Obstacle avoidance planning method and system based on artificial potential field method and vector field method

Abstract

The present invention provides an obstacle avoidance planning method and system based on an artificial potential field method and a vector field method, comprising: initializing information; determining whether an unmanned boat has reached a target point; establishing a virtual attraction from the target point on the unmanned boat and a virtual repulsion from the obstacle on the unmanned boat; determining whether the target position is within the influence range of the obstacle; determining whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within a set safety range; determining whether the cosine value of the angle between the direction of the repulsive force on the unmanned boat and the direction of the water flow is less than 0; determining the direction of motion of the unmanned boat based on the virtual attraction, virtual repulsion, the influence of the water flow, and the influence of the countercurrent, calculating the next position of the unmanned boat, and controlling the unmanned boat to move to the calculated position. The present invention proposes introducing the influence of water flow into artificial potential field path planning to plan the unmanned boat's motion path, thereby avoiding path planning failures caused by the influence of water flow.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to an obstacle avoidance planning method and system based on an artificial potential field method and a vector field method, and more particularly to an obstacle avoidance planning method based on an artificial potential field method and a vector field method under the influence of water flow. Background Art

[0002] Effectively preventing and mitigating casualties and property losses caused by urban flooding is a critical task in my country's disaster prevention and control efforts. Unmanned boats, with their maneuverability, safety, and efficiency, can significantly enhance flood response and rescue capabilities. Obstacles such as urban buildings, natural rocks, rocks, and trees, "reefs" formed by submerged buildings and other natural objects close to the water surface, as well as other moving rescue vessels and large floating objects can hinder the progress of unmanned boats. To reach the rescue target, the unmanned boat must plan a collision-free path from its starting point to its destination, avoiding collisions with obstacles.

[0003] Key point-to-point path planning algorithms for obstacle avoidance include the A* algorithm, genetic algorithm, ant colony algorithm, artificial potential field method, and rapidly expanding random tree method. The artificial potential field method is widely used due to its simple principle and structure, as well as its real-time performance. The artificial potential field method plans the path of an unmanned vessel using a weighted combination of shortest path and path safety as its criteria. The principle is that the robot moves under the combined force of the virtual gravitational force of the target point and the virtual repulsive force of obstacles.

[0004] In urban flood rescue, there are still some problems when using traditional artificial potential field methods to plan the path of unmanned boats. The main problems include:

[0005] (1) When the unmanned boat follows the planned path, the water flow will affect the direction of movement of the unmanned boat, and the movement path may deviate from the planned path, reducing the safety of the path;

[0006] (2) The traditional artificial potential field method is prone to causing the unmanned ship to fall into a local minimum point due to the balance between the virtual attraction and the virtual repulsion, making it impossible to plan the direction of the next movement. Figure 3In the scenario shown, the virtual gravitational force and the virtual repulsive force acting on the unmanned boat reach equilibrium, resulting in a net force of zero, and the boat is trapped in a local minimum. Currently, there are two main methods for resolving local minima: 1. Introducing additional forces to disrupt the force balance, such as establishing virtual target points, virtual obstacles, or setting escape forces; 2. Combining other path planning algorithms to escape the local minimum using algorithms such as RRT, Fireworks, and Simulated Annealing. When the influence of water flow is introduced, if the direction of the water flow is collinear with the line connecting the obstacle and the target point, the boat's path will oscillate near the local minimum. This is because when the virtual net force acting on the boat is balanced, the boat moves toward the water flow, increasing the repulsive force (or gravitational force), creating an imbalance in the virtual force, and causing the boat to move in the opposite direction, known as countercurrent motion. This countercurrent motion will then reach or pass through the virtual net force equilibrium point. After passing this point, the gravitational force (or repulsive force) increases, causing the boat to reverse its motion again, causing the boat to oscillate near the local minimum, leading to path planning failure.

[0007] Therefore, solving the water flow influence and local minimum problems of the existing unmanned boat artificial potential field path planning method is of great significance to the development of unmanned rescue after urban flooding.

[0008] Therefore, it is necessary to propose a new technical solution to improve the above technical problems. Summary of the Invention

[0009] In view of the defects in the prior art, the purpose of the present invention is to provide an obstacle avoidance planning method and system based on artificial potential field method and vector field method.

[0010] According to the present invention, an obstacle avoidance planning method based on an artificial potential field method and a vector field method is provided, the method comprising the following steps:

[0011] Step S1: Initialize information and use GPS to determine the location information of the unmanned boat's starting point and target point. Obstacles between the starting point and target point are obtained based on the existing city grid map. The velocity and direction of the water flow are measured using a current meter and buoy flow measurement method. Obstacles not found on the map are detected using the sonar and GPS installed on the unmanned boat. Their location information and size are obtained through signal processing and incorporated into the planning algorithm for obstacle avoidance.

[0012] Step S2: Determine whether the unmanned boat has reached the target point. If so, end the path planning. Otherwise, detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and proceed to step S3 for path planning.

[0013] Step S3: Establishing the virtual attraction of the target point on the unmanned ship and the virtual repulsion of the obstacle on the unmanned ship;

[0014] Step S4: Determine whether the target position is within the influence range of the obstacle. If so, introduce countercurrent planning and then go to step S5; otherwise, go to step S6;

[0015] Step S5: Determine whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, reduce the repulsion weight coefficient; otherwise, use the original weight coefficient and then go to step S7;

[0016] Step S6: Determine whether the cosine value of the angle between the direction of the repulsive force on the unmanned boat and the direction of the water flow is less than 0. If so, reverse the repulsive force; otherwise, maintain the original repulsive force direction and proceed to step S7.

[0017] Step S7: Calculate the direction of movement of the unmanned boat based on the virtual gravity, virtual repulsion, water flow and countercurrent, calculate the next position of the unmanned boat, control the unmanned boat to move to the calculated position, and then go to step S2.

[0018] Preferably, the specific implementation of step S1 is as follows: initializing information, obtaining the position information of the unmanned boat by the GPS and measurement of the unmanned boat, determining the position of the target point by executing the task, obtaining the position information and size of obstacles between the starting point and the target point based on the existing city grid map, measuring the flow velocity and direction of the water flow by using a current meter and a buoy flow measurement method, detecting obstacles not found in the map in real time by using the sonar and GPS installed on the unmanned boat, obtaining their position information and size by signal processing, approximating all obstacles as circular obstacles for processing, and incorporating them into the path planning algorithm for planning;

[0019] The specific implementation method of step S2 is as follows: calculate the distance between the current position of the unmanned boat and the target point, determine whether the unmanned boat has reached the target point, and end the path planning if so; otherwise, use sonar to detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and use the artificial potential field method to continue planning the unmanned boat's moving path.

[0020] Preferably, step S3 includes the following steps:

[0021] Step S3.1: Establish a virtual gravitational field at the target point, calculate the virtual gravitational force of the target point on the unmanned boat, and attract the unmanned boat to approach the target point;

[0022] Step S3.2: Establish a virtual repulsive force field at the obstacle point, calculate the virtual repulsive force of the obstacle on the unmanned boat, and make the unmanned boat go around the obstacle.

