A path planning method, system, device and storage medium for unmanned ship
By using greedy algorithms and particle swarm algorithms to plan the path of unmanned ships in multi-beam depth sounding systems, the problems of data redundancy and inefficiency in complex sea areas are solved, and accurate measurement of submarine terrain and safe depth sounding operations are achieved.
Patent Information
- Application Number
- CN202410756480.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-13
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-06-13
AI Technical Summary
Multi-beam depth sounding systems have problems of data redundancy, low efficiency and environmental risks in complex rectangular seas, especially in shallow areas where manual watering is required, which poses safety risks.
The greedy algorithm and particle swarm algorithm are used to plan the path of the unmanned ship. By obtaining the open angle and three-dimensional terrain data of the multi-beam transducer, the strip coverage width of each measurement line and the overlap rate of adjacent measurement lines are determined, and the The line position and path are used to ensure that the total length of the line is minimized within the set overlap rate range, and the particle swarm algorithm is used to search for the optimal particles to form an initial planning path.
It reduces data redundancy and missing, ensures accurate detection of the seabed terrain in the entire sea area, improves the efficiency and accuracy of unmanned ships' depth measurement, and reduces environmental risks.
Smart Images

Figure CN118443031B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of surveying technology, and in particular to a path planning method, system, device and storage medium for an unmanned ship. Background Art
[0002] The working principle of the multi-beam bathymetry system is to transmit and receive wide-sector sound waves to the seabed. Compared with the traditional single-beam bathymetry system, which can only measure one seabed depth value in the vertical direction of the hull at a time, the multi-beam bathymetry system can obtain the seabed depth values of multiple measurement points within a strip coverage range, which improves the efficiency of seabed topography measurement. However, due to the way the multi-beam bathymetry strip covers and the ever-changing seabed topography, it is easy to cause problems such as redundant seabed bathymetry data and low efficiency; on the other hand, the environment of some rectangular sea areas is relatively dangerous, and personal safety is difficult to guarantee. Shallow areas require manual underwater measurement, which is risky and takes a long time to measure.
[0003] Therefore, multi-beam bathymetry still has problems such as data redundancy, low efficiency, and environmental risks. Given that unmanned ships are more adaptable to complex rectangular sea environments, it is necessary to provide a method for intelligent path planning for multi-beam bathymetry of unmanned ships. Summary of the invention
[0004] In view of this, the purpose of the embodiments of the present invention is to provide a path planning method, system, device and storage medium for an unmanned ship to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.
[0005] On the one hand, an embodiment of the present invention provides a path planning method for an unmanned ship, the method comprising the following steps:
[0006] S100, acquiring an opening angle of a multi-beam transducer and three-dimensional terrain data within a detection area of the multi-beam transducer;
[0007] S200, determining a strip coverage width of each survey line in the multi-beam transducer and an overlap ratio of adjacent survey lines based on an opening angle of the multi-beam transducer and the three-dimensional terrain data;
[0008] S300, using a greedy algorithm to update the position of each survey line according to the strip coverage width of each survey line and the overlap rate of adjacent survey lines, to obtain an initial position of each survey line; wherein the goal of the greedy algorithm is to minimize the total length of the survey lines within a set overlap rate range;
[0009] S400, starting from the initial position of each measuring line until reaching the longitudinal boundary, searching for each particle passed by each measuring line;
[0010] S500, for each survey line, the initial position of the survey line is used as the initial particle corresponding to the survey line, starting from the initial particle, the optimal particle is searched among the particles through which the survey line passes through by the particle swarm algorithm to obtain the optimal particle corresponding to the survey line, and the optimal particles corresponding to each survey line are connected to form an initial planning path.
[0011] Optionally, the three-dimensional terrain data includes seawater depth and seabed slope; and determining the strip coverage width of each survey line in the multi-beam transducer and the overlap rate of adjacent survey lines based on the opening angle of the multi-beam transducer and the three-dimensional terrain data includes:
[0012] S210, determining a detection area of the multi-beam transducer, establishing a plane coordinate system of the detection area, and setting a dot matrix in the plane coordinate system, wherein the row and column spacings of the dot matrix are equal;
[0013] S220, taking each point in the dot matrix as a particle, and dividing the detection area into a plurality of rectangular sea areas with a plurality of particles as a group;
[0014] S230, obtaining the opening angle, sea water depth and seabed slope of the multi-beam transducer, calculating the strip coverage width corresponding to each particle in each rectangular sea area moving from the current position to different directions based on the opening angle, sea water depth and seabed slope of the multi-beam transducer, and determining the coverage overlap rate between adjacent survey lines based on the strip coverage width of adjacent survey lines.
[0015] Optionally, the updating the position of each survey line by using a greedy algorithm according to the strip coverage width of each survey line and the overlap rate of adjacent survey lines to obtain the initial position of each survey line includes:
[0016] S301, input initial particle h (0,0) ;
[0017] S302, calculate the initial position x1 of the measuring line according to the initial position of the initial particle; the calculation formula is: x1 = h (0,0) *tan(θ / 2); x1 is the initial position of the survey line, θ is the opening angle of the multi-beam transducer;
[0018] S303, calculating the initial spacing D1 between adjacent survey lines; the calculation formula is: D1 = x1;
[0019] S304: Calculate the initial position x of the next survey line based on the initial spacing N+1 ; The calculation formula is: x N+1 =x N +D N , N is the number of the survey line, N≥1;
[0020] S305, calculating the coverage overlap ratio between the current survey line and the previous survey line;
[0021] S306, determining whether the coverage overlap ratio is within a set overlap ratio range, if so, executing S307; otherwise, executing S308;
[0022] S307, record the position x of the survey line N+1 =x (i,0) , determine whether the survey line reaches the lateral boundary B2; if so, determine to obtain the initial position of each survey line; otherwise, update N=N+1 and jump to step S304;
[0023] S308, determine whether the coverage overlap ratio is greater than the maximum value of the overlap ratio range; if so, determine that the coverage overlap ratio is too large, and increase the spacing to D N =D N +1, jump to step S304; otherwise, determine that the coverage overlap rate is too small, and reduce the spacing to D N =D N -1, jump to step S304.
