Agricultural unmanned vehicle and unmanned aerial vehicle cluster collaborative scheduling and path planning system

Abstract

The invention belongs to the technical field of agriculture, and discloses a collaborative scheduling and path planning system. The collaborative scheduling and path planning system comprises an unmanned vehicle system, an unmanned aerial vehicle cluster system and a central management platform, the central management platform is in communication connection with the unmanned vehicle system and the unmanned aerial vehicle cluster system, and is used for realizing cooperative scheduling and path planning of the unmanned vehicle system and the unmanned aerial vehicle cluster system, realizing function complementation and reasonable task allocation of the unmanned vehicle and the unmanned aerial vehicle cluster system through a cooperative scheduling mechanism of the central management platform, and meanwhile, realizing path planning of the unmanned aerial vehicle and the unmanned aerial vehicle cluster system. Based on the dynamic task allocation strategy of the improved Hungary algorithm, the task load can be adjusted in real time according to the residual electric quantity and the operation capability of the equipment, the energy consumption cost is reduced by 15-20%, and the operation efficiency and the resource utilization rate are improved.

Description

Technical Field

[0001] This invention belongs to the field of agricultural technology, specifically a collaborative scheduling and path planning system for agricultural unmanned vehicles and drone swarms. Background Technology

[0002] With global population growth and the increasing prominence of agricultural labor shortages, modern agriculture's demand for intelligent and precision production is becoming increasingly urgent. Unmanned agricultural equipment, as a core means to address labor shortages and improve production efficiency, has become an important direction for agricultural technology development. Among them, unmanned agricultural vehicles and drones, with their unique technological advantages, are widely used in farmland operations.

[0003] Drones have the ability to quickly cover large areas and can be equipped with hyperspectral cameras, thermal imagers and other equipment to complete tasks such as farmland monitoring, early warning of pests and diseases, and assessment of crop growth status. At the same time, multi-rotor drones can achieve low-altitude precision plant protection operations, which greatly improves the efficiency of pesticide spraying. Agricultural unmanned vehicles, on the other hand, rely on their strong load-bearing capacity and terrain adaptability to undertake ground operations such as soil sampling, sowing, fertilization and material transportation, and perform particularly well in precision operations under complex terrain conditions.

[0004] Currently, the application of agricultural unmanned vehicles and drones is still mainly based on independent operation, lacking an efficient collaborative mechanism, which makes it difficult to fully utilize their technological advantages. Specifically, this manifests in several ways: Information silos: Farmland monitoring data acquired by drones (such as pest and disease distribution and soil moisture) cannot be shared with unmanned vehicles in real time. This causes unmanned vehicle operations to rely on preset parameters, making it difficult to dynamically adjust according to actual field conditions, resulting in resource waste or insufficient operational accuracy; Imbalanced task allocation: Due to the lack of a global scheduling strategy, situations of equipment idleness and task backlog are prone to occur simultaneously; Independent path planning: The path planning of unmanned vehicles and drones is independent, without considering the overlap and avoidance needs of their operating areas, which may lead to equipment conflicts (such as the risk of collision caused by drones and unmanned vehicles operating simultaneously in the same area), or increased energy consumption due to repeated coverage of the same area; Insufficient emergency response: When faced with emergencies (such as equipment failure or weather changes), unmanned vehicles or drones operating independently cannot quickly coordinate and adjust, leading to operation interruptions or decreased quality. Summary of the Invention

[0005] The purpose of this invention is to provide a collaborative scheduling and path planning system for agricultural unmanned vehicles and drone swarms, in order to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a collaborative scheduling and path planning system for agricultural unmanned vehicles and drone swarms, the collaborative scheduling and path planning system comprising an unmanned vehicle system, a drone swarm system, and a central management platform; the central management platform is communicatively connected to the unmanned vehicle system and the drone swarm system respectively, and is used to realize collaborative scheduling and path planning for the unmanned vehicle system and the drone swarm system; The unmanned vehicle system includes a vehicle body, a power system, a navigation system, a work execution system, a sensor system, and a communication module. It can autonomously complete farmland work tasks according to the instructions of the central management platform and provide real-time feedback on work status and location information. The drone swarm system comprises multiple drones of different types. Each drone is equipped with a power system, navigation system, payload system, sensor system, and communication module. It can collaboratively complete farmland operation tasks according to the coordinated scheduling strategy and path planning scheme, and maintain real-time communication with the unmanned vehicle system and the central management platform. The central management platform consists of a server, a data processing module, a task allocation module, a path planning module, a communication management module, and a monitoring and early warning module. It is responsible for receiving and processing data uploaded by the unmanned vehicle system and the drone swarm system, performing task allocation and path planning, and monitoring the overall system operation status in real time.

