CN115237139B - Unmanned ship path planning method considering virtual target point - Google Patents
Unmanned ship path planning method considering virtual target point Download PDFInfo
- Publication number
- CN115237139B CN115237139B CN202210959456.5A CN202210959456A CN115237139B CN 115237139 B CN115237139 B CN 115237139B CN 202210959456 A CN202210959456 A CN 202210959456A CN 115237139 B CN115237139 B CN 115237139B
- Authority
- CN
- China
- Prior art keywords
- unmanned ship
- target
- point
- target point
- potential field
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 53
- 238000002922 simulated annealing Methods 0.000 claims abstract description 10
- 238000005381 potential energy Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 238000004088 simulation Methods 0.000 abstract description 32
- 230000004888 barrier function Effects 0.000 abstract description 5
- 238000010276 construction Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 10
- 230000006872 improvement Effects 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004904 shortening Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned ship path planning method considering virtual target points, and aims to solve the problems that an unmanned ship is prone to being trapped in local minima and a target cannot be reached in path planning. For the problem that the target is unreachable, a repulsive force potential field function is created, and according to the distance between the measured target and the obstacle, the repulsive force born by the target is enabled to be zero, so that the unmanned ship can reach the target point. And for the local minimum problem, carrying out analysis on local minima caused by various barriers, and solving the minimum point problem caused by general barriers by combining a simulated annealing algorithm and an artificial potential field method. Aiming at the problem of local minimum caused by non-general U-shaped obstacles, a virtual target point construction algorithm is provided, and the problem is solved by establishing an improved algorithm of the virtual target point. Simulation results show that compared with other methods, the method reduces the problem of overlong paths caused by too large repulsive force, saves time, optimizes path planning, and accelerates algorithm speed.
Description
Technical Field
The invention relates to the field of unmanned ship path planning, in particular to unmanned ship path planning considering virtual target points.
Background
In recent years, with the rapid development of artificial intelligence technology, unmanned ships are widely used in various fields in life. The path planning technology is used as a key for ensuring safe navigation, and becomes a hot spot direction of current research. However, many route planning methods are cumbersome, inefficient, and prone to a large number of errors due to the complexity and uncertainty of the work environment.
The conventional artificial potential field method has the following problems: (1) The problem of local minima is that an unmanned ship is easy to sink into local oscillation, so that a target is not reachable; (2) When an obstacle exists near the target point, the unmanned ship oscillates near the target point and cannot really reach the target point; (3) Under the influence of the obstacle, unmanned ship path planning is easy to sink into local optimum. Patent CN114020032A 'unmanned aerial vehicle path planning method based on artificial potential field method and annealing algorithm' is too simplified in route system constraint, too simple in consideration of unmanned aerial vehicle dynamic constraint, the formulated route is dynamically constrained and practically unavailable, in addition, the environment space is subjected to dimension reduction treatment to two-dimensional space, the planned route is difficult to put into practical use, and the method considers the influence of various water surface environment factors, so that the method can be expanded to the problem of unmanned aerial vehicle path planning on water with more technical content. Patent CN113189984B "unmanned ship path planning method based on improved artificial potential field method" does not consider whether unmanned ship can complete the obtained rotation angle before collision against obstacle, and also does not consider planning effect generated by different navigational speed conditions. In the simulation of the patent CN202210543801.7 self-adaptive path planning method for unmanned ship navigational speed based on the improved artificial potential field method, the obstacle is regularized so as to be equivalent to a circular obstacle, the proposed method has a certain limitation, and is difficult to adapt to the complicated sea surface situation, and the method is also effective in solving the problem of avoiding high-density obstacles.
In summary, the problems of easy local minimum sinking and unreachable targets existing in the conventional artificial potential field method under the actual sailing condition of the unmanned ship become the problems to be solved.
Disclosure of Invention
The invention aims to provide an unmanned ship path planning method considering virtual target points, which solves the problems of unreachable targets and local minimum problems of the traditional manual potential field method applied to the unmanned ship path planning process, and enables a target object to find a collision-free safe path from a starting point to a terminal point in a specified area, and meanwhile, the path is more suitable and has higher efficiency.
