Multi-unmanned aerial vehicle water lifesaving material cooperative delivery path planning method and system

Abstract

The invention relates to a multi-unmanned aerial vehicle water lifesaving material cooperative delivery path planning method and system. The method comprises the following steps: acquiring lifesaving target data of a lifesaving task; acquiring lifesaving unmanned aerial vehicle state data of each lifesaving unmanned aerial vehicle, wherein the lifesaving unmanned aerial vehicle state data comprises unmanned aerial vehicle flight state data, unmanned aerial vehicle position state data and lifesaving material strength data; generating first unmanned aerial vehicle lifesaving task allocation information according to the lifesaving target data and the lifesaving unmanned aerial vehicle state data, wherein the first unmanned aerial vehicle lifesaving task allocation information is used for representing the lifesaving unmanned aerial vehicle state data of the lifesaving unmanned aerial vehicle participating in the lifesaving task; based on the first unmanned aerial vehicle lifesaving task allocation information and the lifesaving target data, path planning is carried out on the lifesaving unmanned aerial vehicle participating in the lifesaving task, and first path planning result information is generated. By adopting the method, lifesaving scene information can be comprehensively mastered, lifesaving unmanned aerial vehicle resources are reasonably allocated, and unmanned aerial vehicle path planning information is accurately and efficiently generated.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of unmanned aerial vehicle path planning control, and particularly relates to a multi-unmanned aerial vehicle water lifesaving resource cooperative delivery path planning method and system. BACKGROUND

[0002] With the continuous development of water lifesaving unmanned aerial vehicle technology, multi-unmanned aerial vehicle water lifesaving cooperative technology appears, which can integrate the operation capabilities of each single machine through information interaction and task cooperation between multiple unmanned aerial vehicles, realize wider water lifesaving operation area coverage and higher water lifesaving task execution efficiency, and promote the transformation of water lifesaving from the traditional single machine operation and manpower dominant mode to the cluster cooperative mode.

[0003] However, the existing multi-unmanned aerial vehicle water lifesaving cooperative technology still faces the bottleneck of poor environmental adaptability and real-time cooperative control difficulty when dealing with complex water environments, and is difficult to meet the needs of large-scale complex water lifesaving tasks. SUMMARY

[0004] Therefore, it is necessary to provide a multi-unmanned aerial vehicle water lifesaving resource cooperative delivery path planning method and system which can comprehensively grasp lifesaving scene information, reasonably allocate lifesaving unmanned aerial vehicle resources, and accurately and efficiently generate unmanned aerial vehicle path planning information.

[0005] In a first aspect, the application provides a multi-unmanned aerial vehicle water lifesaving resource cooperative delivery path planning method, comprising:

[0006] obtaining lifesaving target data of a lifesaving task;

[0007] obtaining lifesaving unmanned aerial vehicle state data of each lifesaving unmanned aerial vehicle, the lifesaving unmanned aerial vehicle state data comprising unmanned aerial vehicle flight state data, unmanned aerial vehicle position state data and lifesaving resource intensity data;

[0008] generating first unmanned aerial vehicle lifesaving task deployment information according to the lifesaving target data and the lifesaving unmanned aerial vehicle state data, the first unmanned aerial vehicle lifesaving task deployment information being used to represent lifesaving unmanned aerial vehicle state data of lifesaving unmanned aerial vehicles participating in the lifesaving task;

[0009] performing path planning on the lifesaving unmanned aerial vehicles participating in the lifesaving task based on the first unmanned aerial vehicle lifesaving task deployment information and the lifesaving target data to generate first path planning result information; wherein the lifesaving unmanned aerial vehicles participating in the lifesaving task are one or more.

[0010] In one of the embodiments, the lifesaving target data comprises lifesaving target position data and lifesaving target intensity data, and the lifesaving target data of the lifesaving task is obtained by:

[0011] obtaining static basic environment monitoring data;

[0012] The static basic environment monitoring data is input into the environment perception model to extract the lifesaving target position data and lifesaving target intensity data.

