative velocity vector of the obstacle is in region 2, the obstacle has a tendency to hit the side of the boat from the front, such as Figure 7 To avoid collision, the unmanned boat should slow down and sail to the right, i.e. Deflect in the direction of π, and eventually the obstacle will bypass the rear of the unmanned boat.

[0110] The evaluation of the encounter time is obtained by the following formula, which is obtained from the distance and speed perpendicular to the bow direction.

[0111]

[0112] At this time, the collision risk value of the obstacle in the angle dimension and distance dimension is expressed as follows:

[0113]

[0114] When the relative position angle of the obstacle is θ∈(-π,-π / 2], it appears in the third quadrant of the collision risk range, and the relative velocity vector is in area 3, the obstacle has a tendency to hit the side of the boat from the rear, such as Figure 8 The unmanned boat should accelerate to the right to avoid obstacles. Deflect in the direction of 0, and finally let the obstacle pass parallel to the left. The corresponding collision risk value is expressed as follows:

[0115]

[0116] When the relative velocity vector of the obstacle is in region 4, the obstacle has a tendency to hit the stern of the boat from behind, e.g. Fig. 9 shown.

[0117] The unmanned boat should accelerate to the left to avoid obstacles. Deflect in the direction of π / 2, and finally let the obstacle bypass the rear of the unmanned boat. The corresponding collision risk value is expressed as follows:

[0118]

[0119] Similarly, the calculation method of collision risk value in other areas can be obtained. When the relative position angle of the obstacle is θ∈(π / 2,π], the calculation formula of collision risk value of its relative velocity vector in areas 5 and 6 refers to the following formulas, where C θ5 Indicates the collision risk value of the angle dimension of the 5-zone, C T5 Indicates the collision risk value of the record dimension of the 5-region. θ6 Indicates the collision risk value of the angle dimension of the 6-zone, C T6 Indicates the collision risk value of the record dimension of the 6-region.

[0120]

[0121]

[0122] When the obstacle relative position angle θ∈(0,π / 2], the collision risk value of its relative velocity vector in the 7 and 8 regions is expressed as follows. θ7 Indicates the collision risk value of the angular dimension of the 7-zone, C T7 Indicates the collision risk value of the record dimension of the 7-region. θ8 Indicates the collision risk value of the angle dimension of the 8-zone, C T8 Indicates the collision risk value of the record dimension in 8 regions.

[0123]

[0124]

[0125] Summarizing the above analysis and expressions, it is believed that when an obstacle enters the collision risk range, it poses a threat to the navigation safety of the unmanned boat. The obstacle avoidance system of the unmanned boat begins to intervene, and the collision risk value combined with the obstacle avoidance strategy is defined. The magnitude of the angular velocity is mapped to the collision risk value C in the angle dimension. θ The magnitude of acceleration is mapped to the collision risk value C in the distance dimension. T The specific calculation expressions of the two are shown in the following formula.

[0126]

[0127]

[0128] In this embodiment, the collision risk value formula in the angle dimension and the collision risk value formula in the distance dimension are first determined by determining the obstacle avoidance danger zone, and then the calculation of the collision risk value is completed through the determined formula, which can effectively ensure the accuracy and efficiency of the collision risk value calculation.

[0129] In an exemplary embodiment, step 209 includes: determining an obstacle avoidance angular velocity control amount based on the maximum angular velocity value of the unmanned boat and the angle dimension collision risk value; determining an obstacle avoidance acceleration control amount based on the maximum acceleration value of the unmanned boat and the distance dimension collision risk value; and performing obstacle avoidance control processing on the unmanned boat based on the obstacle avoidance angular velocity control amount and the obstacle avoidance acceleration control amount.

[0130] Specifically, the final obstacle avoidance strategy of the unmanned boat is output in the form of angular velocity and acceleration control instructions. Therefore, after obtaining the collision risk value of the obstacle, it is also necessary to calculate the specific acceleration value and angular velocity value that are remapped to the control level.

