Cultural algorithm-based flight path planning method in dynamic environment

Abstract

The invention relates to the field of flight path planning, in particular to a culture algorithm-based flight path planning method in a dynamic environment, which comprises the following steps of: constructing a dynamic environment model by monitoring weather conditions and trajectories of surrounding flyers in real time, and online planning a reachable flight path and extracting feature nodes as knowledge reserve in combination with flight mission requirements. And performing off-line planning by using the knowledge to obtain an optimal track. In the flight process, the environment change is continuously monitored, once the current optimal flight path is influenced by the environment change, the influenced part is re-planned by using an online planning method, and previous knowledge is used for guiding optimization. The method has the multiple advantages of adapting to environment changes in real time, improving flight safety, optimizing flight efficiency, reducing flight path adjustment frequency, enhancing autonomous decision-making ability, improving task success rate and the like, has high expandability and flexibility, and can be suitable for different types of unmanned aerial vehicles and flight tasks.

Description

Technical Field

[0001] The present invention relates to the field of trajectory planning, and particularly to a trajectory planning method in a dynamic environment based on a cultural algorithm. Background Art

[0002] The rapid development and wide application of unmanned aerial vehicle (UAV) technology in recent years. With the continuous maturity of UAV technology, it has demonstrated great potential and value in many fields such as military reconnaissance, civilian aerial photography, disaster relief, and logistics distribution. However, with the expansion of the application scope of UAVs, higher requirements are also put forward for the autonomous flight ability, environmental adaptability, and task execution ability of UAVs. Especially in a complex and changing dynamic environment, how to ensure that UAVs can complete tasks safely and efficiently has become an important topic in the current research of UAV technology.

[0003] During the process of UAVs performing tasks, trajectory planning is a crucial link. Trajectory planning refers to planning an optimal flight path from the starting point to the ending point for UAVs according to the requirements of flight tasks and the characteristics of the flight environment. This path needs to meet various requirements such as flight safety, task efficiency, and energy consumption control. However, in a dynamic environment, factors such as changes in weather conditions, the moving trajectories of surrounding flying objects, and the setting of no-fly zones will have a significant impact on the trajectory planning of UAVs. Traditional static trajectory planning methods often cannot adapt to such a complex and changing environment. Therefore, it is particularly urgent to develop a trajectory planning method that can adapt to the changes in the dynamic environment.

[0004] Traditional trajectory planning methods often rely on static environmental models and are difficult to adapt to real-time changes in weather conditions and the dynamic trajectories of surrounding flying objects. This results in the fact that during actual flight, UAVs may need to frequently adjust their trajectories and even face the risk of being unable to continue performing tasks. Summary of the Invention

[0005] To solve the above problems, the present invention provides a trajectory planning method in a dynamic environment based on a cultural algorithm, which is used to construct a dynamic environmental model by real-time monitoring of weather conditions and the trajectories of surrounding flying objects, and adjust the trajectory in real time according to environmental changes to ensure the safe flight of UAVs in a complex environment.

[0006] To achieve the above object, the technical solution of the present invention is as follows: A trajectory planning method in a dynamic environment based on a cultural algorithm, comprising the following steps:

[0007] S1, obtaining environmental and task information: collecting weather condition data, real-time monitoring data of surrounding flying objects, and the requirements of flight tasks, and constructing an environmental model and a task model based on the weather condition data, the real-time monitoring data of surrounding flying objects, and the specific requirements of the flight tasks;

[0008] S2. Online planned reachable flight path: Using the online flight path planning method, according to the environmental model and the mission model, plan the reachable flight path of the aircraft;

[0009] S3. Extract feature nodes and knowledge: Extract feature nodes from the reachable flight path, and store the feature nodes and their related information as knowledge;

[0010] S4. Offline planned optimal flight path: Use the stored knowledge to determine the search space of flight path planning, and use the offline flight path planning method to plan the optimal flight path;

[0011] S5. Dynamic adjustment and replanning: Continuously monitor the environmental changes, which include weather changes and the movement trajectories of surrounding flying objects. When it is found that the environmental changes affect the current optimal flight path, use the online flight path planning method to replan the affected part, and use the previously extracted knowledge to guide the optimization. Then extract the knowledge from the newly planned flight path and update the optimization space to complete the flight path planning.

[0012] The technical principle of the above solution is as follows: This solution is based on the cultural algorithm. By real-time monitoring the environment (including weather conditions and the dynamic trajectories of surrounding flying objects), a dynamic environmental model is constructed. Combining with the flight mission requirements, an online planned reachable flight path is planned and feature nodes are extracted as knowledge reserves. Subsequently, these knowledge are used for offline planning to obtain the optimal flight path. During the flight process, continuously monitor the environmental changes. Once the environmental changes affect the current optimal flight path, use the online planning method to replan the affected part and use the previous knowledge to guide the optimization, so as to ensure the safe flight of the UAV in a complex environment.

[0013] The following beneficial effects can be obtained by adopting the above solution:

[0014] 1. In this solution, by real-time monitoring the weather conditions and the trajectories of surrounding flying objects, a dynamic environmental model is constructed. This means that the UAV can real-time sense and adapt to the environmental changes, such as sudden changes in wind direction, changes in cloud thickness, and the sudden appearance of other flying objects. This real-time nature ensures the safe and effective flight of the UAV in a complex environment.

[0015] 2. In this solution, by dynamically adjusting the flight path, the UAV can avoid potential dangerous areas, such as lightning areas, strong wind areas or conflict areas with other flying objects. This greatly reduces the risk of accidents during the flight process and improves the overall safety of the flight. At the same time, since the flight path is planned in real time, the UAV can more flexibly respond to emergencies, such as emergency obstacle avoidance, etc.

[0016] 3. This solution combines the advantages of online and offline trajectory planning. Online planning can quickly respond to environmental changes to ensure the reachability of the trajectory, while offline planning uses the stored knowledge to optimize the trajectory and find the optimal path. This combination enables the UAV to improve flight efficiency as much as possible while ensuring safety, reducing unnecessary flight time and energy consumption.

