Unmanned aerial vehicle swarm path planning system for complex scene cruising

Abstract

The application belongs to the field of unmanned aerial vehicle group path planning, relates to data analysis technology, is used for solving the problem that the prior art cannot comprehensively analyze all flight parameters, and specifically relates to an unmanned aerial vehicle group path planning system for complex scene cruising, which comprises a path planning platform, an efficiency test module, a coverage analysis module, a planning processing module and a database which are communicatively connected to a path optimization platform; the efficiency test module is used for monitoring and analyzing the cruising efficiency of the unmanned aerial vehicle group in a complex scene; cruising start points and cruising end points are set in the complex scene, all unmanned aerial vehicles of the unmanned aerial vehicle group are controlled to start from the cruising start points and run to the cruising end points for cruising, and then the efficiency sequence of the unmanned aerial vehicle group is obtained; the application can monitor and analyze the cruising efficiency of the unmanned aerial vehicle group in the complex scene, preliminarily screen the cruising process from the perspective of cruising efficiency, and ensure that the navigation efficiency of the finally generated execution path can be higher than the average level.

Description

Technical Field

[0001] This invention belongs to the field of UAV swarm path planning and involves data analysis technology. Specifically, it is a UAV swarm path planning system for cruising in complex scenarios. Background Technology

[0002] Unmanned aerial vehicle (UAV) swarm path planning refers to planning a reasonable flight path for UAVs in three-dimensional space so that they can complete their missions safely and efficiently. Path planning is one of the key technologies for autonomous flight of UAVs, and it can determine the UAV's trajectory through algorithms and models.

[0003] Existing UAV swarm path planning systems can only analyze the shortest path flight plan, but cannot combine all flight parameters for comprehensive analysis. Consequently, they cannot simultaneously optimize the UAV's flight speed, collision probability, and power consumption based on path planning.

[0004] To address the aforementioned technical problems, this application proposes a solution. Summary of the Invention

[0005] The purpose of this invention is to provide a path planning system for unmanned aerial vehicle (UAV) swarms for cruising in complex scenarios, in order to solve the problem that existing technologies cannot combine all flight parameters for comprehensive analysis;

[0006] The technical problem to be solved by this invention is: how to provide a path planning system for drone swarms used for cruising in complex scenarios that can combine all flight parameters for comprehensive analysis.

[0007] The objective of this invention can be achieved through the following technical solutions:

[0008] A path planning system for drone swarms used for cruising in complex scenarios includes a path planning platform, which is communicatively connected to an efficiency testing module, a coverage analysis module, a planning processing module, and a database.

[0009] The efficiency testing module is used to monitor and analyze the cruise efficiency of a drone swarm in complex scenarios: a cruise start point and a cruise end point are set in the complex scenario, all drones in the drone swarm are controlled to start from the cruise start point and run to the cruise end point for cruise, and then the efficiency sequence of the drone swarm is obtained; the efficiency sequence of the drone swarm is sent to the coverage analysis module through the path planning platform.

[0010] The coverage analysis module is used to analyze the coverage of the drone swarm's cruise path and mark the analyzed path;

[0011] The planning and processing module is used to plan and analyze the execution path of the drone swarm and generate the execution path, which is then sent to the mobile terminal of the management personnel through the path planning platform.

[0012] Furthermore, the process of obtaining the efficiency sequence of the drone swarm includes: marking the process from the drone's departure from the cruise starting point to the drone's arrival at the cruise endpoint as the cruise process, obtaining the duration of the cruise process and marking it as the efficiency value of the cruise process, and arranging all the drones' cruise processes in ascending order of efficiency value to obtain the efficiency sequence of the drone swarm.

[0013] Furthermore, the specific process by which the coverage analysis module analyzes the coverage of the drone swarm's cruise path includes: extracting the top Q1 cruise processes from the efficiency sequence as the analysis process, where the value of Q1 is calculated using the formula Q1 = Q2 * t1. e The results show that Q2 is a numerical constant, and the specific value of Q1 is set by the administrator; t1 is a scaling factor, 1.15≤t1≤1.25, e=0; the cruise paths of all analysis processes are obtained and plotted on a map of the complex scene, the complex scene is divided into several cruise areas, and it is determined whether all cruise areas contain at least one cruise path:

[0014] If so, the coverage of the cruise path is determined to meet the requirements, and the analysis process is output.