[0023] Preferably, the specific implementation of step S4 is: calculating the distance between the target position and each obstacle, judging whether the target is located in the virtual repulsive field of the obstacle, if so, introducing countercurrent planning, and then turning to step S5; otherwise, turning to step S6;

[0024] The specific implementation method of step S5 is: calculate whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, the unmanned boat moves in a straight line to the target point without colliding with the obstacle, and the repulsion weight is set to 0; otherwise, the original weight coefficient is used; and then the process goes to step S7.

[0025] Preferably, the specific implementation of step S6 is as follows: calculating the cosine value of the angle between the virtual repulsive force on the unmanned boat at the current position and the direction of the water flow; if it is less than 0, the unmanned boat path will quickly approach the obstacle under the influence of the water flow, and the path safety will be reduced, and the repulsive force is reversed, so that the unmanned boat will go around in the opposite direction to avoid the obstacle; if it is greater than 0, the unmanned boat path will not quickly approach the obstacle under the influence of the water flow, and the original repulsive force direction is maintained; then the process goes to step S7;

[0026] The specific implementation method of step S7 is: normalize the virtual gravity, virtual repulsion, water flow influence and countercurrent influence on the unmanned ship and then perform weighted addition to obtain the next movement direction of the unmanned ship, set the movement step length of the unmanned ship per unit time, obtain the next position of the unmanned ship, and then go to step S2 to continue planning the unmanned ship rescue path.

[0027] The present invention also provides an obstacle avoidance planning system based on artificial potential field method and vector field method, the system comprising the following modules:

[0028] Module M1: Initializes information, uses GPS to determine the location of the unmanned boat's starting and target points, obtains the location and size of obstacles between the starting and target points based on the existing city grid map, measures the flow rate and direction using a current meter and buoy flow measurement method, detects obstacles not found on the map using the sonar and GPS installed on the unmanned boat, obtains their location and size through signal processing, and incorporates this information into the planning algorithm for obstacle avoidance.

[0029] Module M2: Determines whether the unmanned boat has reached the target point. If so, the path planning ends. Otherwise, it detects whether there are new obstacles and their location information, as well as the position changes of known obstacles, and then proceeds to module M3 for path planning.

[0030] Module M3: Establish the virtual gravitational force of the target point on the unmanned ship and the virtual repulsive force of the obstacle on the unmanned ship;

[0031] Module M4: Determine whether the target location is within the influence range of the obstacle. If so, introduce countercurrent planning and then proceed to module M5; otherwise, proceed to module M6;

[0032] Module M5: Determine whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, reduce the repulsion weight coefficient; otherwise, use the original weight coefficient and then transfer to module M7;

[0033] Module M6: Determine whether the cosine value of the angle between the repulsive force acting on the unmanned boat and the water flow direction is less than 0. If so, the repulsive force is reversed; otherwise, the original repulsive force direction is maintained and the process proceeds to module M7.

[0034] Module M7: Calculate the direction of movement of the unmanned boat based on virtual gravity, virtual repulsion, water flow and countercurrent, calculate the next position of the unmanned boat, control the unmanned boat to move to the calculated position, and then transfer to module M2.

[0035] Preferably, the module M1 is specifically implemented as follows: initializing information, obtaining the position information of the unmanned vessel by the GPS and measurement of the unmanned vessel, determining the position of the target point by executing the task, obtaining the position information and size of obstacles between the starting point and the target point based on the existing city grid map, measuring the flow velocity and direction of the water flow using a current meter and a buoy flow measurement method, detecting obstacles not found in the map in real time using the sonar and GPS installed on the unmanned vessel, obtaining their position information and size through signal processing, approximating all obstacles as circular obstacles for processing, and incorporating them into the path planning algorithm for planning;

[0036] The specific implementation method of the module M2 is as follows: calculate the distance between the current position of the unmanned ship and the target point, determine whether the unmanned ship has reached the target point, and end the path planning if so; otherwise, use sonar to detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and use the artificial potential field method to continue planning the unmanned ship's moving path.

[0037] Preferably, the module M3 includes the following modules:

[0038] Module M3.1: Establish a virtual gravitational field at the target point, calculate the virtual gravitational force of the target point on the unmanned boat, and attract the unmanned boat to the target point;

[0039] Module M3.2: Establish a virtual repulsive force field at the obstacle point, calculate the virtual repulsive force of the obstacle on the unmanned boat, and enable the unmanned boat to bypass the obstacle.

[0040] Preferably, the specific implementation of the module M4 is as follows: calculating the distance between the target position and each obstacle, determining whether the target is located in the virtual repulsive field of the obstacle, if so, introducing countercurrent planning, and then transferring to module M5; otherwise, transferring to module M6;

[0041] The specific implementation method of the module M5 is as follows: calculate whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, the unmanned boat moves in a straight line to the target point without colliding with the obstacle, and the repulsion weight is set to 0; otherwise, the original weight coefficient is used; and then the module M7 is entered.

[0042] Preferably, the module M6 is specifically implemented as follows: calculating the cosine value of the angle between the virtual repulsive force on the unmanned boat at the current position and the direction of the water flow; if it is less than 0, the unmanned boat path will quickly approach the obstacle under the influence of the water flow, and the path safety will be reduced, and the repulsive force will be reversed, so that the unmanned boat will go around in the opposite direction to avoid the obstacle; if it is greater than 0, the unmanned boat path will not quickly approach the obstacle under the influence of the water flow, and the original repulsive force direction will be maintained; then the process goes to module M7;

[0043] The specific implementation method of the module M7 is: the virtual gravity, virtual repulsion, water flow influence and countercurrent influence exerted on the unmanned ship are normalized and then weightedly added to obtain the next movement direction of the unmanned ship, the movement step length of the unmanned ship per unit time is set, the next position of the unmanned ship is obtained, and then the module M2 is entered to continue planning the unmanned ship rescue path.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] 1. Water flow will affect the direction of movement of the unmanned boat, thereby changing its movement path. The present invention proposes to introduce the influence of water flow into the artificial potential field path planning to plan the movement path of the unmanned boat, so as to avoid the failure of path planning due to the influence of water flow;

[0046] 2. This invention proposes introducing a vector field as a repulsive field into the artificial potential field method. A repulsive field is constructed around the obstacle, oriented along the obstacle's tangent and away from the obstacle toward the target. This ensures that the cosine of the angle between the virtual repulsive force and the virtual gravitational force acting on the unmanned vehicle is always greater than zero. This prevents the unmanned vehicle from falling into a local minimum due to the force equilibrium between the virtual repulsive force and the virtual gravitational force. This allows the unmanned vehicle to bypass the obstacle and move toward the target, preventing the unmanned vehicle's path from oscillating near the local minimum.