[0017] 4. Since this method can sense environmental changes in real time and adjust the trajectory, compared with traditional methods, the situation where the UAV needs to frequently adjust the trajectory during flight is greatly reduced. This not only reduces the operation complexity of the UAV but also reduces the flight errors and uncertainties that may be caused by frequent trajectory adjustments. By extracting feature nodes and storing relevant knowledge, the UAV can use previous experience to guide current decisions during the trajectory planning process. This autonomous decision-making ability enables the UAV to more intelligently select the optimal path when facing a complex environment, rather than simply relying on preset algorithms or rules.

[0018] Since this method can adjust the trajectory in real time and optimize flight efficiency, the UAV can reach the target position more accurately when performing tasks and complete the established tasks. This greatly improves the success rate of the tasks, especially in tasks that require high precision and high efficiency, such as military reconnaissance and disaster monitoring. This method is based on a cultural algorithm and has high scalability and flexibility. With the continuous development of technology, new algorithms or technologies can be conveniently introduced to further optimize the trajectory planning process. At the same time, since this method can process various types of environmental and task information, it can be applied to different types of UAVs and flight tasks.

[0019] In summary, the trajectory planning method in a dynamic environment based on the cultural algorithm has multiple advantages such as real-time adaptation to environmental changes, improvement of flight safety, optimization of flight efficiency, reduction of trajectory adjustment frequency, enhancement of autonomous decision-making ability, improvement of task success rate, and scalability and flexibility. These advantages make this method have broad application prospects and important practical value in the field of UAV trajectory planning.

[0020] Furthermore, in step S1, the weather condition data is obtained through weather stations, satellite cloud images, and meteorological sensors carried by the UAV to get real-time weather data; the real-time monitoring data of surrounding flying objects is obtained through radar systems, ADS-B systems, and communication protocols between UAVs; the requirements of the flight task include task type, starting point and ending point, time limit, safety requirements, and energy consumption and efficiency.

[0021] Beneficial effects:

[0022] 1. Diversified acquisition of weather condition data: Through weather stations, satellite cloud images, and meteorological sensors carried by drones, comprehensive and real-time weather data can be obtained to ensure the accuracy of the environmental model. It improves the response speed and adaptability of drones to weather changes.

[0023] 2. Real-time monitoring of surrounding flying object data: Using radar systems, ADS-B systems, and communication protocols between drones, the position and trajectory information of surrounding flying objects can be obtained in real time. It enhances the flight safety and obstacle avoidance ability of drones in complex airspaces.

[0024] 3. Clear definition of flight mission requirements: Key elements such as mission type, starting and ending points, time limit, safety requirements, and energy consumption and efficiency are clarified. It provides clear goals and constraint conditions for flight path planning and ensures the efficient execution of the mission.

[0025] Furthermore, in step S1, based on the collected weather data and surrounding flying object data, the environmental model constructs a three-dimensional dynamic environmental model, which includes information on weather impact areas, flying object trajectory prediction areas, and no-fly zones; the mission model defines the objective function and constraint conditions for flight path planning according to the specific requirements of the flight mission. The objective function includes the shortest path, the lowest energy consumption, and the optimal time, and the constraint conditions include avoiding obstacles, complying with flight rules, and meeting safety requirements.

[0026] Beneficial effects:

[0027] 1. Construction of a three-dimensional dynamic environmental model: It includes information such as weather impact areas, flying object trajectory prediction areas, and no-fly zones, providing comprehensive environmental information for flight path planning. It improves the safety and accuracy of flight path planning.

[0028] 2. Definition of the mission model: It defines the objective function and constraint conditions for flight path planning, such as the shortest path, the lowest energy consumption, and the optimal time. It ensures that the flight path planning meets the mission requirements while also meeting the requirements of flight safety and efficiency.

[0029] Furthermore, in step S2, the online flight path planning method uses a heuristic search algorithm. In the environmental model, starting from the starting point, it uses a heuristic function to evaluate the advantages and disadvantages of each adjacent node and selects the optimal node as the next search point. This process is repeated until the end point is reached or no better node can be found; in the two-dimensional plane, the Euclidean distance can be used as the heuristic function, and the calculation formula is as follows:

[0030]

[0031] where d is the straight-line distance from the current node to the adjacent node, (x 2 -x 1 ) and (y2 -y 1 ) are the coordinates of the current node and the target node respectively.

[0032] Beneficial effects:

[0033] 1. Application of heuristic search algorithm: Using a heuristic function to evaluate the advantages and disadvantages of each adjacent node, the search efficiency is improved. It can quickly find a feasible flight path in a complex environment.

[0034] 2. Calculation of heuristic function in a two-dimensional plane: Using the Euclidean distance as the heuristic function, the calculation is simple and intuitive. It ensures the continuity and smoothness of the flight path.

[0035] Furthermore, in step S3, the specific method is as follows: Preprocess the reachable flight path to eliminate redundant nodes or smooth the flight path. Identify feature nodes in the preprocessed flight path. The feature nodes are identified according to the slope, curvature, and speed change parameters of the flight path; Extract relevant information of the feature nodes and store it as knowledge. The stored relevant information includes the parameters of the coordinates, speed, altitude, and heading of the feature nodes, as well as the relative relationships between nodes. The relative relationships include distance, direction, etc. The stored relevant information also includes the position information of the feature nodes in the flight path and the information on the impact of the feature nodes on the overall performance of the flight path.

[0036] Beneficial effects:

[0037] 1. Identification of feature nodes: Identified according to the slope, curvature, and speed change parameters of the flight path, ensuring the accuracy and representativeness of the feature nodes. It provides key information for subsequent flight path planning and optimization.

[0038] 2. Extraction and storage of relevant information: Store the parameters of the coordinates, speed, altitude, and heading of the feature nodes, as well as the relative relationships between nodes. It provides rich knowledge reserves for offline flight path planning and dynamic adjustment.

[0039] Furthermore, in step S4, the specific method is as follows: Use the feature nodes and their relevant information stored in step S3 as a knowledge base to construct an initial flight path search graph. The search graph takes the feature nodes as vertices and the relative relationships between the feature nodes as edges to form a connected network structure. According to the position information of the feature nodes in the flight path and the information on the impact of the feature nodes on the overall performance of the flight path, assign a weight to each edge in the search graph. The weight reflects the cost required to move from one vertex of the edge to another vertex;

[0040] Next, an offline trajectory planning algorithm is adopted to find the optimal path from the starting point to the ending point in the constructed search graph. The process of finding the optimal path is based on the principle of cost minimization, that is, choosing the edges with the smallest weights to form the path; during the planning process, the search algorithm is appropriately adjusted and optimized according to the objective function and constraint conditions in the task model; finally, the offline planning algorithm will output an optimal trajectory from the starting point to the ending point.