[0015] If not, the cruise path coverage is deemed insufficient, and a value is assigned to e: e = e + 1. The value of Q1 is recalculated and the analysis process is re-examined in the complete efficiency sequence. This process is repeated until the cruise path coverage meets the requirements. The cruise path in the analysis process is then marked as the analysis path.

[0016] Furthermore, the specific process of the planning and processing module in planning and analyzing the execution path of the UAV swarm includes: marking the obstacle avoidance priority process, power loss priority process, and speed priority process; determining whether the obstacle avoidance priority process, power loss priority process, and speed priority process contain the same analysis process: if they contain the same analysis process, the corresponding analysis process is marked as a candidate process, the sum of the indices of the candidate process in the obstacle avoidance sequence, power loss sequence, and speed sequence is marked as the candidate value of the candidate process, and the analysis path corresponding to the candidate process with the smallest candidate value is marked as the execution path; if they do not contain the same analysis process, the obstacle avoidance priority process, power loss priority process, and speed priority process are randomly combined to obtain several path combinations, each path combination including a randomly selected obstacle avoidance priority process, power loss priority process, and speed priority process; and performing overlap analysis on the path combinations to obtain the execution path.

[0017] Furthermore, the specific process for marking the obstacle avoidance priority process, power loss priority process, and rate priority process includes: marking the number of obstacles avoided in the analysis path of the analysis process as the obstacle avoidance value of the analysis process; arranging the analysis processes in ascending order of obstacle avoidance value to obtain the obstacle avoidance sequence; marking the difference between the power level of the UAV at the start of the analysis process and the power level of the UAV at the end of the analysis process as the power loss value of the analysis process; arranging the analysis processes in ascending order of power loss value to obtain the power loss sequence; arranging the analysis processes in ascending order of efficiency value to obtain the rate sequence; and extracting K1 analysis processes from the obstacle avoidance sequence, power loss sequence, and rate sequence respectively and marking them as the obstacle avoidance priority process, power loss priority process, and rate priority process.

[0018] Furthermore, the specific process of performing overlap analysis on path combinations includes: marking the parts of the analysis paths corresponding to the obstacle avoidance priority process, power loss priority process, and rate priority process in the path combination that overlap in pairs as the overlapping parts of the path combination; summing and averaging the length values ​​of the analysis paths corresponding to the obstacle avoidance priority process, power loss priority process, and rate priority process in the path combination to obtain the standard analysis value; marking the ratio of the sum of the length values ​​of all overlapping parts in the path combination to the standard analysis value as the overlap coefficient of the path combination; obtaining the overlap threshold from the database; and comparing the overlap coefficient with the overlap threshold: if the overlap coefficient is less than the overlap threshold, an independent recommendation method is used to generate the execution path; if the overlap coefficient is greater than or equal to the overlap threshold, a fusion recommendation method is used to generate the execution path.

[0019] Furthermore, the specific process of generating execution paths using the independent recommendation method includes: marking the analysis paths of the analysis processes ranked first in the obstacle avoidance sequence, power loss sequence, and rate sequence as the obstacle avoidance recommendation path, power loss recommendation path, and rate recommendation path, respectively, and the execution path is composed of the obstacle avoidance recommendation path, power loss recommendation path, and rate recommendation path.

[0020] Furthermore, the specific process of generating execution paths using the fusion recommendation method includes: marking the path combination with the largest overlap coefficient value as the fusion combination; arranging all overlapping parts in the fusion combination in order of distance from the cruise starting point from near to far to obtain the overlap sequence; connecting all overlapping parts end to end in the order of the overlap sequence to obtain the fusion path, which includes the overlapping parts and the connecting parts.

[0021] The present invention has the following beneficial effects:

[0022] 1. The efficiency testing module can monitor and analyze the cruise efficiency of drone swarms in complex scenarios, and perform preliminary screening of the cruise process from the perspective of cruise efficiency to ensure that the flight efficiency of the final generated execution path can be higher than the average level.

[0023] 2. The coverage analysis module can analyze the coverage of the drone swarm's cruise path. After extracting the analysis process from the efficiency sequence, the coverage of the process flight path in relatively complex scenarios is analyzed in a regional analysis manner, thereby improving the reliability of the generated analysis path.