[0007] Preferably, the central management platform communicates with the unmanned vehicle system and the drone swarm system using a hybrid 5G and LoRa networking technology; the 5G network is used to ensure the rapid transmission of large amounts of data between the central management platform and the drone swarm system and the unmanned vehicle system; the LoRa network is used to realize data interaction within the drone swarm system and between the unmanned vehicle system and surrounding environmental sensing devices.

[0008] Preferably, the task allocation module of the central management platform uses an improved Hungarian algorithm for task allocation; the task allocation is based on the type of farmland operation task, the characteristics of the operation area, and the performance parameters of the unmanned vehicle system and the drone swarm system, and takes into account the current working status and remaining power of the equipment, and dynamically adjusts the task allocation.

[0009] Preferably, the path planning module of the central management platform plans the globally optimal path for both the unmanned vehicle system and the unmanned aerial vehicle (UAV) swarm system. For the UAV swarm system, a path planning method based on an improved ant colony algorithm is adopted. This method introduces heuristic information on top of the traditional ant colony algorithm, comprehensively considering factors such as path length, flight altitude, obstacle avoidance, and farmland operation area coverage to optimize the pheromone update rules. For the unmanned vehicle system, based on A... * The algorithm combines farmland terrain slope and soil conditions to plan the global path with the lowest energy consumption and the safest driving, and takes into account the load and turning radius constraints of the unmanned vehicle during the planning process.

[0010] Preferably, during the execution of the global path, the unmanned vehicle system and the UAV swarm system perceive the surrounding environment information in real time through their respective sensor systems; when an obstacle is detected, the Dijkstra algorithm or the artificial potential field method is used for local path replanning to achieve obstacle avoidance; and the UAV swarm system adopts a distributed obstacle avoidance strategy based on Voronoi diagrams. When a UAV detects an obstacle, it shares the obstacle information with other UAVs through the communication network, and each UAV replans its own flight path according to the Voronoi diagram.

[0011] Preferably, the navigation system of the unmanned vehicle system is a fusion of high-precision GPS and inertial navigation, with positioning accuracy down to the centimeter level; the operation execution system includes a seeding device, a fertilization device, and a pesticide spraying device; the sensor system includes a lidar, a camera, an ultrasonic sensor, and a soil sensor.

[0012] Preferably, the drone swarm system comprises multiple drones of different functional types, specifically including fixed-wing drones for large-scale farmland monitoring and multi-rotor drones for low-altitude precision plant protection; each drone's power system is a lithium battery or hydrogen fuel cell, with some models using solar-assisted power; the navigation system combines satellite navigation and visual navigation; the payload system includes a multispectral camera, a thermal imager, and a pesticide spraying device; and the sensor system includes a barometer, a gyroscope, and a lidar.

[0013] Preferably, the monitoring and early warning module of the central management platform monitors the working status of the unmanned vehicle system and the drone swarm system in real time, including equipment location, speed, power consumption, operation progress, and sensor data; when a fault or abnormal operation is detected, it issues an early warning message in a timely manner and displays the location of the faulty equipment and the fault type on the monitoring interface.

[0014] Preferably, the collaborative operation process of the unmanned vehicle system and the drone swarm system for crop pest and disease control scenarios is as follows: S1. The drone swarm system is equipped with a hyperspectral camera and multi-rotor drones that fly at low altitudes to conduct a comprehensive scan of farmland, identify the areas and severity of pests and diseases, and transmit the data to the central management platform in real time. S2. Based on data analysis results, the central management platform plans the driving path of the unmanned vehicle system, guides it to the pest and disease area, and calculates the required pesticide type, dosage, and application method according to the type and severity of the pest and disease. This information is then simultaneously sent to the unmanned vehicle system and the drone swarm system. S3. The drone swarm system provides real-time navigation assistance to the unmanned vehicle system from the air, ensuring that it accurately reaches the application location. At the same time, it monitors the application effect. If uneven application or missed areas are found, it promptly provides feedback to the unmanned vehicle system for re-spraying.