[0024] Optionally, starting from the initial position of each measuring line until reaching the longitudinal boundary, searching for each particle passed by each measuring line includes:
[0025] S410, determining the order of each measurement line, for the first measurement line in the order, starting from the initial position of the measurement line, searching for the particle with the largest next strip coverage width until reaching the longitudinal boundary, and obtaining each particle passed by the first measurement line;
[0026] S420, for the remaining survey lines, starting from the initial position corresponding to the survey line, search for the next particle through the adaptive function until the path of the longitudinal boundary is reached, and the particles passed by the remaining survey lines are obtained respectively; wherein the adaptive function aims to maximize the strip coverage width of the survey line and minimize the coverage overlap rate of the particles on the survey line and the previous survey line.
[0027] Optionally, starting from the initial particle, searching for the optimal particle among the particles through which the measurement line passes by using a particle swarm algorithm to obtain the optimal particle corresponding to the measurement line, and connecting the optimal particles corresponding to each measurement line to form an initial planning path, comprises:
[0028] S510, input the initial particle x corresponding to each measurement line N ;
[0029] S520, record the eight adjacent particles of the (i, j)th particle in the rectangular sea area as the (i+n, j+m)th particle, initialize n=-1, m=0, f max =0; wherein n=-1, 0, 1, m=0, 1, 2, and n and m are not 0 at the same time;
[0030] S530, calculate the fitness value f of the (i+n, j+m)th particle (i+n,j+m) , and the maximum fitness value f of the particle in the rectangular sea area max Compare, if f (i+n,j+m) Greater than f max , then update the maximum fitness value f max =f (i+n,j+m) , and record the coordinates of the (i+n, j+m)th particle i record =i+n,j record =j+m; otherwise jump to S540;
[0031] S540, update m=m+1, determine whether the updated particle exceeds the current rectangular sea area, if not, that is, m<2, jump to S530, if exceeded, that is, m>2, jump to S550;
[0032] S550, update n=n+1, m=0; when n=0, m=1, determine whether the updated particle exceeds the current rectangular sea area, if not, that is, n<1, jump to S530, if exceeded, that is, n>1, jump to S560;
[0033] S560, update i=i record , j = j record , taking the updated (i, j)th particle as the optimal particle, judging whether the longitudinal coordinate of the optimal particle in the rectangular sea area reaches the longitudinal boundary, if not, jumping to S520; if reaching, jumping to S570;
[0034] S570, judging whether the horizontal coordinate of the optimal particle in the rectangular sea area reaches the horizontal coordinate boundary, if not, jumping to S580, if reached, jumping to S590;
[0035] S580, update the initial particle N = N + 1, that is, update the initial particle to the initial position x of the next measurement line N , jump to S510;
[0036] S590, connecting the optimal particles of each measurement line to form an initial planning path.
[0037] Optionally, the method further comprises:
[0038] Obtain the seabed depth collected in real time by multi-beam sonar for the current particles in the rectangular sea area;
[0039] The predicted seawater depth of the front particle is calculated based on the seabed depth, and the front particle includes a particle located in front of the current particle along the survey line direction;
[0040] Determine the predicted strip coverage width of the front particle based on the predicted seawater depth of the front particle, and then obtain the predicted coverage overlap rate of the front particle;
[0041] The strip coverage width of the current particle is replaced by the predicted strip coverage width of the preceding particle, and the coverage overlap rate of the current particle is replaced by the predicted coverage overlap rate of the preceding particle;
[0042] The initial planned path is updated based on the predicted strip coverage width and predicted coverage overlap rate of the front particle to obtain the optimized path.
[0043] Optionally, the method further comprises:
[0044] The fitness function Updated to:
[0045] ;
[0046] The initial planned path is updated based on the updated adaptability function to obtain a dynamic planned path for real-time obstacle avoidance;
[0047] in, is the normalized value of the stripe coverage width, is the normalized value of the coverage overlap ratio, is the normalized penalty value, and the calculation formula of the normalized penalty value is:
[0048] ;
[0049] in, is the maximum value of the obstacle penalty, is the minimum value of the obstacle penalty, is the obstacle penalty value;
[0050] The calculation formula of obstacle penalty value is:
[0051] ;
[0052] Among them, (x (i,j) ,y (i,j) ) is the particle coordinate, (x barrier ,y barrier ) is the obstacle coordinate, and C is the penalty weight.
[0053] On the other hand, an embodiment of the present invention provides a path planning system for an unmanned ship, comprising:
[0054] The first module is used to obtain the opening angle of the multi-beam transducer and the three-dimensional terrain data within the detection area of the multi-beam transducer;
[0055] The second module is used to determine the strip coverage width of each survey line in the multi-beam transducer and the overlap rate of adjacent survey lines based on the opening angle of the multi-beam transducer and the three-dimensional terrain data;
[0056] The third module is used to update the position of each survey line by using a greedy algorithm according to the strip coverage width of each survey line and the overlap rate of adjacent survey lines to obtain the initial position of each survey line; wherein the goal of the greedy algorithm is to minimize the total length of the survey line within a set overlap rate range;
[0057] The fourth module is used to search for each particle that each measuring line passes through, starting from the initial position of each measuring line until it reaches the longitudinal boundary;
[0058] The fifth module is used to use the initial position of each survey line as the initial particle corresponding to the survey line, start from the initial particle, search for the optimal particle among the particles passing through the survey line through the particle swarm algorithm, obtain the optimal particle corresponding to the survey line, and connect the optimal particles corresponding to each survey line to form an initial planning path.