The invention adopts the following technical scheme for solving the problems: by modifying the traditional artificial potential field model, a new potential field function is introduced. The hybrid algorithm is combined with various algorithm characteristics, so that the problem of local minimum caused by common obstacles is effectively solved. Aiming at the local minimum problem caused by the special obstacle, a construction method for solving the virtual target point of the U-shaped obstacle is provided, and another improved algorithm is also provided for solving the special local minimum problem. The method specifically comprises the following steps:
S1：
the controlled object is regarded as a particle and the environment is regarded as a two-dimensional space. A coordinate system is established in the two-dimensional space to determine the position of the controlled object. The gravitational potential field function formula generated by the target point is generally expressed as follows:
in U att (X) is a function of the gravitational potential field, k att Is the gain factor of the attraction potential field, X is the two-dimensional space coordinate of the controlled object, X g Is the coordinates of the target point, ρ (X, X g ) For the distance between the controlled object and the target point, the attraction force F att Is the gravitational potential field U att The derivative of the relative distance of the controlled object from the target point,
representing a partial derivative operator, the expression of which is:
according to equation (2), the gravitational potential field function increases linearly and monotonically with increasing distance between the controlled object and the target point, and the relationship between the controlled object and the destination becomes the orientation of the controlled object to point to the target. Because unmanned ship can remove, so must introduce a new factor with unmanned ship and the distance of target point department, under the effect of barrier like this, unmanned ship and the repulsion potential energy of target point department are zero, can not receive the influence of repulsion to guarantee that unmanned ship's potential energy is minimum at target point department, the repulsion potential field function after the correction is:
in U rep (q) * Is the function of the corrected repulsive force potential field, eta is the gain factor of the repulsive force potential field, q is the current position of the unmanned ship, and q obs Is the position of the minimum distance between the obstacle and the controlled object, q goal Is the position where the target point is located, ρ (q, q goal ) Is the relative distance between the controlled object and the target, ρ 0 Is the range of action of the obstacle, i.e. the disturbance range of its repulsive potential field.
S2：
Constructing an improved repulsive potential field function:
wherein F is req (q) * Is a function of the improved repulsive potential field,
representing partial derivative operator, dividing repulsive force into two parts by improved repulsive force field function, using F respectively 1 And F 2 Representation, F 1 The unmanned ship is connected with the obstacle, and the direction of the unmanned ship is from the obstacle to the unmanned ship; f (F) 2 The unmanned ship and the target point are connected, the direction of the unmanned ship points to the target point, the movement direction of the unmanned ship is changed by controlling the two forces, and the unmanned ship can point the target to the destination through the connection between the unmanned ship and the destination.
S3：
In order to solve the problem of local minimum in the artificial potential field method, two solving methods are proposed for different types of obstacles: the first method combines simulated annealing and artificial potential field methods, and solves the local minimum problem caused by common obstacles through different path planning algorithms. The specific implementation steps are as follows:
s3.1, establishing initial conditions, and determining an initial position, a target position and an obstacle position of the unmanned ship;
s3.2, searching from an initial point to the next point under the guidance of an artificial potential field method;
s3.3, judging whether the unmanned ship reaches a preset position or not when the unmanned ship reaches the next position;
s3.4, when the unmanned ship arrives at the destination, completing the algorithm and maintaining the path; when the unmanned ship does not reach the destination, judging whether the unmanned ship is in a local minimum;
s3.5, when the unmanned ship is in a local optimal state, the stress is balanced, the movement distance of the unmanned ship is shorter than the general movement step length and is almost zero, a simulated annealing algorithm is adopted to move on the next point, and then the unmanned ship starts from the next point;
and S3.6, under the condition of not sinking into the local optimum, continuing to search the path of the next target by using an artificial potential field method until the unmanned ship reaches the designated destination, and ending the algorithm.
S4：
The second approach is to solve the problem with virtual target points for local minimum problem caused by specific obstacle. Aiming at the problem of local minimum caused by a specific obstacle, a structure based on a virtual target point is provided, namely when an unmanned ship enters the local minimum caused by the specific obstacle, a new target point is formed in a movable unobstructed area, the new target point is separated from the local minimum point by the attractive force of the new target point, and finally searching is carried out. The specific implementation steps are as follows:
s4.1, establishing initial conditions, and simultaneously determining the initial position, the obstacle position and the like of the unmanned ship;
s4.2, moving from a starting point to a next point by using an artificial potential field method;
s4.3, when the unmanned ship reaches the next position, judging whether the unmanned ship reaches a target, and if the path is stored, completing an algorithm; if not, carrying out the next step of confirmation;
s4.4, judging whether the unmanned ship is in a local minimum state, if so, establishing a second target, moving the unmanned ship to the second target point, and when the transverse coordinate of the unmanned ship reaching the target point is larger than that of the target point, leaving the second target by the unmanned ship, leaving a local minimum area, and continuing to move to the next target under the influence of the gravity of the original target to enter S4.3;
s4.5 if the unmanned ship is not trapped at a local minimum, it will return to S4.2.
