Path planning method and device based on aircraft power consumption

Abstract

The present invention provides a path planning method and device based on aircraft power consumption. The method includes: obtaining parameters of an ant colony algorithm, multiple target task points, and the power of each aircraft; each target task point corresponds to each node constituting a path in the ant colony algorithm; determining an optimal overall path and its corresponding task groups within a maximum number of iterations based on the parameters of the ant colony algorithm, the power of each aircraft, and an improved ant colony algorithm; the overall path represents multiple target task points and their visit order; during each iteration of the ant colony algorithm, the task groups corresponding to each overall path in the current iteration are determined based on the power of each aircraft, and the optimal overall path in the current iteration is determined based on the power consumed by each aircraft to complete the task and the total time required to complete the multiple target tasks. Based on this, complex multiple tasks can be divided into multiple task groups while ensuring low power consumption and a short overall task completion time.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a path planning method and device based on aircraft power consumption. Background Art

[0002] When an aircraft performs complex missions, different task partitioning methods affect the total time required to complete the mission and the aircraft's power consumption. This power consumption also determines the aircraft's responsiveness to new missions. Therefore, a current research direction is to find a way to divide complex, multi-tasks into multiple task groups while maintaining low power consumption and short overall mission completion times. Summary of the Invention

[0003] The present invention provides a path planning method and device based on aircraft power consumption, which is used to provide a path planning method based on aircraft power consumption, so as to achieve the division of complex multiple tasks into multiple task groups while meeting the requirements of low power consumption and short overall task completion time.

[0004] The present invention provides a path planning method based on aircraft power consumption, comprising: obtaining parameters of an ant colony algorithm, multiple target task points, and the power consumption of each aircraft; wherein the parameters of the ant colony algorithm include a maximum number of iterations; the multiple target task points are task points corresponding to multiple target tasks to be performed by the aircraft, and each target task point corresponds to each node constituting a path in the ant colony algorithm; based on the parameters of the ant colony algorithm, the power consumption of each aircraft, and an improved ant colony algorithm, determining an optimal overall path and its corresponding task group within the maximum number of iterations; wherein the overall path represents the multiple target task points and their corresponding visit order;

[0005] Among them, during each iteration process, the improved ant colony algorithm determines the task group corresponding to each overall path in the current iteration based on the power of each aircraft, and determines the optimal overall path in the current iteration based on the power consumed by each aircraft to complete the task and the overall time to complete multiple target tasks.

[0006] In one embodiment, the method of determining the optimal overall path and its corresponding task group within a maximum number of iterations based on the parameters of the ant colony algorithm, the power of each aircraft, and the improved ant colony algorithm includes: determining multiple overall paths according to the single traveling salesman problem based on the parameters of the ant colony algorithm and the ant colony algorithm; determining multiple task groups corresponding to each overall path based on the power of each aircraft; each task in each task group is performed by one aircraft; determining the optimal overall path in the current iteration from the multiple overall paths based on the total power consumed by each aircraft to complete the tasks in the corresponding task group and the total time required to complete multiple target tasks; updating the pheromones on each overall path based on an objective function that affects pheromone updating; wherein the objective function that affects pheromone updating is determined based on the total power consumed by each aircraft to complete the tasks in the corresponding task group and the total time required to complete multiple target tasks; when the number of iterations is less than the maximum number of iterations, determining the optimal overall path and its corresponding task group in the current iteration and previous iterations based on the updated pheromones; and when the number of iterations is equal to the maximum number of iterations, outputting the optimal overall path and its corresponding task group in the current iteration and previous iterations.

[0007] In one embodiment, the determining of the task group corresponding to each overall path based on the power of each aircraft includes: determining the target task points and their number that can be completed by the first aircraft based on the access order of multiple target task points in each overall path and the total power of the first aircraft, and determining the target task points that can be completed by the first aircraft as the first task group corresponding to the first aircraft; based on the access order of multiple target task points in each overall path and the total power of the second aircraft, determining the target task points and their number that can be completed by the second aircraft from the multiple target task points other than the first task group, and determining the target task points that can be completed by the second aircraft as the second task group corresponding to the second aircraft.

[0008] In one embodiment, the objective function affecting pheromone renewal is Among them, max(T s ) represents the total time to complete multiple target tasks, which is determined based on the maximum time required to complete all corresponding task points on each overall path; E s represents the power consumed by the s-th aircraft to complete the task in the corresponding task group, U is the number of aircraft called to complete all the corresponding task points on each overall path; the pheromone of the k-th ant on the path between the i-th target task point and the j-th target task point determined based on the objective function affecting the pheromone update is: Where tabu is the overall path, k represents the kth ant, i and j represent the i-th task and j-th task respectively, and Q is the pheromone intensity.

[0009] In one embodiment, the maximum time max(T) required to complete all the corresponding task points on each overall path is s ) is determined based on the time required for each aircraft to complete the target task in the corresponding task group; the T s It is the time interval between each aircraft leaving the charging platform and completing the last task in the corresponding task group.

[0010] In one embodiment, the amount of electricity consumed by the s-th aircraft to complete the task in the corresponding task group is E s Including: the power consumed by the sth aircraft during flight and the power consumed by executing tasks Among them, D s V represents the length of the path that the sth aircraft takes when it departs from the charging platform, completes the tasks in the corresponding task group, and finally returns to the charging platform; f Represents the flight speed of the aircraft, P f Indicates the power consumed by the aircraft during flight, t h represents the time required for the aircraft to perform the hth task, P h It represents the power consumed by the aircraft when performing the hth task.

[0011] In one embodiment, the Among them, d s,1 represents the distance the sth aircraft flies from the charging platform to the first target mission point in the corresponding mission group, d s,j represents the distance that the sth aircraft flies from the last target mission point in the corresponding mission group back to the charging platform, d′ h-1,h Represents the flight distance of the s-th aircraft between the h-1-th target mission point and the h-th target mission point.