[0059] On the other hand, an embodiment of the present invention provides a path planning device for an unmanned ship, comprising:
[0060] at least one processor;
[0061] at least one memory for storing at least one program;
[0062] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.
[0063] On the other hand, an embodiment of the present invention provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to perform the above method.
[0064] The embodiment of the present invention has the following beneficial effects: by introducing the greedy algorithm and the particle swarm algorithm, the embodiment plans the optimal path for each step of the unmanned ship, which not only reduces the redundancy and loss of data, but also ensures the accurate detection of the seabed topography in the entire sea area. The present invention can improve the bathymetric efficiency of the unmanned ship, thereby improving the accuracy and reliability of the bathymetric measurement. BRIEF DESCRIPTION OF THE DRAWINGS
[0065] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0066] Figure 1 It is a schematic flow chart of the steps of a path planning method for an unmanned ship provided by an embodiment of the present invention;
[0067] Figure 2 It is a schematic diagram of the initial position of a survey line in a rectangular sea area provided by an embodiment of the present invention;
[0068] Figure 3 is a front view of the seabed slope and the survey line in an embodiment of the present invention;
[0069] Figure 4 is a schematic diagram of the overlapping rate of adjacent survey lines in an embodiment of the present invention;
[0070] Figure 5 is a schematic diagram of a dimension reduction geometric model in a certain survey line direction in an embodiment of the present invention;
[0071] Figure 6 is a seawater depth prediction model diagram for predicting the seawater depth of the next particle position in an embodiment of the present invention;
[0072] Figure 7 is a cross-sectional diagram of a seawater depth prediction model for predicting the seawater depth of the next particle position in an embodiment of the present invention;
[0073] Figure 8 This is an architecture diagram of a path planning system for an unmanned ship provided by an embodiment of the present invention;
[0074] Fig. 9 It is a structural block diagram of a path planning device for an unmanned ship provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0075] 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.
[0076] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0078] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.
[0079] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0080] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0081] like Figure 1 As shown, Figure 1 A path planning method for an unmanned ship is provided in an embodiment of the present invention, and the method comprises the following steps:
[0082] S100, acquiring an opening angle of a multi-beam transducer and three-dimensional terrain data within a detection area of the multi-beam transducer;
[0083] S200, determining a strip coverage width of each survey line in the multi-beam transducer and an overlap ratio of adjacent survey lines based on an opening angle of the multi-beam transducer and the three-dimensional terrain data;
[0084] S300, using a greedy algorithm to update the position of each survey line according to the strip coverage width of each survey line and the overlap rate of adjacent survey lines, to obtain an initial position of each survey line; wherein the goal of the greedy algorithm is to minimize the total length of the survey lines within a set overlap rate range;
[0085] Specifically, under the set overlap rate range, the total length of the measuring line The minimum is the goal, and the initial position of each measuring line (i.e., the triangular particle) is determined. At this time, each measuring line is not optimized, and its length is regarded as the longitudinal boundary length. ;
[0086] S400, starting from the initial position of each measuring line until reaching the longitudinal boundary, searching for each particle passed by each measuring line;
[0087] S500, for each survey line, the initial position of the survey line is used as the initial particle corresponding to the survey line, starting from the initial particle, the optimal particle is searched among the particles through which the survey line passes through by the particle swarm algorithm to obtain the optimal particle corresponding to the survey line, and the optimal particles corresponding to each survey line are connected to form an initial planning path.
[0088] In some embodiments, in order to facilitate the denoising and segmentation of the image, the seabed image is converted into a grayscale image. The grayscale value conversion formula can select the averaging method; in order to reduce the impact of noise and eliminate outliers, the grayscale image is subjected to denoising. The denoising algorithm can select the median filter, mean filter, Gaussian filter, bilateral filter, etc. of the local filter. In order to simplify the subsequent establishment of the bathymetric model based on the greedy algorithm, the three-dimensional image reflects the altitude line and the slope, and the rectangular sea area with similar slope is segmented, that is, segmented along the convex or concave direction of the contour line. Clean up single / multi-beam data by filling in missing values, smoothing noise data, identifying or deleting outliers and resolving inconsistencies. To achieve the purpose of removing abnormal data, correcting errors, and removing duplicate data.
[0089] In some embodiments, the three-dimensional terrain data includes seawater depth and seabed slope; and determining the strip coverage width of each survey line in the multi-beam transducer and the overlap rate of adjacent survey lines based on the opening angle of the multi-beam transducer and the three-dimensional terrain data includes:
[0090] S210, determining a detection area of the multi-beam transducer, establishing a plane coordinate system of the detection area, and setting a dot matrix in the plane coordinate system, wherein the row and column spacings of the dot matrix are equal;
[0091] S220, taking each point in the dot matrix as a particle, and dividing the detection area into a plurality of rectangular sea areas with a plurality of particles as a group;
[0092] Specifically, refer to Figure 2 , each coordinate point (dot) is regarded as a particle, and 8 adjacent particles are selected along its positive y-axis direction to divide it into a small rectangular sea area (that is, several small rectangular sea areas are obtained). A single small rectangular sea area is as follows Figure 2 As shown in the square box in the middle; calculate the strip coverage width corresponding to each small rectangular sea area moving from the current position to different directions, that is, calculate the seabed slope and survey line slope corresponding to the unmanned ship traveling in different directions on the same survey line, and then calculate the strip coverage width.