[0015] Preferably, the collaborative scheduling and path planning system for the sowing operation scenario has the following collaborative operation process: S1. The central management platform plans the sowing path of the unmanned vehicle system based on the farmland planting plan and soil conditions, and sends the sowing parameters to the unmanned vehicle system; S2. The unmanned vehicle system travels along the planned path and completes the sowing task using the sowing device; S3. During the sowing process, the drone swarm system monitors the sowing area from the air to check the sowing uniformity. If any missed or overly dense areas are found, the system will promptly report the information to the drone system for adjustment.

[0016] The beneficial effects of this invention are as follows: 1. In this invention, the collaborative scheduling mechanism of the central management platform enables the functional complementarity and rational task allocation between unmanned vehicles and drone swarms. For example, in seeding operations, the drone swarm is responsible for aerial monitoring and path guidance, while the unmanned vehicles focus on precise seeding on the ground. The two have a clear division of labor and work together in real time, avoiding equipment idleness or repetitive operations, thereby increasing the working area per unit time by more than 30%. At the same time, based on the dynamic task allocation strategy of the improved Hungarian algorithm, the task load can be adjusted in real time according to the remaining power of the equipment and the working capacity, reducing energy consumption costs by 15%-20% and improving work efficiency and resource utilization.

[0017] 2. In this invention, high-precision navigation and collaborative path planning technology are adopted. The unmanned vehicle achieves centimeter-level positioning through "high-precision GPS + inertial navigation". Combined with the real-time aerial calibration of the drone swarm, it ensures that the spatial error of operations such as sowing and fertilization does not exceed 5cm. In the scenario of pest and disease control, the hyperspectral recognition of the drone swarm and the fixed-point application of pesticides by the unmanned vehicle can increase the pesticide utilization rate by more than 40%, reduce the environmental pollution caused by excessive application of pesticides, and at the same time, the pest and disease control coverage rate can reach more than 98% through the supplementary spraying mechanism, thereby improving the accuracy of operation and the quality of agricultural production.

[0018] 3. In this invention, the 5G and LoRa hybrid networking technology solves the communication bottleneck in complex farmland environments. The 5G network ensures the real-time transmission of high-definition images and massive amounts of operational data, while the LoRa network enables low-power, anti-obstruction short-range communication between devices, improving the system's communication stability by 60% in densely vegetated or complex terrain areas. Local path replanning and distributed obstacle avoidance strategies (such as the Voronoi diagram algorithm) can shorten the response time of devices when encountering sudden obstacles to within 0.5 seconds, avoiding operation interruption and enhancing the system's adaptability and anti-interference capabilities.

[0019] 4. In this invention, the system can be quickly adapted to different agricultural scenarios such as pest and disease control and sowing through standardized collaborative processes. For example, in sowing operations, the linkage mechanism of drone monitoring and unmanned vehicle reseeding can improve the sowing uniformity to over 95%; in pest and disease control, the entire process of "identification-planning-application-monitoring" is coordinated to achieve an integrated solution from early warning to precision management, significantly reducing crop loss rates and expanding the operational capabilities and flexibility in multiple scenarios. Attached Figure Description

[0020] Figure 1 This is a system block diagram of the present invention; Figure 2 This is a flowchart illustrating the collaborative operation process for crop pest and disease control in this invention. Figure 3 This invention relates to a collaborative operation process for sowing operations. Detailed Implementation

[0021] 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 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.

[0022] like Figures 1 to 3 As shown, this embodiment of the invention provides a collaborative scheduling and path planning system for agricultural unmanned vehicles and drone swarms. The collaborative scheduling and path planning system includes an unmanned vehicle system, a drone swarm system, and a central management platform. The central management platform is communicatively connected to both the unmanned vehicle system and the drone swarm system to realize collaborative scheduling and path planning for the unmanned vehicle system and the drone swarm system. The unmanned vehicle system includes a vehicle body, power system, navigation system, operation execution system, sensor system and communication module. It can autonomously complete farmland operation tasks according to the instructions of the central management platform and provide real-time feedback on operation status and location information. The drone swarm system consists of multiple drones of different types. Each drone is equipped with a power system, navigation system, payload system, sensor system, and communication module. It can collaboratively complete farmland operation tasks according to the coordinated scheduling strategy and path planning scheme, and maintain real-time communication with the unmanned vehicle system and the central management platform. The central management platform consists of a server, a data processing module, a task allocation module, a path planning module, a communication management module, and a monitoring and early warning module. It is responsible for receiving and processing data uploaded by the unmanned vehicle system and the drone swarm system, performing task allocation and path planning, and monitoring the overall system operation status in real time.