[0041] Beneficial effects:

[0042] 1. Application of the knowledge base: Using the stored feature nodes and their related information to construct an initial trajectory search graph. This improves the efficiency and quality of offline trajectory planning.

[0043] 2. Application of the offline trajectory planning algorithm: Finding the optimal path from the starting point to the ending point in the constructed search graph. This ensures the optimality and feasibility of the trajectory.

[0044] Furthermore, in step S5, the specific content of dynamic adjustment and replanning is as follows: During the actual flight of the UAV, by continuously monitoring the environmental changes, the applicability of the current optimal trajectory is evaluated in real time; once it is found that the environmental changes have a significant impact on the safety or efficiency of the trajectory, the replanning mechanism is immediately triggered; The replanning first determines the affected trajectory segment by comparing the real-time monitoring data with the environmental model used during trajectory planning;

[0045] Next, the online trajectory planning method is used to locally replan the affected part. Using the extracted and stored feature nodes and their related information as guidance, the search process is accelerated and a better alternative trajectory is found. The online planning method uses a heuristic search algorithm. At this time, the starting point and ending point of the search are the starting point and ending point of the affected trajectory segment respectively. The selection of the heuristic function and parameter settings are dynamically adjusted according to the current environmental changes and flight task requirements;

[0046] After the replanning is completed, knowledge extraction is performed on the newly generated trajectory segment, that is, new feature nodes and related information are identified and added to the knowledge base; finally, according to the new trajectory segment and the unaffected part of the original trajectory, the cost estimation of the entire trajectory is updated, and the flight parameters of the UAV are adjusted.

[0047] Furthermore, in the dynamic adjustment and replanning (in order to evaluate the degree of influence of environmental changes on the trajectory), an influence evaluation index I is introduced, and its calculation formula is as follows:

[0048] I = α * ΔW + β * ΔT + γ * ΔS

[0049] Among them, ΔW represents the impact of weather changes on flight performance; ΔT represents the impact of changes in the movement trajectories of surrounding flying objects on flight safety; ΔS represents the cost required for trajectory adjustment; α, β, and γ are weight coefficients;

[0050] When the impact evaluation index I exceeds a preset threshold, it is considered that the impact of environmental changes on the trajectory is significant and a replanning mechanism needs to be triggered; the setting of the threshold is determined according to the safety requirements, time limit, and energy consumption budget of the flight mission.

[0051] Furthermore, in dynamic adjustment and replanning (to evaluate the degree of impact of environmental changes on the trajectory), an impact evaluation index I is introduced, and its calculation formula is as follows:

[0052] I = α * ΔW + β * ΔT + γ * ΔS

[0053] Among them, ΔW represents the impact of weather changes on flight performance; ΔT represents the impact of changes in the movement trajectories of surrounding flying objects on flight safety; ΔS represents the cost required for trajectory adjustment; α, β, and γ are weight coefficients;

[0054] The impact of weather changes on flight performance is calculated by comparing the current weather data with the weather data used during trajectory planning; the impact of changes in the movement trajectories of surrounding flying objects on flight safety is evaluated by calculating the closest distance between the flying object and the trajectory or predicting potential conflict points; the cost required for trajectory adjustment includes an increase in flight time and an increase in energy consumption; the weight coefficients are dynamically adjusted according to the importance of the flight mission and the urgency of environmental changes; when the impact evaluation index I exceeds a preset threshold, it is considered that the impact of environmental changes on the trajectory is significant and a replanning mechanism needs to be triggered; the setting of the threshold is determined according to the safety requirements, time limit, and energy consumption budget of the flight mission.

[0055] Beneficial effects: 1. Real-time monitoring and evaluation of environmental changes: By continuously monitoring environmental changes, the applicability of the current optimal trajectory is evaluated in real time. The response speed and adaptability of the UAV to environmental changes are improved.

[0056] 2. Determination and replanning of affected trajectory segments: By comparing the differences between real-time monitoring data and the environmental model used during trajectory planning, the affected trajectory segments are determined. The online trajectory planning method is used to locally replan the affected part, ensuring the continuity and safety of the trajectory.

[0057] 3. Introduction of the impact evaluation index I: By comprehensively considering weather changes, changes in the movement trajectories of surrounding flying objects, and the cost required for trajectory adjustment, the degree of impact of environmental changes on the trajectory is evaluated. It provides a scientific basis for triggering the replanning mechanism.

[0058] 4. Dynamic adjustment of weight coefficients and thresholds: Dynamically adjust the weight coefficients and thresholds according to the importance of flight missions and the urgency of environmental changes. This improves the flexibility and adaptability of trajectory planning.

[0059] Furthermore, when constructing the trajectory search graph, preferentially use the reserved feature nodes as candidate vertices, dynamically update the relative relationships between feature nodes according to current environmental changes, and assign a dynamic weight to each edge in the search graph based on the impact evaluation index I and the impact information of feature nodes on the overall performance of the trajectory.

[0060] Beneficial effects:

[0061] 1. Preferential use of feature nodes: Preferentially use the reserved feature nodes as candidate vertices, which improves the accuracy and representativeness of the search graph. Reduces the search space and improves the search efficiency.

[0062] 2. Dynamic update and weight assignment: Dynamically update the relative relationships between feature nodes according to current environmental changes. Assign a dynamic weight to each edge in the search graph based on the impact evaluation index I and the impact information of feature nodes on the overall performance of the trajectory. This improves the accuracy and adaptability of trajectory planning.

[0063] Furthermore, the monitor includes a fixed bracket, an adjustment part, and a monitoring part. The adjustment part includes a fixed ring, the fixed ring is fixedly connected to the fixed bracket, a chute is provided on the fixed ring, a slider is slidably connected in the chute, a driving member is embedded in the slider, a telescopic member is hinged to the top of the slider, one end of the telescopic member away from the slider is hinged to an adjustment plate, a sphere is fixedly connected to the middle of the adjustment plate, and a ball hinge seat is fixedly connected to the top of the fixed bracket, and the sphere is rotatably connected in the ball hinge seat; the monitoring part includes a camera, a sensor, and a communication component, and the camera, the sensor, and the communication component are all fixedly connected to the adjustment plate.