[0093] S230, obtaining the opening angle, sea water depth and seabed slope of the multi-beam transducer, calculating the strip coverage width corresponding to each particle in each rectangular sea area moving from the current position to different directions based on the opening angle, sea water depth and seabed slope of the multi-beam transducer, and determining the coverage overlap rate between adjacent survey lines based on the strip coverage width of adjacent survey lines.
[0094] Specifically, the opening angle of the multi-beam transducer It can be obtained by adjusting the transducer type and parameters; the sea depth h is obtained by the multi-beam bathymetric system; the seabed slope The surface formed by the lowest and highest points in the area is used as an approximate straight slope surface, and the seabed slope Calculated by the following formula:
[0095] ;
[0096] in, and are the depths of the sea water at the shallowest and deepest points of a rectangular sea area, respectively. and are the coordinates of the shallowest and deepest points of the rectangular sea area respectively.
[0097] With the current survey line as the center, establish geometric relationships such as Figure 3 shown. Figure 3 It is the front view of the seabed slope and the survey line. Figure 3 In the figure, point A is the launch point of the beam, ∠BAC is the opening angle of the transducer, points B and C are the intersection points of the beam and the seabed slope, point D is the intersection point of the bisector of the transducer opening angle and the seabed slope, point F is the intersection point of point C and the opposite beam at the same height, and point E is the intersection point of line segment CF and line segment AD. Line segment BC is the strip coverage width of the survey line. ;
[0098] After calculating the coverage width, the overlapping ratio of adjacent strips can be obtained. Figure 3 draw Figure 4 Among them, draw a parallelogram AA'B'H, and point G is the intersection of the extended line of line segment B'H and the extended line of line segment AC.
[0099] Figure 4 It is a schematic diagram of the overlapping rate of adjacent survey lines, and the overlapping length of the strips , denoted as , overlap rate of adjacent survey lines for:
[0100] ;
[0101] In some embodiments, the calculation formula for minimizing the total length of the measuring line is as follows:
[0102] ;
[0103] satisfy:
[0104] ;
[0105] in, is the total length of the measuring line, is the coordinate position of the particle, and the initial position of each measuring line is On the axis, that is =0, is the longitudinal boundary length of the detection area, N is the number of the survey line, is the strip coverage width of the Nth survey line, is the opening angle of the multi-beam transducer, is the sea depth measured by the Nth survey line, is the seafloor slope, is the coverage overlap ratio between the Nth survey line and the adjacent survey lines, is the overlap width between the Nth survey line and the adjacent survey line, is the set overlap rate range, is the horizontal coordinate of the N+1th survey line, is the horizontal coordinate of the Nth survey line, For the The horizontal coordinate of a particle, is the distance between the Nth survey line and the adjacent survey line, is the lateral boundary of the detection area.
[0106] In some embodiments, the updating of the position of each measuring line by using a greedy algorithm according to the strip coverage width of each measuring line and the overlap rate of adjacent measuring lines to obtain the initial position of each measuring line includes the following steps:
[0107] S301, input initial particle h (0,0) (i.e. the initial position of the first survey line);
[0108] S302, calculate the initial position x1 of the measuring line according to the initial position of the initial particle; the calculation formula is: x1 = h (0,0) *tan(θ / 2); x1 is the initial position of the survey line, θ is the opening angle of the multi-beam transducer;
[0109] S303, calculating the initial spacing D1 between adjacent survey lines; the calculation formula is: D1 = x1;
[0110] S304: Calculate the initial position x of the next survey line based on the initial spacing N+1 ; The calculation formula is: x N+1 =x N +DN , N is the number of the survey line, N≥1;
[0111] S305, calculating the coverage overlap ratio between the current survey line and the previous survey line;
[0112] S306, determining whether the coverage overlap ratio is within a set overlap ratio range, if so, executing S307; otherwise, executing S308;
[0113] S307, record the position x of the survey line N+1 =x (i,0) , determine whether the survey line reaches the lateral boundary B2; if so, determine to obtain the initial position of each survey line; otherwise, update N=N+1 and jump to step S304;
[0114] S308, determine whether the coverage overlap ratio is greater than the maximum value of the overlap ratio range; if so, determine that the coverage overlap ratio is too large, and increase the spacing to D N =D N +1, jump to step S304; otherwise, determine that the coverage overlap rate is too small, and reduce the spacing to D N =D N -1, jump to step S304.
[0115] In some embodiments, starting from the initial position of each measuring line until reaching the longitudinal boundary, searching for each particle passed by each measuring line includes:
[0116] S410, determining the order of each measurement line, for the first measurement line in the order, starting from the initial position of the measurement line, searching for the particle with the largest next strip coverage width until reaching the longitudinal boundary, and obtaining each particle passed by the first measurement line;
[0117] S420, for the remaining survey lines, starting from the initial position corresponding to the survey line, search for the next particle through the adaptive function until the path of the longitudinal boundary is reached, and the particles passed by the remaining survey lines are obtained respectively; wherein the adaptive function aims to maximize the strip coverage width of the survey line and minimize the coverage overlap rate of the particles on the survey line and the previous survey line.