[0047] 3. The present invention proposes that when the cosine value of the angle between the direction of the virtual repulsive force on the unmanned boat and the direction of the water flow is less than 0, the unmanned boat is directed to follow the water flow in the opposite direction to avoid the obstacle. This prevents the unmanned boat from rapidly approaching the obstacle due to the action of the water flow, thereby improving the path safety under the influence of the water flow.

[0048] 4. When the target point is near an obstacle, the unmanned boat may circumvent the obstacle due to the virtual repulsion weight coefficient being greater than the virtual attraction weight coefficient, causing the unmanned boat to circumvent the obstacle, preventing the unmanned boat from reaching the target point or making the path to the target point longer. Therefore, the present invention designs a safe travel angle for the unmanned boat. Within this angle range, the unmanned boat moves in a straight line toward the target point without colliding with obstacles. At the same time, under the influence of water flow, the unmanned boat may circumvent the obstacle to reach the target point, which will make the path longer. Therefore, it is proposed to introduce countercurrent planning to counter the influence of water flow on the unmanned boat's movement direction, so that the unmanned boat can move along the optimal path planned based on the shortest path and path safety indicators. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0050] Figure 1 This is a flow chart of an obstacle avoidance planning method based on artificial potential field method and vector field method under the influence of water flow provided by the present invention;

[0051] Figure 2 It is a schematic diagram of the path of the present invention;

[0052] Figure 3 It is a schematic diagram of the force at the local minimum point of the unmanned ship;

[0053] Figure 4 is a schematic diagram of a repulsive field established around an obstacle by the present invention;

[0054] Figure 5 This is a simulation process diagram of dynamic obstacle avoidance using the algorithm that introduces the vector field method into the artificial potential field method without considering the influence of water flow;

[0055] Figure 6 This is the simulation result of the dynamic obstacle avoidance algorithm using the vector field method introduced into the artificial potential field method without considering the influence of water flow;

[0056] Figure 7 This is a simulation result diagram that takes the influence of water flow into consideration but does not improve the planning method;

[0057] Figure 8 Simulation results showing improvements to the planning method by taking into account the impact of water flow;

[0058] Figure 9 exist Figure 7 Simulation results of the algorithm incorporating global counterflow planning. DETAILED DESCRIPTION

[0059] The present invention will be described in detail below with reference to specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those skilled in the art, several changes and improvements can be made without departing from the scope of the present invention. These all fall within the scope of protection of the present invention.

[0060] Example 1:

[0061] According to the present invention, an obstacle avoidance planning method based on an artificial potential field method and a vector field method is provided, the method comprising the following steps:

[0062] Step S1: Initialize information, use GPS to determine the position information of the unmanned boat's starting point and target point, obtain the position information and size of obstacles between the starting point and the target point according to the existing city grid map, use a current meter and a buoy flow measurement method to measure the water flow velocity and direction, use the sonar and GPS installed on the unmanned boat to detect obstacles not found in the map, obtain their position information and size through signal processing, and add them to the planning algorithm for obstacle avoidance; Initialize information, use the GPS of the unmanned boat and measure the position information of the unmanned boat, determine the position of the target point by executing the task, obtain the position information and size of obstacles between the starting point and the target point according to the existing city grid map, use a current meter and a buoy flow measurement method to measure the water flow velocity and direction, use the sonar and GPS installed on the unmanned boat to detect obstacles not found in the map in real time, and obtain their position information and size through signal processing, approximate all obstacles as circular obstacles for processing, and add them to the path planning algorithm for planning.

[0063] Step S2: Determine whether the unmanned boat has reached the target point. If so, end the path planning; otherwise, detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and proceed to step S3 for path planning; calculate the distance between the current position of the unmanned boat and the target point, and determine whether the unmanned boat has reached the target point. If so, end the path planning; otherwise, use sonar to detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and use the artificial potential field method to continue planning the unmanned boat's moving path.

[0064] Step S3: Establishing the virtual attraction of the target point on the unmanned ship and the virtual repulsion of the obstacle on the unmanned ship;

[0065] Step S3.1: Establish a virtual gravitational field at the target point, calculate the virtual gravitational force of the target point on the unmanned boat, and attract the unmanned boat to approach the target point;

[0066] Step S3.2: Establish a virtual repulsive force field at the obstacle point, calculate the virtual repulsive force of the obstacle on the unmanned boat, and make the unmanned boat go around the obstacle.

[0067] Step S4: Determine whether the target position is within the influence range of the obstacle. If so, introduce countercurrent planning and then go to step S5; otherwise, go to step S6; calculate the distance between the target position and each obstacle, and determine whether the target is within the virtual repulsive field of the obstacle. If so, introduce countercurrent planning and then go to step S5; otherwise, go to step S6.

[0068] Step S5: Determine whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, reduce the repulsion weight coefficient; otherwise, use the original weight coefficient, and then go to step S7; calculate whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, the unmanned boat moves in a straight line to the target point without colliding with the obstacle, and the repulsion weight is set to 0; otherwise, use the original weight coefficient; then go to step S7.

[0069] Step S6: Determine whether the cosine value of the angle between the direction of the repulsive force on the unmanned boat and the direction of the water flow is less than 0. If so, reverse the repulsive force; otherwise, maintain the original repulsive force direction, and then proceed to step S7; calculate the cosine value of the angle between the virtual repulsive force on the unmanned boat at the current position and the direction of the water flow. If it is less than 0, the unmanned boat path will quickly approach the obstacle under the influence of the water flow, reducing the path safety, and reverse the repulsive force so that the unmanned boat can avoid the obstacle in the opposite direction; if it is greater than 0, the unmanned boat path will not quickly approach the obstacle under the influence of the water flow, and the original repulsive force direction is maintained; then proceed to step S7;

[0070] Step S7: Calculate the direction of movement of the unmanned boat based on the virtual gravity, virtual repulsion, water flow and countercurrent, calculate the next position of the unmanned boat, control the unmanned boat to move to the calculated position, and then go to step S2; normalize the virtual gravity, virtual repulsion, water flow and countercurrent on the unmanned boat and then perform weighted addition to calculate the next direction of movement of the unmanned boat, set the movement step length of the unmanned boat per unit time, calculate the next position of the unmanned boat, and then go to step S2 to continue planning the unmanned boat rescue path.

[0071] The present invention also provides an obstacle avoidance planning system based on the artificial potential field method and the vector field method. The obstacle avoidance planning system based on the artificial potential field method and the vector field method can be implemented by executing the process steps of the obstacle avoidance planning method based on the artificial potential field method and the vector field method. That is, those skilled in the art can understand the obstacle avoidance planning method based on the artificial potential field method and the vector field method as a preferred implementation method of the obstacle avoidance planning system based on the artificial potential field method and the vector field method.

[0072] Example 2:

[0073] Example 2 is a preferred example of Example 1 and is used to illustrate the present invention in more detail.