[0064] Beneficial effects: Use the power member to move the slider in the chute of the fixed ring, drive the telescopic member, the adjustment plate, and the communication part to rotate, and at the same time use the telescopic member to expand and contract to adjust the inclination angle of the adjustment plate. At this time, the sphere rotates in the ball hinge seat, which is convenient for adjusting the adjustment plate. Thus, it is convenient to adjust the directions and angles of the camera, the sensor, and the communication component, and it is convenient to continuously monitor environmental changes.

[0065] The additional aspects and advantages of the present invention will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present invention. Description of the Drawings

[0066] Figure 1 It is a flowchart of the trajectory planning method in a dynamic environment based on the cultural algorithm of the present invention;

[0067] Figure 2Schematic diagram of the monitor for the trajectory planning method in a dynamic environment based on the cultural algorithm of the present invention;

[0068] Figure 3 Schematic diagram of the spherical hinge seat for the trajectory planning method in a dynamic environment based on the cultural algorithm of the present invention;

[0069] Figure 4 Cross-sectional view of the fixed ring for the trajectory planning method in a dynamic environment based on the cultural algorithm of the present invention;

[0070] Reference numerals in the accompanying drawings of the specification include: 1, fixed bracket; 2, fixed ring; 3, chute; 4, slider; 5, driving member; 6, telescopic member; 7, adjusting plate; 8, sphere; 9, spherical hinge seat; 10, monitoring unit. Detailed implementation manners

[0071] Next, the technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0072] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0073] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0074] The following is a further detailed description through specific implementation manners:

[0075] Embodiment 1:

[0076] As shown in the attached Figure 1 figure: A trajectory planning method in a dynamic environment based on the cultural algorithm includes the following steps:

[0077] S1. Obtain environmental and mission information: Collect weather condition data, real-time monitoring data of surrounding flying objects, and requirements of the flight mission. Based on the weather condition data, real-time monitoring data of surrounding flying objects, and specific requirements of the flight mission, construct an environmental model and a mission model.

[0078] The weather condition data obtains real-time weather data through meteorological stations, satellite cloud images, and meteorological sensors carried by the unmanned aerial vehicle. The weather data includes, but is not limited to, wind speed, wind direction, temperature, humidity, precipitation probability, visibility, cloud height and type, etc.; Convert the collected original weather data into a format suitable for flight path planning, and use a meteorological model to predict the weather change trend in the next period of time. Collect real-time monitoring data of surrounding flying objects through radar systems, ADS-B systems, and communication protocols between unmanned aerial vehicles. The real-time monitoring data of surrounding flying objects includes, but is not limited to, the position (longitude, latitude, altitude), speed, heading, aircraft type, identification code, etc. of the flying object. Establish a flying object database, update the position information of the flying object in real time, and predict its possible flight trajectory to evaluate potential conflict risks. The requirements of the flight mission include mission type, starting point and ending point, time limit, safety requirements, and energy consumption and efficiency.

[0079] Mission type: Specify which type of flight mission it is, such as reconnaissance, transportation, search and rescue, shooting, etc.

[0080] Starting point and ending point: Determine the geographical coordinates and altitude of the starting point and ending point of the flight.

[0081] Time limit: Whether the flight mission has strict time requirements, such as it must be completed within a certain time period.

[0082] Safety requirements: Specific requirements for flight safety in the mission, such as the minimum flight altitude, avoiding specific areas, etc.

[0083] Energy consumption and efficiency: Requirements for flight energy consumption and efficiency in the mission, such as whether the shortest path planning is required.

[0084] Based on the collected weather data and surrounding flying object data, construct a three-dimensional dynamic environmental model. The dynamic environmental model includes information on weather impact areas, flying object trajectory prediction areas, and no-fly zones; According to the specific requirements of the flight mission, define the objective function and constraint conditions for flight path planning. The objective function includes the shortest path, the lowest energy consumption, and the optimal time. The constraint conditions include avoiding obstacles, complying with flight rules, and meeting safety requirements.

[0085] S2. Online planned reachable trajectory: Using the online trajectory planning method, according to the environmental model and the task model, plan a reachable trajectory; the online trajectory planning method uses a heuristic search algorithm. In the environmental model, starting from the starting point, use the heuristic function to evaluate the advantages and disadvantages of each adjacent node, and select the optimal node as the next search point. Repeat this process until reaching the end point or no better node can be found; in a two-dimensional plane, the Euclidean distance can be used as the heuristic function, and the calculation formula is as follows:

[0086]

[0087] where d is the distance, and (x 2 - x 1 ) and (y 2 - y 1 ) are the coordinates of the current node and the target node respectively.

[0088] S3. Extract feature nodes and knowledge: Extract feature nodes from the reachable trajectory, and store the feature nodes and their related information as knowledge; preprocess the reachable trajectory to eliminate redundant nodes or smooth the trajectory, identify feature nodes in the preprocessed trajectory, and the feature nodes are identified according to the slope, curvature and speed change parameters of the trajectory; extract the related information of the feature nodes and store it as knowledge. The stored related information includes the parameters of the coordinates, speed, altitude and heading of the feature nodes, as well as the relative relationships between nodes, and the relative relationships include distance and direction, etc. The stored related information also includes the position information of the feature nodes in the trajectory, and the impact information of the feature nodes on the overall performance of the trajectory (such as path length, flight time, energy consumption, etc.).

[0089] S4. Offline planned optimal trajectory: Use the stored knowledge to determine the search space for trajectory planning, and use the offline trajectory planning method to plan the optimal trajectory; among them, use the stored feature nodes and their related information as a knowledge base to construct an initial trajectory search graph. The search graph uses feature nodes as vertices and the relative relationships between feature nodes (including distance, direction, etc.) as edges to form a connected network structure. According to the position information of the feature nodes in the trajectory and their impact information on the overall performance of the trajectory (such as path length, flight time, energy consumption, etc.), assign a weight to each edge in the search graph, and this weight reflects the cost required to move from one vertex of this edge to another vertex.