[0012] The present invention also provides a path planning device based on aircraft power consumption, comprising: a first acquisition module, used to acquire parameters of an ant colony algorithm, multiple target task points and the power of each aircraft; wherein the parameters of the ant colony algorithm include a maximum number of iterations; the multiple target task points are task points corresponding to multiple target tasks that the aircraft is about to perform, and each target task point corresponds to each node constituting a path in the ant colony algorithm; a determination module, used to determine the optimal overall path and its corresponding task group within the maximum number of iterations based on the parameters of the ant colony algorithm, the power of each aircraft and an improved ant colony algorithm; wherein the overall path represents multiple target task points and their corresponding access order; wherein, during each iteration process, the improved ant colony algorithm determines the task group corresponding to each overall path in the current iteration based on the power of each aircraft, and determines the optimal overall path in the current iteration based on the power consumed by each aircraft to complete the task and the overall time for completing multiple target tasks.

[0013] The present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of any of the above-described path planning methods based on aircraft power consumption are implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of any of the above-mentioned path planning methods based on aircraft power consumption are implemented.

[0015] The path planning method and device based on aircraft power consumption provided by the present invention utilizes an ant colony algorithm to determine the optimal overall path for each iteration based on the power consumed by each aircraft to complete its mission and the total time required to complete multiple target tasks. This ensures that the ultimately determined optimal overall path meets the requirements of low power consumption and short overall task completion times. Furthermore, during each iteration, the task groups corresponding to each overall path in the current iteration are determined based on the power consumption of each aircraft. This allows for the division of complex multiple tasks into multiple task groups while maintaining low power consumption and short overall task completion times. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1This is a schematic diagram of an application scenario of aircraft multi-tasking division provided by the present invention;

[0018] Figure 2 This is one of the flow charts of the path planning method based on aircraft power consumption provided by the present invention;

[0019] Figure 3 This is the second flow chart of the path planning method based on aircraft power consumption provided by the present invention;

[0020] Figure 4 This is the third flow chart of the path planning method based on aircraft power consumption provided by the present invention;

[0021] Figure 5 1 is a schematic structural diagram of a path planning device based on aircraft power consumption provided by the present invention;

[0022] Figure 6 1 is a schematic structural diagram of a path planning device based on aircraft power consumption provided by the present invention;

[0023] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0025] In order to facilitate understanding, the technical terms involved in the present invention are first explained.

[0026] (1) Ant Colony Algorithm

[0027] The ant colony algorithm (ACO) was inspired by studies of the foraging behavior of real ant colonies. Biological research has shown that a group of collaborative ants can find the shortest path between food and their nest, whereas individual ants cannot. Through extensive and detailed observations, biologists have discovered that the behavior of individual ants interacts and influences each other. As ants move, they leave behind a substance called pheromone along their paths. This substance acts as a medium for communication between ants. Ants can sense this substance and habitually follow it as they crawl, naturally releasing pheromones as they move. The thicker the pheromone trail on a path, the more likely other ants will follow it, thus strengthening the pheromone trail along that path. Therefore, the collective behavior of a large ant colony exhibits a phenomenon of positive feedback loops. The more ants that travel a path, the more likely subsequent ants are to choose that path.

[0028] Typically, the ant colony algorithm includes the following steps:

[0029] Step 1: Initialize the number of ants m in the ant colony, the pheromone heuristic factor α, the expected heuristic factor β, the pheromone evaporation coefficient ρ, and the pheromone intensity Q. Initialize the map and set the pheromone of all paths in the map to 0.

[0030] Step 2: Start the first round of iteration, place all ants at the starting point, and all ants choose the corresponding route according to probability.

[0031] Step 3: Get the end points of the paths reached by all ants, and update the pheromone left by each ant between two nodes according to the path chosen by each ant.

[0032] Step 4: Perform the next round of iteration until the number of iterations reaches the maximum number of iterations.

[0033] Step 5: The route of one of the ants in the last round is determined to be the optimal route. The optimal route has the most pheromones and the shortest path.

[0034] For ease of understanding, combined Figure 1 Explain the application scenarios of aircraft multi-tasking division, such as Figure 1 As shown, number 1 is the charging platform, located within the mission area. Numbers 2-26 represent the locations of multiple pending target missions, represented by circles. Each mission requires a different time to complete. If the deployed aircraft is low on battery, it must first return to the charging platform to recharge, then depart from the charging platform to perform the mission. After completing the mission, it returns to the charging platform to await the next round of missions.

[0035] It is understood that task division should first ensure that the aircraft performing the task can safely return to the charging platform after completing the task and have rapid response capabilities. That is, the total power consumption of all aircraft performing the task is low, thereby allowing the aircraft batteries to be charged quickly. In addition, the task division should ensure a short overall task completion time. That is, the maximum time interval between the completion time of all tasks and the initial time of aircraft departure should be as small as possible. Therefore, in order to achieve the above-mentioned scenario and to achieve the goal of dividing complex multiple tasks into multiple task groups while ensuring low power consumption and a short overall task completion time, the present invention proposes a path planning method based on aircraft power consumption.

[0036] The following combination Figure 2-Figure 7 The present invention describes a path planning method and device based on aircraft power consumption.

[0037] Figure 2 This is one of the flow charts of the path planning method based on aircraft power consumption provided by the present invention. It should be understood that the path planning method based on aircraft power consumption provided by the present invention can be executed by a path planning device based on aircraft power consumption. Figure 2 As shown, the path planning method based on aircraft power consumption may include the following steps:

[0038] Step 210: Obtain the parameters of the ant colony algorithm, multiple target mission points, and the power of each aircraft.

