Unmanned aerial vehicle autonomous control system and control method

Abstract

The invention provides an unmanned aerial vehicle autonomous control system and control method, and relates to the technical field of unmanned aerial vehicle control. The unmanned aerial vehicle autonomous control system comprises a control module used for receiving flight state information of an unmanned aerial vehicle; the sensing module is connected with the control module and used for collecting the surrounding environment information of the unmanned aerial vehicle; the data processing module is connected with the sensing module, receives and processes the environment information, integrates different sensor data through a data fusion algorithm, and analyzes the processed data through a deep learning algorithm so as to extract environment key features; the decision module is connected with the data processing module and is used for generating a flight decision according to the analysis result in combination with a preset task target and a flight rule; and the control execution module receives the instruction of the decision module and converts the instruction into a flight control action of the unmanned aerial vehicle. According to the invention, the autonomous flight ability, task execution efficiency and flight safety of the unmanned aerial vehicle in a complex environment can be significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle control, and in particular to an unmanned aerial vehicle autonomous control system and a control method. Background Art

[0002] Unmanned aircraft, also known as "drones", are unmanned aircraft that are controlled by radio remote control equipment and self-contained program control devices. There is no cockpit on the aircraft, but it is equipped with autopilots, program control devices and other equipment. Personnel on the ground, on ships or at the remote control station of the mother aircraft use radar and other equipment to track, locate, remotely control, telemeter and digitally transmit it. It can take off like an ordinary aircraft or be launched into the air with a booster rocket under radio remote control, or it can be taken into the air by the mother aircraft for flight. When recovered, it can land automatically in the same way as an ordinary aircraft landing process, or it can be recovered by remote control with a parachute or a blocking net. It can be used repeatedly many times. It is widely used in aerial reconnaissance, surveillance, communication, anti-submarine, electronic interference, etc.

[0003] With the rapid development of drone technology, its application areas are constantly expanding. However, existing drone control systems still have many deficiencies in terms of autonomy, intelligence, and the ability to cope with complex environments. For example, in terms of environmental perception, some drones have difficulty accurately identifying complex terrain and obstacles, leading to flight safety hazards; in terms of path planning, the planning algorithms of traditional systems are often not flexible and efficient enough, and cannot adapt well to dynamically changing mission requirements and environmental conditions. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the deficiencies in the prior art, the present invention provides an autonomous control system and a control method for a UAV, which solve the problems raised by the above-mentioned background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an autonomous control system for unmanned aerial vehicles, comprising:

[0008] A control module, used to receive the flight status information of the UAV;

[0009] The perception module is connected to the control module and is used to collect information about the surrounding environment of the drone;

[0010] A data processing module is connected to the perception module, receives and processes the environmental information, integrates data from different sensors through a data fusion algorithm, and uses a deep learning algorithm to analyze the processed data to extract key environmental features;

[0011] A decision module, connected to the data processing module, generates a flight decision based on the analysis results combined with preset mission objectives and flight rules;

[0012] The control execution module receives the instructions from the decision module and converts them into flight control actions of the UAV, accurately controlling the motor speed and steering gear angle of the UAV to achieve attitude adjustment and position movement.

[0013] Preferably, the perception module includes a laser radar, a visual camera and an ultrasonic sensor, the laser radar is used for long-distance terrain mapping and obstacle detection, the visual camera is used for image acquisition and recognition analysis, and the ultrasonic sensor is used for close-range obstacle detection.

[0014] Preferably, the data processing module uses a high-performance processor that has the ability to quickly run complex algorithm models to deeply understand and judge environmental information. The sensor data includes two-dimensional images, three-dimensional images, point clouds, and environmental perception data;

[0015] Specifically, the calculation method of the data fusion algorithm is:

[0016] And meet

[0017] Among them, there are n data sources in total, the data provided by the i-th data source is Xi, and its corresponding weight is Wi, then the fused result is x.