The invention has the following beneficial effects:
(1) The problem that the unmanned ship target cannot be reached is solved, and a new potential field function is introduced by correcting the traditional artificial potential field model so that the unmanned ship target reaches a target point. Compared with the Krogh improved algorithm, the method reduces the problem of overlong path length caused by too large repulsive force, improves the speed of the algorithm by 15.3% under the condition of the same environmental parameter, and shortens the optimized path length by 24.8%.
(2) The method solves the problem of solving the local minimum problem, combines the characteristics of a hybrid algorithm and other algorithms on the basis, and effectively solves the problem of solving the local minimum problem caused by common obstacles. Aiming at the local minimum problem caused by special obstacle, a construction method for solving the virtual target point of the U-shaped obstacle is provided. Meanwhile, an improved simulated annealing algorithm is provided to solve the problem of special local minimum values, so that the problem of local minimum values can be effectively avoided, a route can be solved, the calculation time is shortened, and the running time of the algorithm is shortened.
Drawings
FIG. 1 is a flow chart for constructing virtual target points;
FIG. 2 is a simulation diagram of a Krogh improved algorithm;
FIG. 3 is a simulation diagram of an improved algorithm for a repulsive force gain factor of 100;
FIG. 4 is a simulation diagram of an improved algorithm for a repulsive force gain factor of 500;
FIG. 5 is a simulation diagram of an improved algorithm with a repulsive force gain coefficient of 5000;
FIG. 6 is a simulation diagram of an improved algorithm for a repulsive force gain coefficient 25000;
FIG. 7 is a simulation of an unmanned ship sinking into a particular local minimum;
FIG. 8 is a simulation of a special local minimum value for an unmanned ship to jump out;
FIG. 9 is a diagram of a first high density obstacle simulation environment;
fig. 10 is a diagram of a second high density obstacle simulation environment.
Detailed Description
Fig. 1 is a flow chart of a method for planning a path of an unmanned ship taking virtual target points into consideration, which comprises the following steps:
S1：
in order to facilitate the comparison of simulation tests, a Krogh improvement algorithm is researched, the distance between an unmanned ship and a target point is combined, so that the repulsive force at the target point is zero, and the function of the repulsive force potential field after improvement is as follows:
S2：
the controlled object is regarded as a particle and the environment is regarded as a two-dimensional space. A coordinate system is established in the two-dimensional space to determine the position of the controlled object. The gravitational potential field function formula generated by the target point is generally expressed as follows:
in U att (X) is a function of the gravitational potential field, k att Is the gain factor of the attraction potential field, X is the two-dimensional space coordinate of the controlled object, X g Is the coordinates of the target point, ρ (X, X g ) For the distance between the controlled object and the target pointSeparation, attraction force F att Is the gravitational potential field U att The derivative of the relative distance of the controlled object from the target point,
representing a partial derivative operator, the expression of which is:
according to equation (3), the gravitational potential field function increases linearly and monotonically with increasing distance between the controlled object and the target point, and the relationship between the controlled object and the destination becomes the orientation of the controlled object to point to the target. The distance between the unmanned ship and the target point is introduced into a new factor, so that the repulsive potential energy between the unmanned ship and the target point is zero under the action of the obstacle, and the influence of the repulsive force is avoided, and the potential energy of the unmanned ship at the target point is ensured to be minimum. The modified repulsive potential field function is:
in U rep (q) * Is the function of the corrected repulsive force potential field, eta is the gain factor of the repulsive force potential field, q is the current position of the unmanned ship, and q obs Is the position of the minimum distance between the obstacle and the controlled object, q goal Is the position where the target point is located, ρ (q, q goal ) Is the relative distance between the controlled object and the target, ρ 0 Is the range of action of the obstacle, i.e. the disturbance range of its repulsive potential field.