[0074] The present invention also provides an obstacle avoidance planning system based on artificial potential field method and vector field method, the system comprising the following modules:

[0075] Module M1: Initialization information, use GPS to determine the position information of the unmanned boat's starting point and target point, obtain the position information and size of the obstacles between the starting point and the target point according to the existing city grid map, use a current meter and buoy flow measurement method to measure the water flow velocity and direction, use the sonar and GPS installed on the unmanned boat to detect obstacles not found in the map, obtain their position information and size through signal processing, and add them to the planning algorithm for obstacle avoidance; Initialization information, use the GPS of the unmanned boat and measure the position information of the unmanned boat, determine the position of the target point by executing the task, obtain the position information and size of the obstacles between the starting point and the target point according to the existing city grid map, use a current meter and buoy flow measurement method to measure the water flow velocity and direction, use the sonar and GPS installed on the unmanned boat to detect obstacles not found in the map in real time, and obtain their position information and size through signal processing, approximate all obstacles as circular obstacles for processing, and add them to the path planning algorithm for planning.

[0076] Module M2: Determine whether the unmanned boat has reached the target point. If so, end the path planning; otherwise, detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and transfer to module M3 for path planning; calculate the distance between the current position of the unmanned boat and the target point, and determine whether the unmanned boat has reached the target point. If so, end the path planning; otherwise, use sonar to detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and use the artificial potential field method to continue planning the unmanned boat's moving path.

[0077] Module M3: Establish the virtual gravitational force of the target point on the unmanned ship and the virtual repulsive force of the obstacle on the unmanned ship;

[0078] Module M3.1: Establish a virtual gravitational field at the target point, calculate the virtual gravitational force of the target point on the unmanned boat, and attract the unmanned boat to the target point;

[0079] Module M3.2: Establish a virtual repulsive force field at the obstacle point, calculate the virtual repulsive force of the obstacle on the unmanned boat, and enable the unmanned boat to bypass the obstacle.

[0080] Module M4: Determine whether the target position is within the influence range of the obstacle. If so, introduce countercurrent planning and then transfer to module M5; otherwise, transfer to module M6; calculate the distance between the target position and each obstacle, and determine whether the target is within the virtual repulsive field of the obstacle. If so, introduce countercurrent planning and then transfer to module M5; otherwise, transfer to module M6.

[0081] Module M5: Determine whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, reduce the repulsion weight coefficient; otherwise, use the original weight coefficient, and then transfer to module M7; calculate whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, the unmanned boat moves in a straight line to the target point without colliding with the obstacle, and the repulsion weight is set to 0; otherwise, use the original weight coefficient; then transfer to module M7.

[0082] Module M6: Determine whether the cosine value of the angle between the direction of the repulsive force on the unmanned boat and the direction of the water flow is less than 0. If so, the repulsive force is reversed; otherwise, the original repulsive force direction is maintained, and then the module is transferred to M7; the cosine value of the angle between the virtual repulsive force on the unmanned boat at the current position and the direction of the water flow is calculated. If it is less than 0, the unmanned boat path will quickly approach the obstacle under the influence of the water flow, and the path safety will be reduced. The repulsive force is reversed, and the unmanned boat is forced to go around in the opposite direction to avoid the obstacle; if it is greater than 0, the unmanned boat path will not quickly approach the obstacle under the influence of the water flow, and the original repulsive force direction is maintained; then the module is transferred to M7.

[0083] Module M7: Calculate the direction of movement of the unmanned boat based on the virtual gravity, virtual repulsion, water flow and countercurrent, calculate the next position of the unmanned boat, control the unmanned boat to move to the calculated position, and then transfer to module M2; normalize the virtual gravity, virtual repulsion, water flow and countercurrent on the unmanned boat and then perform weighted addition to calculate the next direction of movement of the unmanned boat, set the movement step length of the unmanned boat per unit time, calculate the next position of the unmanned boat, and then transfer to module M2 to continue planning the unmanned boat rescue path.

[0084] Example 3:

[0085] Example 3 is a preferred example of Example 1 and is used to illustrate the present invention in more detail.

[0086] When an unmanned boat is moving, the effect of water flow will affect the direction of movement of the unmanned boat. During the movement, the unmanned boat may collide with obstacles. Therefore, the present invention provides an obstacle avoidance planning method based on artificial potential field method and vector field method under the influence of water flow, and introduces the influence of water flow in the artificial potential field path planning. At the same time, the traditional artificial potential field method is prone to fall into local minimum and when the influence of water flow is introduced, the planned path is prone to oscillate near the local minimum point. The present invention introduces the vector field method, and establishes a repulsive field around the obstacle according to the measured position of the unmanned boat and the obstacle, and the current direction of movement of the unmanned boat, so that the virtual resultant force of the unmanned boat is not zero, and the obstacle can be bypassed. At the same time, due to the influence of the water flow direction, the actual driving path will be offset from the planned path, and the path safety will be reduced. Therefore, it is proposed to design an unmanned boat to detour along the direction of the water flow around the obstacle to improve the path safety.

[0087] To achieve the above object, the present invention provides an obstacle avoidance planning method under the influence of water flow based on artificial potential field method and vector field method, comprising the following steps:

[0088] S1: Initialize information, use GPS to determine the location information of the starting point and target point of the unmanned boat, obtain the location information and size of obstacles between the starting point and the target point based on the existing city grid map, measure the flow rate and direction of the water using a current meter and buoy flow measurement method, use the sonar and GPS installed on the unmanned boat to detect obstacles not found in the map, obtain their location information and size through signal processing, and incorporate them into the planning algorithm for obstacle avoidance;

[0089] S2: Determine whether the unmanned boat has reached the target point. If so, end the path planning. Otherwise, detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and proceed to S3 for path planning.

[0090] S3: Establish the virtual gravitational force of the target point on the unmanned ship and the virtual repulsive force of the obstacle on the unmanned ship;

[0091] S4: Determine whether the target position is within the influence range of the obstacle. If so, introduce counterflow planning and then go to S5; otherwise, go to S6;

[0092] S5: Determine whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, reduce the repulsion weight coefficient; otherwise, use the original weight coefficient and then go to S7;

[0093] S6: Determine whether the cosine value of the angle between the repulsive force acting on the unmanned boat and the water flow direction is less than 0. If so, reverse the repulsive force; otherwise, maintain the original repulsive force direction and proceed to S7.

[0094] S7: Calculate the direction of movement of the unmanned boat based on the virtual gravity, virtual repulsion, water flow and countercurrent, calculate the next position of the unmanned boat, control the unmanned boat to move to the calculated position, and then go to S2.

[0095] The specific implementation method of step S1 is as follows: initialize information, use the GPS of the unmanned boat and measure the position information of the unmanned boat, determine the position of the target point by executing the task, obtain the position information and size of the obstacles between the starting point and the target point according to the existing city grid map, use the current meter and buoy current measurement method to measure the flow rate and direction of the water flow, use the sonar and GPS installed on the unmanned boat to detect obstacles not found in the map in real time, such as ships, large floating objects, etc., and obtain their position information and size through signal processing, approximate all obstacles as circular obstacles for processing, and add them to the path planning algorithm for planning.

