Unmanned aerial vehicle dynamic path planning improvement method for improving artificial potential field

Abstract

The invention provides an unmanned aerial vehicle dynamic path planning promotion method for improving an artificial potential field, and relates to the technical field of unmanned aerial vehicle path planning. The method aims at solving the problems that a traditional artificial potential field method has many limitations in aircraft path planning, for example, when facing scenes with different obstacle distribution, shapes, sizes and target accessibility, an aircraft is likely to fall into a local optimal solution, oscillates near obstacles or cannot smoothly pass through a narrow channel, and the like. A repulsive force potential field function and a gravitational force potential field function are improved, multiple environmental perception factors are introduced to dynamically adjust gravitational force and repulsive force, and a weight distribution and resultant force smoothing technology is combined, so that the performance and stability of path planning are improved, and the path planning is more reasonable.

Description

Technical Field

[0001] The invention relates to the technical field of unmanned aerial vehicle path planning, and in particular to an unmanned aerial vehicle dynamic path planning improvement method with an improved artificial potential field. Background Art

[0002] With the rapid development of high-tech technologies such as artificial intelligence, big data, unmanned control and new energy, unmanned aerial vehicles have been widely used in many fields. At present, the number of drones in the airspace continues to rise. Under this circumstance, how to ensure the flight safety of drones has become a research hotspot, and path planning is the key research point to ensure flight safety.

[0003] Dynamic path planning is an important part of the research field of unmanned aerial vehicles. Specifically, it means that the aircraft explores a path from the starting point to the end point in an environment with dynamic obstacles, ensuring that the aircraft can avoid obstacles safely and without collision during the flight along this path. Depending on whether the environmental information in the path planning is known, the path planning algorithm can be divided into global path planning and local path planning.

[0004] At present, in the process of research on UAV path planning algorithms for different application scenarios, a variety of algorithm ideas have emerged, such as genetic algorithm, particle swarm algorithm, ant colony algorithm, artificial potential field method, etc. However, traditional path planning algorithms still have drawbacks and can only be applied to simple scenarios or scenarios with specific conditions. Once the environment is complex and changeable, the target is often unreachable, making it difficult for the UAV to accurately reach the destination. In order to solve the problem of unreachable targets in traditional artificial potential field methods, some studies apply external force when falling into a local minimum in order to escape from the state, but there is still a possibility of falling into it again after escaping. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method for improving the dynamic path planning of unmanned aerial vehicles with an improved artificial potential field in view of the deficiencies of the above-mentioned prior art, optimize the traditional gravity and repulsion models, prevent the UAV from falling into an unreachable state during flight, thereby improving the accuracy and reliability of path planning.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: a method for improving the dynamic path planning of unmanned aerial vehicles based on the improved artificial potential field method. Based on the traditional artificial potential field method, an artificial potential field including obstacles and target points is established, the repulsive potential field function and the gravitational potential field function are improved, and a variety of environmental perception factors are introduced to dynamically adjust the gravity and repulsion. The weight distribution and resultant force smoothing technology are combined to improve the performance and stability of path planning and make the path planning more reasonable.

[0007] The present invention provides a method for improving the dynamic path planning of an unmanned aerial vehicle by improving an artificial potential field, comprising the following steps:

[0008] S1. Obtain the starting point, target point and obstacle information of the UAV, establish an artificial potential field environment in a certain airspace, and regard the UAV, target point and obstacle as mass points;

[0009] S2, constructing an initial repulsive potential field function, introducing the distance factor from the unmanned aerial vehicle to the target point to improve the repulsive potential field function, and obtaining a repulsive potential field function based on the distance from the unmanned aerial vehicle to the target point;

[0010] Define the current position of the UAV as P(x,y), and the position of the target point as P goal (x,y), the position of the obstacle is P ob (x,y), construct the initial repulsive potential field function U rep , as shown in the following formula:

[0011]

[0012] Among them, d(P,P ob ) is the distance between the UAV and the obstacle, d0 is the maximum distance of the obstacle, and obstacles greater than this distance will not affect the flight of the UAV, and η is the repulsion coefficient;

[0013] The distance factor from the UAV to the target point is introduced to improve the repulsive potential field function. The improved repulsive potential field function U r ' ep for:

[0014]

[0015] Among them, k rep and k r ' ep are the repulsive coefficients of the repulsive potential field function based on the distance from the UAV to the target point, d(P,P goal ) is the distance from the UAV to the target point, is the unit vector pointing from the obstacle to the UAV, is the unit vector pointing from the UAV to the target point;