S3：
Constructing an improved repulsive potential field function:
wherein F is req (q) * Is a function of the improved repulsive potential field,
representing partial derivative operator, dividing repulsive force into two parts by improved repulsive force field function, using F respectively 1 And F 2 Representation, F 1 The unmanned ship is connected with the obstacle, and the direction of the unmanned ship is from the obstacle to the unmanned ship; f (F) 2 The unmanned ship and the target point are connected, the direction of the unmanned ship points to the target point, the movement direction of the unmanned ship is changed by controlling the two forces, and the unmanned ship can point the target to the destination through the connection between the unmanned ship and the destination. Both repulsive forces are related to the distance, so that the target position is a global extreme point, and the unmanned ship can smoothly reach the destination.
S4：
When the obstacle is a common obstacle, a simulated annealing method is adopted to solve the local minimum problem. In the solution space, the probability jump feature is combined with the overall optimal solution of the objective function. The probability of being admitted is formulated as:
in the formula, let the solution of the current time search be x t The corresponding system energy (objective function) is E t Applying random disturbance to the search points to generate a new solution x t+1 Accordingly, the system energy is E t+1 The probability of acceptance of the system for the transition from the search point is equation (8).
S5：
In order to solve the problem of local minimum in the artificial potential field method, two solving methods are proposed for different kinds of obstacles. The first is to combine simulated annealing and artificial potential field methods to solve the local minimum problem caused by common obstacles through different path planning algorithms.
The simulated annealing algorithm has good randomness, can solve the problem of local minimum caused by common obstacles, can relatively quickly break the stress balance of the unmanned ship on water, makes the unmanned ship break away from the local minimum, and continuously moves towards the target. The specific implementation steps are as follows:
s5.1, establishing initial conditions, and determining an initial position, a target position and an obstacle position of the unmanned ship;
s5.2, searching from an initial point to the next point under the guidance of an artificial potential field method;
s5.3, judging whether the unmanned ship reaches a preset position or not when the unmanned ship reaches the next position;
s5.4, when the unmanned ship arrives at the destination, completing the algorithm and maintaining the path; when the unmanned ship does not reach the destination, judging whether the unmanned ship is in a local minimum;
s5.5, when the unmanned ship is in a local optimal state, the stress is balanced, the movement distance of the unmanned ship is shorter than the general movement step length and is almost zero, a simulated annealing algorithm is adopted to move on the next point, and then the unmanned ship starts from the next point;
and S5.6, under the condition that the unmanned ship does not fall into the local optimum, continuing to search the path of the next target by using an artificial potential field method until the unmanned ship reaches the designated destination, and ending the algorithm.
S6:
The second is to solve the related problems by adopting a virtual target point method aiming at the local minimum problem caused by the specific obstacle. Aiming at the problem of local minimum caused by a specific obstacle, a structure based on a virtual target point is provided, namely when an unmanned ship enters the local minimum caused by the specific obstacle, a new target point is formed in a movable unobstructed area, the new target point is separated from the local minimum point by the attractive force of the new target point, and finally searching is carried out. The specific implementation steps are as follows:
s6.1, establishing initial conditions, and simultaneously, determining the initial position, the obstacle position and the like of the unmanned ship;
s6.2, moving from a starting point to a next point by using an artificial potential field method;
s6.3, when the unmanned ship reaches the next position, judging whether the unmanned ship reaches a target, and if the path is stored, completing an algorithm; if not, carrying out the next step of confirmation;
s6.4, judging whether the unmanned ship is in a local minimum state, if so, establishing a second target, moving the unmanned ship to the second target point, and when the transverse coordinate of the unmanned ship reaching the target point is larger than that of the target point, leaving the second target by the unmanned ship, leaving a local minimum area, and continuing to move to the next target under the influence of the gravity of the original target to enter S6.3;
s6.5 if the unmanned ship is not trapped in a local minimum, it will return to S6.2.