[0096] The specific implementation method of step S2 is: calculate the distance between the current position of the unmanned boat and the target point, determine whether the unmanned boat has reached the target point, and end the path planning if so; otherwise, use sonar to detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and use the artificial potential field method to continue planning the unmanned boat's moving path.

[0097] Step S3 includes:

[0098] S31: Establish a virtual gravitational field at the target point, calculate the virtual gravitational force of the target point on the unmanned boat, and attract the unmanned boat to approach the target point;

[0099] S32: Establish a virtual repulsive force field at the obstacle point, calculate the virtual repulsive force of the obstacle on the unmanned boat, and make the unmanned boat bypass the obstacle.

[0100] The specific implementation method of step S4 is: calculate the distance between the target position and each obstacle, determine whether the target is located in the virtual repulsive field of the obstacle, and if so, introduce countercurrent planning and then go to S5; otherwise, go to S6.

[0101] The specific implementation method of step S5 is: calculate whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, the unmanned boat moves in a straight line to the target point without colliding with the obstacle, and the repulsion weight is set to 0; otherwise, the original weight coefficient is used; then go to S7.

[0102] Step S6 is implemented by calculating the cosine of the angle between the virtual repulsive force acting on the unmanned boat at its current location and the direction of the water flow. If the cosine is less than 0, the unmanned boat's path will rapidly approach the obstacle under the influence of the water flow, reducing path safety. Therefore, the repulsive force is reversed, forcing the unmanned boat to circumvent the obstacle. If the cosine is greater than 0, the unmanned boat's path will not rapidly approach the obstacle under the influence of the water flow, so the original repulsive force direction is maintained. The process then proceeds to S7.

[0103] The specific implementation method of step S7 is: the virtual gravity, virtual repulsion, water flow influence and countercurrent influence of the unmanned ship are normalized and then weighted added, thereby obtaining the next movement direction of the unmanned ship, setting the movement step length of the unmanned ship per unit time, and then obtaining the next position of the unmanned ship, and then turning to S2 to continue planning the unmanned ship rescue path.

[0104] like Figure 1 As shown, in order to address the deficiencies of the prior art, the present invention provides an obstacle avoidance planning method under the influence of water flow based on an artificial potential field method and a vector field method, comprising the following steps:

[0105] S1: Initialize information, use GPS to determine the location information of the starting point and target point of the unmanned boat, obtain the location information and size of obstacles between the starting point and the target point based on the existing city grid map, measure the flow rate and direction of the water using a current meter and buoy flow measurement method, use the sonar and GPS installed on the unmanned boat to detect obstacles not found in the map, obtain their location information and size through signal processing, and incorporate them into the planning algorithm for obstacle avoidance;

[0106] S2: Determine whether the unmanned boat has reached the target point. If so, end the path planning. Otherwise, detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and proceed to S3 for path planning.

[0107] S3: Establish the virtual gravitational force of the target point on the unmanned ship and the virtual repulsive force of the obstacle on the unmanned ship;

[0108] S4: Determine whether the target position is within the influence range of the obstacle. If so, introduce counterflow planning and then go to S5; otherwise, go to S6;

[0109] S5: Determine whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, reduce the repulsion weight coefficient; otherwise, use the original weight coefficient and then go to S7;

[0110] S6: Determine whether the cosine value of the angle between the repulsive force acting on the unmanned boat and the water flow direction is less than 0. If so, reverse the repulsive force; otherwise, maintain the original repulsive force direction and proceed to S7.

[0111] S7: Calculate the direction of movement of the unmanned boat based on the virtual gravity, virtual repulsion, water flow and countercurrent, calculate the next position of the unmanned boat, control the unmanned boat to move to the calculated position, and then go to S2.

[0112] The specific implementation method of step S1 is as follows: initialize information, use the GPS of the unmanned boat and measure the position information of the unmanned boat, determine the position of the target point by executing the task, obtain the position information and size of the obstacles between the starting point and the target point according to the existing city grid map, use the current meter and buoy current measurement method to measure the flow rate and direction of the water flow, use the sonar and GPS installed on the unmanned boat to detect obstacles not found in the map in real time, such as ships, large floating objects, etc., and obtain their position information and size through signal processing, approximate all obstacles as circular obstacles for processing, and add them to the path planning algorithm for planning.

[0113] The obstacle is approximated as a circular obstacle. The center and radius of the connected obstacle grid are calculated to obtain the obstacle's location and radius: the center of the obstacle grid is obtained by averaging the coordinate values ​​of all connected obstacle grids. The diagonal length of the circumscribed rectangle of the connected obstacle grid is calculated as the diameter, thereby obtaining the radius of the approximately circular obstacle.

[0114] The specific implementation of step S2 is as follows: calculating the distance between the current position of the unmanned boat and the target point, determining whether the distance between the current position of the unmanned boat and the target point is within a set threshold range. If it is within this range, the unmanned boat has reached the target point and the path planning ends; otherwise, using sonar to detect whether there are new obstacles and their location and size information, as well as the position changes of known obstacles, and using the changed obstacle information based on the artificial potential field method to continue planning the unmanned boat's movement path. The present invention uses the unmanned boat's single-step navigation distance l as the threshold for determining whether the unmanned boat has reached the target point. If the distance between the unmanned boat's current position and the target point is less than its single-step navigation distance, the unmanned boat is considered to have reached the target point; otherwise, the unmanned boat is considered to have not reached the target point.

[0115] Step S3 includes:

[0116] S31: Establish a virtual gravitational field at the target point, calculate the virtual gravitational force of the target point on the unmanned boat, and attract the unmanned boat to approach the target point;

[0117] S32: Establish a virtual repulsive force field at the obstacle point, calculate the virtual repulsive force of the obstacle on the unmanned boat, and make the unmanned boat bypass the obstacle.

[0118] The specific implementation method of step S31 to establish a virtual gravitational field is:

[0119]

[0120] U att is the virtual gravitational field function, k is the proportional gravitational gain coefficient, x r ,x g Represent the position vectors of the unmanned ship and the target point at the current moment. The corresponding gravitational force F att is the negative gradient of the gravitational field function:

[0121]

[0122] The specific implementation of step S32 is: define a cluster of virtual repulsive force vector fields U r for:

[0123]

[0124] λ is a parameter that specifies the direction of the repulsive force, λ∈R, R represents a one-dimensional real number set, p specifies the overall direction of the repulsive force field around the obstacle, which is opposite to the direction of motion V of the unmanned ship, p∈R 2 , R 2 represents the two-dimensional real space, p T represents the transpose of p. ro is the position vector of the unmanned ship relative to the obstacle at the current moment, x ro =x r -x o , x o is the position vector of the obstacle at the current moment, Represents x ro The transpose of . Define the obstacle repulsion F on the unmanned boat rep for:

[0125]

[0126] The schematic diagram of repulsive field and repulsive force is as follows Figure 3 shown.