[0090] Next, an offline trajectory planning algorithm (such as the A* algorithm, Dijkstra algorithm, or any other algorithm suitable for graph search) is used to find the optimal path from the starting point to the ending point in the constructed search graph. The process of finding the optimal path is based on the principle of cost minimization, that is, choosing the edges with the smallest weights to form the path (ensuring that the planned trajectory not only meets the requirements of the flight mission but also minimizes costs such as flight time and energy consumption as much as possible); during the planning process, the search algorithm is appropriately adjusted and optimized according to the objective function and constraint conditions in the mission model. For example, if the objective function is the shortest path, then simply choosing the path with the smallest weight is sufficient; but if the objective function is the lowest energy consumption or the optimal time, then more factors need to be considered during the search process, such as flight speed, altitude change, weather impact, etc., and these factors can be reflected by adjusting the heuristic function or weight assignment of the search algorithm.

[0091] Finally, the offline planning algorithm will output an optimal trajectory from the starting point to the ending point. This trajectory not only meets the requirements of the flight mission but also takes into account various constraint conditions in the environmental model and optimizes the flight cost as much as possible. This optimal trajectory can be used as a reference path for the UAV flight. During the actual flight process, it is dynamically adjusted and optimized according to the real-time monitored environmental changes.

[0092] S5, Dynamic adjustment and replanning: Continuously monitor the environmental changes, which include weather changes and the movement trajectories of surrounding flying objects. When it is found that the environmental changes affect the current optimal trajectory, use the online trajectory planning method to replan the affected part, and use the previously extracted knowledge to guide the optimization. Then, extract the knowledge from the newly planned trajectory and update the optimization space to complete the trajectory planning.

[0093] The specific content of dynamic adjustment and replanning is as follows: During the actual flight of the UAV, by continuously monitoring the changes in the environment (including weather conditions and the movement trajectories of surrounding flying objects), the applicability of the current optimal trajectory is evaluated in real time; once it is found that the environmental changes have a significant impact on the safety or efficiency of the trajectory, the replanning mechanism is immediately triggered; the replanning first determines the affected trajectory segment by comparing the real-time monitored data with the environmental model used during the trajectory planning (the determination of the affected trajectory segment may need to consider multiple factors, such as the intensity and scope of weather changes and their impact on flight performance, as well as the movement speed and direction of surrounding flying objects, etc.).

[0094] Next, use the online trajectory planning method to locally replan the affected part. Utilize the extracted and stored feature nodes and their related information as guidance to accelerate the search process and find a better alternative trajectory. The online planning method adopts a heuristic search algorithm. At this time, the starting point and ending point of the search are the starting point and ending point of the affected trajectory segment (or adjusted according to the actual situation). The selection of the heuristic function and parameter settings are dynamically adjusted according to the current environmental changes and flight mission requirements.

[0095] After the replanning is completed, perform knowledge extraction on the newly generated trajectory segment, that is, identify new feature nodes and related information, and add them to the knowledge base (this step helps to enrich and optimize the search space and knowledge reserve for subsequent trajectory planning); finally, according to the new trajectory segment and the unaffected part of the original trajectory, update the cost estimation of the entire trajectory (such as flight time, energy consumption, etc.), and adjust the flight parameters of the UAV (such as speed, altitude, heading, etc.). (To ensure that the UAV can continue to perform the task safely and efficiently).

[0096] In the dynamic adjustment and replanning (to evaluate the degree of influence of environmental changes on the trajectory), an influence evaluation index I is introduced, and its calculation formula is as follows:

[0097] I = α * ΔW + β * ΔT + γ * ΔS

[0098] Where, ΔW represents the influence of weather changes on flight performance; ΔT represents the influence of the change in the moving trajectory of surrounding flying objects on flight safety; ΔS represents the cost required for trajectory adjustment; α, β, and γ are weight coefficients.

[0099] When the influence evaluation index I exceeds the preset threshold, it is considered that the environmental change has a significant impact on the trajectory, and the replanning mechanism needs to be triggered; the setting of the threshold is determined according to the safety requirements, time limit, and energy consumption budget of the flight mission.

[0100] The influence of weather changes on flight performance is calculated by comparing the current weather data with the weather data used during trajectory planning; the influence of the change in the moving trajectory of surrounding flying objects on flight safety is evaluated by calculating the closest distance between the flying object and the trajectory or predicting potential conflict points; the cost required for trajectory adjustment includes an increase in flight time and an increase in energy consumption; the weight coefficients are dynamically adjusted according to the importance of the flight mission and the urgency of environmental changes; when the influence evaluation index I exceeds the preset threshold, it is considered that the environmental change has a significant impact on the trajectory, and the replanning mechanism needs to be triggered; the setting of the threshold is determined according to the safety requirements, time limit, and energy consumption budget of the flight mission.

[0101] When constructing a trajectory search graph, the reserved feature nodes are preferentially used as candidate vertices, and the relative relationships (such as distance, direction, etc.) between feature nodes are dynamically updated according to the current environmental changes. At the same time, according to the impact evaluation index I and the impact information of feature nodes on the overall performance of the trajectory, a dynamic weight is assigned to each edge in the search graph, which helps to quickly find a better alternative trajectory during replanning and reduce unnecessary search and computational overhead.

[0102] The specific implementation process is as follows: For example, there is a drone that needs to take off from airport A and perform a reconnaissance mission. The goal is to reach and reconnoiter the designated target area B and then return to airport A. During the flight, the drone needs to avoid bad weather (such as thunderstorms), other flying objects (such as commercial flights, birds, etc.), and minimize flight time and energy consumption as much as possible.

[0103] The steps are described in detail as follows:

[0104] S1: Obtain environmental and mission information

[0105] Weather condition data: Collect real-time data such as wind speed, wind direction, temperature, humidity, precipitation probability, visibility, cloud height and type through meteorological stations, satellite cloud images and meteorological sensors carried by the drone. For example, it is found that there is a thunderstorm over the target area B, which is expected to last for 2 hours, with a wind speed of 10 m / s and a wind direction of north.

[0106] Real-time monitoring data of surrounding flying objects: Collect information such as the position, speed, heading, aircraft type, identification code of surrounding flying objects through radar systems, ADS-B systems and communication protocols between drones. For example, it is found that a commercial flight will pass above the drone's flight path, with an expected time of 1 hour after takeoff and an altitude of 10,000 meters.

[0107] Requirements of the flight mission: Clearly define that the mission type is reconnaissance, the starting point is airport A, the ending point is the target area B, the time limit is to be completed within 4 hours, the safety requirements are to avoid thunderstorm areas and have an altitude of not less than 500 meters, and the energy consumption and efficiency requirements are to minimize flight time and energy consumption as much as possible.

[0108] Based on the above information, a three-dimensional dynamic environment model and mission model are constructed.

[0109] S2: Online plan reachable trajectories

[0110] Heuristic search algorithm: Starting from airport A, use a heuristic function (such as Euclidean distance) to evaluate the advantages and disadvantages of each adjacent node and select the optimal node as the next search point. In a two-dimensional plane, the straight-line distance between the current node and the target node can be calculated as the value of the heuristic function.

[0111] Plan a reachable flight path: Through a heuristic search algorithm, plan a reachable flight path from airport A to target area B. For example, the planned flight path avoids thunderstorm areas and takes into account the flight trajectories of commercial flights.

[0112] S3: Extract feature nodes and knowledge

[0113] Preprocess the flight path: Preprocess the planned reachable flight path to eliminate redundant nodes or smooth the flight path.

[0114] Identify feature nodes: Based on the slope, curvature, and speed change parameters of the flight path, identify feature nodes. For example, identify turning points, altitude change points, etc. in the flight path.

[0115] Extract relevant information: Extract the parameters of the coordinates, speed, altitude, and heading of the feature nodes, as well as the relative relationships between the nodes (such as distance, direction, etc.). For example, extract that the coordinates of turning point A are (longitude 116.4, latitude 39.9, altitude 1000 meters), the distance to the next node B is 50 kilometers, and the direction is 30 degrees south of east.

[0116] Reserve knowledge: Reserve the extracted feature nodes and their relevant information as knowledge for use in subsequent offline planning.

[0117] S4: Offline plan the optimal flight path

[0118] Construct a search graph: Use the reserved feature nodes and their relevant information to construct an initial flight path search graph. For example, form a connected network structure with feature nodes as vertices and the relative relationships between the nodes as edges.

[0119] Assign weights: According to the position information of the feature nodes in the flight path and the information on their impact on the overall performance of the flight path, assign a weight to each edge in the search graph. For example, consider factors such as flight time and energy consumption, and assign a weight that reflects the cost required to move from one vertex of the edge to another vertex.

[0120] Offline planning algorithm: Use the A* algorithm to find the optimal path from airport A to target area B in the constructed search graph. For example, plan an optimal flight path that avoids thunderstorm areas, commercial flight trajectories, and has low flight time and energy consumption.

[0121] S5: Dynamic adjustment and replanning

[0122] Continuously monitor environmental changes: During the actual flight of the UAV, continuously monitor weather conditions and the movement trajectories of surrounding flying objects. For example, find that the scope of the thunderstorm area has expanded and the flight trajectories of commercial flights have changed.

[0123] Evaluate the impact degree: Introduce the impact evaluation index I, calculate the impact of weather changes and the changes in the movement trajectories of surrounding flying objects on flight performance and safety, as well as the cost required for track adjustment. For example, it is calculated that the value of the impact evaluation index I exceeds the preset threshold.

[0124] Trigger the replanning mechanism: When the impact evaluation index I exceeds the preset threshold, trigger the replanning mechanism. For example, determine that the affected track segment is the part between turning point A and the next node B.

[0125] Local replanning: Use the online track planning method to perform local replanning on the affected part. For example, plan a new track segment to avoid the expanding thunderstorm area and the changed commercial flight trajectories.

[0126] Knowledge extraction and update: Extract knowledge from the newly generated track segment, and update the knowledge base and the optimization space. For example, identify the new feature node C and add it to the knowledge base.

[0127] Update the track and flight parameters: According to the new track segment and the unaffected part of the original track, update the cost estimate of the entire track, and adjust the flight parameters of the UAV. For example, adjust the speed, altitude, and heading of the UAV to ensure that the UAV can continue to perform the task safely and efficiently.

[0128] Through the above steps, the UAV can complete track planning in a dynamic environment, and perform dynamic adjustment and replanning according to environmental changes to ensure the safe and efficient completion of the task.

[0129] Embodiment 2:

[0130] As shown in the appendix Figure 1 As shown, the difference from Embodiment 1 is that the monitor includes a fixed bracket 1, an adjustment part, and a monitoring part 10. The bottom of the fixed bracket 1 is umbrella-shaped. The adjustment part includes a fixed ring 2, which is arranged horizontally. The fixed ring 2 is fixedly connected to the fixed bracket 1 by screws. An annular sliding groove 3 is formed on the fixed ring 2. A T-shaped slider 4 is slidably connected in the sliding groove 3. The bottom of the slider 4 is located in the sliding groove 3. A driving member 5 is embedded on the slider 4 located in the sliding groove 3. The driving member 5 is preferably a double-headed motor. The output shafts of the double-headed motor are coaxially fixedly connected with rollers, and the rollers are abutted against the side wall of the sliding groove 3. The top of the slider 4 is hinged with a telescopic member 6, and the telescopic member 6 is preferably an electric control cylinder.

[0131] The top end of the telescopic member 6 is hinged with a circular adjusting plate 7. The middle part of the bottom side of the adjusting plate 7 is fixedly connected with a sphere 8 by screws. The top of the fixed bracket 1 is fixedly connected with a ball hinge seat 9 by screws. The sphere 8 is rotatably connected in the ball hinge seat 9. The monitoring part 10 includes a camera, a sensor and a communication component. The camera, the sensor and the communication component are all fixedly connected to the adjusting plate 7. The camera is used to capture environmental images or videos. The sensor is used to detect environmental changes, such as temperature, humidity and air quality, etc. The communication component is connected with a remote receiver or a control center, and the communication component is used to transmit the data of the camera and the sensor to the remote receiver or the control center.