[0018] Preferably, the decision module adopts an intelligent decision algorithm, which can continuously learn and optimize the decision process according to environmental changes and task requirements. The intelligent decision algorithm includes:

[0019] The path planning algorithm is used to plan the flight path of the UAV according to the environmental information. Specifically, the calculation formula of the path planning algorithm is:

[0020] f(n)=g(n)+h(n)

[0021] Where n is a node in the path, f(n) is the comprehensive evaluation value of node n, g(n) is the actual cost from the starting point to node n, and h(n) is the heuristic estimated cost from node n to the target point;

[0022] The obstacle avoidance algorithm is used to adjust the flight path when encountering obstacles in the flight path. Specifically, the calculation formula of the obstacle avoidance algorithm is:

[0023]

[0024] Among them, the distance between the UAV and the i-th obstacle after the UAV moves at a speed of (v, w) for time t is di, and dmin is the minimum distance between the UAV and all obstacles.

[0025] Preferably, the control execution module adopts a high-precision control algorithm and a fast-response actuator, and has anti-interference capabilities to ensure stable and accurate flight of the drone under complex conditions. The control execution module includes:

[0026] at least one motor controller for controlling the operation of the motor of the drone;

[0027] At least one servo controller, used to control the operation of the servo of the drone.

[0028] The present invention further discloses a method for autonomous control of a drone, based on the autonomous control system of the drone as described above, comprising the following steps:

[0029] Step 1: Environmental Perception:

[0030] The environmental data is collected simultaneously through the laser radar, visual camera and ultrasonic sensor in the perception module, and transmitted to the data processing module after pre-processing;

[0031] Step 2: Data fusion and analysis:

[0032] The data processing module fuses the pre-processed data from different sensors and uses the deep learning model to extract features and understand the environment of the fused data;

[0033] Step 3: Decision making:

[0034] The decision module uses a multi-objective optimization algorithm to generate the optimal flight decision based on the environmental analysis results provided by the data processing module, combined with the preset mission planning and flight constraints;

[0035] Step 4: Control execution:

[0036] The control execution module receives instructions from the decision-making module, converts them into specific control signals, drives the UAV power system and flight control surfaces, and forms a closed-loop control based on the actual flight status information of the UAV to achieve autonomous flight control.

[0037] Preferably, in step one, the preprocessing includes data cleaning and filtering operations.

[0038] Preferably, in step 2, a convolutional neural network is used to perform target recognition on visual images, and a recurrent neural network is used to perform time series analysis on multiple frames of data.

[0039] (III) Beneficial effects

[0040] The present invention provides an autonomous control system and control method for a drone, which have the following beneficial effects:

[0041] 1. The present invention significantly improves the autonomous flight capability of drones by integrating advanced perception, data processing, decision-making and control execution modules. Compared with traditional drones, the drones of the present invention can perceive the surrounding environment more accurately and respond quickly to complex and changeable flight missions, thereby showing higher efficiency and safety when performing reconnaissance, surveillance, search and rescue and other tasks.

[0042] 2. The autonomous control system of the drone of the present invention uses deep learning algorithms in the data processing module, which can extract key features from a large amount of sensor data and achieve a deep understanding of the environment. This not only improves the drone's ability to identify complex terrain and obstacles, but also enhances its adaptability and flexibility in performing tasks.

[0043] 3. By adopting intelligent decision-making algorithms, the drone of the present invention can dynamically adjust the flight path according to real-time environmental changes and mission requirements, effectively avoid obstacles, and ensure flight safety. At the same time, the application of multi-objective optimization algorithms enables drones to consider multiple factors at the same time when performing tasks, such as energy consumption, time, risk, etc., so as to make more reasonable flight decisions.

[0044] 4. The high-precision control algorithm and fast-response actuator of the control execution module ensure the stable flight of the UAV in complex environments. The UAV can adjust the motor speed and servo angle in real time according to the flight status information to achieve precise attitude control and position movement, which is of great significance for performing high-precision tasks such as aerial photography and precise delivery.