[0118] Specifically, Figure 2 As shown, the measurement lines are sorted along the X-axis direction. The first measurement line starts from the initial position (triangular particle) and reaches the particle with the largest strip coverage width until it reaches the longitudinal boundary. ,like Figure 2 As shown by the multi-segment arrows on the left; the second and subsequent survey lines start from the initial position and use the adaptive function (Next Particle Selection) Search Path, Fitness Function Consider the following:
[0119] 1) Maximum strip coverage width:
[0120] ;
[0121] ;
[0122] in, is the particle position, Indicates the strip coverage width, It represents the angle between the projection of the slope normal on the horizontal plane and the projection of the survey line on the horizontal plane. Indicates the seafloor slope; reference Figure 5 , yes Figure 5 The angle between the auxiliary line and its projection, Follow And change.
[0123] 2) The coverage overlap rate with the particle on the left side of the same line (the particle on the previous measurement line, whose position has been determined) is minimized to reduce redundant data, and the coverage overlap rate is not less than 0;
[0124] ;
[0125] in, For the The horizontal coordinate of a particle, For the The horizontal coordinate of a particle, is the coverage overlap ratio, is the overlap width, is the seafloor slope, is the particle distance (the distance between the current position of the measurement line and the position of the previous measurement line), is the set overlap rate range.
[0126] For each rectangular sea area, the strip coverage width and coverage overlap rate corresponding to the particle's movement to the next particle position are calculated for each particle in the rectangular sea area, corresponding to a total of 8 sets of data. The maximum strip coverage width is recorded as , the minimum value of the stripe coverage width is recorded as ; The maximum value of the coverage overlap ratio is recorded as , the minimum value of the coverage overlap rate is recorded as ; Fitness function satisfy:
[0127] ;
[0128] in:
[0129] ;
[0130] The coverage width and coverage overlap ratio of each set of stripes are processed by Min-Max normalization, where: is the normalized value of the stripe coverage width, is the normalized value of the coverage overlap ratio.
[0131] In some embodiments, starting from the initial particle, searching for the optimal particle among the particles through which the measurement line passes by using a particle swarm algorithm to obtain the optimal particle corresponding to the measurement line, and connecting the optimal particles corresponding to each measurement line to form an initial planning path includes:
[0132] S510, input the initial particle x corresponding to each measurement line N ;
[0133] S520, record the eight adjacent particles of the (i, j)th particle in the rectangular sea area as the (i+n, j+m)th particle, initialize n=-1, m=0, f max =0; wherein n=-1, 0, 1, m=0, 1, 2, and n and m are not 0 at the same time;
[0134] S530, calculate the fitness value f of the (i+n, j+m)th particle (i+n,j+m) , and the maximum fitness value f of the particle in the rectangular sea area max Compare, if f (i+n,j+m) Greater than f max , then update the maximum fitness value f max =f (i+n,j+m) , and record the coordinates of the (i+n, j+m)th particle i record =i+n,j record =j+m; otherwise jump to S540;
[0135] S540, update m=m+1, determine whether the updated particle exceeds the current rectangular sea area, if not, that is, m<2, jump to S530, if exceeded, that is, m>2, jump to S550;
[0136] S550, update n=n+1, m=0; when n=0, m=1, determine whether the updated particle exceeds the current rectangular sea area, if not, that is, n<1, jump to S530, if exceeded, that is, n>1, jump to S560;
[0137] S560, update i=i record , j = j record , take the updated (i, j)th particle as the optimal particle, and determine whether the ordinate of the optimal particle in the rectangular sea area reaches the longitudinal boundary, i.e., y (i,j)>B1, if not reached, jump to S520; if reached, jump to S570; where y (i,j) is the ordinate of the optimal particle, and B1 is the longitudinal boundary;
[0138] S570, determine whether the horizontal coordinate of the optimal particle in the rectangular sea area reaches the horizontal coordinate boundary, that is, x (i,j) >B2, if not reached, jump to S580, if reached, jump to S590;
[0139] S580, update the initial particle N = N + 1, that is, update the initial particle to the initial position x of the next measurement line N , jump to S510;
[0140] S590, connecting the optimal particles of each measurement line to form an initial planning path.
[0141] In some embodiments, the method further comprises:
[0142] Obtain the seabed depth collected in real time by multi-beam sonar for the current particles in the rectangular sea area;
[0143] The predicted seawater depth of the front particle is calculated based on the seabed depth, and the front particle includes a particle located in front of the current particle along the survey line direction;
[0144] Determine the predicted strip coverage width of the front particle based on the predicted seawater depth of the front particle, and then obtain the predicted coverage overlap rate of the front particle;
[0145] The strip coverage width of the current particle is replaced by the predicted strip coverage width of the preceding particle, and the coverage overlap rate of the current particle is replaced by the predicted coverage overlap rate of the preceding particle;
[0146] The initial planned path is updated based on the predicted strip coverage width and predicted coverage overlap rate of the front particle to obtain the optimized path.
[0147] In some embodiments, the predicted seawater depth of the front particle is calculated by the following formula:
[0148] ;
[0149] ;
[0150] in, For the The depth of the sea floor for each particle, To predict the depth, , is the projected slope of the survey line, is the distance between two adjacent particles, (x (i,j) ,y(i,j) ) is the coordinate of the (i, j)th particle, For the The coordinates of the particles.
[0151] refer to Figure 6 and Figure 7 Since the multi-beam bathymetric system emits beams in a plane perpendicular to the survey line (track), it is impossible to obtain the seawater depth corresponding to the next particle for calculation. What you get Establish a seawater depth prediction model; based on the initial planned path, this embodiment obtains depth measurement data in real time through multi-beam sonar, and corrects the initial planned path planning to achieve the purpose of optimizing the real-time planning of the path.