[0023] The central management platform communicates with the unmanned vehicle system and the drone swarm system using a hybrid 5G and LoRa network technology. The 5G network ensures rapid transmission of large amounts of data between the central management platform and the drone swarm system and the unmanned vehicle system. The LoRa network enables data interaction within the drone swarm system and between the unmanned vehicle system and surrounding environmental sensing devices. It is deployed in conjunction with 5G base stations and LoRa gateways, with the 5G network having higher priority than the LoRa network. When the 5G signal strength is below -85dBm, it automatically switches to the LoRa network to transmit critical data (such as device location and fault warnings). Large data transmissions (such as high-definition images) are paused and buffered, and will resume transmission once 5G is restored.

[0024] The task allocation module of the central management platform uses an improved Hungarian algorithm for task allocation. The task allocation is based on the type of farmland operation task, the characteristics of the operation area, and the performance parameters of the unmanned vehicle system and the drone swarm system. It also takes into account the current working status of the equipment and the remaining power, and dynamically adjusts the task allocation.

[0025] The path planning module of the central management platform plans globally optimal paths for both unmanned vehicle (UAV) and drone swarm systems. For drone swarm systems, a path planning method based on an improved ant colony algorithm is adopted. This method introduces heuristic information into the traditional ant colony algorithm, comprehensively considering factors such as path length, flight altitude, obstacle avoidance, and farmland operation area coverage to optimize pheromone update rules. For unmanned vehicle systems, a path planning method based on A... * The algorithm combines farmland terrain slope and soil conditions to plan the global path with the lowest energy consumption and the safest driving, and takes into account the load and turning radius constraints of the unmanned vehicle during the planning process.

[0026] During the execution of the global path, the autonomous vehicle system and the drone swarm system perceive the surrounding environment in real time through their respective sensor systems. When an obstacle is detected, Dijkstra's algorithm or artificial potential field method is used for local path replanning. Specifically, when the sensor detects a static obstacle (e.g., its position remains unchanged for 5 seconds), Dijkstra's algorithm is used to plan the shortest obstacle avoidance path; when the obstacle is dynamic (e.g., its position change rate is ≥0.5m / s), the artificial potential field method is used, with the direction of the obstacle's movement as the direction of the repulsive force, to adjust the path in real time to achieve obstacle avoidance. Furthermore, the drone swarm system adopts a distributed obstacle avoidance strategy based on Voronoi diagrams. The Voronoi diagram is constructed using the real-time coordinates of each drone as generators, and the Voronoi boundaries of adjacent drones serve as a safe distance threshold (e.g., 5 meters). When a drone detects an obstacle, it broadcasts the obstacle's coordinates to the swarm, and each drone recalculates the Voronoi diagram containing the obstacle. The new path is generated along the updated boundary, ensuring a distance of ≥3 meters from the obstacle.

[0027] The navigation system of the unmanned vehicle system is a fusion of high-precision GPS and inertial navigation, with positioning accuracy down to the centimeter level; the operation execution system includes a seeding device, a fertilization device, and a pesticide spraying device; the sensor system includes lidar, cameras, ultrasonic sensors, and soil sensors.

[0028] The drone swarm system comprises multiple drones of different functional types, including fixed-wing drones for large-scale farmland monitoring and multi-rotor drones for low-altitude precision plant protection; each drone is powered by a lithium battery or hydrogen fuel cell, with some models using solar-assisted power; the navigation system combines satellite navigation and visual navigation; the payload system includes a multispectral camera, thermal imager, and pesticide spraying device; and the sensor system includes a barometer, gyroscope, and lidar.

[0029] The central management platform's monitoring and early warning module monitors the operational status of the unmanned vehicle system and drone swarm system in real time, including equipment location, speed, battery level, operation progress, and sensor data. When equipment malfunctions or operational anomalies are detected, it promptly issues early warning information and displays the location and type of malfunction on the monitoring interface.