[0024] 3. The planning and processing module can be used to plan and analyze the execution path of the UAV swarm. By analyzing multiple parameters of UAV flight, the execution path can be obtained. When the UAV is flying on the execution path, its flight efficiency, collision risk and power shortage risk can be controlled to the optimal state. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0027] Figure 2 This is a flowchart of the method in Embodiment 2 of the present invention. Detailed Implementation

[0028] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Example 1: As Figure 1 As shown, the UAV swarm path planning system for complex scenario cruising includes a path planning platform, a path optimization platform communication connection efficiency testing module, a coverage analysis module, a planning processing module, and a database.

[0030] The efficiency testing module is used to monitor and analyze the cruise efficiency of UAV swarms in complex scenarios. In a complex scenario, a cruise start point and a cruise end point are set. All UAVs in the swarm are controlled to depart from the cruise start point and travel to the cruise end point. The process from the start point to the end point is marked as a cruise process. The duration of the cruise process is obtained and marked as its efficiency value. The cruise processes of all UAVs are arranged in ascending order of efficiency value to obtain the efficiency sequence of the UAV swarm. The efficiency sequence of the UAV swarm is sent to the coverage analysis module through the path planning platform. Monitoring and analyzing the cruise efficiency of UAV swarms in complex scenarios allows for initial screening of the cruise process from the perspective of cruise efficiency, ensuring that the final generated execution path has a higher flight efficiency than the average level.

[0031] The coverage analysis module is used to analyze the coverage of the drone swarm's cruise paths: it extracts the top Q1 cruise processes from the efficiency sequence as the analysis process, and the value of Q1 is given by the formula Q1 = Q2 * t1. e The process is as follows: Q2 is a numerical constant, and the specific value of Q1 is set by the administrator; t1 is a scaling factor, 1.15≤t1≤1.25, e=0; the cruise paths of all analysis processes are obtained and plotted on the map of the complex scene, dividing the complex scene into several cruise areas, and determining whether all cruise areas contain at least one cruise path: if yes, the cruise path coverage meets the requirements, and the analysis process is output; if no, the cruise path coverage does not meet the requirements, and e is assigned a value: e=e+1, the value of Q1 is recalculated, and the analysis process is re-extracted in the complete efficiency sequence, and so on, until the cruise path coverage meets the requirements; the cruise paths of the analysis process are marked as analysis paths, and all analysis processes and corresponding analysis paths are sent to the planning processing module through the path planning platform; after extracting the analysis processes in the efficiency sequence, the process navigation path is analyzed relative to the coverage of the complex scene in a regional analysis manner to improve the reliability of the generated analysis path.

[0032] The planning and processing module is used to plan and analyze the execution paths of the UAV swarm: the number of obstacles avoided in the analysis path is marked as the obstacle avoidance value of the analysis process; the analysis process is arranged in ascending order of obstacle avoidance value to obtain the obstacle avoidance sequence; the difference between the power level of the UAV at the beginning and the end of the analysis process is marked as the power loss value of the analysis process; the analysis process is arranged in ascending order of power loss value to obtain the power loss sequence; and the analysis process is arranged in ascending order of efficiency value to obtain the rate sequence.

[0033] K1 analysis processes are extracted from the obstacle avoidance sequence, power loss sequence, and rate sequence and labeled as obstacle avoidance priority process, power loss priority process, and rate priority process, respectively.

[0034] Determine whether the obstacle avoidance priority process, power loss priority process, and rate priority process contain the same analytical process:

[0035] If included, the corresponding analysis process is marked as a candidate process, indicating that there is an analysis process that simultaneously considers rate, power loss, and obstacle avoidance. The sum of the indices of the candidate process in the obstacle avoidance sequence, power loss sequence, and rate sequence is marked as the candidate value of the candidate process. The candidate value represents the overall priority of the candidate process. The smaller the value of the candidate value, the higher the overall priority of the candidate process. The analysis path corresponding to the candidate process with the smallest candidate value is marked as the execution path.

[0036] If not included, the obstacle avoidance priority process, power loss priority process and rate priority process are randomly combined to obtain several path combinations. Each path combination includes a randomly selected obstacle avoidance priority process, power loss priority process and rate priority process.

[0037] Path combination overlap analysis is performed: The overlapping portions of the analysis paths corresponding to obstacle avoidance priority, power loss priority, and rate priority processes within a path combination are marked as overlapping parts. The lengths of the analysis paths corresponding to these processes are summed and averaged to obtain a standard analysis value. The ratio of the sum of the lengths of all overlapping portions to the standard analysis value is marked as the overlap coefficient of the path combination. An overlap threshold is obtained from a database, and the overlap coefficient is compared with the overlap threshold.