[0016] When d(P,P ob )≤d0, set but for

[0017]

[0018] set up but for

[0019]

[0020] When d(P,P ob )>d0, the repulsive potential field function U r ' ep is 0;

[0021] We can further obtain the repulsive potential field function U based on the distance from the unmanned aerial vehicle to the target point according to the vector expansion: r ' ep for:

[0022]

[0023] S3, constructing an initial gravitational potential field function, introducing a variety of environmental perception factors to dynamically adjust the gravitational potential field function, and constructing a gravitational potential field function based on a variety of environmental perception factors;

[0024] S3.1. Constructing the initial gravitational potential field function U att , as shown in the following formula:

[0025]

[0026] Among them, ξ is the gravitational coefficient;

[0027] S3.2. Select key environmental parameters according to the actual working requirements of the UAV, and use multiple key environmental parameters to improve the gravitational potential field function so that gravity can dynamically adapt to the environment;

[0028] Set the number of obstacles around the UAV to n obs To prevent the UAV from blindly rushing towards the target and falling into an obstacle trap, we introduced Term, where α is the weight coefficient, is the reference obstacle quantity threshold;

[0029] Set the average distance between obstacles and UAVs to In order to prevent the UAV from colliding with obstacles, The term adjusts the effect of the distance between the UAV and the obstacle on gravity, where β is the weight coefficient and D is the reference distance value;

[0030] Set the density of obstacles around the UAV to δ obs , introducing -γδ obs The term adjusts the influence of the density of obstacles around the UAV on gravity, where γ is the weight coefficient;

[0031] Set the UAV line of sight obstruction factor λ los ∈[0,1],λ los 1 means the UAV has clear sight line, λlos When 0 is set, it means that the UAV’s line of sight is completely blocked. los The term adjusts gravity, where η is the weight coefficient;

[0032] Based on key environmental parameters, an improved gravitational coefficient k is obtained att , as shown in the following formula:

[0033]

[0034] Among them, θ is the environmental parameter;

[0035] Then we get the improved gravitational potential field function:

[0036]

[0037] S4, setting a gravitational weight factor and a repulsive weight factor, assigning respective weight coefficients to the repulsive potential field based on the distance from the unmanned aerial vehicle to the target point and the gravitational potential field based on multiple environmental perception factors, and obtaining a resultant potential field function;

[0038] The magnitude of the resultant potential field of the UAV is the sum of the repulsive potential field and the gravitational potential field on the UAV. The resultant potential field function U is shown in the following formula:

[0039] U=ω att U att +ω rep U rep (9)

[0040] Among them, ω att is the gravitational weight factor, ω rep is the repulsive force weight factor, and ω att +ω rep =1;

[0041] S5. Calculate the resultant force vector according to the resultant force potential field function, combine the smoothing factor to obtain the resultant force vector for the motion control of the unmanned aerial vehicle, determine the moving direction and step length of the unmanned aerial vehicle, and gradually plan the path of the unmanned aerial vehicle from the starting point to the target point;

[0042] The resultant force on the unmanned aerial vehicle in the resultant potential field is shown in the following formula:

[0043]

[0044] The smoothing factor μ∈[0,1] is introduced to smooth the resultant force on the UAV in the resultant force potential field, and the resultant force vector used for the motion control of the UAV is obtained.

[0045]

[0046] in, It is the resultant force vector of the UAV in the resultant force field at the last moment; when μ=1, the UAV moves completely according to the currently calculated resultant force; when μ<1, the UAV considers the movement trend at the last moment.

[0047] The beneficial effect of adopting the above technical scheme is that: the present invention provides an improved method for dynamic path planning of unmanned aerial vehicles with an improved artificial potential field. In view of the many limitations of the traditional artificial potential field method in aircraft path planning, such as when facing scenes with different obstacle distributions, shapes, sizes and target accessibility, it is easy to cause the aircraft to fall into a local optimal solution, oscillate near obstacles or fail to pass through narrow passages. The repulsive potential field function and the gravitational potential field function are improved, and a variety of environmental perception factors are introduced to dynamically adjust gravity and repulsion, and combined with weight distribution and combined force smoothing technology, the performance and stability of path planning are improved, making path planning more reasonable. The improved method for dynamic path planning of unmanned aerial vehicles with an improved artificial potential field provided by the present invention can adapt to different application scenarios more flexibly, and can be customized and configured according to specific needs to ensure that the path planning system can meet the requirements of different industries, thereby improving the applicability and practicality of the path planning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flow chart of a method for improving the dynamic path planning of an unmanned aerial vehicle with an improved artificial potential field provided by an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of a path planning based on a traditional artificial potential field algorithm provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of path planning for an improved method for dynamic path planning of an unmanned aerial vehicle based on an improved artificial potential field provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0052] In this embodiment, a method for improving the dynamic path planning of an unmanned aerial vehicle using an improved artificial potential field is provided. Figure 1 As shown in the figure, the repulsive potential field function and the gravitational potential field function are improved, and a variety of environmental perception factors are introduced to dynamically adjust the gravitational force and repulsive force. The weight distribution and resultant force smoothing technology are combined to improve the performance and stability of path planning and make the path planning more reasonable. The specific steps include:

[0053] S1. Obtain the starting point, target point and obstacle information of the UAV, establish an artificial potential field environment in a certain airspace, and regard the UAV, target point and obstacle as mass points;

[0054] S2, constructing an initial repulsive potential field function, introducing the distance factor from the unmanned aerial vehicle to the target point to improve the repulsive potential field function, and obtaining a repulsive potential field function based on the distance from the unmanned aerial vehicle to the target point;

[0055] Define the current position of the UAV as P(x,y), and the position of the target point as P goal (x,y), the position of the obstacle is P ob (x,y), construct the initial repulsive potential field function U rep As shown in the following formula:

[0056]

[0057] Among them, d(P,P ob ) is the distance between the UAV and the obstacle, d0 is the maximum distance of the obstacle, and obstacles greater than this distance will not affect the flight of the UAV, and η is the repulsion coefficient;

[0058] The repulsive potential field function is improved by introducing the distance factor from the unmanned aerial vehicle to the target point. The improved repulsive function can effectively avoid the situation where the repulsive force is too large near the target point, thereby solving the problem of unreachable target. The improved repulsive potential field function U r ' ep (P) is:

[0059]

[0060] Among them, k rep and k′ rep are the repulsion coefficients of the repulsion function based on the distance from the UAV to the target point, d(P,P goal ) is the distance from the UAV to the target point, is the unit vector pointing from the obstacle to the UAV, is the unit vector pointing from the UAV to the target point;

[0061] When d(P,P ob )≤d0, set but for

[0062]

[0063] set up but for

[0064]

[0065] When d(P,P ob )>d0, the repulsive potential field function U r ' ep is 0;

[0066] We can further obtain the repulsive potential field function U based on the distance from the unmanned aerial vehicle to the target point according to the vector expansion: r ' ep for:

[0067]

[0068] When the UAV is within the range of obstacles and far away from the target, k rep Plays a major role, generating a strong repulsive force to make the UAV away from obstacles as quickly as possible. At this time, k′ rep is relatively small, and its effect on the UAV is also relatively small; as the UAV gradually moves away from obstacles or gets closer to the target, k′ rep The role of k is gradually becoming prominent, guiding the UAV to move towards the target while avoiding obstacles. For example, when the UAV passes through a narrow passage with obstacles on both sides of the passage, k rep will prevent the aircraft from colliding with the channel wall (obstacle), and k′ rep It will help the aircraft to keep moving towards the channel exit (target direction) while avoiding obstacles.

[0069] S3, constructing an initial gravitational potential field function, introducing a variety of environmental perception factors to dynamically adjust the gravitational potential field function, and constructing a gravitational potential field function based on a variety of environmental perception factors;

[0070] S3.1 Constructing the initial gravitational potential field function U att , as shown in the following formula:

[0071]

[0072] Among them, ξ is the gravitational coefficient;

[0073] S3.2. Select key environmental parameters according to the actual working requirements of the UAV, and use multiple key environmental parameters to improve the gravitational potential field function so that gravity can dynamically adapt to the environment;

[0074] In actual complex environments, such as when there are complex obstacle layouts around the target, fixed gravity may make it impossible for the UAV to balance obstacle avoidance and approaching the target, and fall into a local optimal dilemma. For example, when the UAV is close to the target but there are dense obstacles in between, the strong and constant gravity may drive the UAV to rush straight to the obstacle instead of finding a reasonable detour. In order to enable gravity to dynamically adapt to the environment, multiple key environmental parameters are introduced to improve the gravity function. In this embodiment, the key environmental parameters include: the number of obstacles around the UAV, the average distance between the obstacles and the UAV, the density of obstacles, and the line of sight obstruction factor.

