Unmanned aerial vehicle path planning method and system based on improved particle swarm optimization
By combining improved particle swarm algorithm and hybrid genetic algorithm, the global optimal path problem in local minimum values and complex environments in drone path planning is solved, and more efficient path planning convergence capabilities are achieved.
Patent Information
- Application Number
- CN202411019133.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-12-06
AI Technical Summary
Traditional drone path planning algorithms are difficult to find global optimal paths in complex environments, and are prone to falling into local minimum values, and cannot effectively deal with the problems of dynamic environmental changes and high-dimensional state space.
Adopting improved particle swarm algorithm, through the adaptive velocity and position update mechanism of particle swarm, combined with the concept of mixed probability and genetic algorithm, progeny particles are generated to improve the convergence ability of path planning, avoid local minimum values, and find the global optimal path .
It effectively improves the convergence capability of the path planning algorithm, overcomes the local minimum trap, and is suitable for UAV route planning in complex environments, ensuring that the global optimal path is found.
Smart Images

Figure CN119088048A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of unmanned aerial vehicles. Background Art
[0002] UAV path planning refers to planning the path and route of the UAV flight during the flight mission to ensure that the UAV can complete the mission efficiently and safely. Good path planning can ensure that the UAV reaches the destination in the shortest path when performing the mission, thereby improving flight efficiency. This not only helps to save time and energy, but also increases the benefits of mission execution. There are many traditional UAV path planning algorithms. The Dijkstra algorithm can find the shortest path from the starting point to the end point, but does not consider the obstacles in the actual environment, cannot cope with the changes in the dynamic environment, and is not suitable for UAV missions that require obstacle avoidance. The A-star algorithm combines breadth-first search and heuristic search, taking into account both the shortest path and obstacle avoidance. However, the computational overhead is large on large-scale maps and requires more computing resources; for problems in high-dimensional state space, the design of heuristic functions may be more difficult. The artificial potential field method avoids obstacles by simulating the movement of particles in the potential field, but it is easy to fall into the local optimal solution and is not suitable for complex environments; there is a hovering problem, and it cannot guarantee that the global optimal path is found. Summary of the invention
[0003] The present invention aims to solve the problem of complex route planning of unmanned aerial vehicles in the prior art.
[0004] To solve the above technical problems, the present invention is achieved through the following technical solutions:
[0005] Solution 1: The present invention proposes a UAV path planning method based on an improved particle swarm algorithm, and the UAV path planning method comprises the following steps:
[0006] Step 1: The airway control point size of the selected PSO population is m, the initial route control point position is F, and its speed is v. The coordinates of the best solution of each particle in the PSO population are set as the current position, and the corresponding individual extreme value is calculated. The global extreme value is the best value among them; the best value of each particle is recorded, and the coordinates of the best solution of the entire population are set as the current best position of the particle;
[0007] Step 2: Evaluate the position of each particle in the PSO population and calculate the fitness value of each particle. If it is better than the current individual extreme value of the particle, set the coordinates of the best solution to the position of the particle and update the individual extreme value; if the best value among the individual extreme values of all particles is better than the current global extreme value, set the coordinates of the best solution of the entire population obtained in step 1 to the position of the particle, record the number of particles, and update the global extreme value;
[0008] Step 3: Use the contraction coefficient formula to update the speed and position of each particle. For each particle, compare its adaptive value with the best position it has passed. If it is better, set it as the best position. Compare the best value of the particle obtained in steps 1 and 2 with the best value of the entire population, and update the best solution for the entire population.
[0009] Step 4: Select particles to enter the mixing pool according to the mixing probability. The particles in the mixing pool will randomly mix with each other to produce the same number of offspring particles, keeping the best solution and the best solution found by the entire population unchanged, and check whether the end condition is met. If the current iteration reaches the predefined maximum number of times, stop the iteration and output the optimal solution, otherwise continue to step 3.