[0039] The parameters of the ant colony algorithm include the maximum number of iterations. Furthermore, the parameters of the ant colony algorithm also include: the number of ants m, the pheromone heuristic factor α, the expected heuristic factor β, the pheromone evaporation coefficient ρ, and the pheromone strength Q. The multiple target mission points correspond to multiple target missions that the aircraft is about to perform, and each target mission point corresponds to a node constituting a path in the ant colony algorithm.

[0040] Step 220, based on the parameters of the ant colony algorithm, the power of each aircraft and the improved ant colony algorithm, determine the optimal overall path and its corresponding task group within the maximum number of iterations; wherein the overall path represents multiple target task points and their corresponding visit order.

[0041] Among them, during each iteration process, the improved ant colony algorithm determines the task group corresponding to each overall path in the current iteration based on the power of each aircraft, and determines the optimal overall path in the current iteration based on the power consumed by each aircraft to complete the task and the overall time to complete multiple target tasks.

[0042] It is understood that, under normal circumstances, the ant colony algorithm will determine the optimal path for the current iteration during each iteration, and then update the pheromone based on the optimal path for the current iteration. The optimal overall path is mainly determined by the length of the path. In the present invention, in order to meet the requirements of low power consumption and short overall task completion time, the optimal overall path for the current iteration is determined based on the power consumed by each aircraft to complete the task and the total time required to complete multiple target tasks. This ensures that the ultimately determined optimal overall path can meet the requirements of low power consumption and short overall task completion time. At the same time, the task groups corresponding to each overall path in the current iteration are determined based on the power consumption of each aircraft. This can achieve the division of complex multiple tasks into multiple task groups while meeting the requirements of low power consumption and short overall task completion time.

[0043] The path planning method based on aircraft power consumption provided by the present invention uses an ant colony algorithm to determine the optimal overall path for the current iteration based on the power consumed by each aircraft to complete the task and the total time required to complete multiple target tasks during each iteration. This ensures that the ultimately determined optimal overall path meets the requirements of low power consumption and short overall task completion time. Furthermore, during each iteration, the task groups corresponding to each overall path in the current iteration are determined based on the power consumption of each aircraft. This allows for the division of complex multiple tasks into multiple task groups while maintaining low power consumption and short overall task completion time.

[0044] In one embodiment, the optimal overall path and its corresponding task group within the maximum number of iterations are determined based on the parameters of the ant colony algorithm, the power of each aircraft, and the improved ant colony algorithm, such as Figure 3 As shown, the following steps are included:

[0045] Step 310 : Based on the parameters of the ant colony algorithm and the ant colony algorithm, multiple overall paths are determined according to the single traveling salesman problem.

[0046] For example, the single traveling salesman problem involves a person visiting 34 cities and designing the shortest possible route from a starting point to all the cities and back to the starting point. Correspondingly, in the present invention, determining multiple overall paths according to the single traveling salesman problem can be understood as each ant determining an overall path corresponding to completing multiple target tasks. Therefore, the multiple ants in the ant colony determine multiple overall paths corresponding to the multiple target tasks, with each overall path representing multiple target tasks and their visit order.

[0047] Step 320 : Determine multiple task groups corresponding to each overall path based on the power of each aircraft; tasks in each task group are executed by one aircraft.

[0048] Among them, the task group is a set of multiple tasks obtained by dividing multiple target tasks in each total path.

[0049] It can be understood that since the power of one aircraft is not enough to complete multiple target tasks in each overall path, multiple aircraft can perform multiple target tasks on each overall path. Therefore, multiple task sets (i.e., multiple task groups) corresponding to each overall path can be determined based on the power of each aircraft, and then each aircraft completes the target tasks in the corresponding task group.

[0050] It is understood that each target mission can only be performed once by the aircraft, which can also be expressed as Here, exec(i,j) represents the execution status between the i-th aircraft and the j-th task. 1 indicates that the aircraft executed the task, and 0 indicates that the aircraft did not execute the task. U is the number of aircraft called, and M is the number of tasks.

[0051] Step 330 : Based on the total power consumed by each aircraft in completing the tasks in the corresponding task group and the total time required to complete the multiple target tasks, determine the optimal overall path in the current iteration from the multiple overall paths.

[0052] As previously mentioned, during each iteration, each ant can determine an overall path. Consequently, multiple ants can determine multiple overall paths. Each overall path corresponds to multiple task groups, with each task group being performed by a single aircraft. Therefore, to determine the optimal overall path from among these multiple overall paths, and to ensure that this optimal overall path meets the requirements of low power consumption and a short overall task completion time, the optimal overall path for the current iteration can be determined from these multiple overall paths based on the total power consumed by each aircraft completing the tasks in the corresponding task group and the total completion time of the multiple target tasks.

[0053] It can be understood that the tasks in the corresponding task groups completed by each aircraft collectively constitute the multiple target tasks within each overall path. In other words, the optimal overall path for the current iteration is determined from the multiple overall paths based on the total power consumed by the aircraft required to complete the multiple target tasks within each overall path and the total time required to complete the multiple target tasks. It should be noted that the optimal overall path is the one that minimizes the total power consumed by each aircraft in completing the tasks in the corresponding task groups and minimizes the total time required to complete the multiple target tasks.

[0054] Step 340: Update the pheromones on each overall path based on an objective function that affects pheromone updating; wherein the objective function that affects pheromone updating is determined based on the total amount of electricity consumed by each aircraft to complete the tasks in the corresponding task group and the total time required to complete multiple target tasks.