[0030] The collaborative operation process of unmanned vehicle systems and drone swarm systems for crop pest and disease control is as follows: S1. The drone swarm system is equipped with a hyperspectral camera and multi-rotor drones that fly at low altitudes to conduct a comprehensive scan of farmland, identify the areas and severity of pests and diseases, and transmit the data to the central management platform in real time. S2. Based on the data analysis results, the central management platform plans the driving path of the unmanned vehicle system, guides it to the pest and disease area, and calculates the required pesticide type, dosage and application method according to the type and severity of the pest and disease. This information is then sent to the unmanned vehicle system and the drone swarm system simultaneously. S3. The drone swarm system provides real-time navigation assistance to the unmanned vehicle system in the air. The drone swarm identifies farmland boundary markers (such as pre-buried fluorescent stakes) through multispectral cameras, calculates the real-time offset of the unmanned vehicle by combining its own GPS coordinates, and sends correction commands to the unmanned vehicle every 0.5 seconds via LoRa (such as 'offset 0.3 meters to the east') to ensure that it accurately reaches the spraying position. At the same time, it monitors the spraying effect. The lidar on the drone scans the sowing area. When the seed reflection signal intensity is lower than the preset threshold (such as 20dB) and the duration is ≥2 meters, it is determined to be a missed area. The GPS coordinates of the area are marked simultaneously (accuracy ±0.1 meters) and transmitted to the central management platform. If uneven spraying or missed areas are found, feedback is promptly given to the unmanned vehicle system for re-spraying.

[0031] The collaborative scheduling and path planning system for seeding operations follows this workflow: S1. The central management platform plans the sowing path of the unmanned vehicle system based on the farmland planting plan and soil conditions, and sends the sowing parameters to the unmanned vehicle system; S2. The unmanned vehicle system travels along the planned path and completes the sowing task using the sowing device; S3. During the sowing process, the drone swarm system monitors the sowing area from the air to check the sowing uniformity. If any missed or overly dense areas are found, the system will promptly report the information to the drone system for adjustment.

[0032] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0033] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A collaborative scheduling and path planning system for agricultural unmanned vehicles and drone swarms, characterized in that: The collaborative scheduling and path planning system includes an unmanned vehicle system, an unmanned aerial vehicle (UAV) swarm system, and a central management platform. The central management platform is communicatively connected to the unmanned vehicle system and the UAV swarm system, respectively, and is used to realize the collaborative scheduling and path planning of the unmanned vehicle system and the UAV swarm system. The unmanned vehicle system includes a vehicle body, a power system, a navigation system, a work execution system, a sensor system, and a communication module. It can autonomously complete farmland work tasks according to the instructions of the central management platform and provide real-time feedback on work status and location information. The drone swarm system comprises multiple drones of different types. Each drone is equipped with a power system, navigation system, payload system, sensor system, and communication module. It can collaboratively complete farmland operation tasks according to the coordinated scheduling strategy and path planning scheme, and maintain real-time communication with the unmanned vehicle system and the central management platform. The central management platform consists of a server, a data processing module, a task allocation module, a path planning module, a communication management module, and a monitoring and early warning module. It is responsible for receiving and processing data uploaded by the unmanned vehicle system and the drone swarm system, performing task allocation and path planning, and monitoring the overall system operation status in real time.

2. The agricultural unmanned vehicle and drone swarm collaborative scheduling and path planning system according to claim 1, characterized in that: The central management platform communicates with the unmanned vehicle system and the drone swarm system using a hybrid 5G and LoRa networking technology. The 5G network is used to ensure the rapid transmission of large amounts of data between the central management platform and the drone swarm system and the unmanned vehicle system. The LoRa network is used to realize data interaction within the drone swarm system and between the unmanned vehicle system and surrounding environmental sensing devices.

3. The agricultural unmanned vehicle and drone swarm collaborative scheduling and path planning system according to claim 1, characterized in that: The task allocation module of the central management platform uses an improved Hungarian algorithm for task allocation. The task allocation is based on the type of farmland operation task, the characteristics of the operation area, and the performance parameters of the unmanned vehicle system and the drone swarm system, and takes into account the current working status and remaining power of the equipment to dynamically adjust the task allocation.