[0075] Set the number of obstacles around the UAV to n obs , when n obs Increase, the complexity of the environment increases accordingly. In order to prevent the UAV from blindly rushing towards the target and falling into an obstacle trap, the gravity needs to be weakened accordingly. Term, where α is the weight coefficient, is the reference obstacle quantity threshold. obs relatively increases, the effect of this term on reducing the gravitational constant increases, making the gravitational force smaller;

[0076] Set the average distance between obstacles and UAVs to when When the UAV approaches an obstacle, the gravity needs to be appropriately weakened to prevent the UAV from colliding with the obstacle. The term adjusts the effect of the distance between the UAV and the obstacle on gravity, where β is the weight coefficient and D is the reference distance value;

[0077] Set the density of obstacles around the UAV to δ obs , δ obs The higher it is, the more complex and difficult the environment will be. The gravity needs to be weakened accordingly. -γδ is introduced. obs The term adjusts the influence of the density of obstacles around the UAV on gravity, where γ is the weight coefficient;

[0078] Set the UAV line of sight obstruction factor λ los ∈[0,1],λ los 1 means the UAV has clear sight line, λ los 0 means the UAV’s line of sight is completely blocked. los It becomes smaller, the unmanned aerial vehicle cannot reach the target directly, the gravity needs to be reduced, and ηλ is introduced los The term adjusts gravity, where η is the weight coefficient;

[0079] Based on key environmental parameters, an improved gravitational coefficient k is obtained att , as shown in the following formula:

[0080]

[0081] Among them, θ is the environmental parameter;

[0082] Then we get the improved gravitational potential field function:

[0083]

[0084] S4, setting a gravitational weight factor and a repulsive weight factor, assigning respective weight coefficients to the repulsive potential field based on the distance from the unmanned aerial vehicle to the target point and the gravitational potential field based on multiple environmental perception factors, and obtaining a resultant potential field function;

[0085] The magnitude of the resultant potential field of the UAV is the sum of the repulsive potential field and the gravitational potential field on the UAV. The resultant potential field function U is shown in the following formula:

[0086] U=ω att U att +ω rep U rep (9)

[0087] Among them, ω att is the gravitational weight factor, ω rep is the repulsive force weight factor, and ω att +ω rep =1;

[0088] S5. Calculate the resultant force vector according to the resultant force potential field function, combine the smoothing factor to obtain the resultant force vector for the motion control of the unmanned aerial vehicle, determine the moving direction and step length of the unmanned aerial vehicle, and gradually plan the path of the unmanned aerial vehicle from the starting point to the target point;

[0089] The resultant force on the unmanned aerial vehicle in the resultant potential field is shown in the following formula:

[0090]

[0091] The smoothing factor μ∈[0,1] is introduced to smooth the resultant force on the UAV in the resultant force potential field, and the resultant force vector used for the motion control of the UAV is obtained.

[0092]

[0093] in, It is the resultant force vector of the UAV in the resultant force field at the previous moment; when μ=1, the UAV moves completely according to the currently calculated resultant force; when μ<1, the UAV considers the movement trend at the previous moment; the introduction of the smoothing factor makes the UAV movement smoother, effectively reduces the motion instability caused by the sudden change of the potential field, and improves the accuracy and reliability of the UAV motion control.

[0094] The UAV path planning method based on the traditional artificial potential field has defects when facing scenes with obstacles of different distribution, shape, size and target accessibility, which can easily cause the UAV to fall into the local optimal solution, oscillate near obstacles or have difficulty passing through narrow passages. Figure 2 As shown, the path of the unmanned aerial vehicle is tortuous, and there is a significant deviation between the end point of the unmanned aerial vehicle and the target point; the planning path of the unmanned aerial vehicle dynamic path planning improvement method based on the improved artificial potential field described in this embodiment is as follows Figure 3 As shown, compared Figure 2 and Figure 3 It can be seen that the improved path planning method can effectively solve the problem of unreachable targets; this embodiment fully considers the distance relationship between the aircraft and the target point, further optimizes the path, and improves the success rate, accuracy and reliability of path planning.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope defined by the claims of the present invention.