[0013] In one of the embodiments, the lifesaving target intensity data includes lifesaving target personnel quantity data, lifesaving target personnel state information, lifesaving target personnel life support demand data, and lifesaving environment parameters, the lifesaving environment parameters include water flow speed parameters and water wave height parameters, the static basic environment monitoring data includes static basic environment monitoring images, the static basic environment monitoring data is input into the environment perception model to extract the lifesaving target position data and lifesaving target intensity data, which includes:

[0014] The static basic environment monitoring images are input into a lifesaving target personnel recognition unit in the environment perception model to generate lifesaving target personnel recognition result information and lifesaving target personnel segmentation images corresponding to the lifesaving target personnel recognition result information, the lifesaving target personnel recognition result information including lifesaving target personnel quantity data;

[0015] Based on the lifesaving target personnel recognition result information, the lifesaving target personnel segmentation images are input into a lifesaving target personnel state recognition unit in the environment perception model to obtain lifesaving target personnel state information;

[0016] Based on the lifesaving target personnel recognition result information, the lifesaving target personnel segmentation images are input into a lifesaving target personnel life support demand recognition unit in the environment perception model to obtain lifesaving target personnel life support demand data;

[0017] The static basic environment monitoring images are input into a water flow speed recognition unit in the environment perception model to obtain water flow speed parameters;

[0018] The static basic environment monitoring images are input into a water wave height recognition unit in the environment perception model to obtain water wave height parameters.

[0019] In one of the embodiments, the first lifesaving task deployment information of the lifesaving unmanned aerial vehicle is generated according to the lifesaving target data and lifesaving unmanned aerial vehicle state data, which includes:

[0020] Based on the lifesaving target personnel state information, a task deployment target function weight parameter in the unmanned aerial vehicle lifesaving task deployment target function is configured;

[0021] Based on the task deployment target function weight parameter, the lifesaving target data, and the lifesaving unmanned aerial vehicle state data, a task deployment target function value of the unmanned aerial vehicle lifesaving task deployment target function is calculated;

[0022] Based on the task deployment target function value, a task deployment is performed in combination with a task deployment intelligent optimization algorithm to generate the first lifesaving task deployment information of the unmanned aerial vehicle.

[0023] In one embodiment, the weight parameters of the mission allocation objective function include a maximum rescue time weight parameter, an average rescue time weight parameter, and a rescue supplies weight parameter. The mathematical expression of the UAV rescue mission allocation objective function is as follows:

[0024]

[0025] In the formula, To configure the objective function for drone rescue missions, , and These are the maximum rescue time weight parameter, the average rescue time weight parameter, and the rescue supplies weight parameter, respectively. The total number of rescue drones allocated, For the first Data on the intensity of rescue supplies from rescue drones. For the number of people targeted for rescue, For the first Data on the life-saving material needs of each life-saving target personnel. For the first Flight status data of the rescue drone, the first The first rescue drone was calculated using its position data, the rescue target's position data, and the water flow velocity parameters. Rescue time parameters for a rescue drone. It is a function for maximizing the value.

[0026] In one embodiment, the rescue drone includes a supply delivery drone and a rescue target enhancement and monitoring drone. The multi-drone water rescue supply collaborative delivery path planning method also includes:

[0027] Dynamically enhanced rescue target data is acquired using drones that enhance rescue target monitoring.

[0028] Calculate the drone rescue mission allocation objective function corresponding to the dynamically enhanced rescue target data;

[0029] If the objective function of the UAV rescue mission allocation is lower than the preset rescue capability adaptation threshold, the rescue UAV status data is updated. Based on the dynamically enhanced rescue objective data and the updated rescue UAV status data, a second UAV rescue mission allocation information is generated, and the first UAV rescue mission allocation information is updated based on the second UAV rescue mission allocation information. The second UAV rescue mission allocation information is used to characterize the rescue UAV status data of the rescue UAVs participating in the rescue mission based on the dynamically enhanced rescue objective data.

[0030] Based on the second unmanned aerial vehicle lifesaving task deployment information and the dynamic enhanced lifesaving target data, the lifesaving unmanned aerial vehicles participating in the lifesaving task are path planned, a second path planning result information is generated, and the first path planning result information is updated based on the second path planning result information.