[0045] In summary, the UAV autonomous control system and control method of the present invention, by comprehensively using advanced perception technology, data processing technology, intelligent decision-making algorithm and high-precision control technology, significantly improves the autonomous flight capability of the UAV, and opens up a new path for the development and application of UAV technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of a control system of the present invention;

[0047] Figure 2 It is a schematic diagram of sensor data of the present invention;

[0048] Figure 3 It is a schematic diagram of the implementation flow of the obstacle avoidance algorithm of the present invention;

[0049] Figure 4 It is a schematic diagram of a control execution module of the present invention;

[0050] Figure 5It is a schematic flow chart of the control method of the present invention. DETAILED DESCRIPTION

[0051] 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.

[0052] Embodiment 1:

[0053] like Figure 1 As shown, an embodiment of the present invention provides an autonomous control system for a drone, comprising:

[0054] A control module, used to receive the flight status information of the UAV;

[0055] The perception module is connected to the control module and is used to collect information about the surrounding environment of the drone;

[0056] The data processing module is connected to the perception module to receive and process environmental information, integrate different sensor data through data fusion algorithms, and use deep learning algorithms to analyze the processed data to extract key environmental features;

[0057] The decision module is connected to the data processing module and generates flight decisions based on the analysis results combined with the preset mission objectives and flight rules;

[0058] The control execution module receives instructions from the decision-making module and converts them into flight control actions of the UAV, accurately controlling the motor speed and servo angle of the UAV to achieve attitude adjustment and position movement.

[0059] like Figure 5 As shown, an embodiment of the present invention further provides a method for autonomous control of a drone, based on the above-mentioned autonomous control system of a drone, comprising the following steps:

[0060] Step 1: Environmental Perception:

[0061] The environmental data is collected simultaneously through the laser radar, visual camera and ultrasonic sensor in the perception module, and transmitted to the data processing module after pre-processing;

[0062] Step 2: Data fusion and analysis:

[0063] The data processing module fuses the pre-processed data from different sensors and uses the deep learning model to extract features and understand the environment of the fused data;

[0064] Step 3: Decision making:

[0065] The decision module uses a multi-objective optimization algorithm to generate the optimal flight decision based on the environmental analysis results provided by the data processing module, combined with the preset mission planning and flight constraints;

[0066] Step 4: Control execution:

[0067] The control execution module receives instructions from the decision-making module, converts them into specific control signals, drives the UAV power system and flight control surfaces, and forms a closed-loop control based on the actual flight status information of the UAV to achieve autonomous flight control.

[0068] Embodiment 2:

[0069] like Figure 1-Figure 4 As shown, an embodiment of the present invention provides an autonomous control system for a drone, comprising:

[0070] A control module, used to receive the flight status information of the UAV;

[0071] The perception module is connected to the control module and is used to collect information about the drone's surrounding environment. Specifically, the perception module includes a laser radar, a visual camera, and an ultrasonic sensor. The laser radar is used for long-distance terrain mapping and obstacle detection, the visual camera is used for image acquisition and recognition analysis, and the ultrasonic sensor is used for close-range obstacle detection.

[0072] The data processing module is connected to the perception module, receives and processes environmental information, integrates different sensor data through data fusion algorithms, and uses deep learning algorithms to analyze the processed data to extract key environmental features. Specifically, the data processing module uses a high-performance processor that has the ability to quickly run complex algorithm models to deeply understand and judge environmental information. Secondly, sensor data includes two-dimensional images, three-dimensional images, point clouds, and environmental perception data;

[0073] Specifically, the calculation method of the data fusion algorithm is:

[0074] And meet

[0075] There are n data sources in total, the data provided by the i-th data source is Xi, and its corresponding weight is Wi, then the fusion result is x;

[0076] The decision module is connected to the data processing module and generates flight decisions based on the analysis results combined with the preset mission objectives and flight rules. Specifically, the decision module adopts an intelligent decision algorithm that can continuously learn and optimize the decision process according to environmental changes and mission requirements. The intelligent decision algorithm includes:

[0077] The path planning algorithm is used to plan the flight path of the UAV according to the environmental information. Specifically, the calculation formula of the path planning algorithm is:

[0078] f(n)=g(n)+h(n)

[0079] Where n is a node in the path, f(n) is the comprehensive evaluation value of node n, g(n) is the actual cost from the starting point to node n, and h(n) is the heuristic estimated cost from node n to the target point;

[0080] The obstacle avoidance algorithm is used to adjust the flight path when encountering obstacles in the flight path. Specifically, the calculation formula of the obstacle avoidance algorithm is:

[0081]

[0082] Among them, the distance between the UAV and the ith obstacle after the UAV moves at the speed (v, w) for time t is di, and dmin is the minimum distance between the UAV and all obstacles;

[0083] Specifically, the distance between the drone and the obstacle after the drone moves at a preset speed for a period of time is determined by the minimum distance, thereby effectively ensuring that the flight efficiency can be maximized while avoiding obstacles.

[0084] The control execution module receives the instructions from the decision module and converts them into flight control actions of the UAV, accurately controls the motor speed and servo angle of the UAV to achieve attitude adjustment and position movement. Specifically, the control execution module adopts high-precision control algorithms and fast-response actuators, and has anti-interference capabilities to ensure stable and accurate flight of the UAV under complex conditions. The control execution module includes:

[0085] at least one motor controller for controlling the operation of the motor of the drone;

[0086] At least one servo controller, used to control the operation of the servo of the drone.

[0087] like Figure 5 As shown, an embodiment of the present invention further provides a method for autonomous control of a drone, based on the above-mentioned autonomous control system of a drone, comprising the following steps:

[0088] Step 1: Environmental Perception:

[0089] Environmental data is collected simultaneously through the laser radar, visual camera and ultrasonic sensor in the perception module, and transmitted to the data processing module after preprocessing, where the preprocessing includes data cleaning and filtering operations;

[0090] Step 2: Data fusion and analysis:

[0091] The data processing module fuses the pre-processed data from different sensors and uses a deep learning model to extract features and understand the environment of the fused data. Specifically, it uses a convolutional neural network to identify targets in visual images and a recurrent neural network to perform time series analysis on multiple frames of data.

[0092] Step 3: Decision making:

[0093] The decision module uses a multi-objective optimization algorithm to generate the optimal flight decision based on the environmental analysis results provided by the data processing module, combined with the preset mission planning and flight constraints;

[0094] Step 4: Control execution:

[0095] The control execution module receives instructions from the decision-making module, converts them into specific control signals, drives the UAV power system and flight control surfaces, and forms a closed-loop control based on the actual flight status information of the UAV to achieve autonomous flight control.

[0096] Embodiment three:

[0097] This embodiment provides a specific process of autonomous control of the UAV: ​​before the UAV takes off, the various sensors of the perception module are calibrated and initialized to ensure that they can work normally and collect accurate data. After startup, the perception module continuously collects environmental data, the data processing module processes according to the set data fusion and analysis process, the decision module generates flight decisions according to the initial mission planning and real-time environmental information, and the control execution module drives the UAV to take off and fly according to the decision instructions. During the flight process, the modules continuously interact with each other and work together. For example, when the perception module detects a new obstacle, it promptly transmits the information to the data processing module and the decision module. The decision module quickly adjusts the flight decision, and the control execution module immediately executes the new control instruction, so that the UAV avoids obstacles and continues to perform the task safely. At the same time, the system also has self-diagnosis and fault warning functions. When a module or component is abnormal, it can issue an alarm in time and take corresponding emergency measures to ensure the flight safety of the UAV and the smooth completion of the task.

[0098] To sum up, the above-mentioned UAV autonomous control system and control method can significantly improve the autonomous flight capability, mission execution efficiency and flight safety of UAVs in complex environments, expand the application scope of UAVs, and have broad application prospects in fields such as aerial photography and mapping, logistics distribution, and emergency rescue.