[0038] If the overlap coefficient is less than the overlap threshold, an independent recommendation method is used to generate the execution path: the analysis path of the first-ranked analysis process in the obstacle avoidance sequence, power loss sequence, and rate sequence is marked as the obstacle avoidance recommended path, power loss recommended path, and rate recommended path, respectively. The execution path is composed of the obstacle avoidance recommended path, power loss recommended path, and rate recommended path. This process directly outputs the corresponding recommended path from different angles when the overlap rate of all analysis paths within the path combination is low, so that users with different needs can directly select the best path solution from the corresponding angle; for example, users who pursue efficiency can choose the rate recommended path for drone cruise control.

[0039] If the overlap coefficient is greater than or equal to the overlap threshold, the execution path is generated using a fusion recommendation method: the path combination with the largest overlap coefficient is marked as the fusion combination; all overlapping parts in the fusion combination are arranged in order of distance from the cruise start point to obtain the overlap sequence; all overlapping parts are connected end to end according to the order of the overlap sequence to obtain the fusion path (the start point of the first overlapping part is connected to the cruise start point, and the end point of the last overlapping part is connected to the cruise end point). The fusion path includes overlapping parts and connecting parts (the connecting part is the end-to-end connection of adjacent overlapping parts). The connecting part is randomly selected from the two analysis paths corresponding to the next overlapping part (when the number of identical analysis paths in the analysis paths corresponding to the two overlapping parts is not one, it is directly randomly selected from the identical analysis paths; when the number of identical analysis paths in the analysis paths corresponding to the two overlapping parts is one, it is directly selected as the connecting part).

[0040] Example 2: Figure 2 As shown, the UAV swarm path planning method for cruising in complex scenarios includes the following steps:

[0041] Step 1: Monitor and analyze the cruise efficiency of UAV swarms in complex scenarios and generate an efficiency sequence. Perform preliminary screening of the cruise process from the perspective of cruise efficiency to ensure that the flight efficiency of the final generated execution path can be higher than the average level.

[0042] Step 2: Analyze the coverage of the drone swarm's cruise path and mark the analysis path. Analyze the coverage of the flight path in relatively complex scenarios by using a regional analysis method to improve the reliability of the generated analysis path.

[0043] Step 3: Plan, process, and analyze the execution path of the drone swarm and generate the execution path. Analyze multiple parameters of drone flight to obtain the execution path. When the drones are flying on the execution path, their flight efficiency, collision risk, and power shortage risk can all be controlled to the optimal state.

[0044] This UAV swarm path planning system for complex scenario navigation sets a cruise start point and a cruise end point in the complex scenario. It controls all UAVs in the swarm to start from the cruise start point and run to the cruise end point. Based on the efficiency of the cruise process, it generates an efficiency sequence of the UAV swarm. From the efficiency sequence, it extracts the analysis process and generates obstacle avoidance sequence, power loss sequence, and speed sequence. It then performs comprehensive analysis and processing of the obstacle avoidance sequence, power loss sequence, and speed sequence to generate the execution path. By analyzing multiple parameters of UAV flight, the execution path is obtained. When UAVs fly along the execution path, their flight efficiency, collision risk, and power loss risk can all be controlled to the optimal state.

[0045] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.