[0010] Further, a preferred embodiment is provided, the formula of the shrinkage coefficient formula in step three is:
[0011] v id (t+1)=v id (t)+c1×rand()×[p id (t)-x id (t)]+
[0012] c2×rand()×[p gd (t)-x id (t)]
[0013] x id (t+1)=x id (t)+v id (t+1)1≤i≤n1≤d≤D
[0014] Where D is the dimension of the search space, n is the position of the i-th particle described as a vector X i =(x i1 ,x i2 ,…x iD ), the particle’s best past position is described as P i =(p i1 ,p i2 ,…,p iD ), P g is the optimal position; the position, velocity and speed of the i-th particle are described as vector V i =(v i1 ,v i2 ,…,V iD ), c1 and c2 are learning factors or acceleration coefficients.
[0015] Further, a preferred implementation is provided, in which the calculation method of the particle fitness function in step 2 is:
[0016] minW=w1c1L+w2c2 / dmin
[0017] Among them, w1 and w2 are weight coefficients, d is the dimension of the particle, W is the fitness, and L is the path length.
[0018] Further, a preferred embodiment is provided, in which a method for selecting a certain number of particles to enter the mixing pool according to the mixing probability is:
[0019] child(x)=p parent1(x)+(1-p)·parent2(x)
[0020] child (x) =(1-p)·parent1(x)+p·parent2(x)
[0021] p is a random number between 0 and 1.
[0022] Further, a preferred embodiment is provided, in which the particles in the mixing pool are randomly mixed with each other to produce the same number of offspring particles, and the calculation formula of the speed of the offspring particles is:
[0023]
[0024] Solution 2: A UAV path planning system based on an improved particle swarm algorithm, the UAV path planning system comprising:
[0025] Position determination module, for the selected PSO population, the airway control point size is m, the initial route control point position is F, and its speed is v. The coordinates of the best solution of each particle in the PSO population are set as the current position, and the corresponding individual extreme value is calculated, and the global extreme value is the best value among them; the best value of each particle is recorded, and the coordinates of the best solution of the entire population are set as the current best position of the particle;
[0026] The evaluation module is used to evaluate the position of each particle in the PSO population and calculate the fitness value of each particle. If it is better than the current individual extreme value of the particle, the coordinates of the best solution are set to the position of the particle and the individual extreme value is updated; if the best value among the individual extreme values of all particles is better than the current global extreme value, the coordinates of the best solution of the entire population obtained in step 1 are set to the position of the particle, the number of particles is recorded, and the global extreme value is updated;
[0027] The position update module is used to update the speed and position of each particle using the contraction coefficient formula. For each particle, its adaptive value is compared with the best position it has passed. If it is better, it is set as the best position. The best value of the particle obtained in step 1 and step 2 is compared with the best value of the entire population, and the best solution of the entire population is updated;
[0028] The judgment module is used to select particles to enter the mixing pool according to the mixing probability. The particles in the mixing pool will randomly mix with each other to produce the same number of offspring particles, keeping the best solution and the best solution found by the entire population unchanged, and checking whether the end condition is met. If the current iteration reaches the predefined maximum number of times, the iteration is stopped and the optimal solution is output, otherwise the position update module continues to execute.
[0029] Solution three: a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of Solution one.
[0030] Solution 4: A computer device includes a memory and a processor, wherein the memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes any one of the methods described in Solution 1.
[0031] The present invention is beneficial in that:
[0032] The present invention proposes an improved hybrid particle swarm UAV path planning method with a shrinkage factor. On the basis of simplifying the total cost function of the UAV path, an improved hybrid particle swarm UAV path planning method with a shrinkage factor is proposed.
[0033] The unmanned aerial vehicle path planning method based on the improved particle swarm algorithm described in the present invention effectively improves the convergence ability of the path planning algorithm.
[0034] The improved particle swarm algorithm UAV path planning method described in the present invention overcomes the shortcoming that the basic particle swarm algorithm is prone to fall into a local minimum.
[0035] The unmanned aerial vehicle path planning method based on the improved particle swarm algorithm described in the present invention can be used to solve complex route planning problems of unmanned aerial vehicles.
[0036] The present invention is also applicable to the field of finding a global optimal path in a complex environment. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 Schematic diagram of particle swarm algorithm in a UAV path planning method based on improved particle swarm algorithm described in Implementation Method 9.
