A multi-agent parallel path planning system and method

Abstract

This invention relates to unmanned aerial vehicle (UAV) path planning, specifically to a multi-agent parallel path planning system and method. The system includes a unit grid map generation module, which divides an initial map into grids of fixed sizes to generate unit grid maps; a database agent, responsible for storing and indexing the unit grid maps, managing UAV missions, and providing data support to the planning and scheduling agents; a planning agent, which performs parallel path planning for UAVs on a specified number of unit grid maps, achieving global situational awareness and efficient reasoning; and a scheduling agent, responsible for batch scheduling and priority management of UAV missions, ensuring efficient and orderly mission execution. This invention effectively overcomes the shortcomings of existing technologies in the low efficiency of parallel UAV path planning.

Description

Technical Field

[0001] This invention relates to path planning for unmanned aerial vehicles (UAVs), and more specifically to a multi-agent parallel path planning system and method. Background Technology

[0002] Parallel computation for UAV path planning needs to consider data competition and the balance between spatial and temporal search. Traditional planning algorithms cannot meet the requirements in large-scale spatiotemporal planning scenarios.

[0003] An improved algorithm based on traditional planning algorithms, the specific process of which is as follows: Figure 7 As shown, the algorithm mainly consists of three parts: spatiotemporal planning, spatiotemporal detection, and oscillation detection. Spatiotemporal planning primarily involves preliminary planning based on the input. This preliminary planning process searches all possible paths until the destination is found, at which point the path is confirmed. Paths are then checked by the spatiotemporal detection unit: if the required time for a path has not been acquired by other drones, the time is acquired to complete the path planning; if it has been acquired by other drones, the current path and time are replaced with the previous departure point and time for replanning, until the spatiotemporal detection unit completes all path checks. During parallel planning, the coupling between drones can cause path oscillations. This can be addressed by using a dynamic oscillation spatiotemporal detection unit to detect these oscillations, loading the oscillation spatiotemporal data into a closedSet, and simultaneously merging it into the spatiotemporal planning algorithm to mask the oscillation space.

[0004] While the improved algorithm described above can perform parallel path planning for UAVs, its efficiency remains low, and its main problems include:

[0005] 1) The spatiotemporal planning of drones is decoupled, and a single planning only considers the historical drone paths, without considering drones that are currently in operation;

[0006] 2) Oscillation detection finds feasible paths by searching historical paths, and replanning is required for each search. Summary of the Invention

[0007] (a) Technical problems to be solved

[0008] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a multi-agent parallel path planning system and method, which can effectively overcome the shortcomings of low efficiency of UAV path parallel planning in the existing technology.

[0009] (II) Technical Solution

[0010] To achieve the above objectives, the present invention provides the following technical solution:

[0011] A multi-agent parallel path planning system includes a unit grid map generation module, a database agent, a planning agent, and a scheduling agent;

[0012] The unit grid map generation module divides the initial map into grids according to a fixed size to generate a unit grid map.

[0013] The database agent is responsible for storing and indexing the unit grid map, managing UAV missions, and providing data support for the planning agent and the scheduling agent.

[0014] The planning agent completes parallel path planning for UAVs on a specified number of unit grid maps, achieving global situational awareness and efficient reasoning;

[0015] The scheduling agent is responsible for batch scheduling and priority management of UAV missions to ensure efficient and orderly execution of missions.

[0016] Preferably, the unit grid map generation module takes the initial map as input, uses a gridding algorithm to divide the initial map into multiple fixed-size unit grids, generates a unit grid map, and outputs it to the database agent, planning agent, and scheduling agent.

[0017] Preferably, the functions of the database agent specifically include:

[0018] Storage and Indexing: Receives the unit grid map output by the unit grid map generation module, and based on the unit grid map combined with vector database technology, stores the initial map as a vector according to the unit grid map through a language model for fast retrieval and maintains the database;

[0019] Task queue management: Maintain a suspending queue for sorting and scheduling UAV tasks, ensuring that tasks are executed according to priority and order;

[0020] Data support: Provide corresponding data support based on the requests of the planning agent and the scheduling agent.