[0152] Specifically, the six particles in the rectangular sea area that are located in front of the current particle along the survey line direction are calculated ( Figure 6 The predicted strip coverage width of the current particle can be obtained by measuring the seawater depth (6 particles in the middle box), and then the predicted coverage overlap rate between the current particle and the adjacent particles can be obtained; the strip coverage width of the current particle is replaced by the predicted strip coverage width, and the coverage overlap rate of the current particle is replaced by the predicted coverage overlap rate; the predicted strip coverage width and predicted coverage overlap rate of the current particle are substituted into the fitness function and the particle swarm algorithm to correct the route and obtain the optimized path.
[0153] In some embodiments, the method further comprises:
[0154] The fitness function Updated to:
[0155] ;
[0156] The initial planned path is updated based on the updated adaptability function to obtain a dynamic planned path for real-time obstacle avoidance;
[0157] in, is the normalized penalty value, and the calculation formula of the normalized penalty value is:
[0158] ;
[0159] in, is the maximum value of the obstacle penalty, is the minimum value of the obstacle penalty, is the obstacle penalty value;
[0160] The calculation formula of obstacle penalty value is:
[0161] ;
[0162] Among them, (x(i,j) ,y (i,j) ) is the particle coordinate, (x barrier ,y barrier ) is the obstacle coordinate, and C is the penalty weight.
[0163] In this embodiment, the distance and azimuth information between the hull and the obstacle are obtained through radar detection, and the obstacle penalty item is added to each particle to obtain the obstacle penalty value; the obstacle penalty value is processed by Min-Max normalization to obtain the normalized penalty value; the optimized path can judge the coordinates of the obstacle according to the existing data, and add the obstacle penalty value to the adaptability function to form the optimized path; the real-time path detects obstacles on the sea surface by radar, obtains the obstacle coordinates, and adds the obstacle penalty value to the adaptability function.
[0164] In the embodiment provided by the present invention, first, a clear seabed image is obtained through aerial photography, the obtained clear seabed terrain image is processed, and a three-dimensional image is established in combination with previous bathymetric data, and then the rectangular sea area is divided according to the slope; then, the previous single / multi-beam bathymetric data of the same rectangular sea area is input into the established multi-beam path planning model to obtain the initial planning path planning; the unmanned ship performs bathymetric work along the initial planning path, and the multi-beam sonar data obtained in real time is analyzed in a small rectangular sea area through the bathymetric model established based on the greedy algorithm, and the initial planning path is corrected to achieve the purpose of optimizing the path; the radar detection data obtained in real time is analyzed through the horizontal obstacle avoidance model, and the optimized path is corrected by adding obstacle penalty items to the fitness function of the particles to obtain a dynamic planning path, so as to realize the intelligent path planning of multi-beam bathymetric sounding of the unmanned ship.
[0165] Compared with the prior art, the advantages of the present invention are:
[0166] The present invention divides the area to be measured by image processing, reducing the complexity of the bathymetric system judgment and data processing; by establishing a mathematical model, the initial bathymetric path is formed using the existing single / multi-beam global data; a greedy algorithm is introduced to calculate and optimize the bathymetric path of the unmanned ship in a small range in real time, thereby improving the bathymetric efficiency of the unmanned ship and thus improving the accuracy and reliability of bathymetric sounding. The invention only uses data detected by multi-beam sonar and radar for real-time obstacle avoidance and path planning, with a small amount of calculation, effectively reducing the collection of redundant bathymetric data. In addition, bathymetric data can be collected through multi-beam sonar and used as model information as input, and can be operated in an environment without communication or light.
[0167] See also Figure 8 , an embodiment of the present invention provides a path planning system for an unmanned ship, comprising:
[0168] The first module is used to obtain the opening angle of the multi-beam transducer and the three-dimensional terrain data within the detection area of the multi-beam transducer;
[0169] The second module is used to determine the strip coverage width of each survey line in the multi-beam transducer and the overlap rate of adjacent survey lines based on the opening angle of the multi-beam transducer and the three-dimensional terrain data;
[0170] The third module is used to update the position of each survey line by using a greedy algorithm according to the strip coverage width of each survey line and the overlap rate of adjacent survey lines to obtain the initial position of each survey line; wherein the goal of the greedy algorithm is to minimize the total length of the survey line within a set overlap rate range;
[0171] The fourth module is used to search for each particle that each measuring line passes through, starting from the initial position of each measuring line until it reaches the longitudinal boundary;
[0172] The fifth module is used to use the initial position of each survey line as the initial particle corresponding to the survey line, start from the initial particle, search for the optimal particle among the particles passing through the survey line through the particle swarm algorithm, obtain the optimal particle corresponding to the survey line, and connect the optimal particles corresponding to each survey line to form an initial planning path.
[0173] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0174] See also Fig. 9 , an embodiment of the present invention provides a path planning device for an unmanned ship, comprising:
[0175] at least one processor;
[0176] at least one memory for storing at least one program;
[0177] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.
[0178] It can be seen that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0179] In addition, the embodiment of the present application also discloses a computer program product or a computer program, and the computer program product or the computer program is stored in a computer-readable storage medium. The processor of the computer device can read the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device performs the above method. Similarly, the contents in the above method embodiment are all applicable to the storage medium embodiment, and the functions specifically implemented by the storage medium embodiment are the same as those in the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method embodiment.
[0180] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0181] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0182] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0183] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0184] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0185] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0186] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0187] If the integrated unit 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 technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only-Memory, referred to as ROM), random access memory (Random-Access-Memory, referred to as RAM), disk or optical disk and other media that can store programs.
[0188] The preferred embodiments of the present application are described above with reference to the accompanying drawings, but the scope of the rights of the present application is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present application should be within the scope of the rights of the present application.