[0038] Figure 2 Schematic diagram of the movement direction of particles in a UAV path planning method based on an improved particle swarm algorithm described in Implementation Example 9. DETAILED DESCRIPTION
[0039] In order to make the purpose, technical solutions and advantages of the implementation methods of the present application clearer, the technical solutions in the implementation methods of the present application will be clearly and completely described below in conjunction with the drawings in the implementation methods of the present application. Obviously, the described implementation methods are only part of the implementation methods of the present application, not all of the implementation methods.
[0040] Implementation method 1: This implementation method provides a UAV path planning method based on an improved particle swarm algorithm, and the UAV path planning method includes the following steps:
[0041] Step 1: The airway control point size of the selected PSO population is m, the initial route control point position is F, and its speed is v. The coordinates of the best solution of each particle in the PSO population are set as the current position, and the corresponding individual extreme value is calculated. The global extreme value is the best value among them; the best value of each particle is recorded, and the coordinates of the best solution of the entire population are set as the current best position of the particle;
[0042] Step 2: Evaluate the position of each particle in the PSO population and calculate the fitness value of each particle. If it is better than the current individual extreme value of the particle, set the coordinates of the best solution to the position of the particle and update the individual extreme value; if the best value among the individual extreme values of all particles is better than the current global extreme value, set the coordinates of the best solution of the entire population obtained in step 1 to the position of the particle, record the number of particles, and update the global extreme value;
[0043] Step 3: Use the contraction coefficient formula to update the speed and position of each particle. For each particle, compare its adaptive value with the best position it has passed. If it is better, set it as the best position. Compare the best value of the particle obtained in steps 1 and 2 with the best value of the entire population, and update the best solution for the entire population.
[0044] Step 4: Select particles to enter the mixing pool according to the mixing probability. The particles in the mixing pool will randomly mix with each other to produce the same number of offspring particles, keeping the best solution and the best solution found by the entire population unchanged, and check whether the end condition is met. If the current iteration reaches the predefined maximum number of times, stop the iteration and output the optimal solution, otherwise continue to step 3.
[0045] Implementation method 2: This implementation method is a further limitation of the UAV path planning method based on the improved particle swarm algorithm described in implementation method 1. The formula of the contraction coefficient formula described in step 3 is:
[0046] v id (t+1)=v id (t)+c1×rand()×[p id (t)-x id (t)]+
[0047] c2×rand()×[p gd (t)-x id (t)]
[0048] x id (t+1)=x id (t)+v id (t+1)1≤i≤n1≤d≤D
[0049] Where D is the dimension of the search space, n is the position of the i-th particle described as a vector X i =(x i1 ,x i2 ,…x iD ), the particle’s best past position is described as P i =(p i1 ,p i2 ,…,p iD ), P g is the optimal position; the position, velocity and speed of the i-th particle are described as vector V i =(v i1 ,v i2 ,…,V iD ), c1 and c2 are learning factors or acceleration coefficients.
[0050] Implementation method 3: This implementation method is a further limitation of the UAV path planning method based on the improved particle swarm algorithm described in implementation method 1. The calculation method of the particle fitness function in step 2 is:
[0051] minW=w1c1L+w2c2 / d min
[0052] Among them, w1 and w2 are weight coefficients, d is the dimension of the particle, W is the fitness, and L is the path length.
[0053] Implementation method 4: This implementation method is a further limitation of the UAV path planning method based on the improved particle swarm algorithm described in implementation method 1. The method of selecting a certain number of particles to enter the mixing pool according to the mixing probability is:
[0054] child(x)=p parent1(x)+(1-p)·parent2(x)
[0055] child (x) =(1-p)·parent1(x)+p·parent2(x)
[0056] p is a random number between 0 and 1.