[0021] Preferably, the functions of the planning agent specifically include:

[0022] Data reception: Receives the unit grid map output by the unit grid map generation module, and the hanging queue output by the database agent;

[0023] Task decomposition: Break down large-scale planning tasks into multiple smaller-scale planning subtasks for parallel execution;

[0024] Global Situation Awareness: Utilizes a global attention mechanism to achieve global situation awareness on a unit grid map, enabling avoidance among multiple drones, avoidance of buildings by multiple drones, and avoidance of control by multiple drones through map understanding;

[0025] Parallel path planning: Based on the results of global situational awareness, multiple small-scale planning sub-tasks are executed in parallel to plan the optimal path for each UAV and avoid collisions and conflicts;

[0026] Output results: Output the UAV path planning information corresponding to each UAV mission to the database agent and the scheduling agent.

[0027] Preferably, the functions of the scheduling agent specifically include:

[0028] Data reception: Receives the unit grid map output by the unit grid map generation module, as well as the suspended queue and UAV path planning information output by the database agent;

[0029] Task scheduling: Based on the priority of drone tasks and drone status, combined with invocation rules, drone tasks are assigned to the corresponding drones;

[0030] Task execution: Based on the initial spatial position of the UAV and the UAV path planning information of the corresponding UAV mission, select an appropriate unit grid map for the UAV to perform the mission, ensuring the rationality and efficiency of the planned area;

[0031] Scheduling End: When the number of drones on the unit grid map reaches the specified number or all drone missions have been assigned, the scheduling of the current batch of drone missions ends and preparations are made for the scheduling of the next batch of drone missions.

[0032] Mission monitoring: Continuously monitor the execution status of each drone mission, including mission progress and drone status.

[0033] Preferably, the database agent, planning agent, and scheduling agent are registered through MCP to enable communication between the agents, and data flows are transmitted between the agents on demand to achieve database maintenance.

[0034] A multi-agent parallel path planning method includes the following steps:

[0035] S1. The unit grid map generation module divides the initial map into grids according to a fixed size, generates a unit grid map, and outputs it to the database agent, planning agent, and scheduling agent.

[0036] S2. The database agent stores and indexes the unit grid map, maintains a suspended queue for sorting and scheduling UAV missions, and provides corresponding data support according to the requests of the planning agent and the scheduling agent.

[0037] S3. The planning agent uses a global attention mechanism to achieve global situational awareness on a unit grid map. Based on the global situational awareness results, it executes multiple small-scale planning sub-tasks in parallel to plan the optimal path for each UAV and outputs the UAV path planning information corresponding to each UAV task to the database agent and the scheduling agent.

[0038] S4. The scheduling agent assigns drone tasks to the corresponding drones based on the priority and status of the drone tasks. It also selects an appropriate unit grid map for the drones to execute tasks based on the initial spatial position of the drones and the drone path planning information of the corresponding drone tasks, while continuously monitoring the execution status of each drone task.

[0039] Preferably, the work content of the database agent in S2 specifically includes:

[0040] Storage and Indexing: Receives the unit grid map output by the unit grid map generation module, and based on the unit grid map combined with vector database technology, stores the initial map as a vector according to the unit grid map through a language model for fast retrieval and maintains the database;

[0041] Task queue management: Maintain a suspending queue for sorting and scheduling UAV tasks, ensuring that tasks are executed according to priority and order;

[0042] Data support: Provide corresponding data support based on the requests of the planning agent and the scheduling agent.

[0043] Preferably, the working process of planning the intelligent agent in S3 specifically includes:

[0044] S31. Data reception: Receive the unit grid map output by the unit grid map generation module and the hanging queue output by the database agent;

[0045] S32. Task decomposition: Decompose large-scale planning tasks into multiple small-scale planning sub-tasks so that they can be executed in parallel;

[0046] S33. Global Situation Awareness: Utilizes a global attention mechanism to achieve global situation awareness on a unit grid map, and enables avoidance among multiple UAVs, avoidance of buildings by multiple UAVs, and avoidance of control by multiple UAVs through map understanding;

[0047] S34. Parallel Path Planning: Based on the global situational awareness results, multiple small-scale planning sub-tasks are executed in parallel to plan the optimal path for each UAV and avoid collisions and conflicts.