[0055] It can be understood that the pheromone update and optimal path determination process during each iteration are similar. Similarly, as previously mentioned, each ant can determine an overall path, so multiple ants can determine multiple overall paths. Each overall path corresponds to multiple task groups, and the tasks in each task group are performed by a single aircraft. The pheromone intensity along each overall path is a criterion for determining the optimal overall path. Therefore, the objective function affecting pheromone updates can be determined based on the total power consumed by each aircraft to complete the tasks in the corresponding task group and the total time required to complete the multiple target tasks. The pheromones on each overall path are updated based on the objective function affecting pheromone updates, thereby determining the final optimal path that meets the requirements of low power consumption and short overall task completion time.

[0056] Step 350, when the number of iterations is less than the maximum number of iterations, determine the optimal overall path and its corresponding task group in the current iteration and the historical iterations based on the updated pheromone; when the number of iterations is equal to the maximum number of iterations, output the optimal overall path and its corresponding task group in the current iteration and the historical iterations.

[0057] The optimal overall path in the current iteration and the previous iterations is the optimal path determined from the current number of iterations and the previous iterations. It will be appreciated that after each iteration, the optimal overall path determined in the current iteration can be compared with the optimal path determined in the previous iteration to determine whether to update the optimal overall path. Furthermore, each optimal overall path corresponds to a different task group. Therefore, when the number of iterations equals the maximum number of iterations, the optimal overall path and its corresponding task group for the current iteration and the previous iteration are output.

[0058] In one embodiment, the objective function affecting pheromone renewal is Among them, max(T s ) represents the total time to complete multiple target tasks, which can be determined based on the maximum time required to complete all corresponding task points on each overall path (i.e., the maximum time required for each aircraft to complete the corresponding task group), E s represents the power consumed by the s-th aircraft to complete the task in the corresponding task group, U is the number of aircraft called to complete all the corresponding task points on each overall path; the pheromone of the k-th ant on the path between the i-th target task point and the j-th target task point determined based on the objective function affecting the pheromone update is: Where tabu is the overall path, k represents the kth ant, i and j represent the i-th task and j-th task respectively, and Q is the pheromone intensity.

[0059] The maximum time required to complete all the corresponding task points on each overall path is max(T s ) is determined based on the time required for each aircraft to complete the target task in the corresponding task group; the T s It is the time interval between each aircraft leaving the charging platform and completing the last task in the corresponding task group.

[0060] The amount of electricity consumed by the sth aircraft to complete the task in the corresponding task group is E s Including: the power consumed by the sth aircraft during flight and the power consumed by executing tasks Among them, D s V represents the length of the path that the sth aircraft takes when it departs from the charging platform, completes the tasks in the corresponding task group, and finally returns to the charging platform; f Represents the flight speed of the aircraft, P f Indicates the power consumed by the aircraft during flight, t h represents the time required for the aircraft to perform the hth task, P h It represents the power consumed by the aircraft when performing the hth task.

[0061] in, Among them, d s,1 represents the distance the sth aircraft flies from the charging platform to the first target mission point in the corresponding mission group, d s,j represents the distance that the sth aircraft flies from the last target mission point in the corresponding mission group back to the charging platform, d′ h-1,h represents the flight distance of the s-th aircraft between the h-1-th target mission point and the h-th target mission point; specifically, the distance between the starting position of the s-th aircraft and the j-th target mission point The distance between the h-1th target task point and the hth target task point is Among them, x B-s and y B-s They represent the starting position of the sth aircraft, that is, the horizontal and vertical coordinates of the aircraft charging platform on the coordinate axis, x M-j and y M-j They represent the horizontal and vertical coordinates of the j-th task point on the coordinate axis, x M-(h-1) and y M-(h-1) They represent the horizontal and vertical coordinates of the h-1th target task point on the coordinate axis, respectively. M-h and y M-h They respectively represent the horizontal and vertical coordinates of the h-th target task point on the coordinate axis.

[0062] In one embodiment, the task group corresponding to each overall path is determined based on the power of each aircraft, such as Figure 4 As shown, the following steps are included:

[0063] Step 410, based on the access order of multiple target mission points in each overall path and the total power of the first aircraft, determine the target mission points and their number that the first aircraft can complete, and determine the target mission points that the first aircraft can complete as the first mission group corresponding to the first aircraft.

[0064] Specifically, regarding the order of accessing multiple target task points in each overall path generated by the ant colony algorithm, assuming that the first aircraft departs from the charging platform, it first calculates its remaining power after completing the first target task. If the remaining power can support it to travel to the next task point on the path and complete the task, and the remaining power after completing the next task can still guarantee that it can fly back to the starting position, then the first aircraft will continue to perform the task. Similarly, the first aircraft will calculate the remaining power after each task it completes according to the path plan. Assuming that in a certain calculation, the above requirements for the remaining power of the aircraft cannot be met, if the next task point on the path at this time is named Task J, then the first aircraft will no longer perform Task J and will directly return to the charging platform. The tasks that have been performed before Task J are determined to be the first task group corresponding to the first aircraft.

[0065] Step 420, based on the access order of multiple target mission points in each overall path and the total power of the second aircraft, determine the target mission points and their number that can be completed by the second aircraft from the multiple target mission points other than the first mission group, and determine the target mission points that can be completed by the second aircraft as the second mission group corresponding to the second aircraft.

[0066] Similar to the process of determining the task group of the first aircraft mentioned above, based on the access order of multiple target task points in each overall path generated by the ant colony algorithm, the second aircraft will fly directly from the charging platform to task J, and start from task J to perform subsequent unfinished tasks in the order of access to multiple target task points, and calculate the remaining power, so as to determine the second task group corresponding to the second aircraft.

[0067] It will be appreciated that the above calculations terminate once all of the target tasks are completed, thereby achieving the goal of partitioning the multiple tasks within the constraints of the aircraft's own battery capacity. In other words, steps 410 and 420 are repeated until all of the target tasks are completed, completing the process of partitioning the multiple target tasks into multiple task groups. Each task group is then executed by a corresponding aircraft.