[0057] Implementation mode 5: This implementation mode further limits the UAV path planning method based on the improved particle swarm algorithm described in implementation mode 1. The particles in the mixing pool are randomly mixed with each other to generate the same number of offspring particles. The calculation formula of the speed of the offspring particles is:
[0058]
[0059] Implementation 6: This implementation proposes a UAV path planning system based on an improved particle swarm algorithm, and the UAV path planning system includes:
[0060] Position determination module, for the selected PSO population, the airway control point size is m, the initial route control point position is F, and its speed is v. The coordinates of the best solution of each particle in the PSO population are set as the current position, and the corresponding individual extreme value is calculated, and the global extreme value is the best value among them; the best value of each particle is recorded, and the coordinates of the best solution of the entire population are set as the current best position of the particle;
[0061] The evaluation module is used to evaluate the position of each particle in the PSO population and calculate the fitness value of each particle. If it is better than the current individual extreme value of the particle, the coordinates of the best solution are set to the position of the particle and the individual extreme value is updated; if the best value among the individual extreme values of all particles is better than the current global extreme value, the coordinates of the best solution of the entire population obtained in step 1 are set to the position of the particle, the number of particles is recorded, and the global extreme value is updated;
[0062] The position update module is used to update the speed and position of each particle using the contraction coefficient formula. For each particle, its adaptive value is compared with the best position it has passed. If it is better, it is set as the best position. The best value of the particle obtained in step 1 and step 2 is compared with the best value of the entire population, and the best solution of the entire population is updated;
[0063] The judgment module is used to select particles to enter the mixing pool according to the mixing probability. The particles in the mixing pool will randomly mix with each other to produce the same number of offspring particles, keeping the best solution and the best solution found by the entire population unchanged, and checking whether the end condition is met. If the current iteration reaches the predefined maximum number of times, the iteration is stopped and the optimal solution is output, otherwise the position update module continues to execute.
[0064] Embodiment 7: A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of a drone path planning method based on an improved particle swarm algorithm as described in any one of embodiments 1 to 5.
[0065] Embodiment 8: A computer device includes a memory and a processor, wherein the memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes a drone path planning method based on an improved particle swarm algorithm as described in any one of embodiments 1 to 5.
[0066] Embodiment 9: This embodiment provides an example, which is used to explain the above embodiments 1 to 8. The specific example is as follows:
[0067] See also Figure 1 and Figure 2 The present implementation scheme is described, which includes: (1) a basic particle swarm optimization (PSO) algorithm and (2) an improved particle swarm algorithm;
[0068] The basic particle swarm optimization (PSO) algorithm proposes an important evolutionary algorithm, the basic idea of which comes from the study of the foraging behavior of biological groups such as birds and fish in nature. The particle swarm optimization (PSO) algorithm "learns" the behavior of excellent particles through individuals, and is a new type of global intelligent optimization algorithm.
[0069] Assume that the search space is D-dimensional, the total number of particles is n, and the position of the i-th particle is described as the vector X i =(x i1 ,x i2 ,…x iD ); the best position of the particle in the past (converting the position of number i into the optimal position) is described as P i =(p i1 ,p i2 ,…,p iD ), where the past optimal position P g is optimal; the position rate (speed) of the i-th particle is described as vector V i =(v i1 ,v i2 ,…,V iD ), the position of each particle changes as follows:
[0070] v id (t+1)=v id (t)+c1×rand()×[p id (t)-x id (t)]+
[0071] c2×rand()×[p gd (t)-x id (t)]
[0072] x id (t+1)=x id (t)+v id(t+1)1≤i≤n1≤d≤D
[0073] c1 and c2: learning factors or acceleration coefficients, usually positive constants. The learning factor enables particles to summarize themselves and learn from excellent individuals in the group, so that particles are closer to the maximum advantage of their own history, and also closer to the maximum advantage of their own historical group or neighboring groups. The effect of these two parameters has little effect on the convergence of the particle swarm algorithm, but if these two parameters are properly adjusted, the trouble of falling into local minima can be reduced, and of course the convergence speed can be faster. Since the particle swarm algorithm has no actual control mechanism, it is necessary to limit the maximum speed (maxV). Because when the value is too large, the optimal solution will be skipped, and when the value is too small, the space will not be fully searched.