[0048] S35. Output Results: Output the UAV path planning information corresponding to each UAV mission to the database agent and the scheduling agent.

[0049] Preferably, the working process of scheduling the agent in S4 specifically includes:

[0050] S41. Data reception: Receive the unit grid map output by the unit grid map generation module, as well as the suspended queue and UAV path planning information output by the database agent;

[0051] S42. Task Scheduling: Based on the priority of the drone task and the drone status, combined with the calling rules, the drone task is assigned to the corresponding drone.

[0052] S43. Mission Execution: Based on the initial spatial position of the UAV and the UAV path planning information of the corresponding UAV mission, select an appropriate unit grid map for the UAV to execute the mission, ensuring the rationality and efficiency of the planned area;

[0053] S44. Scheduling End: When the number of drones on the unit grid map reaches the specified number or all drone tasks have been assigned, the scheduling of the current batch of drone tasks ends and preparations are made for the scheduling of the next batch of drone tasks.

[0054] S45. Mission Monitoring: Continuously monitor the execution status of each UAV mission, including mission progress and UAV status.

[0055] (III) Beneficial Effects

[0056] Compared with the prior art, the multi-agent parallel path planning system and method provided by the present invention have the following beneficial effects:

[0057] 1) Utilize the global attention mechanism to achieve global situational awareness on a unit grid map, enabling parallel path planning for multiple UAVs during operation without the need for spatiotemporal detection;

[0058] 2) Global attention can be used to perceive the status of surrounding drones without the need for oscillation detection;

[0059] 3) Utilize the parallel computing capabilities of language models to achieve GPU inference and improve computational efficiency. Attached Figure Description

[0060] 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.

[0061] Figure 1 This is a schematic diagram of the system operation of the present invention;

[0062] Figure 2 This is a schematic diagram illustrating the generation of a unit grid map in this invention;

[0063] Figure 3 This is a functional diagram of the database agent in this invention;

[0064] Figure 4 This is a functional diagram of the planning intelligent agent in this invention;

[0065] Figure 5 This is a functional diagram of the scheduling agent in this invention;

[0066] Figure 6 This is a schematic diagram of communication between intelligent agents in this invention;

[0067] Figure 7 This is a flowchart illustrating an improved algorithm based on a traditional planning algorithm. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0069] The following describes the specific functional modules of the multi-agent parallel path planning system provided by this invention, using concrete examples (such as...). Figure 1 (As shown) and its technical effects. The system's functional modules include: a unit grid map generation module, a database agent, a planning agent, and a scheduling agent;

[0070] The unit grid map generation module divides the initial map into grids according to a fixed size to generate a unit grid map.

[0071] The database agent is responsible for storing and indexing the unit grid map, managing UAV missions, and providing data support for the planning agent and the scheduling agent.

[0072] The planning agent completes parallel path planning for UAVs on a specified number of unit grid maps, achieving global situational awareness and efficient reasoning;

[0073] The scheduling agent is responsible for batch scheduling and priority management of UAV missions to ensure efficient and orderly execution of missions.

[0074] I. Unit Grid Map Generation Module

[0075] like Figure 2As shown, the unit grid map generation module takes the initial map as input, uses a gridding algorithm to divide the initial map into multiple fixed-size unit grids, generates a unit grid map, and outputs it to the database agent, planning agent, and scheduling agent.

[0076] II. Database Intelligent Agent

[0077] The functions of database intelligent agents, such as Figure 3 As shown, it specifically includes:

[0078] Storage and Indexing: Receives the unit grid map output by the unit grid map generation module, and based on the unit grid map combined with vector database technology, stores the initial map as a vector according to the unit grid map through a language model for fast retrieval and maintains the database;

[0079] Task queue management: Maintain a suspending queue for sorting and scheduling UAV tasks, ensuring that tasks are executed according to priority and order;

[0080] Data support: Provide corresponding data support based on the requests of the planning agent and the scheduling agent.