[0046] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0047] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A path planning system for unmanned aerial vehicle (UAV) swarms used for cruising in complex scenarios, characterized in that, It includes a route planning platform, which is communicatively connected to an efficiency testing module, a coverage analysis module, a planning processing module, and a database; The efficiency testing module is used to monitor and analyze the cruise efficiency of a drone swarm in complex scenarios: a cruise start point and a cruise end point are set in the complex scenario, all drones in the drone swarm are controlled to start from the cruise start point and run to the cruise end point for cruise, and then the efficiency sequence of the drone swarm is obtained; the efficiency sequence of the drone swarm is sent to the coverage analysis module through the path planning platform. The coverage analysis module is used to analyze the coverage of the drone swarm's cruise path and mark the analyzed path; The planning and processing module is used to plan and analyze the execution path of the drone swarm and generate the execution path, and then send the execution path to the mobile terminal of the management personnel through the path planning platform. The process of obtaining the efficiency sequence of the drone swarm includes: marking the process from the drone's departure from the cruise start point to the drone's arrival at the cruise end point as the cruise process, obtaining the duration of the cruise process and marking it as the efficiency value of the cruise process, and arranging the cruise processes of all drones in ascending order of efficiency value to obtain the efficiency sequence of the drone swarm. The coverage analysis module analyzes the coverage of the drone swarm's cruise paths. The specific process includes: extracting the top Q1 cruise cycles from the efficiency sequence as the analysis steps. The value of Q1 is calculated using the formula Q1 = Q2 * t1. e The results show that Q2 is a numerical constant, and the specific value of Q1 is set by the administrator; t1 is a scaling factor, 1.15≤t1≤1.25, e=0; the cruise paths of all analysis processes are obtained and plotted on a map of the complex scene, the complex scene is divided into several cruise areas, and it is determined whether all cruise areas contain at least one cruise path: If so, the coverage of the cruise route is determined to meet the requirements, and the analysis process is output. If not, the cruise path coverage is deemed insufficient, and a value is assigned to e: e = e + 1. The value of Q1 is recalculated and the analysis process is re-examined in the complete efficiency sequence. This process is repeated until the cruise path coverage meets the requirements. The cruise path in the analysis process is then marked as the analysis path. The specific process of the planning and processing module in planning and analyzing the execution paths of the UAV swarm includes: marking the obstacle avoidance priority process, power loss priority process, and speed priority process; determining whether the obstacle avoidance priority process, power loss priority process, and speed priority process contain the same analysis process: if they do, the corresponding analysis process is marked as a candidate process, the sum of the indices of the candidate process in the obstacle avoidance sequence, power loss sequence, and speed sequence is marked as the candidate value of the candidate process, and the analysis path corresponding to the candidate process with the smallest candidate value is marked as the execution path; if they do not contain the same analysis process, the obstacle avoidance priority process, power loss priority process, and speed priority process are randomly combined to obtain several path combinations, each path combination including one randomly selected obstacle avoidance priority process, power loss priority process, and speed priority process; and performing overlap analysis on the path combinations to obtain the execution path. The specific process for marking the obstacle avoidance priority process, power loss priority process, and rate priority process includes: marking the number of obstacles avoided in the analysis path of the analysis process as the obstacle avoidance value of the analysis process; arranging the analysis processes in ascending order of obstacle avoidance value to obtain the obstacle avoidance sequence; marking the difference between the power level of the UAV at the start of the analysis process and the power level of the UAV at the end of the analysis process as the power loss value of the analysis process; arranging the analysis processes in ascending order of power loss value to obtain the power loss sequence; arranging the analysis processes in ascending order of efficiency value to obtain the rate sequence; and extracting K1 analysis processes from the obstacle avoidance sequence, power loss sequence, and rate sequence respectively and marking them as the obstacle avoidance priority process, power loss priority process, and rate priority process.

2. The UAV swarm path planning system for complex scene cruising according to claim 1, characterized in that, The specific process of performing overlap analysis on path combinations includes: marking the parts of the analysis paths corresponding to the obstacle avoidance priority process, power loss priority process, and rate priority process in the path combination that overlap in pairs as the overlapping parts of the path combination; summing and averaging the length values ​​of the analysis paths corresponding to the obstacle avoidance priority process, power loss priority process, and rate priority process in the path combination to obtain the standard analysis value; marking the ratio of the sum of the length values ​​of all overlapping parts in the path combination to the standard analysis value as the overlap coefficient of the path combination; obtaining the overlap threshold from the database; and comparing the overlap coefficient with the overlap threshold: if the overlap coefficient is less than the overlap threshold, an independent recommendation method is used to generate the execution path; if the overlap coefficient is greater than or equal to the overlap threshold, a fusion recommendation method is used to generate the execution path.

3. The UAV swarm path planning system for complex scene cruising according to claim 2, characterized in that, The specific process of generating execution paths using the independent recommendation method includes: marking the analysis paths of the analysis processes ranked first in the obstacle avoidance sequence, power loss sequence, and rate sequence as the obstacle avoidance recommendation path, power loss recommendation path, and rate recommendation path, respectively, and the execution path is composed of the obstacle avoidance recommendation path, power loss recommendation path, and rate recommendation path.

4. The UAV swarm path planning system for complex scene cruising according to claim 3, characterized in that, The specific process of generating execution paths using the fusion recommendation method includes: marking the path combination with the largest overlap coefficient value as the fusion combination; arranging all overlapping parts in the fusion combination in order of distance from the cruise starting point from near to far to obtain the overlap sequence; connecting all overlapping parts end to end in the order of the overlap sequence to obtain the fusion path, which includes the overlapping parts and the connecting parts.

Images