Experiment one: in order to verify the effectiveness of the method, the improved algorithm uses MATLAB simulation software to carry out a simulation experiment in the whole process, basic parameter setting is carried out before the experiment, the value of the gravitational gain index is set to be 50, the value of the repulsive gain index is set to be 100, the influence distance of the obstacle is set to be 2, (1, 1) is the starting point, and (14, 14) is the overall target point. Assuming that a plurality of obstacles exist in the space, the coordinates of the obstacles are (5, 6), (6, 12), (7, 16), (7, 9), (10, 7), (12, 10) and (14.5,6), the full-automatic measuring and calculating program is executed, the length of the path is long and short, the index value takes two digits, and the improvement algorithm is applied to enable the unmanned water craft to bypass the obstacles from the starting point to reach the overall target point.
Fig. 2 is a simulation diagram of a Krogh improved algorithm, fig. 3 is a simulation diagram of an improved algorithm, and comparison can be seen: the improved method not only can effectively solve the phenomenon that the target is not reachable, but also can obtain a more proper path, thereby greatly shortening the length of the path. The simulation result pairs of the Krogh improvement algorithm and the improvement algorithm of the invention after operation are shown in table 1.
Table 1 simulation comparison of Krogh algorithm and improved algorithm of the present invention
It can be seen from the table that in the same case, the correct path can be well planned using both the Krogh improved method and the improved method herein, but the time spent is different and the optimized path length is also different. Compared with the Krogh improved method, the improved algorithm has the advantages that the time is consumed, the path length planned by the improved algorithm is smaller in the deviation of the designed route under the condition that no obstacle exists around the unmanned ship. By combining the results, a new optimization method is provided, and has the advantages of saving time, shortening paths, improving planning efficiency and the like, and the effectiveness of the method is verified.
In order to explore the proper gain coefficient value interval, three identical simulation environment simulation tests are designed. Except that the repulsive force gain coefficients are different, the other parameters are the same, and the operation time and the path length of the program are two digits after decimal points are removed. As shown in fig. 4, 5 and 6, the simulation results show that the longer the time required for calculation to the target position, the longer the distance of the unmanned ship to reach the target position, with the increase of the repulsive force gain coefficient. The improved algorithm of the invention has adjustable speed, shortens the length of the route, can be more suitable for real-time requirements, and also verifies the effectiveness of the algorithm. Three sets of simulation data are summarized in table 2:
table 2 comparison of simulation results
Experiment II:
for convenience of description and analysis, common obstacles in the environment are simplified into circles, and are divided into a plane, and different obstacles are arranged on different obstacles. Different parameters are initialized by MATLAB simulation software, and whether a route, a route length and time can be successfully planned or not is used as an evaluation index. Firstly, carrying out a local minimization test on U-shaped barriers by using a traditional artificial potential field method in the environment, and finding that the unmanned ship is in a local minimum state when the movement distance of the unmanned ship at two positions is zero. By improving the method, certain parameters are set: the attraction gain is 50, the repulsion coefficient is 100, the obstacle influence distance is 2, (0, 0) is the starting point, and (10.2) is the target, on the basis, the unmanned ship falls into a local minimum area after entering the U-shaped obstacle area, when the unmanned ship approaches the target, the unmanned ship stops moving to the target position, and under the guidance of an artificial potential field algorithm, the unmanned ship cannot deviate from the local minimum area, so that the path planning task is ended. As shown in the red path, the simulation results for the special local minimum problem are shown in fig. 7 below.
The invention combines the same obstacle, simulation environment and parameter setting in figure 7 with the improved algorithm to carry out simulation experiments and adopts the method, so that when the unmanned ship falls into local optimum, the method can effectively jump out of local minimum points when passing through U-shaped obstacles, thereby realizing overall path planning. The simulation results are shown in fig. 8.
From the simulation angle, it can be seen that when the unmanned ship passes through the U-shaped obstacle, the unmanned ship falls into a local optimal state when turning to the target position, and an extreme value cannot be jumped out by adopting an uncorrected artificial potential field algorithm, so that the unmanned ship stops in a period of time when approaching the target position. The method provided by the invention can effectively avoid the problem of local minimum values, and can solve an optimal route, so that the required time is less. Simulation experiments prove that the method is effective in solving the problem of local minimum values.
Experiment III: the navigation environment of unmanned ships on water is complicated, not only ships, reefs, shoal of fish, waste garbage and the like are arranged on the way to a destination, but also inner flow areas such as canyons, islands and the like can navigate, and local minimum value areas formed by high-density barriers sunk at two sides still exist. Therefore, in the simulation environment of the unmanned ship, not only the 'circle' is used for replacing the obstacle, but also the problem of avoiding the high-density obstacle needs to be emphasized. Simulation experiments are performed for such cases in combination with the improved algorithm to verify whether the improved algorithm can solve such cases, and fig. 9 and fig. 10 are two simulated environment simulation diagrams, respectively. Simulation experiments show that the method is effective in solving such local minimum problems.