[0131] In angular velocity control, the collision risk value of a single obstacle indicates the possibility of collision with the unmanned boat and the magnitude of the obstacle avoidance action that the unmanned boat should take. The greater the collision risk value, the greater the obstacle avoidance action that the unmanned boat should take. Considering the motion performance of the unmanned boat, the angular velocity is limited, so the angular velocity control value corresponding to the collision risk value of a single obstacle should be as follows:

[0132] w u = u C θ ·w max

[0133] In the formula, w u is the obstacle avoidance angular velocity control amount that the unmanned boat should perform on the u-th obstacle; u C θ is the collision risk value of the u-th obstacle in the angle dimension; w max is the maximum angular velocity of the unmanned boat, which is determined by the performance of the unmanned boat.

[0134] The unmanned boat will also face the situation where multiple obstacles are in danger of colliding with it at the same time. Therefore, the optimal value of the angular velocity is the result of analyzing multiple obstacles. The optimal obstacle avoidance angular velocity output value w b For details, please refer to the following formula:

[0135]

[0136] Similarly, the optimal obstacle avoidance output value calculation method for acceleration control can be obtained as shown in the following formula.

[0137] a u = u C T ·a max

[0138]

[0139] In the formula, a b is the optimal obstacle avoidance acceleration output value; a u is the obstacle avoidance acceleration control amount that the unmanned boat should perform on the u-th obstacle; u C T is the collision risk value of the u-th obstacle in the distance dimension; a max In this embodiment, the control parameter of the unmanned boat is determined by combining the performance parameters of the unmanned boat and the collision risk value, so as to effectively complete the angular velocity and acceleration control of the unmanned boat during the obstacle avoidance process, thereby effectively improving the accuracy of the obstacle avoidance process.

[0140] In one of the embodiments, the obstacle avoidance of the unmanned boat in this embodiment can be realized by the unmanned boat control processor on the unmanned boat. The unmanned boat control processor can determine the position information of the unmanned boat through the positioning device, and detect the obstacles encountered by the unmanned boat through the sensor, and obtain the relative position information and relative speed information of the obstacle relative to the unmanned boat through the obstacle detection module. When encountering obstacles and performing obstacle avoidance processing, the control processor can construct a bow coordinate system encounter model based on the position information and obstacle information of the unmanned boat, and then determine the relative position information and relative speed information of the obstacle relative to the unmanned boat based on the obstacle information; determine the relative position angle and relative distance based on the relative position information, and determine the relative speed angle and relative speed absolute value based on the relative speed information. And determine the obstacle mirror point of the obstacle relative to the bow coordinate system based on the relative encounter parameters; determine the rectangular area surrounded by the obstacle and the obstacle mirror point as the collision risk range between the unmanned boat and the obstacle. When the obstacle is within the collision danger range, the obstacle avoidance danger area corresponding to the obstacle is identified; the angle dimension collision danger value formula and the distance dimension collision danger value formula corresponding to the identified obstacle avoidance danger area are determined; the angle dimension collision danger value is determined based on the relative position angle, the relative velocity angle and the angle dimension collision danger value formula; the distance dimension collision danger value is determined based on the relative position angle, the relative velocity angle, the relative distance, the absolute value of the relative velocity and the distance dimension collision danger value formula. Finally, the obstacle avoidance angular velocity control amount is determined based on the maximum angular velocity value of the unmanned boat and the angle dimension collision danger value; the obstacle avoidance acceleration control amount is determined based on the maximum acceleration value of the unmanned boat and the distance dimension collision danger value; and the unmanned boat is subjected to obstacle avoidance control processing based on the obstacle avoidance angular velocity control amount and the obstacle avoidance acceleration control amount.

[0141] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0142] Based on the same inventive concept, the embodiment of the present application also provides an unmanned boat obstacle avoidance device for implementing the unmanned boat obstacle avoidance method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more unmanned boat obstacle avoidance device embodiments provided below can refer to the limitations of the unmanned boat obstacle avoidance method above, and will not be repeated here.