[0068] It can also be understood that after the mission group is determined, each aircraft can simultaneously execute the tasks in the corresponding mission group during the actual execution process.

[0069] In one embodiment, a detailed implementation method of path planning based on aircraft power consumption is provided, which is described in detail below.

[0070] Specifically, the influence of different parameter values ​​on the ant algorithm can be explored based on the MATLAB R2016a environment. In this embodiment, the PC configuration can be Intel(R) Core(TM) i5-9300H@2.4Ghz, with a processor number of four cores and eight threads and 16G memory.

[0071] The simulation scene can refer to Figure 1 The target mission point location and the time required to complete the corresponding mission are shown in Table 1. The relevant performance parameters of the aircraft are shown in Table 2.

[0072] Table 1 Target mission point location and corresponding mission time information

[0073]

[0074] Table 2 Performance parameters of aircraft in mission division scenarios

[0075]

[0076]

[0077] The following will analyze the impact of different values ​​of the six parameters in the ant colony algorithm, namely the number of ants m, pheromone heuristic factor α, expected heuristic factor β, pheromone evaporation coefficient ρ, pheromone intensity Q and maximum number of iterations G on the objective function, and find the optimal parameter settings before conducting subsequent simulation verification.

[0078] 1. About Pheromone Heuristic Factor α and Expectation Heuristic Factor β

[0079] If the value of α is relatively small, the search process may become trapped in a local optimum, while a larger value will weaken the algorithm's randomness. On the other hand, a relatively large value of β, while increasing the algorithm's convergence speed, weakens the randomness of the solution process. There is a strong correlation between α and β. To ensure that the ant colony algorithm exhibits strong randomness and high convergence performance in global search, it is necessary to properly select the relationship between the two.

[0080] To determine the values ​​of α and β, the number of ants m was set to 20, ρ was set to 0.2, Q was set to 10, and G was set to 100. For different values ​​of the above two parameters, each group was simulated 50 times, and the optimal, worst, and average values ​​of the three indicators of the objective function z were calculated, as shown in Table 3.

[0081] Table 3 The impact of different values ​​of α and β on the objective function

[0082]

[0083]

[0084] According to Table 3, by comparing the values ​​of the three indicators of the objective function when α and β take different values, it can be found that when α and β are 1 and 5 respectively, the above three indicators are better than the other values.

[0085] Regarding the pheromone evaporation coefficient ρ, which typically ranges from 0 to 1, it directly affects the randomness of the algorithm's search process. To determine the value of ρ, m was set to 20, α and β to 1 and 5, respectively, Q to 10, and G to 100. Each simulation was run 50 times for different values ​​of ρ, and the optimal, worst, and average values ​​of the objective function were recorded, as shown in Table 4 below.

[0086] Table 4 The impact of different values ​​of ρ on the objective function

[0087]

[0088] By comparing the optimal, worst, and average values ​​of the objective function for different values ​​of the pheromone evaporation coefficient ρ, it can be found that when the pheromone evaporation coefficient ρ is between 0.1 and 0.3, the above three indicators are all better than those for the other values.

[0089] 3. About the number of ants in the ant colony m

[0090] If the value of m is relatively large, the algorithm will generate too many identical solutions, thus affecting the positive feedback ability of the pheromone. However, if the number is relatively small, the randomness of the search process will be weakened.

[0091] To determine the value of m, α and β were set to 1 and 5, respectively, ρ was set to 0.1, Q was set to 10, and G was set to 100. For different values ​​of the number of ants m, each group was simulated 50 times, and the three indicators of the objective function and the running time of the algorithm were statistically analyzed, as shown in Table 5 below.

[0092] Table 5 The impact of the value of m on the objective function

[0093]

[0094] By comparing the optimal, worst, and average values ​​of the objective function for different values ​​of the number of ants, m, we can see that as m increases, the algorithm's optimization capability improves, but the program's runtime also increases. Taking into account the three metrics of the objective function and the program's runtime, the number of ants, m, can be adjusted between 20 and 40.

[0095] 4. About Pheromone Intensity Q

[0096] The selection of Q is highly dependent on the values ​​of α, β, and ρ. To determine the value of Q, α and β were set to 1 and 5, respectively, ρ was set to 0.1, m was set to 20, and G was set to 100. For different values ​​of Q, each group was simulated 50 times, and the optimal, worst, and average values ​​of the objective function were recorded, as shown in Table 6 below.

[0097] Table 6 The impact of the value of Q on the objective function

[0098]

[0099] By comparing the optimal, worst, and average values ​​of the objective function for different values ​​of pheromone intensity Q, it is clear that pheromone intensity Q does not significantly affect the performance of the algorithm. By comparing the three indicators mentioned above, when the values ​​of α, β, and ρ are set to 1, 5, and 0.1, respectively, the value of pheromone intensity Q is selected as 10.

[0100] 5. About the maximum number of iterations G

[0101] The maximum number of iterations, G, is a parameter that affects the termination of the ant colony algorithm. If the number of iterations reaches G, the algorithm stops and outputs the current optimal solution. To determine the value of the maximum number of iterations, G, α and β were set to 1 and 5, respectively, ρ was set to 0.1, m was set to 20, and Q was set to 10. Each simulation was run 50 times for different values ​​of the maximum number of iterations, and the three objective function metrics and algorithm runtime were calculated, as shown in Table 7 below.

[0102] Table 7 The impact of the value of G on the objective function

[0103]

[0104]

[0105] By comparing the optimal, worst, and average values ​​of the objective function for different values ​​of the maximum number of iterations G, we can see that as G increases, the average values ​​of the three objective function metrics decrease slightly, but the runtime increases accordingly. Therefore, considering both the average value and runtime, the maximum number of iterations G is set to 100.