The above embodiments further illustrate the objects, technical solutions and advantageous effects of the present invention, and the above examples are only for illustrating the technical solutions of the present invention, but not for limiting the scope of protection of the present invention, and those skilled in the art should understand that modifications, equivalents and alternatives of the technical solutions of the present invention are included in the scope of protection of the present invention.
Claims (1)
1. The unmanned ship path planning method taking virtual target points into consideration is characterized by comprising the following steps of:
S1：
the controlled object is regarded as a particle, the environment is regarded as a two-dimensional space, a coordinate system is established in the two-dimensional space to determine the position of the controlled object, and because the unmanned ship moves, a new factor is introduced into the distance between the unmanned ship and the target point, so that under the action of the obstacle, the repulsive potential energy between the unmanned ship and the target point is zero and is not influenced by the repulsive force, the potential energy of the unmanned ship at the target point is ensured to be minimum, and the corrected repulsive potential field function is as follows:
in U rep (q) * Is the function of the corrected repulsive force potential field, eta is the gain factor of the repulsive force potential field, q is the current position of the unmanned ship, and q obs Is the position of the minimum distance between the obstacle and the controlled object, q goal Is the position where the target point is located, ρ (q, q goal ) Is the relative distance between the controlled object and the target, ρ 0 Is the range of action of the obstacle, i.eThe disturbance range of the repulsive potential field;
S2：
constructing an improved repulsive potential field function:
wherein F is req (q) * Is a function of the improved repulsive potential field,
representing partial derivative operator, dividing repulsive force into two parts by improved repulsive force field function, using F respectively 1 And F 2 Representation, F 1 The unmanned ship is connected with the obstacle, and the direction of the unmanned ship is from the obstacle to the unmanned ship; f (F) 2 The unmanned ship is connected with the target point, the unmanned ship points to the target point, the movement direction of the unmanned ship is changed by controlling the two forces, and the unmanned ship can point the target to the destination through the connection between the unmanned ship and the destination;
S3：
in order to solve the problem of local minimum in the artificial potential field method, two solving methods are proposed for different types of obstacles: the first method combines simulated annealing and artificial potential field method, solves the local minimum problem caused by common obstacles through different path planning algorithms, and comprises the following specific implementation steps:
s3.1, establishing initial conditions, and determining an initial position, a target position and an obstacle position of the unmanned ship;
s3.2, searching from an initial point to the next point under the guidance of an artificial potential field method;
s3.3, judging whether the unmanned ship reaches a preset position or not when the unmanned ship reaches the next position;
s3.4, when the unmanned ship arrives at the destination, completing the algorithm and maintaining the path; when the unmanned ship does not reach the destination, judging whether the unmanned ship is in a local minimum;
s3.5, when the unmanned ship is in a local optimal state, the stress is balanced, the movement distance of the unmanned ship is shorter than the general movement step length and is almost zero, a simulated annealing algorithm is adopted to move on the next point, and then the unmanned ship starts from the next point;
s3.6, under the condition of not sinking into local optimum, continuing to search a path of the next target by using an artificial potential field method until the unmanned ship reaches a specified destination and ending the algorithm;
S4：
the second is to solve the related problems by adopting a virtual target point method aiming at the local minimum problem caused by a specific obstacle, and a structure based on the virtual target point is provided, namely when an unmanned ship enters the local minimum value caused by the specific obstacle, a new target point is formed in a movable unobstructed area, the new target point is separated from the local minimum value point by the attractive force of the new target point, and finally, the searching is carried out, wherein the specific implementation steps are as follows:
s4.1, establishing initial conditions, and simultaneously determining the initial position and the obstacle position of the unmanned ship;
s4.2, moving from a starting point to a next point by using an artificial potential field method;