[0143] In one embodiment, Fig.10 As shown, an unmanned boat obstacle avoidance device is provided, comprising:

[0144] The model building module 1001 is used to build a bow coordinate system encounter model based on the position information of the unmanned boat and the obstacle information, and the obstacle information is detected by the obstacle detection module of the unmanned boat.

[0145] The parameter conversion module 1003 is used to convert the obstacle information into the relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model.

[0146] The range identification module 1005 is used to determine the collision risk range between the unmanned boat and the obstacle based on the relative encounter parameters.

[0147] The risk value identification module 1007 is used to determine the collision risk value of the obstacle based on the relative encounter parameter when the obstacle is located in the collision risk range.

[0148] The obstacle avoidance control module 1009 is used to perform obstacle avoidance control processing on the unmanned boat based on the collision risk value.

[0149] In one embodiment, the relative encounter parameters include a relative position angle, a relative speed angle, a relative distance, and a relative speed absolute value. The parameter conversion module 1003 is specifically used to: determine the relative position information and relative speed information of the obstacle relative to the unmanned boat based on the obstacle information; determine the relative position angle and relative distance based on the relative position information, and determine the relative speed angle and relative speed absolute value based on the relative speed information.

[0150] In one of the embodiments, the range identification module 1005 is specifically used to: determine the obstacle mirror point of the obstacle relative to the bow coordinate system based on the relative encounter parameter; and determine the rectangular area enclosed by the obstacle and the obstacle mirror point as the collision risk range between the unmanned boat and the obstacle.

[0151] In one embodiment, the collision risk value includes an angle dimension collision risk value and a distance dimension collision risk value. The risk value identification module 1007 is specifically used to identify the obstacle avoidance risk area corresponding to the obstacle when the obstacle is located in the collision risk range; based on the identified obstacle avoidance risk area and the relative encounter parameter, determine the angle dimension collision risk value and the distance dimension collision risk value.

[0152] In one embodiment, the relative encounter parameters include the relative position angle, the relative speed angle, the relative distance and the absolute value of the relative speed; the hazard value identification module 1007 is also used to: determine the angle dimension collision hazard value formula and the distance dimension collision hazard value formula corresponding to the identified obstacle avoidance hazard area; determine the angle dimension collision hazard value based on the relative position angle, the relative speed angle and the angle dimension collision hazard value formula; determine the distance dimension collision hazard value based on the relative position angle, the relative speed angle, the relative distance, the absolute value of the relative speed and the distance dimension collision hazard value formula.

[0153] In one embodiment, the obstacle avoidance control module 1009 is specifically used to: determine the obstacle avoidance angular velocity control amount based on the maximum angular velocity value of the unmanned boat and the angle dimension collision risk value; determine the obstacle avoidance acceleration control amount based on the maximum acceleration value of the unmanned boat and the distance dimension collision risk value; perform obstacle avoidance control processing on the unmanned boat based on the obstacle avoidance angular velocity control amount and the obstacle avoidance acceleration control amount.

[0154] Each module in the above-mentioned obstacle avoidance device for unmanned boats can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0155] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.11 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to the unmanned boat obstacle avoidance process. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an unmanned boat obstacle avoidance method is implemented.

[0156] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0157] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0158] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0159] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0160] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0161] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0162] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An unmanned boat obstacle avoidance method, characterized in that: The method comprises: Constructing a bow coordinate system encounter model based on the position information of the unmanned boat and the obstacle information, wherein the obstacle information is detected by the obstacle detection module of the unmanned boat; The obstacle information is converted into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model; Determining the obstacle mirror point of the obstacle relative to the bow coordinate system based on the relative encounter parameter, the obstacle mirror point includes the obstacle mirror point relative to the X-axis of the bow coordinate system, the obstacle mirror point relative to the Y-axis of the bow coordinate system, and the obstacle mirror point relative to the origin of the bow coordinate system; Determine a rectangular area enclosed by the obstacle and the mirror image point of the obstacle as a collision risk range between the unmanned boat and the obstacle; When the obstacle is located in the collision risk range, determining a collision risk value of the obstacle based on the relative encounter parameter; Obstacle avoidance control is performed on the unmanned boat based on the collision risk value.