[0081] III. Planning Intelligent Agents

[0082] Plan the functions of the intelligent agent, such as Figure 4 As shown, it specifically includes:

[0083] Data reception: Receives the unit grid map output by the unit grid map generation module, and the hanging queue output by the database agent;

[0084] Task decomposition: Break down large-scale planning tasks into multiple smaller-scale planning subtasks for parallel execution;

[0085] Global Situation Awareness: Utilizes a global attention mechanism to achieve global situation awareness on a unit grid map, enabling avoidance among multiple drones, avoidance of buildings by multiple drones, and avoidance of control by multiple drones through map understanding;

[0086] Parallel path planning: Based on the results of global situational awareness, multiple small-scale planning sub-tasks are executed in parallel to plan the optimal path for each UAV and avoid collisions and conflicts;

[0087] Output results: Output the UAV path planning information corresponding to each UAV mission to the database agent and the scheduling agent.

[0088] IV. Scheduling Intelligent Agent

[0089] The functions of scheduling agents, such as Figure 5 As shown, it specifically includes:

[0090] Data reception: Receives the unit grid map output by the unit grid map generation module, as well as the suspended queue and UAV path planning information output by the database agent;

[0091] Task scheduling: Based on the priority of drone tasks and drone status, combined with invocation rules, drone tasks are assigned to the corresponding drones;

[0092] Task execution: Based on the initial spatial position of the UAV and the UAV path planning information of the corresponding UAV mission, select an appropriate unit grid map for the UAV to perform the mission, ensuring the rationality and efficiency of the planned area;

[0093] Scheduling End: When the number of drones on the unit grid map reaches the specified number or all drone missions have been assigned, the scheduling of the current batch of drone missions ends and preparations are made for the scheduling of the next batch of drone missions.

[0094] Mission monitoring: Continuously monitor the execution status of each drone mission, including mission progress and drone status.

[0095] In the technical solution of this application, such as Figure 6 As shown, the database agent, planning agent, and scheduling agent register with each other through MCP to achieve communication between the agents. Data flows between the agents are transmitted on demand to achieve database maintenance.

[0096] Based on the aforementioned multi-agent parallel path planning system, this invention also discloses a multi-agent parallel path planning method, comprising the following steps:

[0097] S1. The unit grid map generation module divides the initial map into grids according to a fixed size, generates a unit grid map, and outputs it to the database agent, planning agent, and scheduling agent.

[0098] S2. The database agent stores and indexes the unit grid map, maintains a suspended queue for sorting and scheduling UAV missions, and provides corresponding data support according to the requests of the planning agent and the scheduling agent.

[0099] S3. The planning agent uses a global attention mechanism to achieve global situational awareness on a unit grid map. Based on the global situational awareness results, it executes multiple small-scale planning sub-tasks in parallel to plan the optimal path for each UAV and outputs the UAV path planning information corresponding to each UAV task to the database agent and the scheduling agent.

[0100] S4. The scheduling agent assigns drone tasks to the corresponding drones based on the priority and status of the drone tasks. It also selects an appropriate unit grid map for the drones to execute tasks based on the initial spatial position of the drones and the drone path planning information of the corresponding drone tasks, while continuously monitoring the execution status of each drone task.

[0101] Specifically, the tasks of the database agent in S2 include:

[0102] Storage and Indexing: Receives the unit grid map output by the unit grid map generation module, and based on the unit grid map combined with vector database technology, stores the initial map as a vector according to the unit grid map through a language model for fast retrieval and maintains the database;

[0103] Task queue management: Maintain a suspending queue for sorting and scheduling UAV tasks, ensuring that tasks are executed according to priority and order;

[0104] Data support: Provide corresponding data support based on the requests of the planning agent and the scheduling agent.

[0105] Specifically, the working process of planning intelligent agents in S3 includes:

[0106] S31. Data reception: Receive the unit grid map output by the unit grid map generation module and the hanging queue output by the database agent;

[0107] S32. Task decomposition: Decompose large-scale planning tasks into multiple small-scale planning sub-tasks so that they can be executed in parallel;

[0108] S33. Global Situation Awareness: Utilizes a global attention mechanism to achieve global situation awareness on a unit grid map, and enables avoidance among multiple UAVs, avoidance of buildings by multiple UAVs, and avoidance of control by multiple UAVs through map understanding;

[0109] S34. Parallel Path Planning: Based on the global situational awareness results, multiple small-scale planning sub-tasks are executed in parallel to plan the optimal path for each UAV and avoid collisions and conflicts.