[0127] The weight coefficients of virtual attraction and virtual repulsion are:

[0128]

[0129] W att is the weight coefficient of virtual gravity, W rep is the weight coefficient of the virtual repulsion. α is the weight coefficient of the obstacle repulsion and is related to the distance of the unmanned ship from the obstacle. When the unmanned ship is far away from the obstacle O, the repulsion of the obstacle O has no effect on the unmanned ship, at which point α = 1; as the unmanned ship gets closer to the obstacle O, the value of α decreases; when the unmanned ship is at the safety boundary of the obstacle O, the repulsion of the obstacle O has the greatest effect on the unmanned ship, at which point α = 0. α is defined as:

[0130]

[0131] Where ρ0 is the safe range of the unmanned vessel from the center of obstacle O when moving near it, and its value is 1.5 times the obstacle radius. ρ1 is the influence range of the repulsive field of obstacle O, with the center of the repulsive field at the center of obstacle O. ρ1 is three times the obstacle radius, and ρ is the distance between the unmanned vessel and the center of obstacle O. The values ​​of ρ0 and ρ1 can also be adjusted based on the simulation results.

[0132] If there are multiple obstacles, the weight coefficients of virtual attraction and virtual repulsion are expanded to:

[0133]

[0134] α iis the weight coefficient of the repulsive force of the i-th obstacle, i = 1, 2, ..., M, where M is the number of obstacles.

[0135] Step S4 is implemented by calculating the distance between the target location and each obstacle. If the distance between the target location and the obstacle is not greater than the range of influence of the obstacle's virtual repulsive field, the target is within the obstacle's virtual repulsive field. Under the influence of the water flow, the unmanned boat may have to circumvent the obstacle to reach the target point, resulting in a longer path. Therefore, countercurrent planning is introduced to counteract the influence of the water flow on the unmanned boat's movement direction, allowing the unmanned boat to move along the optimal path planned based on the shortest path and path safety indicators. The process then proceeds to S5 to plan the unmanned boat's movement path. If the distance between the target location and the obstacle is greater than the range of influence of the obstacle's virtual repulsive field, the target is outside the obstacle's repulsive field, and the process proceeds to S6 to plan the unmanned boat's movement path.

[0136]

[0137] W count is the weight coefficient of countercurrent planning, W count = -1, introduce countercurrent motion to plan the path of the unmanned boat, W count =1, countercurrent motion is not introduced to plan the path of the unmanned boat. Going against the current, the unmanned boat needs to consume extra energy; going with the current can save energy; going sideways not only consumes extra energy, but also increases the difficulty of control. Sideways navigation is the worst, going against the current is average, and going with the current is the best. Therefore, global countercurrent planning is not added to the planning algorithm of the present invention to resist the influence of water flow on the path. Table 1 shows the path energy consumption weights considering the influence of water flow direction, which are set with reference to Lin Yulong's "Research on Autonomous Sea Sweeping Path Planning of Unmanned Boats in Complex Marine Environments".

[0138] Table 1 Path energy consumption weights considering the influence of water flow direction

[0139]

[0140] Step S5 is implemented as follows: To prevent the unmanned boat from colliding with obstacles, the obstacle's repulsive force increases as the boat approaches the obstacle. However, when the target point is near an obstacle, the obstacle's virtual repulsive force becomes greater than the target point's virtual attractive force on the boat, forcing the boat to circumvent the obstacle, preventing it from reaching the target or increasing the distance to the target. Therefore, a safe travel angle for the unmanned boat is designed, within which the boat can move in a straight line toward the target point without colliding with an obstacle.

[0141] Calculate the vector x of the unmanned boat relative to the obstacle at the current moment ro Vector x relative to the obstacle goWhether the angle β is within the range of the set safety angle γ, if so, the unmanned boat moves in a straight line to the target point without colliding with obstacles, and the repulsive force weight is set to 0; otherwise, the original weight coefficient is used; and then the process goes to S7.

[0142]

[0143]

[0144]

[0145] where x go =x g -x o . l s is the single-step sailing distance of the unmanned boat in still water, l s The value is not greater than v r t, v r is the still water speed of the unmanned ship, and the present invention takes v r is 4 knots, t is the single-step sailing time, and the present invention takes l s =v r ·t. l s It should not be larger than the diameter of the smallest obstacle to prevent the unmanned vessel from crossing the obstacle in a single step.

[0146] The specific implementation of step S6 is: calculate the virtual repulsive force F that the unmanned ship is subjected to at its current location rep With water flow direction D dir If the cosine value of the angle θ is less than 0, the unmanned boat path will quickly approach the obstacle under the influence of the water flow, and the path safety will be reduced. Therefore, the repulsive force is reversed, causing the unmanned boat to go around in the opposite direction to avoid the obstacle. If it is not less than 0, the unmanned boat path will not quickly approach the obstacle under the influence of the water flow, so the original repulsive direction is maintained.

[0147]

[0148]

[0149] The specific implementation method of step S7 is: the virtual gravity, virtual repulsion, water flow influence and countercurrent influence of the unmanned ship are normalized and then weighted added, thereby obtaining the next movement direction of the unmanned ship, setting the movement step length of the unmanned ship per unit time, and then obtaining the next position of the unmanned ship, and then turning to S2 to continue planning the unmanned ship rescue path.

[0150] Virtual force F acting on the unmanned ship vt for:

[0151]

[0152] is the repulsive force of the i-th obstacle on the unmanned boat.

[0153] When W count = 1, the motion F of the unmanned ship in the bow direction st for:

[0154]

[0155] When W count = -1, the countercurrent planning is introduced to offset the influence of the water flow direction on the movement direction of the unmanned boat, so that the actual movement direction of the unmanned boat is the virtual resultant force F vt The purpose of counterflow planning is to make the virtual resultant force F vt The direction is the actual movement direction, the bow direction F st +Water flow direction dir = Actual direction of movement F vt .v flow is the water flow velocity. This invention refers to the water flow velocity in the flooded area after the heavy rain in Zhengzhou in 2021, and takes v flow =0.8m / s. The speed of the unmanned boat cannot be less than the water flow velocity, otherwise it may not be able to reach the target point. dir For the water flow direction, the present invention takes flow dir =(1,-1). According to the flow direction of water flow dir and flow rate v flow , the speed of the unmanned ship in the upstream planning direction, that is, the bow direction of the unmanned ship is its still water speed v r , and the actual direction of movement F vt , use the law of cosines to find the speed v of the unmanned ship in the actual direction of motion rr The upstream planning single-step sailing distance of the unmanned boat l d =v rr t. Movement of the unmanned ship in the bow direction F st for:

[0156]

[0157] In summary, the motion F of the unmanned ship in the bow direction can be obtained st for:

[0158]

[0159] Therefore, the actual motion of the unmanned boat under the influence of water flow is F t for:

[0160] F t =F st +v flow flow dir (18)

[0161] The next position of the unmanned ship planning x p(r+1) for:

[0162] x p(r+1) =x r +F st (19)

[0163] The actual next position x of the unmanned boat under the influence of water flow r+1 for:

[0164] x r+1 =x r +F t (20)

[0165] The present invention proposes to introduce a vector field as a repulsive field into the artificial potential field method to plan an obstacle avoidance path, so that the unmanned boat can bypass obstacles, solving the problem that the unmanned boat is prone to falling into local extreme values ​​in the artificial potential field method. The present invention proposes to consider the influence of water flow in the path planning based on the artificial potential field method and the vector field method, and designs the unmanned boat to bypass the obstacle in the direction of the water flow to improve the safety of the path. When the target point exists near the obstacle, the present invention designs a variable weight coefficient and plans the countercurrent movement at the same time to prevent the unmanned boat from being unable to reach the target point or generating an oscillating path due to the repulsive force and the influence of the water flow.

[0166] like Figure 1 This is a flow chart of an obstacle avoidance planning method based on artificial potential field method and vector field method under the influence of water flow provided by the present invention.

[0167] like Figure 2 It is a path schematic diagram of the present invention.

[0168] like Figure 3 Schematic diagram of the force acting on the local minimum point of the unmanned ship when . At this time, the virtual resultant force acting on the unmanned ship is 0.

[0169] like Figure 4 It is the repulsive field set around the obstacle when the present invention realizes the artificial potential field obstacle avoidance. The gray arrows around the obstacle indicate the direction of the repulsive force.

[0170] like Figure 5 This diagram illustrates the simulation process for dynamic obstacle avoidance using the vector field method in the artificial potential field method, without considering the effects of water flow. In the figure, black circles represent static obstacles, and gray circles represent dynamic obstacles. These obstacles are set to move horizontally between 60 and 100 meters on the horizontal axis at a speed of 1 meter per second. Gray dots represent each planned path point. Black squares represent the initial position, and gray squares represent the target position. The coordinate axes are in meters.

[0171] like Figure 6This is the simulation result of the dynamic obstacle avoidance algorithm using the vector field method introduced into the artificial potential field method without considering the influence of water flow. Figure 5 and Figure 6 It can be seen that the path planned by the algorithm can avoid collisions with moving obstacles, and the algorithm is real-time.

[0172] like Figure 7 This figure shows the simulation results when the influence of water flow is included but the planning method is not modified. As can be seen from the figure, the actual path of the unmanned boat can approach obstacles due to the influence of water flow, and may even collide with obstacles, significantly reducing the safety of the path. Furthermore, the shortest path indicator of the unmanned boat is also degraded due to the influence of water flow.

[0173] like Figure 8 Simulation results showing an improved planning method that considers the effects of current. When the cosine of the angle between the virtual repulsive force and the current direction is less than 0, the repulsive force is reversed, allowing the unmanned boat to bypass the obstacle with the current, improving path safety. As shown in the figure, the unmanned boat successfully navigates the obstacle with the current, improving path safety. When the target point is near an obstacle, countercurrent planning is introduced to counteract the effects of the current, allowing the unmanned boat to move in the desired direction. As shown in the figure, under the influence of the current, the unmanned boat is able to avoid the obstacle and reach the target point.

[0174] like Figure 9 is Figure 7 The simulation results of the algorithm using global counterflow planning are shown in the figure. Figure 6 The results are similar, and the countercurrent planning method used can successfully resist the influence of water flow on the moving direction of the unmanned boat. Figure 8 The energy consumption value of the path obtained by the algorithm is 534.7155. Figure 9 The energy consumption of the path obtained by the algorithm is 611.9596. The countercurrent planning has a large energy loss on the unmanned boat, so the global countercurrent planning is not used to resist the influence of water flow.

[0175] Those skilled in the art may understand this embodiment as a more specific description of Embodiment 1 and Embodiment 2.

[0176] Those skilled in the art will appreciate that, in addition to implementing the system and its various devices, modules, and units provided by the present invention in purely computer-readable program code, it is entirely possible to implement the same functions of the system and its various devices, modules, and units provided by the present invention in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; the devices, modules, and units for implementing various functions can also be considered as both software modules implementing the method and structures within the hardware component.

[0177] The above describes specific embodiments of the present invention. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art may make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. The embodiments of this application and the features in the embodiments may be combined with each other in any manner unless there is a conflict.

Claims

1. An obstacle avoidance planning method based on artificial potential field method and vector field method, characterized in that: The method comprises the following steps: Step S1: Initialize information and use GPS to determine the location information of the unmanned boat's starting point and target point. Obstacles between the starting point and target point are obtained based on the existing city grid map. The velocity and direction of the water flow are measured using a current meter and buoy flow measurement method. Obstacles not found on the map are detected using the sonar and GPS installed on the unmanned boat. Their location information and size are obtained through signal processing and incorporated into the planning algorithm for obstacle avoidance. Step S2: Determine whether the unmanned boat has reached the target point. If so, end the path planning. Otherwise, detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and proceed to step S3 for path planning. Step S3: Establishing the virtual attraction of the target point on the unmanned ship and the virtual repulsion of the obstacle on the unmanned ship; Step S4: Determine whether the target position is within the influence range of the obstacle. If so, introduce countercurrent planning and then go to step S5; otherwise, go to step S6; Step S5: Determine whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, reduce the repulsion weight coefficient; otherwise, use the original weight coefficient and then go to step S7; Step S6: Determine whether the cosine value of the angle between the direction of the repulsive force on the unmanned boat and the direction of the water flow is less than 0. If so, reverse the repulsive force; otherwise, maintain the original repulsive force direction and proceed to step S7. Step S7: Calculate the direction of movement of the unmanned boat based on the virtual gravity, virtual repulsion, water flow and countercurrent, calculate the next position of the unmanned boat, control the unmanned boat to move to the calculated position, and then go to step S2.

2. The obstacle avoidance planning method based on the artificial potential field method and the vector field method according to claim 1 is characterized in that: The specific implementation of step S1 is as follows: initializing information, obtaining the position information of the unmanned vessel by GPS and measuring the position information of the unmanned vessel, determining the position of the target point by executing the task, obtaining the position information and size of obstacles between the starting point and the target point based on the existing city grid map, measuring the flow velocity and direction of the water flow using a current meter and a buoy flow measurement method, detecting obstacles not found in the map in real time using the sonar and GPS installed on the unmanned vessel, obtaining their position information and size through signal processing, approximating all obstacles as circular obstacles for processing, and incorporating them into the path planning algorithm for planning; The specific implementation method of step S2 is as follows: calculate the distance between the current position of the unmanned boat and the target point, determine whether the unmanned boat has reached the target point, and end the path planning if so; otherwise, use sonar to detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and use the artificial potential field method to continue planning the unmanned boat's moving path.