Claims
1. A path planning method for an unmanned ship, characterized in that: The method comprises the following steps: S100, acquiring an opening angle of a multi-beam transducer and three-dimensional terrain data within a detection area of the multi-beam transducer; S200, determining a strip coverage width of each survey line in the multi-beam transducer and an overlap ratio of adjacent survey lines based on an opening angle of the multi-beam transducer and the three-dimensional terrain data; S300, using a greedy algorithm to update the position of each survey line according to the strip coverage width of each survey line and the overlap rate of adjacent survey lines, to obtain an initial position of each survey line; wherein the goal of the greedy algorithm is to minimize the total length of the survey lines within a set overlap rate range; S400, starting from the initial position of each measuring line until reaching the longitudinal boundary, searching for each particle passed by each measuring line; S500, for each measuring line, the initial position of the measuring line is used as the initial particle corresponding to the measuring line, starting from the initial particle, searching for the optimal particle among the particles through which the measuring line passes through by using a particle swarm algorithm, obtaining the optimal particle corresponding to the measuring line, and connecting the optimal particles corresponding to each measuring line to form an initial planning path; Starting from the initial particle, searching for the optimal particle among the particles through which the measurement line passes by using a particle swarm algorithm to obtain the optimal particle corresponding to the measurement line, and connecting the optimal particles corresponding to each measurement line to form an initial planning path, includes: S510, input the initial particle x corresponding to each measurement line N ; S520, record the eight adjacent particles of the (i, j)th particle in the rectangular sea area as the (i+n, j+m)th particle, initialize n=-1, m=0, f max =0; wherein n=-1, 0, 1, m=0, 1, 2, and n and m are not 0 at the same time; S530, calculate the fitness value f of the (i+n, j+m)th particle (i+n,j+m) , and the maximum fitness value f of the particle in the rectangular sea area max Compare, if f (i+n,j+m) Greater than f max , then update the maximum fitness value f max =f (i+n,j+m) , and record the coordinates of the (i+n, j+m)th particle i record =i+n,j record =j+m; otherwise jump to S540; S540, assign the value of m+1 to parameter m for updating, and determine whether the updated particle exceeds the current rectangular sea area. If not, that is, m<2, jump to S530; if exceeded, that is, m>2, jump to S550; S550, assign the value of n+1 to parameter n for updating, m=0; when n=0, m=1, determine whether the updated particle exceeds the current rectangular sea area, if not, that is, n<1, jump to S530, if exceeded, that is, n>1, jump to S560; S560, update i=i record , j = j record , taking the updated (i, j)th particle as the optimal particle, judging whether the longitudinal coordinate of the optimal particle in the rectangular sea area reaches the longitudinal boundary, if not, jumping to S520; if reaching, jumping to S570; S570, judging whether the horizontal coordinate of the optimal particle in the rectangular sea area reaches the horizontal coordinate boundary, if not, jumping to S580, if reached, jumping to S590; S580, assign the value of N+1 to the initial particle parameter N for updating, that is, updating the initial particle to the initial position x of the next measurement line N , jump to S510; S590, connecting the optimal particles of each measurement line to form an initial planning path.
2. The method according to claim 1, characterized in that The three-dimensional terrain data includes seawater depth and seabed slope; the determining of the strip coverage width of each survey line in the multi-beam transducer and the overlap rate of adjacent survey lines based on the opening angle of the multi-beam transducer and the three-dimensional terrain data includes: S210, determining a detection area of the multi-beam transducer, establishing a plane coordinate system of the detection area, and setting a dot matrix in the plane coordinate system, wherein the row and column spacings of the dot matrix are equal; S220, taking each point in the dot matrix as a particle, and dividing the detection area into a plurality of rectangular sea areas with a plurality of particles as a group; S230, obtaining the opening angle, sea water depth and seabed slope of the multi-beam transducer, calculating the strip coverage width corresponding to each particle in each rectangular sea area moving from the current position to different directions based on the opening angle, sea water depth and seabed slope of the multi-beam transducer, and determining the coverage overlap rate between adjacent survey lines based on the strip coverage width of adjacent survey lines.
3. The method according to claim 2, characterized in that The method of updating the position of each survey line by a greedy algorithm according to the strip coverage width of each survey line and the overlap rate of adjacent survey lines to obtain the initial position of each survey line includes: S301, input initial particle h (0,0) ; S302, calculate the initial position x1 of the measuring line according to the initial position of the initial particle; the calculation formula is: x1 = h (0,0) *tan(θ / 2); x1 is the initial position of the survey line, θ is the opening angle of the multi-beam transducer; S303, calculating the initial spacing D1 between adjacent survey lines; the calculation formula is: D1 = x1; S304: Calculate the initial position x of the next survey line based on the initial spacing N+1 ; The calculation formula is: x N+1 =x N +D N , N is the number of the survey line, N≥1; S305, calculating the coverage overlap ratio between the current survey line and the previous survey line; S306, determining whether the coverage overlap ratio is within a set overlap ratio range, if so, executing S307; otherwise, executing S308; S307, record the position x of the survey line N+1 =x (i,0) , determine whether the survey line reaches the lateral boundary B2; if so, determine to obtain the initial position of each survey line; otherwise, assign the value of N+1 to the parameter N for updating, and then jump to step S304; S308, determine whether the coverage overlap ratio is greater than the maximum value of the overlap ratio range; if so, determine that the coverage overlap ratio is too large, and increase the spacing to D N =D N +1, jump to step S304; otherwise, determine that the coverage overlap rate is too small, and reduce the spacing to D N =D N -1, jump to step S304.