s4.3, when the unmanned ship reaches the next position, judging whether the unmanned ship reaches a target, and if the path is stored, completing an algorithm; if not, carrying out the next step of confirmation;
s4.4, judging whether the unmanned ship is in a local minimum state, if so, establishing a second target, moving the unmanned ship to the second target point, and when the transverse coordinate of the unmanned ship reaching the target point is larger than that of the target point, leaving the second target by the unmanned ship, leaving a local minimum area, and continuing to move to the next target under the influence of the gravity of the original target to enter S4.3;
s4.5 if the unmanned ship is not trapped at a local minimum, it will return to S4.2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210959456.5A CN115237139B (en) | 2022-08-10 | 2022-08-10 | Unmanned ship path planning method considering virtual target point |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210959456.5A CN115237139B (en) | 2022-08-10 | 2022-08-10 | Unmanned ship path planning method considering virtual target point |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115237139A CN115237139A (en) | 2022-10-25 |
| CN115237139B true CN115237139B (en) | 2023-05-23 |
Family
ID=83679178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210959456.5A Active CN115237139B (en) | 2022-08-10 | 2022-08-10 | Unmanned ship path planning method considering virtual target point |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115237139B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9096106B2 (en) * | 2011-05-12 | 2015-08-04 | Unmanned Innovations, Inc | Multi-role unmanned vehicle system and associated methods |
| CN112631293A (en) * | 2020-12-16 | 2021-04-09 | 江苏大学 | Unmanned ship anti-collision Internet of things control system and method based on artificial potential field method |
| CN113189984B (en) * | 2021-04-16 | 2021-10-29 | 哈尔滨理工大学 | Unmanned ship path planning method based on improved artificial potential field method |
| CN114003047B (en) * | 2021-12-31 | 2022-04-08 | 山东科技大学 | Path planning method for small unmanned ship |
| CN114839994B (en) * | 2022-05-18 | 2022-11-15 | 哈尔滨理工大学 | Unmanned ship navigational speed self-adaptive path planning method based on improved artificial potential field method |
-
2022
- 2022-08-10 CN CN202210959456.5A patent/CN115237139B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115237139A (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | A hybrid path planning algorithm for unmanned surface vehicles in complex environment with dynamic obstacles | |
| CN113064426B (en) | Intelligent vehicle path planning method for improving bidirectional fast search random tree algorithm | |
| CN111399506A (en) | Global-local hybrid unmanned ship path planning method based on dynamic constraints | |
| CN110956853B (en) | Multi-ship collision prediction method, system and storage medium | |
| CN110703762A (en) | Hybrid path planning method for unmanned surface vehicle in complex environment | |
| CN109579854B (en) | Unmanned vehicle obstacle avoidance method based on fast expansion random tree | |
| CN107883961A (en) | A kind of underwater robot method for optimizing route based on Smooth RRT algorithms | |
| CN111338350A (en) | Unmanned ship path planning method and system based on greedy mechanism particle swarm algorithm | |
| CN112650256A (en) | Improved bidirectional RRT robot path planning method | |
| CN113961004A (en) | Pirate area ship route planning method and system, electronic equipment and storage medium | |
| CN109931943B (en) | Unmanned ship global path planning method and electronic equipment | |
| CN113359775B (en) | Dynamic variable sampling area RRT unmanned vehicle path planning method | |
| CN113467476B (en) | Collision-free detection rapid random tree global path planning method considering corner constraint | |
| CN110906935A (en) | Unmanned ship path planning method | |
| CN109765890B (en) | Multi-USV group collaborative collision avoidance planning method based on genetic algorithm | |
| CN114625150B (en) | Rapid ant colony unmanned ship dynamic obstacle avoidance method based on danger coefficient and distance function | |
| CN115167398A (en) | Unmanned ship path planning method based on improved A star algorithm | |
| CN111307158A (en) | AUV three-dimensional route planning method | |
| CN110954124A (en) | Adaptive path planning method and system based on A-PSO algorithm | |
| CN114705196A (en) | Self-adaptive heuristic global path planning method and system for robot | |
| CN110262473B (en) | Unmanned ship automatic collision avoidance method based on improved Bi-RRT algorithm | |
| CN115237139B (en) | Unmanned ship path planning method considering virtual target point | |
| Wang et al. | Autonomous path planning method of uuv in complex environment based on improved ant colony optimization algorithm | |
| Nian et al. | Research on global path planning of unmanned sailboat based on improved ant colony optimization | |
| Li et al. | A Global Dynamic Path Planning Algorithm Based on Optimized A* Algorithm and Improved Dynamic Window Method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |