Unmanned aerial vehicle task execution comprehensive control system based on AI assistance

Abstract

The invention relates to the technical field of AI control, in particular to an unmanned aerial vehicle task execution comprehensive control system based on AI assistance. The system comprises a flight control unit which is responsible for attitude control, speed control and position control of an unmanned aerial vehicle, and a sensing obstacle avoidance unit which is used for adjusting the flight position according to the type of an obstacle so as to perform real-time obstacle avoidance in the flight process. The trajectory planning unit is used for calculating an optimal flight trajectory according to the task demand and the environment information transmitted by the instruction transceiving unit, and dynamically adjusting the trajectory according to the updated flight position; and the instruction transceiving unit is used for receiving the flight instruction from the ground control station and executing a corresponding flight task. The system can more accurately simulate the obstacle avoidance process, and especially when the obstacle is large, the urgency of collision avoidance and the required obstacle avoidance force are stronger; meanwhile, the unmanned aerial vehicle can more accurately avoid obstacles in a complex environment, and the reliability and flexibility of obstacle avoidance are improved.

Description

Technical Field

[0001] The present invention relates to the field of AI control technology, and in particular to an AI-assisted integrated control system for unmanned aerial vehicle mission execution. Background Art

[0002] With the rapid development of drone technology, its application scenarios are becoming more and more extensive. Drones can be seen in many fields such as civil logistics distribution, agricultural monitoring, and environmental testing. However, with the expansion of the scope of application, the flight environment faced by drones has become more complex and changeable, which puts higher requirements on the safety and reliability of drones. Especially when performing diversified tasks in low-altitude fusion airspace, drones not only need to deal with fixed obstacles such as static buildings and trees, but also face the challenges brought by other dynamic aircraft. Traditional obstacle avoidance algorithms usually assume that all obstacles have similar importance and ignore the differences in collision risks brought by obstacles of different sizes. When encountering larger obstacles, traditional obstacle avoidance strategies may not provide sufficient safety margins, resulting in potential collision hazards. In addition, the flight environment in the real world is often dynamically changing, especially changes in wind speed and wind direction will have a significant impact on the flight trajectory of drones. Some existing obstacle avoidance systems may not fully consider the role of these external factors, so that drones may deviate from the scheduled route or even lose control under strong wind conditions. Therefore, an AI-assisted drone task execution integrated control system is designed. Summary of the invention

[0003] The purpose of the present invention is to provide an AI-assisted integrated control system for UAV mission execution to solve the problem that the traditional obstacle avoidance algorithm proposed in the above background technology usually assumes that all obstacles have similar importance, ignores the differences in collision risks brought about by obstacles of different sizes, and does not fully consider the effects of external factors such as wind speed and wind direction, resulting in the UAV deviating from the planned route or even losing control under strong wind conditions.

[0004] To achieve the above objectives, the present invention provides an AI-assisted integrated control system for UAV mission execution, comprising: A flight control unit, which is responsible for the attitude control, speed control and position control of the UAV, and adjusts flight parameters in real time to cope with different flight states and environmental conditions; Among them, the flight control unit includes an attitude control module, a speed control module and a position control module; A sensing and obstacle avoidance unit, which is used to sense the surrounding environment in real time, analyze environmental data to detect and classify obstacles, adjust the flight position according to the type of obstacles, and then avoid obstacles in real time during flight. The types of obstacles include static obstacles and dynamic obstacles. If it is a static obstacle, a static obstacle avoidance decision is triggered; if it is a dynamic obstacle, a dynamic obstacle avoidance decision is triggered. In the process of static obstacle avoidance decision, the influencing factor of the size of the static obstacle is introduced for optimization, and in the process of dynamic obstacle avoidance decision, the influencing factor of wind speed is introduced for optimization; Among them, the perception and obstacle avoidance unit includes a detection and classification module, an obstacle avoidance module and a data update module; A trajectory planning unit, the trajectory planning unit is used to calculate the optimal flight trajectory according to the mission requirements and environmental information transmitted by the command transceiver unit, and dynamically adjust the trajectory according to the updated flight position; The command transceiver unit is used to receive flight instructions from the ground control station, execute corresponding flight missions, and feedback the real-time flight status and mission path progress of the UAV to the ground control station.

[0005] As a further improvement of the technical solution, in the flight control unit: The attitude control module is used to monitor and adjust the pitch angle, roll angle, and yaw angle of the drone, and to correct the attitude deviation caused by external disturbances in real time; the speed control module is used to control the speed of the drone and adjust the speed according to the emergency situation required by the mission; the position control module is used to calculate and adjust the current position of the drone, dynamically adjust the flight path and target position based on the flight plan or real-time mission requirements, and adjust the path according to environmental changes, so as to track the target position.

[0006] As a further improvement of the technical solution, in the obstacle avoidance sensing unit: The detection and classification module is used to obtain information about the drone's surrounding environment in real time through sensors, detect obstacles and obtain their locations and sizes. If the location of an obstacle exceeds the safety threshold, the motion trajectory is used to determine whether the obstacle is a static obstacle or a dynamic obstacle. The obstacle avoidance module is used to determine whether to implement a static obstacle avoidance strategy or a dynamic obstacle avoidance strategy based on the obstacle type and location and size obtained by the detection and classification module, thereby adjusting the drone's attitude, speed, and position to avoid obstacles. The update data module is used to calculate the flight parameters of the UAV after obstacle avoidance, and feed back the flight parameter results to the flight control unit, thereby updating the flight parameters of the UAV in real time.

[0007] As a further improvement of the technical solution, in the detection and classification module, obstacles are detected and the position and size of the obstacles are obtained, as follows: Obstacle position detection: ; in, The distance from the current position of the drone to the obstacle; is the three-dimensional coordinate of the obstacle; is the current position of the drone; if , the distance between the UAV and the obstacle is less than the safe distance, and the obstacle avoidance module 22 activates the obstacle avoidance signal; The size of the obstacle is detected by combining lidar, ultrasonic sensors and cameras to obtain the size of the obstacle.

[0008] As a further improvement of the present technical solution, in the detection and classification module, the obstacle is judged as a static obstacle or a dynamic obstacle by the motion trajectory. Specifically, if the speed and acceleration are both zero, it is judged as a static obstacle; if the speed is not equal to zero and changes, and the acceleration is not zero and there is a change pattern, it is judged as a dynamic obstacle.

[0009] As a further improvement of the technical solution, the static obstacle avoidance strategy in the obstacle avoidance module is based on the static total force, as follows: Target attraction: ; in, For target attraction; is the attraction coefficient; is the target static obstacle position; is the current position of the drone; Obstacle avoidance for a single static obstacle: ; in, is the obstacle avoidance force of a single static obstacle; is the repulsion coefficient; is the distance between the UAV and the static obstacle; To avoid obstacles; ; in, is the total force on a single static obstacle; Obstacle avoidance for multiple static obstacles: ; in, Obstacle avoidance for multiple static obstacles; For drones and The distance to a static obstacle; For the The obstacle avoidance direction of a static obstacle; is the number of static obstacles; ; ; in, is the total force of multiple static obstacles.

[0010] As a further improvement of the technical solution, in the perception and obstacle avoidance unit, the influencing factor of the size of the static obstacle is introduced in the process of static obstacle avoidance decision-making for optimization, and the optimization is specifically as follows: The effect of obstacle size on attraction: ; in, is the attraction of static obstacles; The effect of obstacle size on the avoidance of a single static obstacle: ; in, is the optimized obstacle avoidance force of a single static obstacle; is the influence coefficient of obstacle size on obstacle avoidance force; is the volume of the obstacle; ; in, is the total force of a single static obstacle after optimization; The effect of obstacle size on the avoidance of multiple static obstacles: ; in, The obstacle avoidance for multiple static obstacles is optimized; For the The volume of the obstacle; ; in, is the total force on multiple static obstacles after optimization.

[0011] As a further improvement of the technical solution, the dynamic obstacle avoidance strategy in the obstacle avoidance module is based on the dynamic total force, as follows: Predicting the location of dynamic obstacles: ; in, For dynamic obstacles at time location; For dynamic obstacles at time location; For dynamic obstacles at time speed; is the time step; For dynamic obstacles at time acceleration; Calculate the distance between the drone and the future position of the dynamic obstacle: ; ; in, is the distance from the current position of the drone to the future position of the dynamic obstacle; Obstacle avoidance based on dynamic obstacles: ; in, is the obstacle avoidance force of dynamic obstacles; is the unit vector from the UAV to the future position of the dynamic obstacle; is the adjustment coefficient of the dynamic obstacle avoidance force; is the predicted speed of the dynamic obstacle; is the current speed of the drone; Total force based on dynamic obstacles: ; in, is the total force on the dynamic obstacle.

[0012] As a further improvement of the technical solution, in the perception and obstacle avoidance unit, the influencing factor of wind speed is introduced in the process of dynamic obstacle avoidance decision-making for optimization, and the optimization is specifically as follows: The effect of wind speed on attraction: ; ; in, The attraction of the optimized dynamic obstacle; is the wind speed vector; is the optimized wind speed vector; is the adjustment coefficient of wind speed influence factor; The influence of wind speed on obstacle avoidance: ; in, The obstacle avoidance capability for optimized dynamic obstacles; The total force based on the dynamic obstacle is: ; in, is the total force on the optimized dynamic obstacle.

[0013] As a further improvement of the technical solution, the update data module is specifically as follows: Posture Adjustment: ; in, The total torque required for attitude adjustment; is the gain coefficient of the guiding force; is the total force, ; is the unit vector of the force direction; is the gain factor of gyro feedback; is the current attitude angular rate; Speed ​​adjustment: ; in, Adjusted flight speed for drones; is the current speed of the drone; is the speed gain coefficient; For target attraction, ; To avoid obstacles, ; is the environmental factor; Path Adjustment: ; in, is the adjusted flight position; is the current flight position; is the unit vector in the target direction.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. In this AI-assisted integrated control system for UAV mission execution, the obstacle avoidance process can be simulated more accurately by introducing the influence of obstacle volume and wind speed during the obstacle avoidance process. Especially when the obstacle is large, the urgency of avoiding collision and the required obstacle avoidance force will be stronger; at the same time, the UAV can avoid obstacles more accurately in complex environments, especially when the wind speed and wind direction are uncertain, thereby improving the reliability and flexibility of obstacle avoidance.

[0015] 2. In this AI-assisted integrated control system for drone mission execution, the obstacle avoidance module adopts the most appropriate obstacle avoidance strategy according to the specific type of obstacle, and the data update module continuously collects the latest location information and feeds it back to other system components, so that the entire flight control system can respond to environmental changes in real time and dynamically adjust the flight plan, thereby improving the drone's mission execution efficiency and success rate. It not only enhances the drone's ability to respond to emergencies, but also greatly reduces the risk of collision, laying a solid foundation for achieving more intelligent and reliable unmanned flight. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is the overall flow chart of the present invention; The meaning of each number in the figure is: 1. Flight control unit; 11. Attitude control module; 12. Speed ​​control module; 13. Position control module; 2. Perception and obstacle avoidance unit; 21. Detection and classification module; 22. Obstacle avoidance module; 23. Update data module; 3. Trajectory planning unit; 4. Command transceiver unit. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0018] See also Figure 1 As shown, an integrated control system for UAV mission execution based on AI assistance is provided, including: a flight control unit 1, a perception and obstacle avoidance unit 2, a trajectory planning unit 3 and a command transceiver unit 4; The flight control unit 1 transmits the flight parameters of the aircraft to the obstacle avoidance module 22 and the trajectory planning unit 3; the obstacle avoidance module 22 performs obstacle avoidance according to the flight data, and transmits the obstacle avoidance completion data to the update data module 23, and the update data module 23 transmits the real-time updated flight parameters back to the flight control unit 1; When receiving a new destination from the ground station, the command transceiver unit 4 will transmit the relevant information from the starting point to the end point to the trajectory planning unit 3. After completing the path planning, the trajectory planning unit 3 will hand over the detailed flight plan (the specific position, speed and attitude requirements that should be reached at each moment) to the flight control unit 1 for execution. In the actual flight process, due to factors such as wind speed changes and GPS signal fluctuations, deviations may occur. At this time, the trajectory planning unit 3 needs to continuously receive updated flight position information and modify the original plan in a timely manner to ensure the smooth completion of the overall mission; at the same time, the command transceiver unit 4 will continue to receive the flight status of the flight control unit 1. The specific steps are as follows: The flight control unit 1 is responsible for the attitude control, speed control and position control of the UAV, and adjusts the flight parameters (such as thrust, control input, etc.) in real time to cope with different flight states and environmental conditions; The flight control unit 1 includes an attitude control module 11, a speed control module 12 and a position control module 13; In flight control unit 1: The attitude control module 11 is used to monitor and adjust the pitch angle, roll angle, and yaw angle of the drone, and to correct attitude deviations caused by external disturbances (such as wind speed, airflow, etc.) in real time to maintain flight stability; The speed control module 12 is used to control the speed of the drone, including the forward speed, lateral speed and vertical speed, and adjust the speed according to the emergency situation of the mission requirements to ensure the efficiency and safety of the flight; when adjusting the flight speed, the dynamic characteristics of the aircraft, environmental conditions (such as wind speed) and mission requirements are considered; The position control module 13 is used to calculate and adjust the current position of the drone to ensure that it reaches the target position accurately, dynamically adjust the flight path and target position based on the flight plan or real-time mission requirements, and adjust the path according to environmental changes (such as obstacles, wind speed, etc.) to track the target position; The obstacle avoidance sensing unit 2 is used to sense the surrounding environment (obstacles, dynamic objects, terrain, etc.) in real time, analyze environmental data to detect and classify obstacles, adjust the flight position according to the type of obstacles, and then avoid obstacles in real time during flight. The types of obstacles include static obstacles and dynamic obstacles. If it is a static obstacle, a static obstacle avoidance decision is triggered; if it is a dynamic obstacle, a dynamic obstacle avoidance decision is triggered. In the process of static obstacle avoidance decision, the influencing factor of the size of the static obstacle is introduced for optimization, and in the process of dynamic obstacle avoidance decision, the influencing factor of the wind speed is introduced for optimization; The perception obstacle avoidance unit 2 includes a detection and classification module 21, an obstacle avoidance module 22 and a data update module 23; The detection and classification module 21 is used to obtain information about the environment around the drone in real time through sensors (such as laser radar, ultrasound, camera, etc.), detect obstacles and obtain the position and size of the obstacles. If the position of the obstacle exceeds the safety threshold, it is determined whether the obstacle is a static obstacle or a dynamic obstacle through the motion trajectory; In the detection and classification module 21, obstacles are detected and the position and size of the obstacles are obtained, as follows: Obstacle position detection: ; in, The distance from the current position of the drone to the obstacle; is the three-dimensional coordinate of the obstacle; is the current position of the drone; if , the distance between the UAV and the obstacle is less than the safe distance, and the obstacle avoidance module 22 activates the obstacle avoidance signal; The size of the obstacle is detected by combining lidar, ultrasonic sensors and cameras to obtain the size of the obstacle.

[0019] For long distances and complex environments, the use of lidar, especially in complex outdoor environments, can provide high-precision obstacle detection; for close-range obstacle detection, if the drone mainly performs close-range obstacle avoidance, especially when flying at low altitudes or in a small range, ultrasonic sensors are an ideal choice; for indoor flights or low-cost applications, cameras and computer vision can be used to obtain the size and position of obstacles through image processing technology, which is especially suitable for indoor flights or cost-sensitive applications.

[0020] In the detection and classification module 21, the obstacle is determined to be a static obstacle or a dynamic obstacle by the motion trajectory. Specifically, if the speed and acceleration are both zero, it is determined to be a static obstacle; if the speed is not equal to zero and changes, and the acceleration is not zero and changes regularly, it is determined to be a dynamic obstacle; The obstacle avoidance module 22 is used to determine whether to execute a static obstacle avoidance strategy or a dynamic obstacle avoidance strategy according to the obstacle type and the location and size of the obstacle obtained by the detection and classification module 21, so as to adjust the attitude, speed and position of the drone to avoid obstacles; The static obstacle avoidance strategy in the obstacle avoidance module 22 is based on the static total force, as follows: Target attraction: ; in, For target attraction; is the attraction coefficient, which determines the strength of the flying target; is the target static obstacle position; is the current position of the drone; Obstacle avoidance for a single static obstacle: ; in, is the obstacle avoidance force of a single static obstacle; is the repulsion coefficient, which controls the obstacle avoidance reaction strength; is the distance between the UAV and the static obstacle; is the obstacle avoidance direction, which represents the unit vector pointing from the drone to the obstacle; ; in, is the total force on a single static obstacle; Obstacle avoidance for multiple static obstacles: ; in, Obstacle avoidance for multiple static obstacles; For drones and The distance to a static obstacle; For the The obstacle avoidance direction of a static obstacle; is the number of static obstacles; ; ; in, is the total force on multiple static obstacles; This mechanism ensures that even in the presence of multiple static obstacles, the drone can reach its destination along the optimal path. At the same time, the obstacle avoidance force generated by a single or multiple static obstacles follows the inverse square law, that is, the obstacle avoidance force gradually decreases as the distance increases, which helps to avoid unnecessary large turns or decelerations and improves flight efficiency. According to the obstacle type and location information provided by the detection and classification module 21, a static or dynamic obstacle avoidance strategy is intelligently selected, and the attitude, speed and position of the drone are adjusted accordingly to ensure safe flight. In particular, for static obstacles, a method based on potential field theory is used to calculate the obstacle avoidance force. This method is not only simple and intuitive, but also can effectively simulate the physical laws of nature, making the behavior of the drone more in line with human intuition, thereby improving the reliability and safety of the system.

[0021] In the perception and obstacle avoidance unit 2, the influencing factor of the size of the static obstacle is introduced in the static obstacle avoidance decision process for optimization. The optimization is as follows: The effect of obstacle size on attraction: ; in, is the attraction of a static obstacle; this attraction is not affected by the size of the obstacle; The effect of obstacle size on the avoidance of a single static obstacle: ; in, is the optimized obstacle avoidance force of a single static obstacle; is the influence coefficient of obstacle size on obstacle avoidance force; is the volume of the obstacle; the larger the volume, the stronger the obstacle avoidance, even at a greater distance; ; in, is the total force of a single static obstacle after optimization; The effect of obstacle size on the avoidance of multiple static obstacles: ; in, The obstacle avoidance for multiple static obstacles is optimized; For the The volume of the obstacle; ; in, is the total force of multiple static obstacles after optimization; Existing technologies usually ignore the size of obstacles and focus mainly on distance and direction. In practical applications, large obstacles may require stronger avoidance response even at a longer distance. By introducing a combination of obstacle volume (or area) and distance, the obstacle avoidance process can be simulated more accurately, especially when the obstacle is large, the urgency of avoiding collision and the required avoidance force will be stronger; By adjusting the coefficient of the size factor , can flexibly control the impact of obstacle size on obstacle avoidance strategy. For different types of missions (such as urban flight, forest flight, etc.), this coefficient can be adjusted according to environmental requirements to provide a more adaptive obstacle avoidance solution.

[0022] The dynamic obstacle avoidance strategy in the obstacle avoidance module 22 is based on the dynamic total force, as follows: Predicting the location of dynamic obstacles: ; in, For dynamic obstacles at time location; For dynamic obstacles at time location; For dynamic obstacles at time speed; is the time step; For dynamic obstacles at time acceleration; this predictive capability enables the drone to plan obstacle avoidance paths in advance in dynamic environments, avoiding the risk of collision due to sudden obstacles.

[0023] Calculate the distance between the drone and the future position of the dynamic obstacle: ; ; in, is the distance from the current position of the drone to the future position of the dynamic obstacle; it helps to determine the most appropriate obstacle avoidance solution, ensuring that the drone can avoid obstacles while maintaining an efficient mission execution path. In addition, considering the motion characteristics in three-dimensional space, this method can adapt to changes at different height levels, enhancing the flexibility and adaptability of the system.

[0024] Obstacle avoidance based on dynamic obstacles: ; in, is the obstacle avoidance force of dynamic obstacles; is the unit vector from the UAV to the future position of the dynamic obstacle, indicating the obstacle avoidance direction; is the adjustment coefficient of the dynamic obstacle avoidance force, which determines the contribution of the speed difference to the obstacle avoidance force; is the predicted speed of the dynamic obstacle; is the current speed of the drone. It not only takes the distance factor into account, but also adds the speed difference term, so that the drone can make a faster and more accurate response based on the relative speed between itself and the obstacle, thereby improving the efficiency and safety of obstacle avoidance.

[0025] Total force based on dynamic obstacles: ; in, is the total force on dynamic obstacles; integrating obstacle avoidance logic into the overall path planning process enables the drone to maintain stability and continuity in complex and changing environments, and to make appropriate adjustments quickly even in the face of unforeseen situations.

[0026] In the perception and obstacle avoidance unit 2, the influencing factor of wind speed is introduced in the process of dynamic obstacle avoidance decision-making for optimization. After optimization, the specific results are: The effect of wind speed on attraction: ; ; in, The attraction of the optimized dynamic obstacle; is the wind speed vector; The optimized wind speed vector takes into account the long-term impact of wind speed changes on the flight trajectory; is the adjustment coefficient of the wind speed influencing factor, which can be adjusted according to environmental conditions; the optimized dynamic obstacle avoidance strategy will enable the drone to adjust the obstacle avoidance strategy more sensitively in an environment with large wind speed changes, thereby reducing the risk of collision with obstacles.

[0027] The influence of wind speed on obstacle avoidance: ; in, The obstacle avoidance capability for optimized dynamic obstacles; The total force based on the dynamic obstacle is: ; in, is the total force of the optimized dynamic obstacle; By introducing the influence of wind speed on dynamic obstacle avoidance, the optimized dynamic obstacle avoidance strategy enables the drone to avoid obstacles more accurately in complex environments, especially when the wind speed is uncertain. The optimization of wind speed not only affects the relative speed between the drone and the obstacle, but also adjusts the size and direction of the obstacle avoidance force, improving the reliability and flexibility of obstacle avoidance.

[0028] The update data module 23 is used to calculate the flight parameters of the UAV after obstacle avoidance, and feed back the flight parameter results to the flight control unit 1, thereby updating the flight parameters of the UAV in real time; Update data module 23, as follows: Posture Adjustment: ; in, The total torque required for attitude adjustment (used to adjust the pitch, roll, and yaw angles of the drone); is the gain coefficient of the guiding force; is the total force, the calculated combined force between the drone, the target and the obstacle, ; is the unit vector of the force direction (from the drone to the target or obstacle avoidance direction); is the gain factor of gyro feedback; The current attitude angular rate is used to prevent overshoot and improve system stability; Speed ​​adjustment: ; in, Adjusted flight speed for drones; is the current speed of the drone; is the speed gain coefficient, which is used to adjust the adjustment range of the flight speed; For target attraction, ; To avoid obstacles, ; The environmental factor takes into account the impact of environmental factors (such as wind speed, airflow, etc.) and dynamically adjusts the flight speed as the environment changes; Path Adjustment: ; in, is the adjusted flight position; is the current flight position; is the unit vector in the target direction; the effects of the target attraction and obstacle avoidance are comprehensively considered, so that the drone can move towards the predetermined target while avoiding obstacles. In addition, due to the introduction of the time step ,The algorithm supports continuous time series prediction, which can better simulate the motion process in the real world, and provide the UAV with a smoother and reasonable flight trajectory.

[0029] The trajectory planning unit 3 is used to calculate the optimal flight trajectory according to the mission requirements and environmental information transmitted by the instruction transceiver unit 4, and dynamically adjust the trajectory according to the updated flight position; The trajectory planning unit 3 supports dynamic adjustment functions. When the drone receives a new flight position update, it can immediately re-evaluate the existing trajectory and make corresponding modifications based on the latest information. This capability enables the drone to perform well even in unknown or semi-structured environments, significantly enhancing its autonomy and intelligence. For example, when encountering emergencies such as sudden air traffic control areas or temporarily established no-fly zones, the drone can quickly adjust its route to avoid violations while minimizing the impact on the original plan.

[0030] The command transceiver unit 4 is used to receive flight instructions from the ground control station, execute the corresponding flight mission, and feedback the real-time flight status and mission path progress of the UAV to the ground control station; the command transceiver unit 4 plays the role of a bridge between the ground control station and the UAV. On the one hand, it receives flight instructions from the ground control station and ensures that these instructions are accurately conveyed to the UAV so that the latter can perform the mission according to the predetermined plan; on the other hand, the command transceiver unit also feeds back the real-time flight status and mission path progress of the UAV to the ground control station, so that the operator can keep track of the mission execution at any time and intervene or adjust when necessary.

[0031] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only preferred examples of the present invention, and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. An AI-assisted integrated control system for UAV mission execution, characterized in that: include: A flight control unit (1), the flight control unit (1) being responsible for attitude control, speed control and position control of the UAV, and adjusting flight parameters in real time to cope with different flight states and environmental conditions; The flight control unit (1) comprises an attitude control module (11), a speed control module (12) and a position control module (13); A sensing obstacle avoidance unit (2), the sensing obstacle avoidance unit (2) being used to sense the surrounding environment in real time, and simultaneously analyzing environmental data to detect and classify obstacles, and adjusting the flight position according to the type of obstacle so as to avoid obstacles in real time during flight, wherein the types of obstacles include static obstacles and dynamic obstacles, and if it is a static obstacle, a static obstacle avoidance decision is triggered; if it is a dynamic obstacle, a dynamic obstacle avoidance decision is triggered, and in the process of static obstacle avoidance decision, an influencing factor of the size of the static obstacle is introduced for optimization, and in the process of dynamic obstacle avoidance decision, an influencing factor of the wind speed is introduced for optimization; The perception and obstacle avoidance unit (2) includes a detection and classification module (21), an obstacle avoidance module (22) and a data update module (23); A trajectory planning unit (3), the trajectory planning unit (3) being used to calculate an optimal flight trajectory according to mission requirements and environmental information transmitted by the command transceiver unit (4), and dynamically adjust the trajectory according to an updated flight position; A command transceiver unit (4) is used to receive flight instructions from a ground control station, execute corresponding flight tasks, and feed back the real-time flight status and task path progress of the UAV to the ground control station.

2. The AI-assisted UAV task execution integrated control system according to claim 1 is characterized in that: The flight control unit (1) comprises: The attitude control module (11) is used to monitor and adjust the pitch angle, roll angle and yaw angle of the UAV, and to correct attitude deviations caused by external disturbances in real time; the speed control module (12) is used to control the speed of the UAV, and to adjust the speed according to the emergency situation required by the mission; the position control module (13) is used to calculate and adjust the current position of the UAV, dynamically adjust the flight path and target position based on the flight plan or real-time mission requirements, and adjust the path according to environmental changes, so as to track the target position.

3. The AI-assisted UAV task execution integrated control system according to claim 2 is characterized in that: In the obstacle avoidance sensing unit (2): The detection and classification module (21) is used to obtain information about the environment around the drone in real time through sensors, detect obstacles and obtain the position and size of the obstacles. If the position of the obstacle exceeds a safety threshold, it is determined whether the obstacle is a static obstacle or a dynamic obstacle through the motion trajectory. The obstacle avoidance module (22) is used to determine whether to execute a static obstacle avoidance strategy or a dynamic obstacle avoidance strategy based on the obstacle type and the location and size of the obstacle obtained by the detection and classification module (21), thereby adjusting the attitude, speed and position of the drone to avoid the obstacle; The data update module (23) is used to calculate the flight parameters of the UAV after obstacle avoidance, and feed back the flight parameter results to the flight control unit (1), thereby updating the flight parameters of the UAV in real time.

4. The AI-assisted UAV task execution integrated control system according to claim 3 is characterized by: In the detection and classification module (21), obstacles are detected and the position and size of the obstacles are obtained, as follows: Obstacle position detection: ； in, The distance from the current position of the drone to the obstacle; is the three-dimensional coordinate of the obstacle; is the current position of the drone; if , the distance between the UAV and the obstacle is less than the safe distance, and the obstacle avoidance module (22) activates the obstacle avoidance signal; The size of the obstacle is detected by combining lidar, ultrasonic sensors and cameras to obtain the size of the obstacle.

5. The AI-assisted UAV task execution integrated control system according to claim 4 is characterized in that: In the detection and classification module (21), whether the obstacle is a static obstacle or a dynamic obstacle is determined by the motion trajectory. Specifically, if the speed and acceleration are both zero, it is determined to be a static obstacle; if the speed is not equal to zero and changes, and the acceleration is not zero and has a changing pattern, it is determined to be a dynamic obstacle.

6. The AI-assisted UAV task execution integrated control system according to claim 5 is characterized in that: The static obstacle avoidance strategy in the obstacle avoidance module (22) is based on the static total force, which is as follows: Target attraction: ； in, For target attraction; is the attraction coefficient; is the target static obstacle position; is the current position of the drone; Obstacle avoidance for a single static obstacle: ； in, is the obstacle avoidance force of a single static obstacle; is the repulsion coefficient; is the distance between the UAV and the static obstacle; To avoid obstacles; ； in, is the total force on a single static obstacle; Obstacle avoidance for multiple static obstacles: ； in, Obstacle avoidance for multiple static obstacles; For drones and The distance to a static obstacle; For the The obstacle avoidance direction of a static obstacle; is the number of static obstacles; ; ； in, is the total force of multiple static obstacles.

7. The AI-assisted UAV task execution integrated control system according to claim 6 is characterized in that: In the obstacle avoidance sensing unit (2), the influencing factor of the size of the static obstacle is introduced in the static obstacle avoidance decision process for optimization. After optimization, the specific results are: The effect of obstacle size on attraction: ； in, is the attraction of static obstacles; The effect of obstacle size on the avoidance of a single static obstacle: ； in, is the optimized obstacle avoidance force of a single static obstacle; is the influence coefficient of obstacle size on obstacle avoidance force; is the volume of the obstacle; ； in, is the total force of a single static obstacle after optimization; The effect of obstacle size on the avoidance of multiple static obstacles: ； in, The obstacle avoidance for multiple static obstacles is optimized; For the The volume of the obstacle; ； in, is the total force on multiple static obstacles after optimization.

8. The AI-assisted UAV task execution integrated control system according to claim 7 is characterized in that: The dynamic obstacle avoidance strategy in the obstacle avoidance module (22) is based on the dynamic total force, which is as follows: Predicting the location of dynamic obstacles: ； in, For dynamic obstacles at time location; For dynamic obstacles at time location; For dynamic obstacles at time speed; is the time step; For dynamic obstacles at time acceleration; Calculate the distance between the drone and the future position of the dynamic obstacle: ； ； in, is the distance from the current position of the drone to the future position of the dynamic obstacle; Obstacle avoidance based on dynamic obstacles: ； in, is the obstacle avoidance force of dynamic obstacles; is the unit vector from the UAV to the future position of the dynamic obstacle; is the adjustment coefficient of the dynamic obstacle avoidance force; is the predicted speed of the dynamic obstacle; is the current speed of the drone; Total force based on dynamic obstacles: ； in, is the total force on the dynamic obstacle.

9. The AI-assisted UAV task execution integrated control system according to claim 8, characterized in that: In the obstacle avoidance sensing unit (2), the influencing factor of wind speed is introduced to optimize the dynamic obstacle avoidance decision process, and the optimization is as follows: The effect of wind speed on attraction: ; ； in, The attraction of the optimized dynamic obstacle; is the wind speed vector; is the optimized wind speed vector; is the adjustment coefficient of wind speed influence factor; The influence of wind speed on obstacle avoidance: ； in, The obstacle avoidance capability for optimized dynamic obstacles; The total force based on the dynamic obstacle is: ； in, is the total force on the optimized dynamic obstacle.

10. The AI-assisted UAV mission execution integrated control system according to claim 9, characterized in that: The update data module (23) is specifically as follows: Posture Adjustment: ； in, The total torque required for attitude adjustment; is the gain coefficient of the guiding force; is the total force, ; is the unit vector of the force direction; is the gain factor of gyro feedback; is the current attitude angular rate; Speed ​​adjustment: ； in, Adjusted flight speed for drones; is the current speed of the drone; is the speed gain coefficient; For target attraction, ; To avoid obstacles, ; is the environmental factor; Path Adjustment: ； in, is the adjusted flight position; is the current flight position; is the unit vector in the target direction.

Images