[0110] S35. Output Results: Output the UAV path planning information corresponding to each UAV mission to the database agent and the scheduling agent.

[0111] Specifically, the working process of scheduling agents in S4 includes:

[0112] S41. Data reception: Receive the unit grid map output by the unit grid map generation module, as well as the suspended queue and UAV path planning information output by the database agent;

[0113] S42. Task Scheduling: Based on the priority of the drone task and the drone status, combined with the calling rules, the drone task is assigned to the corresponding drone.

[0114] S43. Mission Execution: Based on the initial spatial position of the UAV and the UAV path planning information of the corresponding UAV mission, select an appropriate unit grid map for the UAV to execute the mission, ensuring the rationality and efficiency of the planned area;

[0115] S44. Scheduling End: When the number of drones on the unit grid map reaches the specified number or all drone tasks have been assigned, the scheduling of the current batch of drone tasks ends and preparations are made for the scheduling of the next batch of drone tasks.

[0116] S45. Mission Monitoring: Continuously monitor the execution status of each UAV mission, including mission progress and UAV status.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-agent parallel path planning system, characterized in that: It includes a unit grid map generation module, a database agent, a planning agent, and a scheduling agent; The unit grid map generation module divides the initial map into grids according to a fixed size to generate a unit grid map. The database agent is responsible for storing and indexing the unit grid map, managing UAV missions, and providing data support for the planning agent and the scheduling agent. The planning agent completes parallel path planning for UAVs on a specified number of unit grid maps, achieving global situational awareness and efficient reasoning; The scheduling agent is responsible for batch scheduling and priority management of UAV missions to ensure efficient and orderly execution of missions.

2. The multi-agent parallel path planning system according to claim 1, characterized in that: The unit grid map generation module takes the initial map as input, uses a gridding algorithm to divide the initial map into multiple fixed-size unit grids, generates a unit grid map, and outputs it to the database agent, planning agent, and scheduling agent.

3. The multi-agent parallel path planning system according to claim 2, characterized in that: The functions of the database agent specifically include: Storage and Indexing: Receives the unit grid map output by the unit grid map generation module, and based on the unit grid map combined with vector database technology, stores the initial map as a vector according to the unit grid map through a language model for fast retrieval and maintains the database; Task queue management: Maintain a suspending queue for sorting and scheduling UAV tasks, ensuring that tasks are executed according to priority and order; Data support: Provide corresponding data support based on the requests of the planning agent and the scheduling agent.

4. The multi-agent parallel path planning system according to claim 3, characterized in that: The functions of the planning agent specifically include: Data reception: Receives the unit grid map output by the unit grid map generation module, and the hanging queue output by the database agent; Task decomposition: Break down large-scale planning tasks into multiple smaller-scale planning subtasks for parallel execution; Global Situation Awareness: Utilizes a global attention mechanism to achieve global situation awareness on a unit grid map, enabling avoidance among multiple drones, avoidance of buildings by multiple drones, and avoidance of control by multiple drones through map understanding; Parallel path planning: Based on the results of global situational awareness, multiple small-scale planning sub-tasks are executed in parallel to plan the optimal path for each UAV and avoid collisions and conflicts; Output results: Output the UAV path planning information corresponding to each UAV mission to the database agent and the scheduling agent.

5. The multi-agent parallel path planning system according to claim 4, characterized in that: The functions of the scheduling agent specifically include: Data reception: Receives the unit grid map output by the unit grid map generation module, as well as the suspended queue and UAV path planning information output by the database agent; Task scheduling: Based on the priority of drone tasks and drone status, combined with invocation rules, drone tasks are assigned to the corresponding drones; Task execution: Based on the initial spatial position of the UAV and the UAV path planning information of the corresponding UAV mission, select an appropriate unit grid map for the UAV to perform the mission, ensuring the rationality and efficiency of the planned area; Scheduling End: When the number of drones on the unit grid map reaches the specified number or all drone missions have been assigned, the scheduling of the current batch of drone missions ends and preparations are made for the scheduling of the next batch of drone missions. Mission monitoring: Continuously monitor the execution status of each drone mission, including mission progress and drone status.