[0074] (2) Improved particle swarm algorithm
[0075] Referring to the concept of hybrid genetic algorithm, a certain number of particles are selected to enter the hybrid pool according to the mixing rate of each iteration. The particles in the pool randomly hybridize with each other to produce the same number of offspring particles (children) and replace the parent particles (parents). The offspring position is obtained from the crossover of the father, and the relevant formula is as follows:
[0076] child(x)=p parent1(x)+(1-p)·parent2(x)
[0077] child (x) =(1-p)·parent1(x)+p·parent2(x)
[0078] In the function, p is a random number between 0 and 1; the calculation formula of the sub-speed is as follows:
[0079]
[0080] When using the above algorithm to solve the UAV route planning problem, each feasible route is a "particle". If there are d path control points, the dimension of the particle is d. The fitness function of the particle is:
[0081] minW=w1c1L+w2c2 / d min
[0082] In the function: w1 and w2 are weight coefficients, which can be adjusted according to different tasks. Their values determine whether to cross or bypass terrain obstacles and threat points. The particle swarm algorithm generates a group of random particles (random paths). The particles update themselves by tracking two "extreme values" in each iteration. One extreme point is the best solution found by the particle itself (pbest), and the other extreme point is the best solution found by the entire population (gbest). The algorithm is implemented as follows:
[0083] Step 1: The size of the selected PSO population (airway control point) is m, the initial route control point position is F, and its speed is v (usually randomly generated within the allowed range). The pbest coordinate of each particle is set to the current position, and the corresponding individual extreme value (i.e., the fitness value of the individual extreme value) is calculated. The global extreme value (i.e., the fitness value of the global extreme value) is the best value. The best value of the particle is recorded, and gbest is set as the current best position of the particle.
[0084] Step 2: Evaluate each particle and calculate the fitness value of each particle: If it is better than the current individual extreme value of the particle, set pbest to the position of the particle and update the individual extreme value. If the best individual extreme value of all particles is better than the current global extreme value, set gbest obtained in step 1 to the position of the particle, then record the number of particles and update the global extreme value.
[0085] Step 3: Use the contraction coefficient formula to update the speed and position of each particle. For each particle, compare its adaptive value with the best position it has passed. If it is better than the best position, set it as the best position. Compare the pbest and gbest values obtained in steps 1 and 2, and update gbest.
[0086] Step 4: Select a certain number of particles according to the mixing probability to enter the mixing pool. The particles in the mixing pool will randomly mix with each other to produce the same number of offspring particles. The position and speed of the offspring particles are calculated by the above formula, keeping pbest and gbest unchanged. Check whether the end condition is met. If the current iteration reaches the predefined maximum number of times, stop the iteration and output the optimal solution. Otherwise, continue to step 3.
[0087] This embodiment proposes an improved hybrid particle swarm UAV path planning method with a contraction factor. On the basis of simplifying the total cost function of the UAV path, an improved hybrid particle swarm UAV path planning method with a contraction factor is proposed. The method described in this embodiment effectively improves the convergence ability of the path planning algorithm.
[0088] The method described in this embodiment overcomes the shortcoming of the basic particle swarm algorithm that it is easy to fall into a local minimum.
[0089] The method described in this embodiment can be used to solve complex route planning problems for UAVs.
[0090] For the purposes of the present specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use with an instruction execution system, device or equipment or in conjunction with these instruction execution systems, devices or equipment. More specific examples of computer-readable media (non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program may be printed, because the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting or processing in other suitable ways as necessary, and then stored in a computer memory. It should be understood that the various parts of the present invention may be implemented in hardware, software, firmware or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0091] Those skilled in the art will appreciate that the above are only preferred embodiments of the present invention, and the various embodiments of the present disclosure and / or the features described in the claims may be combined or combined in various ways, even if such combinations or combinations are not explicitly described in the present disclosure. It is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art may still modify the technical solutions described in the aforementioned embodiments, or perform equivalent substitutions on some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.
[0092] Although preferred embodiments of the present invention have been described, additional changes and modifications may be made to these embodiments by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A UAV path planning method based on improved particle swarm algorithm, It is characterized in that The UAV path planning method comprises the following steps: Step 1: The airway control point size of the selected PSO population is m, the initial route control point position is F, and its speed is v. The coordinates of the best solution of each particle in the PSO population are set as the current position, and the corresponding individual extreme value is calculated. The global extreme value is the best value among them; the best value of each particle is recorded, and the coordinates of the best solution of the entire population are set as the current best position of the particle; Step 2: Evaluate the position of each particle in the PSO population and calculate the fitness value of each particle. If it is better than the current individual extreme value of the particle, set the coordinates of the best solution to the position of the particle and update the individual extreme value; if the best value among the individual extreme values of all particles is better than the current global extreme value, set the coordinates of the best solution of the entire population obtained in step 1 to the position of the particle, record the number of particles, and update the global extreme value; Step 3: Use the contraction coefficient formula to update the speed and position of each particle. For each particle, compare its adaptive value with the best position it has passed. If it is better, set it as the best position. Compare the best value of the particle obtained in steps 1 and 2 with the best value of the entire population, and update the best solution for the entire population. Step 4: Select particles to enter the mixing pool according to the mixing probability. The particles in the mixing pool will randomly mix with each other to produce the same number of offspring particles, keeping the best solution and the best solution found by the entire population unchanged, and check whether the end condition is met. If the current iteration reaches the predefined maximum number of times, stop the iteration and output the optimal solution, otherwise continue to step 3.