[0106] Based on the above analysis of the values ​​of the relevant parameters of the ant colony algorithm, the parameter settings are shown in Table 8 below during the simulation verification.

[0107] Table 8 Parameter settings of ant colony algorithm

[0108]

[0109] Table 9 shows the results of the multi-task partitioning algorithm optimized under the aforementioned parameter settings. The third column shows the power consumption after the aircraft departs from the charging platform, completes each task, and returns to the charging platform, following the order of tasks listed in the second column. The fourth column shows the time interval between the aircraft's departure from the charging platform and the completion of the tasks listed in the second column. Based on the multi-task partitioning results shown in the second column, the total power consumption of the aircraft is 909.4588 Wh, and the total time required to complete the tasks is 131.6407 hours.

[0110] Table 9 Optimized multi-task partitioning results

[0111]

[0112]

[0113] According to the multi-task division results shown in Table 9, the flight path of the aircraft can be drawn as follows: Figure 5 As shown. The task points corresponding to the circles represent the tasks in the task group numbered 1, the task points corresponding to the rectangles represent the tasks in the task group numbered 5, the task points corresponding to the diamonds represent the tasks in the task group numbered 6, the task points corresponding to the plus sign (+) represent the tasks in the task group numbered 2, the task points corresponding to the multiplication sign (x) represent the tasks in the task group numbered 4, and the task points corresponding to the asterisk (*) represent the tasks in the task group numbered 3.

[0114] The path planning device based on aircraft power consumption provided by the present invention is described below. The path planning device based on aircraft power consumption described below and the path planning method based on aircraft power consumption described above can refer to each other.

[0115] Figure 6 Schematic diagram of a path planning device based on aircraft power consumption provided by the present invention, such as Figure 6As shown, the path planning device based on aircraft power consumption provided by an embodiment of the present invention includes:

[0116] Acquisition module 610 is configured to acquire parameters of an ant colony algorithm, multiple target mission points, and the power level of each aircraft; wherein the parameters of the ant colony algorithm include a maximum number of iterations; the multiple target mission points are mission points corresponding to multiple target missions to be performed by the aircraft, and each target mission point corresponds to each node constituting a path in the ant colony algorithm;

[0117] Determination module 610 is configured to determine an optimal overall path and its corresponding task group within a maximum number of iterations based on the parameters of the ant colony algorithm, the power of each aircraft, and the improved ant colony algorithm; wherein the overall path represents multiple target task points and their corresponding visit order;

[0118] Among them, during each iteration process, the improved ant colony algorithm determines the task group corresponding to each overall path in the current iteration based on the power of each aircraft, and determines the optimal overall path in the current iteration based on the power consumed by each aircraft to complete the task and the overall time to complete multiple target tasks.

[0119] The path planning device based on aircraft power consumption provided by the present invention uses an ant colony algorithm to determine the optimal overall path for the current iteration based on the power consumed by each aircraft to complete the task and the total time required to complete multiple target tasks during each iteration. This ensures that the ultimately determined optimal overall path meets the requirements of low power consumption and short overall task completion time. Furthermore, during each iteration, the task groups corresponding to each overall path in the current iteration are determined based on the power consumption of each aircraft. This allows for the division of complex multiple tasks into multiple task groups while maintaining low power consumption and short overall task completion time.

[0120] Based on any of the above embodiments, in this embodiment, the determining module 620 includes:

[0121] A first determining unit is configured to determine a plurality of overall paths according to a single traveling salesman problem based on parameters of an ant colony algorithm and the ant colony algorithm;

[0122] A second determining unit is configured to determine a plurality of task groups corresponding to each overall path based on the power levels of each aircraft; a task in each task group is performed by one aircraft;

[0123] a third determining unit, configured to determine an optimal overall path for a current iteration from among the multiple overall paths based on the total power consumed by each aircraft in completing the tasks in the corresponding task group and the total time required to complete the multiple target tasks;

[0124] an updating unit, configured to update the pheromones on each overall path based on an objective function affecting pheromone updating; wherein the objective function affecting pheromone updating is determined based on the total amount of power consumed by each aircraft in completing tasks in the corresponding task group and the total time required to complete the multiple target tasks;

[0125] The fourth determination unit is used to determine the optimal overall path and its corresponding task group in the current iteration and historical iterations based on the updated pheromone when the number of iterations is less than the maximum number of iterations; and output the optimal overall path and its corresponding task group in the current iteration and historical iterations when the number of iterations is equal to the maximum number of iterations.

[0126] Based on any of the foregoing embodiments, in this embodiment, the second determining unit includes:

[0127] a fifth determining unit, configured to determine, based on an order of accessing the plurality of target mission points in each overall path and a total power level of the first aircraft, the target mission points that can be completed by the first aircraft and the number of target mission points that can be completed by the first aircraft, and to determine the target mission points that can be completed by the first aircraft as a first mission group corresponding to the first aircraft;

[0128] The sixth determination unit is used to determine the target mission points and their number that can be completed by the second aircraft from the multiple target mission points except the first mission group based on the access order of multiple target mission points in each overall path and the total power of the second aircraft, and determine the target mission points that can be completed by the second aircraft as the second mission group corresponding to the second aircraft.

[0129] Based on any of the above embodiments, in this embodiment, the objective function affecting pheromone update is Among them, max(T s ) represents the total time to complete multiple target tasks, which is determined based on the maximum time required to complete all corresponding task points on each overall path; E s represents the amount of power consumed by the sth aircraft to complete the task in the corresponding task group, and U is the number of aircraft called to complete all the corresponding task points on each overall path;

[0130] The pheromone of the kth ant on the path between the i-th target task point and the j-th target task point determined based on the objective function affecting the pheromone update is: Where tabu is the overall path, k represents the kth ant, i and j represent the i-th task and j-th task respectively, and Q is the pheromone intensity.