4. The method according to claim 3, characterized in that: Starting from the initial position of each measuring line until reaching the longitudinal boundary, searching for each particle passed by each measuring line includes: S410, determining the order of each measurement line, for the first measurement line in the order, starting from the initial position of the measurement line, searching for the particle with the largest next strip coverage width until reaching the longitudinal boundary, and obtaining each particle passed by the first measurement line; S420, for the remaining survey lines, starting from the initial position corresponding to the survey line, search for the next particle through the adaptive function until the path of the longitudinal boundary is reached, and the particles passed by the remaining survey lines are obtained respectively; wherein the adaptive function aims to maximize the strip coverage width of the survey line and minimize the coverage overlap rate of the particles on the survey line and the previous survey line.
5. The method according to claim 1, characterized in that The method further comprises: Obtain the seabed depth collected in real time by multi-beam sonar for the current particles in the rectangular sea area; The predicted seawater depth of the front particle is calculated based on the seabed depth, and the front particle includes a particle located in front of the current particle along the survey line direction; Determine the predicted strip coverage width of the front particle based on the predicted seawater depth of the front particle, and then obtain the predicted coverage overlap rate of the front particle; The strip coverage width of the current particle is replaced by the predicted strip coverage width of the preceding particle, and the coverage overlap rate of the current particle is replaced by the predicted coverage overlap rate of the preceding particle; The initial planned path is updated based on the predicted strip coverage width and predicted coverage overlap rate of the front particle to obtain the optimized path.
6. The method according to claim 1, characterized in that The method further comprises: The fitness function Updated to: ; The initial planned path is updated based on the updated adaptability function to obtain a dynamic planned path for real-time obstacle avoidance; in, is the normalized value of the stripe coverage width, is the normalized value of the coverage overlap ratio, is the normalized penalty value, and the calculation formula of the normalized penalty value is: ; in, is the maximum value of the obstacle penalty, is the minimum value of the obstacle penalty, is the obstacle penalty value; The calculation formula of obstacle penalty value is: ; Among them, (x (i,j) ,y (i,j) ) is the particle coordinate, (x barrier ,y barrier ) is the obstacle coordinate, and C is the penalty weight.
7. A path planning system for an unmanned ship, characterized in that: The system comprises: The first module is used to obtain the opening angle of the multi-beam transducer and the three-dimensional terrain data within the detection area of the multi-beam transducer; The second module is used to determine the strip coverage width of each survey line in the multi-beam transducer and the overlap rate of adjacent survey lines based on the opening angle of the multi-beam transducer and the three-dimensional terrain data; The third module is used to update the position of each survey line by using a greedy algorithm according to the strip coverage width of each survey line and the overlap rate of adjacent survey lines to obtain the initial position of each survey line; wherein the goal of the greedy algorithm is to minimize the total length of the survey line within a set overlap rate range; The fourth module is used to search for each particle that each measuring line passes through, starting from the initial position of each measuring line until it reaches the longitudinal boundary; The fifth module is used to use the initial position of each measuring line as the initial particle corresponding to the measuring line, start from the initial particle, search for the optimal particle among the particles passing through the measuring line by using the particle swarm algorithm, obtain the optimal particle corresponding to the measuring line, and connect the optimal particles corresponding to each measuring line to form an initial planning path; Starting from the initial particle, searching for the optimal particle among the particles through which the measurement line passes by using a particle swarm algorithm to obtain the optimal particle corresponding to the measurement line, and connecting the optimal particles corresponding to each measurement line to form an initial planning path, includes: S510, input the initial particle x corresponding to each measurement line N ; S520, record the eight adjacent particles of the (i, j)th particle in the rectangular sea area as the (i+n, j+m)th particle, initialize n=-1, m=0, f max =0; wherein n=-1, 0, 1, m=0, 1, 2, and n and m are not 0 at the same time; S530, calculate the fitness value f of the (i+n, j+m)th particle (i+n,j+m) , and the maximum fitness value f of the particle in the rectangular sea area max Compare, if f (i+n,j+m) Greater than f max , then update the maximum fitness value f max =f (i+n,j+m) , and record the coordinates of the (i+n, j+m)th particle i record =i+n,j record =j+m; otherwise jump to S540; S540, assign the value of m+1 to parameter m for updating, and determine whether the updated particle exceeds the current rectangular sea area. If not, that is, m<2, jump to S530; if exceeded, that is, m>2, jump to S550; S550, assign the value of n+1 to parameter n for updating, m=0; when n=0, m=1, determine whether the updated particle exceeds the current rectangular sea area, if not, that is, n<1, jump to S530, if exceeded, that is, n>1, jump to S560; S560, update i=i record , j = j record , taking the updated (i, j)th particle as the optimal particle, judging whether the longitudinal coordinate of the optimal particle in the rectangular sea area reaches the longitudinal boundary, if not, jumping to S520; if reaching, jumping to S570; S570, judging whether the horizontal coordinate of the optimal particle in the rectangular sea area reaches the horizontal coordinate boundary, if not, jumping to S580, if reached, jumping to S590; S580, assign the value of N+1 to the initial particle parameter N for updating, that is, updating the initial particle to the initial position x of the next measurement line N , jump to S510; S590, connecting the optimal particles of each measurement line to form an initial planning path.
8. A path planning device for an unmanned ship, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 6.
9. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to perform the method according to any one of claims 1 to 6 when executed by the processor.
Citation Information
Patent Citations
Unmanned ship path planning method and system based on greedy mechanism particle swarm algorithm
CN111338350A
Local path planning method based on obstacle self-protection artificial potential field method of particle swarm algorithm
CN113805597A
Measurement wiring design method, device and equipment of multi-beam measurement ship and medium
CN117709207A
Multi-beam survey line layout method, system and device and storage medium
CN118171586A