[0099] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An autonomous control system for an unmanned aerial vehicle, characterized in that: include: A control module, used to receive the flight status information of the UAV; The perception module is connected to the control module and is used to collect information about the surrounding environment of the drone; A data processing module is connected to the perception module, receives and processes the environmental information, integrates data from different sensors through a data fusion algorithm, and uses a deep learning algorithm to analyze the processed data to extract key environmental features; A decision module, connected to the data processing module, generates a flight decision based on the analysis results combined with preset mission objectives and flight rules; The control execution module receives the instructions from the decision module and converts them into flight control actions of the UAV, accurately controlling the motor speed and steering gear angle of the UAV to achieve attitude adjustment and position movement.

2. The autonomous control system of a UAV according to claim 1, characterized in that: The perception module includes a laser radar, a visual camera and an ultrasonic sensor. The laser radar is used for long-distance terrain mapping and obstacle detection, the visual camera is used for image acquisition and recognition analysis, and the ultrasonic sensor is used for short-distance obstacle detection.

3. The autonomous control system of a UAV according to claim 1, characterized in that: The data processing module uses a high-performance processor that has the ability to quickly run complex algorithm models to deeply understand and judge environmental information. The sensor data includes two-dimensional images, three-dimensional images, point clouds, and environmental perception data; Specifically, the calculation method of the data fusion algorithm is: And meet Among them, there are n data sources in total, the data provided by the i-th data source is Xi, and its corresponding weight is Wi, then the fused result is x.

4. The autonomous control system of a UAV according to claim 1, characterized in that: The decision module adopts an intelligent decision algorithm, which can continuously learn and optimize the decision process according to environmental changes and task requirements. The intelligent decision algorithm includes: The path planning algorithm is used to plan the flight path of the UAV according to the environmental information. Specifically, the calculation formula of the path planning algorithm is: f(n)=g(n)+h(n) Where n is a node in the path, f(n) is the comprehensive evaluation value of node n, g(n) is the actual cost from the starting point to node n, and h(n) is the heuristic estimated cost from node n to the target point; The obstacle avoidance algorithm is used to adjust the flight path when encountering obstacles in the flight path. Specifically, the calculation formula of the obstacle avoidance algorithm is: Among them, the distance between the UAV and the i-th obstacle after the UAV moves at a speed of (v, w) for time t is di, and dmin is the minimum distance between the UAV and all obstacles.

5. The autonomous control system of a UAV according to claim 1, characterized in that: The control execution module adopts high-precision control algorithm and fast-response actuator, and has anti-interference ability to ensure stable and accurate flight of the UAV under complex conditions. The control execution module includes: at least one motor controller for controlling the operation of the motor of the drone; At least one servo controller, used to control the operation of the servo of the drone.

6. A method for autonomous control of a drone, based on an autonomous control system of a drone according to any one of claims 1 to 5, characterized in that: The following steps are involved: Step 1: Environmental Perception: The environmental data is collected simultaneously through the laser radar, visual camera and ultrasonic sensor in the perception module, and transmitted to the data processing module after pre-processing; Step 2: Data fusion and analysis: The data processing module fuses the pre-processed data from different sensors and uses the deep learning model to extract features and understand the environment of the fused data; Step 3: Decision making: The decision module uses a multi-objective optimization algorithm to generate the optimal flight decision based on the environmental analysis results provided by the data processing module, combined with the preset mission planning and flight constraints; Step 4: Control execution: The control execution module receives instructions from the decision-making module, converts them into specific control signals, drives the UAV power system and flight control surfaces, and forms a closed-loop control based on the actual flight status information of the UAV to achieve autonomous flight control.

7. The autonomous control method of a drone according to claim 6, characterized in that: In step one, the preprocessing includes data cleaning and filtering operations.

8. The autonomous control method of a drone according to claim 6, characterized in that: In step 2, a convolutional neural network is used to identify targets in visual images, and a recurrent neural network is used to perform time series analysis on multiple frames of data.

Images