[0131] Based on any of the above embodiments, in this embodiment, the maximum time max (T s) is determined based on the time required for each aircraft to complete the target task in the corresponding task group; the T s It is the time interval between each aircraft leaving the charging platform and completing the last task in the corresponding task group.

[0132] In one embodiment, the amount of electricity consumed by the s-th aircraft to complete the task in the corresponding task group is E s Including: the power consumed by the sth aircraft during flight and the power consumed by executing tasks Among them, D s V represents the length of the path that the sth aircraft takes when it departs from the charging platform, completes the tasks in the corresponding task group, and finally returns to the charging platform; f Represents the flight speed of the aircraft, P f Indicates the power consumed by the aircraft during flight, t h represents the time required for the aircraft to perform the hth task, P h It represents the power consumed by the aircraft when performing the hth task.

[0133] Based on any of the above embodiments, in this embodiment, the Among them, d s,1 represents the distance the sth aircraft flies from the charging platform to the first target mission point in the corresponding mission group, d s,j represents the distance that the sth aircraft flies from the last target mission point in the corresponding mission group back to the charging platform, d′ h-1,h Represents the flight distance of the s-th aircraft between the h-1-th target mission point and the h-th target mission point.

[0134] Figure 7 An example of a physical structure diagram of an electronic device is shown below. Figure 7As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740. The processor 710, the communication interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 may invoke logic instructions in the memory 730 to execute a path planning method based on aircraft power consumption. Among them, the path planning method based on aircraft power consumption includes: obtaining the parameters of the ant colony algorithm, multiple target task points and the power of each aircraft; wherein, the parameters of the ant colony algorithm include the maximum number of iterations; the multiple target task points are task points corresponding to multiple target tasks that the aircraft is about to perform, and each target task point corresponds to each node constituting the path in the ant colony algorithm; based on the parameters of the ant colony algorithm, the power of each aircraft and the improved ant colony algorithm, determining the optimal overall path and its corresponding task group within the maximum number of iterations; wherein, the overall path represents multiple target task points and their corresponding access order; wherein, during each iteration process, the improved ant colony algorithm determines the task group corresponding to each overall path in the current iteration based on the power of each aircraft, and determines the optimal overall path in the current iteration based on the power consumed by each aircraft to complete the task and the overall time for completing multiple target tasks.

[0135] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk, etc. Various media that can store program codes.

[0136] On the other hand, the present invention also provides a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, and when the program instructions are executed by a computer, the computer is capable of executing the path planning method based on aircraft power consumption provided by the present invention. The path planning method based on aircraft power consumption comprises: obtaining parameters of an ant colony algorithm, a plurality of target task points, and the power of each aircraft; wherein the parameters of the ant colony algorithm include a maximum number of iterations; the plurality of target task points are task points corresponding to a plurality of target tasks to be performed by the aircraft, each target task point corresponding to each node constituting a path in the ant colony algorithm; based on the parameters of the ant colony algorithm, the power of each aircraft, and an improved ant colony algorithm, determining an optimal overall path and its corresponding task groups within the maximum number of iterations; wherein the overall path represents a plurality of target task points and their corresponding visit order; wherein, during each iteration, the improved ant colony algorithm determines the task groups corresponding to each overall path in the current iteration based on the power of each aircraft, and determines the optimal overall path in the current iteration based on the power consumed by each aircraft to complete the task and the total time required to complete the plurality of target tasks.

[0137] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the path planning method based on aircraft power consumption provided by the present invention. The path planning method based on aircraft power consumption includes: obtaining parameters of an ant colony algorithm, multiple target task points, and the power consumption of each aircraft; wherein the parameters of the ant colony algorithm include a maximum number of iterations; the multiple target task points are task points corresponding to multiple target tasks to be performed by the aircraft, each target task point corresponding to each node constituting a path in the ant colony algorithm; based on the parameters of the ant colony algorithm, the power consumption of each aircraft, and an improved ant colony algorithm, determining an optimal overall path and its corresponding task groups within the maximum number of iterations; wherein the overall path represents multiple target task points and their corresponding visit order; wherein, during each iteration, the improved ant colony algorithm determines the task groups corresponding to each overall path in the current iteration based on the power consumption of each aircraft, and determines the optimal overall path in the current iteration based on the power consumption of each aircraft to complete the task and the total time required to complete the multiple target tasks.

[0138] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0139] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0140] It can be understood 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 of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A path planning method based on aircraft power consumption, characterized in that: Place The methods include: Obtaining parameters of an ant colony algorithm, multiple target mission points, and the power level of each aircraft; wherein the parameters of the ant colony algorithm include a maximum number of iterations; the multiple target mission points are mission points corresponding to multiple target missions to be performed by the aircraft, and each target mission point corresponds to each node constituting a path in the ant colony algorithm; Based on the parameters of the ant colony algorithm, the power of each aircraft, and the improved ant colony algorithm, determine the optimal overall path and its corresponding task group within the maximum number of iterations; wherein the overall path represents multiple target task points and their corresponding visit order; The improved ant colony algorithm determines, during each iteration, the task groups corresponding to the overall paths in the current iteration based on the power of each aircraft, and the optimal overall path in the current iteration based on the power consumed by each aircraft to complete the task and the total time required to complete multiple target tasks. The method of determining the optimal overall path and its corresponding task group within a maximum number of iterations based on the parameters of the ant colony algorithm, the power of each aircraft, and the improved ant colony algorithm includes: Based on the parameters of the ant colony algorithm and the ant colony algorithm, multiple overall paths are determined according to the single traveling salesman problem; Determine multiple task groups corresponding to each overall path based on the power of each aircraft; tasks in each task group are performed by one aircraft; Based on the total power consumed by each aircraft to complete the tasks in the corresponding mission group and the total time to complete multiple target tasks, the optimal overall path under the current iteration is determined from multiple overall paths; Updating the pheromones on each overall path based on an objective function affecting pheromone updating; wherein the objective function affecting pheromone updating is determined based on the total amount of electricity consumed by each aircraft in completing tasks in the corresponding task group and the total time required to complete multiple target tasks; When the number of iterations is less than the maximum number of iterations, the optimal overall path and its corresponding task group in the current iteration and the previous iterations are determined based on the updated pheromone; when the number of iterations is equal to the maximum number of iterations, the optimal overall path and its corresponding task group in the current iteration and the previous iterations are output; The objective function affecting pheromone update is: ,in, The total time to complete multiple target tasks is determined based on the maximum time required to complete all corresponding task points on each overall path; Indicates the amount of power consumed by the sth aircraft to complete the task in the corresponding task group. The number of aircraft called to complete all corresponding mission points on each overall path; The pheromone of the kth ant's path between the i-th and j-th target task points determined based on the objective function affecting the pheromone update is: ,in, is the overall path, represents the kth ant, i and j represent the i-th and j-th tasks respectively, and Q is the pheromone intensity.