[0031] In one of the embodiments, the lifesaving unmanned aerial vehicles participating in the lifesaving task are multiple, the lifesaving unmanned aerial vehicles participating in the lifesaving task are path planned based on the first unmanned aerial vehicle lifesaving task deployment information and the lifesaving target data, a first path planning result information is generated, including:

[0032] The lifesaving unmanned aerial vehicles corresponding to the lifesaving task in the first unmanned aerial vehicle lifesaving task deployment information are respectively path planned based on the lifesaving target position data, the water flow speed parameter, the unmanned aerial vehicle flight state data of each lifesaving unmanned aerial vehicle and the unmanned aerial vehicle position state data of each lifesaving unmanned aerial vehicle, the lifesaving unmanned aerial vehicles corresponding to the lifesaving task in the first unmanned aerial vehicle lifesaving task deployment information are combined with a path planning algorithm, the unmanned aerial vehicle preliminary path planning information of each lifesaving unmanned aerial vehicle is generated;

[0033] After the unmanned aerial vehicle preliminary path planning information of each lifesaving unmanned aerial vehicle is subjected to multi-unmanned aerial vehicle path conflict processing, the first path planning result information is obtained by summarizing.

[0034] In a second aspect, the application further provides a multi-unmanned aerial vehicle water lifesaving equipment collaborative delivery path planning system, including:

[0035] A water lifesaving environment monitoring module is configured to obtain lifesaving target data of a lifesaving task;

[0036] A lifesaving equipment state monitoring module is configured to obtain lifesaving unmanned aerial vehicle state data of each lifesaving unmanned aerial vehicle, the lifesaving unmanned aerial vehicle state data including unmanned aerial vehicle flight state data, unmanned aerial vehicle position state data and lifesaving equipment intensity data;

[0037] A lifesaving equipment deployment module is configured to generate first unmanned aerial vehicle lifesaving task deployment information according to the lifesaving target data and the lifesaving unmanned aerial vehicle state data, the first unmanned aerial vehicle lifesaving task deployment information being used to represent lifesaving unmanned aerial vehicle state data of lifesaving unmanned aerial vehicles participating in the lifesaving task;

[0038] A lifesaving equipment path planning module is configured to path plan lifesaving unmanned aerial vehicles participating in a lifesaving task based on first unmanned aerial vehicle lifesaving task deployment information and lifesaving target data, and generate first path planning result information; wherein the lifesaving unmanned aerial vehicles participating in the lifesaving task are one or more.

[0039] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method as described in any of the first aspects of this application.

[0040] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the first aspects of this application.

[0041] The aforementioned method and system for collaborative delivery of multi-UAV water rescue supplies integrates rescue target data and rescue UAV status data to comprehensively and accurately identify rescue mission requirements and rescue resource capabilities, thereby significantly improving the utilization efficiency of rescue resources and ensuring the efficient initiation of rescue operations. Through intelligent evaluation based on real-time status data, it can dynamically identify the optimal combination of rescue UAVs, enabling the rational allocation of rescue UAV resources. By fusing allocation information and rescue target data for path planning, it can improve the efficiency of collaborative delivery path planning for multi-UAV water rescue supplies, ensuring the efficiency and success rate of multi-UAV collaborative water rescue supplies delivery, and achieving accurate and efficient collaborative delivery path planning for multi-UAV water rescue supplies. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 A flowchart illustrating a multi-UAV collaborative delivery path planning method for water rescue supplies, provided as an embodiment of this application;

[0044] Figure 2 This is a schematic diagram of a multi-UAV collaborative delivery path planning system for water rescue supplies, provided as an embodiment of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0046] In one exemplary embodiment of this application, such as Figure 1As shown, a method for collaborative delivery path planning of multi-UAV water rescue supplies is provided. This embodiment illustrates the application of this method to a multi-UAV rescue path planning terminal. It is understood that this method can also be applied to a multi-UAV rescue path planning server, and further to a multi-UAV rescue path planning system including both a multi-UAV rescue path planning terminal and a multi-UAV rescue path planning server, and is implemented through the interaction between the multi-UAV rescue path planning terminal and the multi-UAV rescue path planning server. In this embodiment, the method includes the following steps:

[0047] Step S101: Obtain the rescue target data for the rescue mission.

[0048] Specifically, the multi-UAV rescue path planning terminal can acquire rescue target data for rescue missions. This rescue target data can include rescue target location data and rescue target intensity data.