Claims

1. A method for improving the dynamic path planning of unmanned aerial vehicles using an improved artificial potential field, characterized in that: The following steps are involved: S1. Obtain the starting point, target point and obstacle information of the UAV, establish an artificial potential field environment in a certain airspace, and regard the UAV, target point and obstacle as mass points; S2, constructing an initial repulsive potential field function, introducing the distance factor from the unmanned aerial vehicle to the target point to improve the repulsive potential field function, and obtaining a repulsive potential field function based on the distance from the unmanned aerial vehicle to the target point; S3, constructing an initial gravitational potential field function, introducing a variety of environmental perception factors to dynamically adjust the gravitational potential field function, and constructing a gravitational potential field function based on a variety of environmental perception factors; S4, setting a gravitational weight factor and a repulsive weight factor, assigning respective weight coefficients to the repulsive potential field based on the distance from the unmanned aerial vehicle to the target point and the gravitational potential field based on multiple environmental perception factors, and obtaining a resultant potential field function; S5. Calculate the resultant force vector according to the resultant force potential field function, combine the smoothing factor to obtain the resultant force vector used for the motion control of the UAV, determine the moving direction and step size of the UAV, and gradually plan the path of the UAV from the starting point to the target point.

2. The method for improving the dynamic path planning of an unmanned aerial vehicle with an improved artificial potential field according to claim 1, characterized in that: The specific method of step 2 is: Define the current position of the UAV as P(x,y), and the position of the target point as P goal (x,y), the position of the obstacle is P ob (x, y), construct the initial repulsive potential field function Urep, as shown in the following formula: Among them, d(P,P ob ) is the distance between the UAV and the obstacle, d0 is the maximum distance of the obstacle, and obstacles greater than this distance will not affect the flight of the UAV, and η is the repulsion coefficient; The distance factor from the UAV to the target point is introduced to improve the repulsive potential field function. The improved repulsive potential field function U r ' ep for: Among them, k rep and k r ' ep are the repulsive coefficients of the repulsive potential field function based on the distance from the UAV to the target point, d(P,P goal ) is the distance from the UAV to the target point, is the unit vector pointing from the obstacle to the UAV, is the unit vector pointing from the UAV to the target point; When d(P,P ob )≤d0, set but for set up but for When d(P,P ob )>d0, the repulsive potential field function U r ' ep is 0; We can further obtain the repulsive potential field function U based on the distance from the unmanned aerial vehicle to the target point according to the vector expansion: r ' ep for:

3. The method for improving the dynamic path planning of an unmanned aerial vehicle with an improved artificial potential field according to claim 2, characterized in that: The step 3 comprises the following steps: S3.

1. Constructing the initial gravitational potential field function U att , as shown in the following formula: Among them, ξ is the gravitational coefficient; S3.

2. Select key environmental parameters according to the actual working requirements of the UAV, and use multiple key environmental parameters to improve the gravitational potential field function so that gravity can dynamically adapt to the environment; Set the number of obstacles around the UAV to n obs To prevent the UAV from blindly rushing towards the target and falling into an obstacle trap, we introduced Term, where α is the weight coefficient, is the reference obstacle quantity threshold; Set the average distance between obstacles and UAVs to In order to prevent the UAV from colliding with obstacles, The term adjusts the effect of the distance between the UAV and the obstacle on gravity, where β is the weight coefficient and D is the reference distance value; Set the density of obstacles around the UAV to δ obs , introducing -γδ obs The term adjusts the influence of the density of obstacles around the UAV on gravity, where γ is the weight coefficient; Set the UAV line of sight obstruction factor λ los ∈[0,1],λ los 1 means the UAV has clear sight line, λ los When 0 is set, it means that the UAV’s line of sight is completely blocked. los The term adjusts gravity, where η is the weight coefficient; Based on key environmental parameters, an improved gravitational coefficient k is obtained att , as shown in the following formula: Among them, θ is the environmental parameter; Then we get the improved gravitational potential field function:

4. The method for improving the dynamic path planning of an unmanned aerial vehicle with an improved artificial potential field according to claim 3, characterized in that: The step 4 comprises the following steps: The magnitude of the resultant potential field of the UAV is the sum of the repulsive potential field and the gravitational potential field on the UAV. The resultant potential field function U is shown in the following formula: U=ω att IN att +ω rep IN rep (9) Among them, ω att is the gravitational weight factor, ω rep is the repulsive force weight factor, and ω att +ω rep =1.

5. The method for improving the dynamic path planning of unmanned aerial vehicles with improved artificial potential field according to claim 4, characterized in that: The step 5 comprises the following steps: The resultant force on the unmanned aerial vehicle in the resultant potential field is shown in the following formula: The smoothing factor μ∈[0,1] is introduced to smooth the resultant force on the UAV in the resultant force potential field, and the resultant force vector used for the motion control of the UAV is obtained. in, It is the resultant force vector of the UAV in the resultant force field at the last moment; when μ=1, the UAV moves completely according to the currently calculated resultant force; when μ<1, the UAV considers the movement trend at the last moment.

Images