4. The agricultural unmanned vehicle and drone swarm collaborative scheduling and path planning system according to claim 1, characterized in that: The path planning module of the central management platform plans globally optimal paths for both the unmanned vehicle system and the drone swarm system. For the drone swarm system, a path planning method based on an improved ant colony algorithm is adopted. This method introduces heuristic information into the traditional ant colony algorithm, comprehensively considering factors such as path length, flight altitude, obstacle avoidance, and farmland operation area coverage to optimize pheromone update rules. For the unmanned vehicle system, based on A... * The algorithm combines farmland terrain slope and soil conditions to plan the global path with the lowest energy consumption and the safest driving, and takes into account the load and turning radius constraints of the unmanned vehicle during the planning process.

5. The agricultural unmanned vehicle and drone swarm collaborative scheduling and path planning system according to claim 1, characterized in that: During the execution of the global path, the unmanned vehicle system and the drone swarm system perceive the surrounding environment in real time through their respective sensor systems. When an obstacle is detected, the Dijkstra algorithm or the artificial potential field method is used for local path replanning to achieve obstacle avoidance. Furthermore, the drone swarm system adopts a distributed obstacle avoidance strategy based on Voronoi diagrams. When a drone detects an obstacle, it shares the obstacle information with other drones through the communication network, and each drone replans its own flight path according to the Voronoi diagram.

6. The agricultural unmanned vehicle and drone swarm collaborative scheduling and path planning system according to claim 1, characterized in that: The navigation system of the unmanned vehicle system is a fusion of high-precision GPS and inertial navigation, with positioning accuracy down to the centimeter level; the operation execution system includes a seeding device, a fertilization device, and a pesticide spraying device; the sensor system includes lidar, cameras, ultrasonic sensors, and soil sensors.

7. The agricultural unmanned vehicle and drone swarm collaborative scheduling and path planning system according to claim 1, characterized in that: The drone swarm system comprises multiple drones of different functional types, including fixed-wing drones for large-scale farmland monitoring and multi-rotor drones for low-altitude precision plant protection; each drone is powered by a lithium battery or hydrogen fuel cell, with some models using solar-assisted power; the navigation system combines satellite navigation and visual navigation; the payload system includes a multispectral camera, a thermal imager, and a pesticide spraying device; and the sensor system includes a barometer, a gyroscope, and a lidar.

8. The agricultural unmanned vehicle and drone swarm collaborative scheduling and path planning system according to claim 1, characterized in that: The monitoring and early warning module of the central management platform monitors the working status of the unmanned vehicle system and the drone swarm system in real time, including equipment location, speed, battery level, operation progress, and sensor data. When equipment malfunctions or operational abnormalities are detected, a timely warning message is issued, and the location of the faulty equipment and the type of malfunction are displayed on the monitoring interface.

9. The agricultural unmanned vehicle and drone swarm collaborative scheduling and path planning system according to claim 1, characterized in that: The collaborative operation process between the unmanned vehicle system and the drone swarm system for crop pest and disease control is as follows: S1. The drone swarm system is equipped with a hyperspectral camera and multi-rotor drones that fly at low altitudes to conduct a comprehensive scan of farmland, identify the areas and severity of pests and diseases, and transmit the data to the central management platform in real time. S2. Based on data analysis results, the central management platform plans the driving path of the unmanned vehicle system, guides it to the pest and disease area, and calculates the required pesticide type, dosage, and application method according to the type and severity of the pest and disease. This information is then simultaneously sent to the unmanned vehicle system and the drone swarm system. S3. The drone swarm system provides real-time navigation assistance to the unmanned vehicle system from the air, ensuring that it accurately reaches the application location. At the same time, it monitors the application effect. If uneven application or missed areas are found, it promptly provides feedback to the unmanned vehicle system for re-spraying.

10. The agricultural unmanned vehicle and drone swarm collaborative scheduling and path planning system according to claim 1, characterized in that: The collaborative scheduling and path planning system for the sowing operation scenario has the following collaborative operation process: S1. The central management platform plans the sowing path of the unmanned vehicle system based on the farmland planting plan and soil conditions, and sends the sowing parameters to the unmanned vehicle system; S2. The unmanned vehicle system travels along the planned path and completes the sowing task using the sowing device; S3. During the sowing process, the drone swarm system monitors the sowing area from the air to check the sowing uniformity. If any missed or overly dense areas are found, the system will promptly report the information to the drone system for adjustment.

Images