[0049] Optionally, the rescue target intensity data may include, but is not limited to, data on the number of rescue target personnel, their status information, their rescue material needs, and rescue environment parameters. These rescue environment parameters may include water flow velocity parameters and wave height parameters.

[0050] Step S102: Obtain the status data of each rescue drone.

[0051] Optionally, the rescue drone status data includes drone flight status data, drone location status data, and rescue material intensity data.

[0052] Step S103: Generate the first UAV rescue mission allocation information based on the rescue target data and the rescue UAV status data.

[0053] Specifically, the multi-drone rescue path planning terminal can generate the first drone rescue mission allocation information based on rescue target data and rescue drone status data, combined with intelligent optimization algorithms.

[0054] Optionally, the intelligent optimization algorithm used to generate the first UAV rescue mission allocation information based on the rescue target data and the rescue UAV status data may include, but is not limited to, one or more of the following: particle swarm optimization algorithm, genetic algorithm, simulated annealing algorithm, Hungarian algorithm, and reinforcement learning algorithm.

[0055] Optionally, the first drone rescue mission deployment information can be used to characterize the status data of the rescue drones participating in the rescue mission.

[0056] Step S104: Based on the first UAV rescue mission allocation information and rescue target data, perform path planning for the rescue UAVs participating in the rescue mission and generate the first path planning result information.

[0057] Specifically, the multi-drone rescue path planning terminal can perform path planning for the rescue drones participating in the rescue mission based on the first drone rescue mission allocation information and rescue target data, combined with path planning algorithms, and generate the first path planning result information.

[0058] Optionally, the path planning algorithm may include, but is not limited to, graph search-based path planning algorithms, model predictive control (MPC) algorithms and their improved versions, multi-agent path planning (MAPF) algorithms and their improved versions, and reinforcement learning (RL) path planning algorithms and their improved versions. Graph search-based path planning algorithms may include, but are not limited to, A's algorithm and its improved versions, and Dijkstra's algorithm and its improved versions.

[0059] Optionally, one or more rescue drones may be used in the rescue mission.

[0060] Optionally, when multiple rescue drones participate in the rescue mission, the multi-drone rescue path planning terminal can perform collaborative path planning for multiple rescue drones to obtain the first path planning result information; alternatively, the multi-drone rescue path planning terminal can perform path planning for each individual rescue drone separately, and then perform multi-drone path collaborative optimization to obtain the first path planning result information. No limitation is imposed here.

[0061] In the aforementioned multi-UAV collaborative delivery path planning method for water rescue supplies, by acquiring rescue target data and status data of each rescue UAV, a comprehensive understanding of the core needs of the rescue mission and the current status of UAV resources can be achieved, improving the rationality and accuracy of multi-UAV collaborative delivery path planning for water rescue supplies. By generating first UAV rescue mission allocation information based on rescue target data and rescue UAV status data, the rescue UAVs participating in the rescue mission can be accurately and efficiently matched, ensuring a high degree of compatibility between the rescue UAVs and the rescue target requirements. This optimizes UAV resource allocation, reduces waste of rescue resources, and improves rescue efficiency. By planning the paths of UAVs participating in the rescue mission based on the first UAV rescue mission allocation information and rescue target data, the flight status, position status, and rescue supply intensity of each rescue UAV can be combined to ensure that rescue supplies can be accurately and quickly delivered to the target location, achieving accurate and efficient multi-UAV collaborative delivery path planning for water rescue supplies and improving the success rate of water rescue.

[0062] In an optional embodiment of this application, the rescue target data may include rescue target location data and rescue target intensity data. Obtaining the rescue target data for a rescue mission may include:

[0063] Specifically, multi-drone rescue path planning terminals can acquire static basic environmental monitoring data.

[0064] Specifically, the multi-drone rescue path planning terminal can input static basic environmental monitoring data into the environmental perception model to extract rescue target location data and rescue target intensity data.

[0065] Optionally, the environmental perception model can be mounted on a multi-UAV rescue path planning terminal, a multi-UAV rescue path planning server, or a multi-UAV rescue path planning system that includes both a multi-UAV rescue path planning terminal and a multi-UAV rescue path planning server. It can be implemented through the interaction between the multi-UAV rescue path planning terminal and the multi-UAV rescue path planning server. No limitation is made here.