2. According to claim 1, a UAV path planning method based on improved particle swarm algorithm, It is characterized in that The formula for the shrinkage factor formula described in step three is: v id (t+1)=v id (t)+c 1 ×rand()×[p id (t)-x id (t)]+ c 2 ×rand()×[p gd (t)-x id (t)] x id (t+1)=x id (t)+v id (t+1)1≤i≤n 1≤d≤D Where D is the dimension of the search space, n is the position of the i-th particle described as a vector X i =(x i1 ,x i2 ,…x iD ), the particle’s best past position is described as P i =(p i1 ,p i2 ,…,p iD ), P g is the optimal position; the position, velocity and speed of the i-th particle are described as vector V i =(v i1 ,v i2 ,…,V iD ), c 1 and c 2 is the learning factor or acceleration coefficient.
3. According to claim 1, a UAV path planning method based on improved particle swarm algorithm, It is characterized in that The calculation method of the particle fitness function in step 2 is: minW=w 1 c 1 L+w 2 c 2 / d min Among them, w 1 and w 2 is the weight coefficient, d is the dimension of the particle, W is the fitness, and L is the path length.
4. According to claim 1, a UAV path planning method based on improved particle swarm algorithm, It is characterized in that The method of selecting particles to enter the mixing pool according to the mixing probability is: child(x)=p parent 1 (x)+(1-p)·parent 2 (x) child (x) =(1-p)·parent 1 (x)+p·parent 2 (x) p is a random number between 0 and 1.
5. The UAV path planning method based on improved particle swarm algorithm according to claim 1, It is characterized in that The particles in the mixing pool will randomly mix with each other to produce the same number of offspring particles. The speed of the offspring particles is calculated as follows:
6. A UAV path planning system based on improved particle swarm algorithm, It is characterized in that The UAV path planning system comprises: Position determination module, for the selected PSO population, the airway control point size is m, the initial route control point position is F, and its speed is v. The coordinates of the best solution of each particle in the PSO population are set as the current position, and the corresponding individual extreme value is calculated, and the global extreme value is the best value among them; the best value of each particle is recorded, and the coordinates of the best solution of the entire population are set as the current best position of the particle; The evaluation module is used to evaluate the position of each particle in the PSO population and calculate the fitness value of each particle. If it is better than the current individual extreme value of the particle, the coordinates of the best solution are set to the position of the particle and the individual extreme value is updated; if the best value among the individual extreme values of all particles is better than the current global extreme value, the coordinates of the best solution of the entire population obtained in step 1 are set to the position of the particle, the number of particles is recorded, and the global extreme value is updated; The position update module is used to update the speed and position of each particle using the contraction coefficient formula. For each particle, its adaptive value is compared with the best position it has passed. If it is better, it is set as the best position. The best value of the particle obtained in step 1 and step 2 is compared with the best value of the entire population, and the best solution of the entire population is updated; The judgment module is used to select particles to enter the mixing pool according to the mixing probability. The particles in the mixing pool will randomly mix with each other to produce the same number of offspring particles, keeping the best solution and the best solution found by the entire population unchanged, and checking whether the end condition is met. If the current iteration reaches the predefined maximum number of times, the iteration is stopped and the optimal solution is output, otherwise the position update module continues to execute.
7. Computer readable storage medium, It is characterized in that The computer-readable storage medium is used to store a computer program, and the computer program executes the method according to any one of claims 1 to 5.
8. Computer equipment, including memory and processors, It is characterized in that A computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor implements the method according to any one of claims 1 to 5.
Citation Information
Cited By
Solar unmanned aerial vehicle energy-path collaborative management method based on hierarchical PSO algorithm
CN120949795A