2. The path planning method based on aircraft power consumption according to claim 1, characterized in that: Determining the task group corresponding to each overall path based on the power of each aircraft includes: Determine the target mission points and their number that can be completed by the first aircraft based on the order in which the multiple target mission points are visited in each overall path and the total power of the first aircraft, and determine the target mission points that can be completed by the first aircraft as a first mission group corresponding to the first aircraft; Based on the access order of multiple target mission points in each overall path and the total power of the second aircraft, the target mission points and their number that the second aircraft can complete are determined in turn from the multiple target mission points except the first mission group, and the target mission points that the second aircraft can complete are determined as the second mission group corresponding to the second aircraft.

3. The path planning method based on aircraft power consumption according to claim 1, characterized in that: The maximum time required to complete all the corresponding task points on each overall path Determined based on the time required for each aircraft to complete the target task in the corresponding mission group; It is the time interval between each aircraft leaving the charging platform and completing the last task in the corresponding task group.

4. The path planning method based on aircraft power consumption according to claim 3, characterized in that: The amount of electricity consumed by the sth aircraft to complete the task in the corresponding task group Including: the power consumed by the sth aircraft during flight and the power consumed by executing tasks ; in, represents the length of the path that the sth aircraft takes when it departs from the charging platform, completes the tasks in the corresponding task group, and finally returns to the charging platform; Represents the flight speed of the aircraft, Indicates the power consumed by the aircraft during flight. represents the time required for the aircraft to perform the hth task, It represents the power consumed by the aircraft when performing the hth task.

5. The path planning method based on aircraft power consumption according to claim 4, characterized in that: described ,in, It represents the distance that the sth aircraft flies from the charging platform to the first target mission point in the corresponding mission group. It represents the distance that the sth aircraft flies from the last target mission point in the corresponding mission group back to the charging platform. Indicates that the sth aircraft is in the Target mission point and The flight distance between the target mission points.

6. A path planning device based on aircraft power consumption, characterized in that: The device comprises: A first acquisition module is configured to acquire parameters of an ant colony algorithm, multiple target mission points, and the power level of each aircraft; wherein the parameters of the ant colony algorithm include a maximum number of iterations; the multiple target mission points are mission points corresponding to multiple target missions to be performed by the aircraft, and each target mission point corresponds to each node constituting a path in the ant colony algorithm; a determination module, configured to determine an optimal overall path and its corresponding task group within a maximum number of iterations based on the parameters of the ant colony algorithm, the power of each aircraft, and the improved ant colony algorithm; wherein the overall path represents multiple target task points and their corresponding visit order; The improved ant colony algorithm determines, during each iteration, the task groups corresponding to the overall paths in the current iteration based on the power of each aircraft, and the optimal overall path in the current iteration based on the power consumed by each aircraft to complete the task and the total time required to complete multiple target tasks. The determination module includes: A first determining unit is configured to determine a plurality of overall paths according to a single traveling salesman problem based on parameters of an ant colony algorithm and the ant colony algorithm; A second determining unit is configured to determine a plurality of task groups corresponding to each overall path based on the power levels of each aircraft; a task in each task group is performed by one aircraft; a third determining unit, configured to determine an optimal overall path for a current iteration from among the multiple overall paths based on the total power consumed by each aircraft in completing the tasks in the corresponding task group and the total time required to complete the multiple target tasks; an updating unit, configured to update the pheromones on each overall path based on an objective function affecting pheromone updating; wherein the objective function affecting pheromone updating is determined based on the total amount of power consumed by each aircraft in completing tasks in the corresponding task group and the total time required to complete the multiple target tasks; A fourth determining unit is configured to determine, based on the updated pheromone, the optimal overall path and the corresponding task group in the current iteration and the previous iterations when the number of iterations is less than the maximum number of iterations; and output the optimal overall path and the corresponding task group in the current iteration and the previous iterations when the number of iterations is equal to the maximum number of iterations; The objective function that affects pheromone renewal ,in, The total time to complete multiple target tasks is determined based on the maximum time required to complete all corresponding task points on each overall path; Indicates the amount of power consumed by the sth aircraft to complete the task in the corresponding task group. The number of aircraft called to complete all corresponding mission points on each overall path; The pheromone of the kth ant's path between the i-th and j-th target task points determined based on the objective function affecting the pheromone update is: ,in, is the overall path, represents the kth ant, i and j represent the i-th and j-th tasks respectively, and Q is the pheromone intensity.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the path planning method based on aircraft power consumption are implemented as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the path planning method based on aircraft power consumption are implemented as described in any one of claims 1 to 5.

Images