[0066] In an optional embodiment of this application, the rescue target intensity data may include rescue target personnel quantity data, rescue target personnel status information, rescue target personnel rescue material needs data, and rescue environment parameters. The rescue environment parameters may include water flow velocity parameters and wave height parameters. Static basic environmental monitoring data may include static basic environmental monitoring images. Inputting the static basic environmental monitoring data into an environmental perception model to extract rescue target location data and rescue target intensity data may include:

[0067] Specifically, the multi-UAV rescue path planning terminal can input static basic environmental monitoring images into the rescue target personnel identification unit in the environmental perception model to generate rescue target personnel identification result information and rescue target personnel segmentation images corresponding to the rescue target personnel identification result information. The rescue target personnel identification result information includes the number of rescue target personnel data.

[0068] Specifically, the multi-UAV rescue path planning terminal can input the segmented image of the rescue target person into the rescue target person status recognition unit in the environmental perception model based on the rescue target person identification result information to obtain the rescue target person status information.

[0069] Specifically, the multi-drone rescue path planning terminal can input the segmented image of the rescue target person into the rescue target person's rescue material demand identification unit in the environmental perception model based on the rescue target person identification result information to obtain the rescue target person's rescue material demand data.

[0070] Specifically, the multi-UAV rescue path planning terminal can input static basic environmental monitoring images into the water flow velocity recognition unit in the environmental perception model to obtain water flow velocity parameters.

[0071] Specifically, the multi-drone rescue path planning terminal can input static basic environmental monitoring images into the wave height recognition unit in the environmental perception model to obtain wave height parameters.

[0072] In an optional embodiment of this application, generating first UAV rescue mission deployment information based on rescue target data and rescue UAV status data may include:

[0073] Specifically, the multi-drone rescue path planning terminal can configure the task allocation objective function weight parameters in the drone rescue task allocation objective function based on the status information of the rescue target personnel.

[0074] Specifically, the multi-drone rescue path planning terminal can calculate the task allocation objective function value of the drone rescue task allocation objective function based on the task allocation objective function weight parameters, rescue target data, and rescue drone status data.

[0075] Specifically, the multi-drone rescue path planning terminal can perform task allocation based on the objective function value of task allocation and combined with the intelligent optimization algorithm of task allocation, and generate the first drone rescue task allocation information.

[0076] In an optional embodiment of this application, the weight parameters of the mission allocation objective function may include a maximum rescue time weight parameter, an average rescue time weight parameter, and a rescue supplies weight parameter. The mathematical expression of the UAV rescue mission allocation objective function can be:

[0077]

[0078] In the formula, To configure the objective function for drone rescue missions, , and These are the maximum rescue time weight parameter, the average rescue time weight parameter, and the rescue supplies weight parameter, respectively. The total number of rescue drones allocated, For the first Data on the intensity of rescue supplies from rescue drones. For the number of people targeted for rescue, For the first Data on the life-saving material needs of each life-saving target personnel. For the first Flight status data of the rescue drone, the first The first rescue drone was calculated using its position data, the rescue target's position data, and the water flow velocity parameters. Rescue time parameters for a rescue drone. It is a function for maximizing the value.

[0079] This is illustrative; the status information of the rescue target may include, but is not limited to, normal status, emergency status, and severe emergency status. The more urgent the status of the rescue target, the higher the weighting parameter of the average rescue time. and maximum lifesaving time weighting parameters Compared to the weight parameters of life-saving materials The larger the value, the greater the weighting parameter for maximum lifesaving time. Weighted parameters of average rescue time The larger the ratio, the faster the delivery of life-saving supplies can begin.

[0080] In an optional embodiment of this application, the rescue drone may include a material delivery drone and a rescue target enhancement and monitoring drone. The multi-drone water rescue material collaborative delivery path planning method may further include:

[0081] Specifically, the multi-drone rescue path planning terminal can acquire dynamically enhanced rescue target data based on the rescue target enhancement monitoring drone.

[0082] Specifically, the multi-drone rescue path planning terminal can calculate the drone rescue mission allocation objective function corresponding to the dynamic enhanced rescue target data, based on the first drone rescue mission allocation information.