3. The obstacle avoidance planning method based on artificial potential field method and vector field method according to claim 1 is characterized in that: The step S3 comprises the following steps: Step S3.1: Establish a virtual gravitational field at the target point, calculate the virtual gravitational force of the target point on the unmanned boat, and attract the unmanned boat to approach the target point; Step S3.2: Establish a virtual repulsive force field at the obstacle point, calculate the virtual repulsive force of the obstacle on the unmanned boat, and make the unmanned boat go around the obstacle.

4. The obstacle avoidance planning method based on artificial potential field method and vector field method according to claim 1, characterized in that: The specific implementation of step S4 is as follows: calculating the distance between the target position and each obstacle, determining whether the target is located in the virtual repulsive field of the obstacle, and if so, introducing counterflow planning, and then turning to step S5; otherwise, turning to step S6; The specific implementation method of step S5 is: calculate whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, the unmanned boat moves in a straight line to the target point without colliding with the obstacle, and the repulsion weight is set to 0; otherwise, the original weight coefficient is used; and then the process goes to step S7.

5. The obstacle avoidance planning method based on artificial potential field method and vector field method according to claim 1, characterized in that: The specific implementation of step S6 is as follows: the cosine value of the angle between the virtual repulsive force exerted on the unmanned boat at the current position and the direction of the water flow is calculated; if the cosine value is less than 0, the unmanned boat path will quickly approach the obstacle under the influence of the water flow, reducing the path safety, and the repulsive force is reversed, causing the unmanned boat to bypass the obstacle in the opposite direction; if the cosine value is greater than 0, the unmanned boat path will not quickly approach the obstacle under the influence of the water flow, and the original repulsive force direction is maintained; then the process goes to step S7; The specific implementation method of step S7 is: normalize the virtual gravity, virtual repulsion, water flow influence and countercurrent influence on the unmanned ship and then perform weighted addition to obtain the next movement direction of the unmanned ship, set the movement step length of the unmanned ship per unit time, obtain the next position of the unmanned ship, and then go to step S2 to continue planning the unmanned ship rescue path.

6. An obstacle avoidance planning system based on artificial potential field method and vector field method, characterized in that: The system includes the following modules: Module M1: Initializes information, uses GPS to determine the location of the unmanned boat's starting and target points, obtains the location and size of obstacles between the starting and target points based on the existing city grid map, measures the flow rate and direction using a current meter and buoy flow measurement method, detects obstacles not found on the map using the sonar and GPS installed on the unmanned boat, obtains their location and size through signal processing, and incorporates this information into the planning algorithm for obstacle avoidance. Module M2: Determines whether the unmanned boat has reached the target point. If so, the path planning ends. Otherwise, it detects whether there are new obstacles and their location information, as well as the position changes of known obstacles, and then proceeds to module M3 for path planning. Module M3: Establish the virtual gravitational force of the target point on the unmanned ship and the virtual repulsive force of the obstacle on the unmanned ship; Module M4: Determine whether the target location is within the influence range of the obstacle. If so, introduce countercurrent planning and then proceed to module M5; otherwise, proceed to module M6; Module M5: Determine whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, reduce the repulsion weight coefficient; otherwise, use the original weight coefficient and then transfer to module M7; Module M6: Determine whether the cosine value of the angle between the repulsive force acting on the unmanned boat and the water flow direction is less than 0. If so, the repulsive force is reversed; otherwise, the original repulsive force direction is maintained and the process proceeds to module M7. Module M7: Calculate the direction of movement of the unmanned boat based on virtual gravity, virtual repulsion, water flow and countercurrent, calculate the next position of the unmanned boat, control the unmanned boat to move to the calculated position, and then transfer to module M2.

7. The obstacle avoidance planning system based on artificial potential field method and vector field method according to claim 6, characterized in that: The specific implementation of the module M1 is as follows: initializing information, obtaining the position information of the unmanned boat by GPS and measuring the position information of the unmanned boat, determining the position of the target point by executing the task, obtaining the position information and size of obstacles between the starting point and the target point based on the existing city grid map, measuring the flow velocity and direction of the water flow using a current meter and buoy flow measurement method, detecting obstacles not found in the map in real time using the sonar and GPS installed on the unmanned boat, obtaining their position information and size through signal processing, approximating all obstacles as circular obstacles for processing, and incorporating them into the path planning algorithm for planning; The specific implementation method of the module M2 is as follows: calculate the distance between the current position of the unmanned ship and the target point, determine whether the unmanned ship has reached the target point, and end the path planning if so; otherwise, use sonar to detect whether there are new obstacles and their location information, as well as the position changes of known obstacles, and use the artificial potential field method to continue planning the unmanned ship's moving path.

8. The obstacle avoidance planning system based on artificial potential field method and vector field method according to claim 6, characterized in that: The module M3 includes the following modules: Module M3.1: Establish a virtual gravitational field at the target point, calculate the virtual gravitational force of the target point on the unmanned boat, and attract the unmanned boat to the target point; Module M3.2: Establish a virtual repulsive force field at the obstacle point, calculate the virtual repulsive force of the obstacle on the unmanned boat, and enable the unmanned boat to bypass the obstacle.

9. The obstacle avoidance planning system based on artificial potential field method and vector field method according to claim 6, characterized in that: The specific implementation of the module M4 is as follows: calculating the distance between the target position and each obstacle, judging whether the target is located in the virtual repulsive field of the obstacle, if so, introducing countercurrent planning, and then transferring to module M5; otherwise, transferring to module M6; The specific implementation method of the module M5 is as follows: calculate whether the angle between the vector of the unmanned boat relative to the obstacle and the vector of the target relative to the obstacle is within the set safety range. If so, the unmanned boat moves in a straight line to the target point without colliding with the obstacle, and the repulsion weight is set to 0; otherwise, the original weight coefficient is used; and then the module M7 is entered.

10. The obstacle avoidance planning system based on artificial potential field method and vector field method according to claim 6, characterized in that: The specific implementation of module M6 is as follows: the cosine value of the angle between the virtual repulsive force on the unmanned boat at the current position and the direction of the water flow is calculated. If the cosine value is less than 0, the unmanned boat path will quickly approach the obstacle under the influence of the water flow, reducing the path safety, and the repulsive force is reversed, causing the unmanned boat to bypass the obstacle in the opposite direction; if the cosine value is greater than 0, the unmanned boat path will not quickly approach the obstacle under the influence of the water flow, and the original repulsive force direction is maintained; then the process goes to module M7; The specific implementation method of the module M7 is: the virtual gravity, virtual repulsion, water flow influence and countercurrent influence exerted on the unmanned ship are normalized and then weightedly added to obtain the next movement direction of the unmanned ship, the movement step length of the unmanned ship per unit time is set, the next position of the unmanned ship is obtained, and then the module M2 is entered to continue planning the unmanned ship rescue path.

Images