[0132] The specific implementation process is as follows:

[0133] 1. Installation preparation

[0134] Determine the installation location:

[0135] According to the monitoring requirements, select a suitable installation location to ensure that the monitor can fully cover the target area. Considering the umbrella-shaped bottom design of the fixed bracket 1, ensure that the ground is flat and can stably support.

[0136] Prepare installation tools and materials:

[0137] Prepare installation tools such as screws, screwdrivers, wrenches, electric drills, etc.

[0138] Prepare monitor components such as a double-headed motor, an electric control cylinder, a camera, a sensor, a communication component, etc.

[0139] Ensure that all components meet the design requirements and check their integrity.

[0140] 2. Assembly of the adjusting part

[0141] Installation of the fixing ring 2:

[0142] Arrange the fixing ring 2 horizontally and fixedly connect it to the fixed bracket 1 by screws.

[0143] Ensure that the connection between the fixing ring 2 and the fixed bracket 1 is firm and reliable.

[0144] Installation of the slider 4 and the driving part 5:

[0145] Completely embed the bottom of the inverted T-shaped slider 4 into the chute 3.

[0146] Embed a double-headed motor in the slider 4 and ensure that the output shaft of the double-headed motor is coaxially fixedly connected with a roller. Adjust the contact between the roller and the side wall of the chute 3 to ensure that the slider 4 can slide smoothly.

[0147] Installation of the telescopic member 6 and the adjusting plate 7:

[0148] One end of the electric control cylinder is hinged to the top of the slider 4 through a hinge seat.

[0149] Hinge the other end of the electric control cylinder to the circular adjusting plate 7.

[0150] Ensure that the telescopic function of the electric control cylinder is normal and it can drive the adjusting plate 7 to perform tilt adjustment.

[0151] Installation of the sphere 8 and the ball hinge seat 9:

[0152] Fix and connect the sphere 8 to the middle part of the bottom side of the adjusting plate 7 with screws.

[0153] Fix and connect the ball hinge seat 9 to the top of the fixed bracket 1 with screws.

[0154] Rotatably connect the sphere 8 to the ball hinge seat 9 to ensure that the adjusting plate 7 can perform three-dimensional rotation.

[0155] 3. Installation of the monitoring unit 10

[0156] Installation of the camera:

[0157] Fix and connect the camera to the adjusting plate 7 to ensure that the camera can capture environmental images or videos. Adjust the direction and angle of the camera to ensure that the target area can be fully covered.

[0158] Installation of the sensor:

[0159] Fix and connect the sensor to the adjusting plate 7 to ensure that the sensor can detect environmental changes.

[0160] Select the appropriate type and quantity of sensors according to the monitoring requirements.

[0161] Installation of the communication component:

[0162] Fix and connect the communication component to the adjusting plate 7 and ensure that its connection with the remote receiver or control center is normal.

[0163] Check the transmission function of the communication component to ensure that the data of the camera and the sensor can be transmitted in real time.

[0164] 4. Debugging and operation

[0165] System debugging:

[0166] Start the double-headed motor and test the sliding function of the slider 4 to ensure that the slider 4 can slide smoothly in the chute 3.

[0167] Start the electric control cylinder and test its telescopic function to ensure that it can drive the adjusting plate 7 to perform tilt adjustment.

[0168] Check the functions of the camera and the sensor to ensure that they can normally capture environmental images or videos and detect environmental changes.

[0169] Test the transmission function of the communication component to ensure that data can be transmitted to the remote receiver or control center in real time.

[0170] Operation monitoring:

[0171] Put the monitor in the working state and start continuously monitoring environmental changes.

[0172] Adjust the directions and angles of the camera, sensors and communication components as needed to ensure the best monitoring effect.

[0173] Regularly check the operation status of the monitor and promptly detect and handle faults or problems.

[0174] Data recording and analysis:

[0175] The remote receiver or control center receives and stores the data from the camera and sensors.

[0176] Analyze and process the data to extract useful information for environmental monitoring and early warning.

[0177] Maintenance and servicing:

[0178] Regularly maintain and service the monitor to ensure the normal operation of each component and extend its service life.

[0179] Check and replace worn or damaged components to ensure the stability and reliability of the monitor.

[0180] Obviously, the above embodiments are only examples given for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or variations can be made based on the above description. It is not necessary and impossible to list all the implementation manners here. And the obvious changes or variations derived therefrom are still within the protection scope of the present invention.

Claims

1. A trajectory planning method in a dynamic environment based on a cultural algorithm, characterized in that: The following steps are involved: S1, obtain environment and mission information: collect weather condition data, real-time monitoring data of surrounding flying objects and flight mission requirements, and build environment model and mission model based on weather condition data, real-time monitoring data of surrounding flying objects and specific requirements of flight mission; S2, online planning of achievable trajectory: using online trajectory planning method, according to the environment model and mission model, planning the achievable trajectory of the aircraft; S3, extracting characteristic nodes and knowledge: extracting characteristic nodes from reachable trajectories, and storing characteristic nodes and related information as knowledge; S4, offline optimal trajectory planning: use the stored knowledge to determine the search space for trajectory planning, and use the offline trajectory planning method to plan the optimal trajectory; S5, dynamic adjustment and re-planning: Continuously monitor environmental changes, including weather changes and the movement trajectories of surrounding flying objects. When it is found that environmental changes affect the current optimal trajectory, use the online trajectory planning method to re-plan the affected part, and use the previously extracted knowledge to guide the optimization. Then extract knowledge from the newly planned trajectory, update the optimization space, and complete the trajectory planning.

2. The method for trajectory planning in a dynamic environment based on a cultural algorithm according to claim 1 is characterized in that: In step S1, weather condition data is obtained through weather stations, satellite cloud maps and meteorological sensors carried by drones; real-time monitoring data of surrounding flying objects is collected through radar systems, ADS-B systems and communication protocols between drones; flight mission requirements include mission type, starting and end points, time limits, safety requirements, and energy consumption and efficiency.

3. The method for trajectory planning in a dynamic environment based on a cultural algorithm according to claim 2 is characterized in that: In step S1, the environmental model constructs a three-dimensional dynamic environmental model based on the collected weather data and surrounding flying object data. The dynamic environmental model includes information on weather impact areas, flying object trajectory prediction areas, and no-fly zones. The mission model defines the objective function and constraints of trajectory planning according to the specific requirements of the flight mission. The objective functions include the shortest path, the lowest energy consumption, and the best time. The constraints include avoiding obstacles, complying with flight rules, and meeting safety requirements.