[0083] Specifically, if the objective function of the UAV rescue mission allocation is lower than the preset rescue capability adaptation threshold, the multi-UAV rescue path planning terminal can update the rescue UAV status data, generate second UAV rescue mission allocation information based on the dynamically enhanced rescue objective data and the updated rescue UAV status data, and update the first UAV rescue mission allocation information based on the second UAV rescue mission allocation information. The second UAV rescue mission allocation information is used to characterize the rescue UAV status data of the rescue UAVs participating in the rescue mission based on the dynamically enhanced rescue objective data.

[0084] Specifically, the multi-drone rescue path planning terminal can perform path planning for rescue drones participating in the rescue mission based on the second drone rescue mission allocation information and dynamically enhanced rescue target data, generate second path planning result information, and update the first path planning result information based on the second path planning result information.

[0085] In an optional embodiment of this application, multiple rescue drones may participate in the rescue mission. Based on the first drone rescue mission deployment information and rescue target data, path planning is performed on the rescue drones participating in the rescue mission to generate first path planning result information, which may include:

[0086] Specifically, the multi-drone rescue path planning terminal can perform path planning for each rescue drone corresponding to the rescue mission in the first drone rescue mission allocation information, based on rescue target location data, water flow velocity parameters, drone flight status data, and drone position status data, and combine path planning algorithms to generate preliminary drone path planning information for each rescue drone.

[0087] Specifically, the multi-drone rescue path planning terminal can process the initial path planning information of each rescue drone, handle multi-drone path conflicts, and then summarize the information to obtain the first path planning result.

[0088] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0089] Based on the same inventive concept, this application also provides a multi-UAV (unmanned aerial vehicle) collaborative delivery path planning system for implementing the aforementioned multi-UAV collaborative delivery path planning method for water rescue supplies. The solution provided by this system is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more embodiments of the multi-UAV collaborative delivery path planning system for water rescue supplies provided below can be found in the limitations of the multi-UAV collaborative delivery path planning method for water rescue supplies described above, and will not be repeated here.

[0090] In one exemplary embodiment, such as Figure 2 As shown, a multi-UAV collaborative delivery path planning system 200 for water rescue supplies is provided, including:

[0091] The water rescue environment monitoring module 201 can be used to acquire rescue target data for rescue missions.

[0092] The rescue equipment status monitoring module 202 can be used to acquire the status data of each rescue drone, including drone flight status data, drone position status data, and rescue material intensity data.

[0093] The water rescue equipment allocation module 203 can be used to generate first UAV rescue mission allocation information based on rescue target data and rescue UAV status data. The first UAV rescue mission allocation information is used to characterize the rescue UAV status data of the rescue UAVs participating in the rescue mission.

[0094] The rescue equipment path planning module 204 can be used to plan the paths of rescue drones participating in the rescue mission based on the first drone rescue mission deployment information and rescue target data, and generate first path planning result information. The rescue drones participating in the rescue mission can be one or more.

[0095] In an optional embodiment of this application, the aquatic lifesaving environment monitoring module 201 can also be used for:

[0096] Obtain static basic environmental monitoring data.

[0097] Static basic environmental monitoring data is input into the environmental perception model to extract the location data and intensity data of the rescue targets.

[0098] In an optional embodiment of this application, the aquatic lifesaving environment monitoring module 201 can also be used for:

[0099] The static basic environmental monitoring image is input into the rescue target personnel identification unit in the environmental perception model to generate rescue target personnel identification result information and rescue target personnel segmentation image corresponding to the rescue target personnel identification result information. The rescue target personnel identification result information includes the number of rescue target personnel.

[0100] Based on the identification results of the rescue target personnel, the segmented image of the rescue target personnel is input into the rescue target personnel status identification unit in the environmental perception model to obtain the status information of the rescue target personnel.

[0101] Based on the identification results of the rescue target personnel, the segmented images of the rescue target personnel are input into the rescue target personnel's rescue material needs identification unit in the environmental perception model to obtain the rescue target personnel's rescue material needs data.

[0102] The static basic environmental monitoring image is input into the water flow velocity recognition unit in the environmental perception model to obtain the water flow velocity parameters.

[0103] The static basic environmental monitoring image is input into the wave height recognition unit in the environmental perception model to obtain the wave height parameter.

[0104] In an optional embodiment of this application, the water rescue equipment allocation module 203 can also be used for:

[0105] The weight parameters of the mission allocation objective function in the UAV rescue mission allocation objective function are configured based on the status information of the rescued personnel.