2. The method according to claim 1, characterized in that The relative encounter parameters include relative position angle, relative speed angle, relative distance and relative speed absolute value; The step of converting the obstacle information into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model includes: Based on the obstacle information, determining relative position information and relative speed information of the obstacle relative to the unmanned boat; The relative position angle and the relative distance are determined based on the relative position information, and the relative speed angle and the relative speed absolute value are determined based on the relative speed information.

3. The method according to claim 1, characterized in that The collision risk value includes an angle dimension collision risk value and a distance dimension collision risk value; When the obstacle is located in the collision risk range, determining the collision risk value of the obstacle based on the relative encounter parameter includes: When the obstacle is located in the collision risk range, identifying an obstacle avoidance risk area corresponding to the obstacle; Based on the identified obstacle avoidance danger zone and the relative encounter parameter, a collision danger value in an angle dimension and a collision danger value in a distance dimension are determined.

4. The method according to claim 3, characterized in that The relative encounter parameters include relative position angle, relative speed angle, relative distance and relative speed absolute value; The determining of the collision risk value in the angle dimension and the collision risk value in the distance dimension based on the obstacle avoidance danger zone and the relative encounter parameter comprises: Determine the angle dimension collision risk value formula and the distance dimension collision risk value formula corresponding to the identified obstacle avoidance danger zone; Determine an angle dimension collision risk value based on the relative position angle, the relative speed angle and the angle dimension collision risk value formula; The distance dimension collision risk value is determined based on the relative position angle, the relative speed angle, the relative distance, the absolute value of the relative speed and the distance dimension collision risk value formula.

5. The method according to claim 3, characterized in that: The performing obstacle avoidance control processing on the unmanned boat based on the collision risk value includes: Determining an obstacle avoidance angular velocity control amount based on the maximum angular velocity value of the unmanned boat and the angular dimension collision risk value; Determining an obstacle avoidance acceleration control amount based on the maximum acceleration value of the unmanned boat and the distance dimension collision risk value; Obstacle avoidance control processing is performed on the unmanned boat based on the obstacle avoidance angular velocity control amount and the obstacle avoidance acceleration control amount.

6. An unmanned boat obstacle avoidance device, characterized in that: The device comprises: A model building module, used to build a bow coordinate system encounter model based on the position information of the unmanned boat and the obstacle information, wherein the obstacle information is detected by the obstacle detection module of the unmanned boat; A parameter conversion module, used to convert the obstacle information into relative encounter parameters between the unmanned boat and the obstacle through the bow coordinate system encounter model; A range identification module is used to determine the obstacle mirror point of the obstacle relative to the bow coordinate system based on the relative encounter parameter, wherein the obstacle mirror point includes the obstacle mirror point relative to the X-axis of the bow coordinate system, the obstacle mirror point relative to the Y-axis of the bow coordinate system, and the obstacle mirror point relative to the origin of the bow coordinate system; and determine the rectangular area enclosed by the obstacle and the obstacle mirror point as the collision risk range between the unmanned boat and the obstacle; a risk value identification module, configured to determine a collision risk value of the obstacle based on the relative encounter parameter when the obstacle is located in the collision risk range; The obstacle avoidance control module is used to perform obstacle avoidance control processing on the unmanned boat based on the collision risk value.

7. The device according to claim 6, characterized in that The relative encounter parameters include relative position angle, relative speed angle, relative distance and relative speed absolute value; The parameter conversion module is specifically used to: determine the relative position information and relative speed information of the obstacle relative to the unmanned boat based on the obstacle information; determine the relative position angle and the relative distance based on the relative position information, and determine the relative speed angle and the absolute value of the relative speed based on the relative speed information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, 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 5 are implemented.

10. A computer program product, comprising 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 5 are implemented.

Images