4. The method for trajectory planning in a dynamic environment based on a cultural algorithm according to claim 3 is characterized in that: In step S2, the online trajectory planning method adopts a heuristic search algorithm. In the environment model, starting from the starting point, the heuristic function is used to evaluate the quality of each adjacent node, and the optimal node is selected as the next search point. This process is repeated until the end point is reached or no better node can be found. In the two-dimensional plane, the Euclidean distance can be used as the heuristic function, and the calculation formula is as follows: Where d is the straight-line distance from the current node to the adjacent node, x2-x1 and y2-y1 are the coordinates of the current node and the target node respectively.

5. The method for trajectory planning in a dynamic environment based on a cultural algorithm according to claim 4 is characterized in that: In step S3, the specific method is: pre-processing the achievable track, eliminating redundant nodes or smoothing the track, identifying characteristic nodes in the pre-processed track, and identifying the characteristic nodes according to the slope, curvature and speed change parameters of the track; extracting relevant information of the characteristic nodes and storing it as knowledge, the stored relevant information includes the coordinates, speed, altitude and heading parameters of the characteristic nodes, and the relative relationship between the nodes, the relative relationship includes distance and direction, etc. The stored relevant information also includes the position information of the characteristic nodes in the track, and the influence information of the characteristic nodes on the overall performance of the track.

6. The method for trajectory planning in a dynamic environment based on a cultural algorithm according to claim 5 is characterized in that: In step S4, the specific method is as follows: using the feature nodes and related information stored in step S3 as a knowledge base, an initial track search graph is constructed, the search graph takes the feature nodes as vertices and the relative relationships between the feature nodes as edges, forming a connected network structure, and assigning a weight to each edge in the search graph according to the position information of the feature nodes in the track and the information on the impact of the overall performance of the track, the weight reflects the cost required to move from one vertex of the edge to another vertex; Next, an offline trajectory planning algorithm is used to find the optimal path from the starting point to the end point in the constructed search graph. The optimal path search process is based on the principle of cost minimization, that is, the edges with the smallest weight are selected to form the path; during the planning process, the search algorithm is appropriately adjusted and optimized according to the objective function and constraints in the task model; finally, the offline planning algorithm will output an optimal trajectory from the starting point to the end point.

7. The method for trajectory planning in a dynamic environment based on a cultural algorithm according to claim 6 is characterized in that: In step S5, the specific contents of dynamic adjustment and re-planning are as follows: during the actual flight of the UAV, the monitor is used to continuously monitor the changes in the environment and evaluate the applicability of the current optimal track in real time; once it is found that the environmental changes have a significant impact on the safety or efficiency of the track, the re-planning mechanism is immediately triggered; the re-planning first determines the affected track segment, which is achieved by comparing the difference between the real-time monitoring data and the environmental model used in track planning; Next, the online trajectory planning method is used to locally replan the affected part, using the extracted and stored feature nodes and their related information as a guide to accelerate the search process and find a better alternative trajectory. The online planning method uses a heuristic search algorithm. At this time, the starting point and end point of the search are the starting point and end point of the affected trajectory segment, respectively. The selection and parameter setting of the heuristic function are dynamically adjusted according to the current environmental changes and flight mission requirements. After the replanning is completed, knowledge extraction is performed on the newly generated track segment, that is, new feature nodes and related information are identified and added to the knowledge base; finally, based on the new track segment and the unaffected part of the original track, the cost estimate of the entire track is updated and the flight parameters of the UAV are adjusted.

8. The method for trajectory planning in a dynamic environment based on a cultural algorithm according to claim 7 is characterized in that: In dynamic adjustment and replanning (in order to evaluate the impact of environmental changes on the track), an impact assessment index I is introduced, and its calculation formula is as follows: I=α*ΔW+β*ΔT+γ*ΔS Among them, ΔW represents the impact of weather changes on flight performance; ΔT represents the impact of changes in the movement trajectory of surrounding flying objects on flight safety; ΔS represents the cost required for track adjustment; α, β and γ are weight coefficients; The impact of weather changes on flight performance is calculated by comparing current weather data with the weather data used in trajectory planning; the impact of changes in the movement trajectory of surrounding flying objects on flight safety is evaluated by calculating the closest distance between the flying object and the trajectory or predicting potential conflict points; the cost required for trajectory adjustment includes increased flight time and increased energy consumption; the weight coefficient is dynamically adjusted according to the importance of the flight mission and the urgency of environmental changes; when the impact assessment index I exceeds the preset threshold, it is considered that the impact of environmental changes on the trajectory is significant and a re-planning mechanism needs to be triggered; the setting of the threshold is determined based on the safety requirements, time limits and energy consumption budget of the flight mission.

9. The method for trajectory planning in a dynamic environment based on a cultural algorithm according to claim 8, characterized in that: When constructing the track search graph, the reserved feature nodes are prioritized as candidate vertices, and the relative relationship between the feature nodes is dynamically updated according to the current environmental changes. At the same time, a dynamic weight is assigned to each edge in the search graph based on the impact evaluation index I and the impact information of the feature node on the overall performance of the track.

10. The method for trajectory planning in a dynamic environment based on a cultural algorithm according to claim 9, characterized in that: The monitor comprises a fixed bracket (1), an adjustment part and a monitoring part (10), wherein the adjustment part comprises a fixed ring (2), the fixed ring (2) is fixedly connected to the fixed bracket (1), a slide groove (3) is provided on the fixed ring (2), a slider (4) is slidably connected in the slide groove (3), a driving part (5) is embedded in the slider (4), a telescopic part (6) is hinged on the top of the slider (4), an adjustment plate (7) is hinged on the end of the telescopic part (6) away from the slider (4), a ball (8) is fixedly connected in the middle of the adjustment plate (7), a ball joint seat (9) is fixedly connected to the top of the fixed bracket (1), and the ball (8) is rotatably connected in the ball joint seat (9); the monitoring part (10) comprises a camera, a sensor and a communication part, and the camera, the sensor and the communication part are all fixedly connected to the adjustment plate (7).

Images