[0106] The objective function value of the drone rescue mission is calculated based on the weight parameters of the objective function, the rescue target data, and the state data of the rescue drone.

[0107] Based on the objective function value of task allocation and combined with the intelligent optimization algorithm for task allocation, task allocation is carried out to generate the first UAV rescue mission allocation information.

[0108] In an optional embodiment of this application, the multi-UAV water rescue supplies collaborative delivery path planning system 200 can also be used for:

[0109] Dynamically enhanced life-saving target data is acquired using drones that enhance life-saving target monitoring.

[0110] The objective function for the deployment of the first UAV rescue mission is calculated, which corresponds to the dynamically enhanced rescue target data.

[0111] If the objective function for the UAV rescue mission allocation is lower than the preset rescue capability adaptation threshold, the rescue UAV status data is updated. Based on the dynamically enhanced rescue objective data and the updated rescue UAV status data, a second UAV rescue mission allocation information is generated. The first UAV rescue mission allocation information is then updated based on the second UAV rescue mission allocation information. The second UAV rescue mission allocation information is used to characterize the rescue UAV status data of the rescue UAVs participating in the rescue mission based on the dynamically enhanced rescue objective data.

[0112] Based on the second UAV rescue mission allocation information and dynamically enhanced rescue target data, path planning is performed on the rescue UAVs participating in the rescue mission, generating second path planning result information, and the first path planning result information is updated based on the second path planning result information.

[0113] In an optional embodiment of this application, the lifesaving equipment path planning module 204 can also be used for:

[0114] For each rescue drone corresponding to the rescue mission in the first drone rescue mission allocation information, based on the rescue target location data, water flow velocity parameters, drone flight status data, and drone position status data, path planning is performed using a path planning algorithm to generate preliminary drone path planning information for each rescue drone.

[0115] After processing multi-drone path conflict, the initial path planning information of each rescue drone is summarized to obtain the first path planning result information.

[0116] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the multi-UAV collaborative delivery path planning method for water rescue supplies as described above.

[0117] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0118] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0119] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A method for collaborative delivery path planning of multi-UAV water rescue supplies, characterized in that, The method includes: Obtain rescue target data for the rescue mission; Acquire the status data of each rescue drone, including drone flight status data, drone position status data, and rescue material intensity data; First UAV rescue mission allocation information is generated based on the rescue target data and the rescue UAV status data. The first UAV rescue mission allocation information is used to characterize the rescue UAV status data of the rescue UAV participating in the rescue mission. Based on the first UAV rescue mission allocation information and the rescue target data, path planning is performed on the rescue UAVs participating in the rescue mission to generate first path planning result information; wherein, the rescue UAVs participating in the rescue mission are one or more.

2. The method according to claim 1, characterized in that, The rescue target data includes rescue target location data and rescue target intensity data. The acquisition of rescue target data for a rescue mission includes: Obtain static basic environmental monitoring data; The static basic environmental monitoring data is input into the environmental perception model to extract the location data and intensity data of the rescue target.

3. The method according to claim 2, characterized in that, The rescue target intensity data includes data on the number of rescue personnel, their status, their life-saving supplies needs, and rescue environment parameters. These parameters include water flow velocity and wave height. The static basic environmental monitoring data includes static basic environmental monitoring images. The step of inputting the static basic environmental monitoring data into the environmental perception model to extract the rescue target location data and rescue target intensity data includes: The static basic environmental monitoring image is input into the rescue target personnel identification unit in the environmental perception model to generate rescue target personnel identification result information and rescue target personnel segmentation image corresponding to the rescue target personnel identification result information. The rescue target personnel identification result information includes the number of rescue target personnel. Based on the identification results of the rescue target personnel, the segmented image of the rescue target personnel is input into the rescue target personnel status identification unit in the environmental perception model to obtain the status information of the rescue target personnel; Based on the identification results of the rescue target personnel, the segmented image of the rescue target personnel is input into the rescue target personnel's rescue material needs identification unit in the environmental perception model to obtain the rescue target personnel's rescue material needs data; The static basic environmental monitoring image is input into the water flow velocity recognition unit in the environmental perception model to obtain the water flow velocity parameter; The static basic environmental monitoring image is input into the wave height recognition unit in the environmental perception model to obtain the wave height parameter.