6. The multi-agent parallel path planning system according to claim 1, characterized in that: The database agent, planning agent, and scheduling agent are registered through MCP to enable communication between the agents. Data flows are transmitted between the agents on demand to achieve database maintenance.

7. A multi-agent parallel path planning method, applicable to the multi-agent parallel path planning system of claim 1, characterized in that: Includes the following steps: S1. The unit grid map generation module divides the initial map into grids according to a fixed size, generates a unit grid map, and outputs it to the database agent, planning agent, and scheduling agent. S2. The database agent stores and indexes the unit grid map, maintains a suspended queue for sorting and scheduling UAV missions, and provides corresponding data support according to the requests of the planning agent and the scheduling agent. S3. The planning agent uses a global attention mechanism to achieve global situational awareness on a unit grid map. Based on the global situational awareness results, it executes multiple small-scale planning sub-tasks in parallel to plan the optimal path for each UAV and outputs the UAV path planning information corresponding to each UAV task to the database agent and the scheduling agent. S4. The scheduling agent assigns drone tasks to the corresponding drones based on the priority and status of the drone tasks. It also selects an appropriate unit grid map for the drones to execute tasks based on the initial spatial position of the drones and the drone path planning information of the corresponding drone tasks, while continuously monitoring the execution status of each drone task.

8. The multi-agent parallel path planning method according to claim 7, characterized in that: The tasks of the database agent in S2 specifically include: Storage and Indexing: Receives the unit grid map output by the unit grid map generation module, and based on the unit grid map combined with vector database technology, stores the initial map as a vector according to the unit grid map through a language model for fast retrieval and maintains the database; Task queue management: Maintain a suspending queue for sorting and scheduling UAV tasks, ensuring that tasks are executed according to priority and order; Data support: Provide corresponding data support based on the requests of the planning agent and the scheduling agent.

9. The multi-agent parallel path planning method according to claim 8, characterized in that: The process of planning the operation of an intelligent agent in S3 specifically includes: S31. Data reception: Receive the unit grid map output by the unit grid map generation module and the hanging queue output by the database agent; S32. Task decomposition: Decompose large-scale planning tasks into multiple small-scale planning sub-tasks so that they can be executed in parallel; S33. Global Situation Awareness: Utilizes a global attention mechanism to achieve global situation awareness on a unit grid map, and enables avoidance among multiple UAVs, avoidance of buildings by multiple UAVs, and avoidance of control by multiple UAVs through map understanding; S34. Parallel Path Planning: Based on the global situational awareness results, multiple small-scale planning sub-tasks are executed in parallel to plan the optimal path for each UAV and avoid collisions and conflicts. S35. Output Results: Output the UAV path planning information corresponding to each UAV mission to the database agent and the scheduling agent.

10. The multi-agent parallel path planning method according to claim 9, characterized in that: The workflow of scheduling agents in S4 specifically includes: S41. Data reception: Receive the unit grid map output by the unit grid map generation module, as well as the suspended queue and UAV path planning information output by the database agent; S42. Task Scheduling: Based on the priority of the drone task and the drone status, combined with the calling rules, the drone task is assigned to the corresponding drone. S43. Mission Execution: Based on the initial spatial position of the UAV and the UAV path planning information of the corresponding UAV mission, select an appropriate unit grid map for the UAV to execute the mission, ensuring the rationality and efficiency of the planned area; S44. Scheduling End: When the number of drones on the unit grid map reaches the specified number or all drone tasks have been assigned, the scheduling of the current batch of drone tasks ends and preparations are made for the scheduling of the next batch of drone tasks. S45. Mission Monitoring: Continuously monitor the execution status of each UAV mission, including mission progress and UAV status.

Images