4. The method according to claim 3, characterized in that... The step of generating first drone rescue mission allocation information based on the rescue target data and the rescue drone status data includes: Configure the weight parameters of the task allocation objective function in the UAV rescue task allocation objective function based on the status information of the rescued personnel; The task allocation objective function value of the UAV rescue mission allocation objective function is calculated based on the weight parameters of the task allocation objective function, the rescue objective data, and the state data of the rescue UAV. Based on the objective function value of the task allocation, and combined with the intelligent optimization algorithm for task allocation, task allocation is performed to generate the allocation information for the first UAV rescue mission.

5. The method according to claim 4, characterized in that, The weight parameters of the mission allocation objective function include the maximum rescue time weight parameter, the average rescue time weight parameter, and the rescue supplies weight parameter. The mathematical expression of the UAV rescue mission allocation objective function is as follows: In the formula, Assign an objective function to the aforementioned drone rescue mission. , and These are the maximum rescue time weight parameter, the average rescue time weight parameter, and the rescue supplies weight parameter, respectively. For the total number of the allocated rescue drones, For the first The rescue material strength data of the aforementioned rescue drone. The data pertains to the number of people targeted for rescue. For the first The data on the life-saving material needs of each life-saving target person. For the first The flight status data of the rescue drone, the first The first value obtained by calculating the drone's position status data, the rescue target's position data, and the water flow velocity parameters of the rescue drone is as follows: The rescue time parameters of the aforementioned rescue drone, It is a function for maximizing the value.

6. The method according to any one of claims 4 to 5, characterized in that, The rescue drone includes a supply delivery drone and a rescue target enhancement and monitoring drone, and the method further includes: Based on the aforementioned life-saving target enhancement monitoring drone, dynamic enhanced life-saving target data is acquired; Calculate the drone rescue mission allocation objective function corresponding to the dynamically enhanced rescue target data for the first drone rescue mission allocation information; If the objective function for the UAV rescue mission allocation is lower than a preset rescue capability adaptation threshold, the status data of the rescue UAV is updated. Second UAV rescue mission allocation information is generated based on the dynamically enhanced rescue objective data and the updated status data of the rescue UAV. The first UAV rescue mission allocation information is updated based on the second UAV rescue mission allocation information. The second UAV rescue mission allocation information is used to characterize the status data of the rescue UAV participating in the rescue mission based on the dynamically enhanced rescue objective data. Based on the second UAV rescue mission allocation information and the dynamically enhanced rescue target data, path planning is performed on the rescue UAVs participating in the rescue mission to generate second path planning result information, and the first path planning result information is updated based on the second path planning result information.

7. The method according to claim 3, characterized in that, Multiple rescue drones participate in the rescue mission. Based on the first drone rescue mission deployment information and the rescue target data, path planning is performed on the rescue drones participating in the rescue mission to generate first path planning result information, including: For each of the rescue drones corresponding to the rescue mission in the first drone rescue mission allocation information, based on the rescue target location data, the water flow velocity parameters, the drone flight status data and the drone position status data of each rescue drone, path planning is performed on the rescue drones corresponding to the rescue mission in the first drone rescue mission allocation information, combined with a path planning algorithm, to generate preliminary drone path planning information for each rescue drone; After processing the initial path planning information of each of the rescue drones to resolve multi-drone path conflicts, the first path planning result information is obtained by summarizing the information.

8. A multi-UAV collaborative delivery path planning system for water rescue supplies, characterized in that, The system includes: The water rescue environment monitoring module is used to acquire rescue target data for rescue missions; The rescue equipment status monitoring module is used to acquire the status data of each rescue drone, including drone flight status data, drone position status data, and rescue material intensity data. A water rescue equipment allocation module is used to generate first drone rescue mission allocation information based on the rescue target data and the rescue drone status data. The first drone rescue mission allocation information is used to characterize the rescue drone status data of the rescue drones participating in the rescue mission. The rescue equipment path planning module is used to perform path planning for the rescue drones participating in the rescue mission based on the first drone rescue mission allocation information and the rescue target data, and generate first path planning result information; wherein, the rescue drones participating in the rescue mission are one or more drones.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images