Unmanned aerial vehicle refined route planning method and device and electronic equipment

Abstract

The invention provides an unmanned aerial vehicle refined route planning method and device and electronic equipment, and relates to the field of data processing. The method comprises the following steps: acquiring three-dimensional coordinates of a target location where an unmanned aerial vehicle flies, an initial position and state of the unmanned aerial vehicle, environment information and flight conditions; calculating route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the unmanned aerial vehicle according to the three-dimensional coordinates of the target location, the initial position and state of the unmanned aerial vehicle, the environment information and the flight condition; determining a minimum comprehensive cost function based on the route length cost, the energy consumption cost, the route smoothness cost and the obstacle avoidance cost; determining constraint conditions of the unmanned aerial vehicle, wherein the constraint conditions comprise dynamic constraint, control input limitation and environmental constraint; and generating a refined route of the unmanned aerial vehicle by minimizing the comprehensive cost function and the constraint condition. By implementing the technical scheme provided by the invention, the accuracy of route planning is improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to a method, device and electronic equipment for fine-grained route planning of unmanned aerial vehicles. Background Art

[0002] With the rapid development of drone technology, its application in various industries is becoming more and more extensive, including but not limited to agricultural monitoring, environmental protection, logistics distribution and public safety.

[0003] At present, in the process of applying drones in chemical, electric power, and fire inspection, traditional drone route planning methods generally rely on preset flight routes or simple map information for real-time adjustments. However, static map data cannot reflect changes in the environment in a timely manner, which will cause the planned route to be inconsistent with the actual environment, thereby reducing the accuracy of route planning.

[0004] Therefore, there is an urgent need for a method, device and electronic equipment for fine-grained route planning of unmanned aerial vehicles. Summary of the invention

[0005] The present application provides a method, device and electronic equipment for refined route planning of unmanned aerial vehicles, which are convenient for improving the accuracy of route planning.

[0006] In a first aspect of the present application, a method for refined route planning of an unmanned aerial vehicle is provided, the method comprising: obtaining the three-dimensional coordinates of the target location of the unmanned aerial vehicle, the initial position and state of the unmanned aerial vehicle, environmental information and flight conditions; calculating the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the unmanned aerial vehicle according to the three-dimensional coordinates of the target location, the initial position and state of the unmanned aerial vehicle, environmental information and flight conditions; determining a minimized comprehensive cost function based on the route length cost, the energy consumption cost, the route smoothness cost and the obstacle avoidance cost; determining the constraints of the unmanned aerial vehicle, the constraints comprising dynamic constraints, control input restrictions and environmental constraints; and generating a refined route of the unmanned aerial vehicle by minimizing the comprehensive cost function and the constraints.

[0007] By adopting the above technical solution, by obtaining the three-dimensional coordinates, initial position, environmental information and flight conditions of the target location of the drone, the route planning can be ensured to be more in line with the actual situation. This method avoids the planning errors caused by using static or overly simple map information, can improve the accuracy and safety of the route, and ensure that the drone effectively avoids obstacles during flight. In the process of calculating the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost, multiple optimization objectives are considered. This multi-objective optimization method helps to balance the requirements of different tasks, and can reduce energy consumption and improve safety while minimizing the flight time, ensuring the efficiency and economy of task execution. Through real-time acquisition and analysis of environmental information, the planning process can better cope with dynamic environmental changes. This means that the drone can adjust its flight strategy according to real-time data and respond to emergencies in a timely manner. By clarifying the dynamic constraints, control input restrictions and environmental constraints, the flight behavior of the drone can be effectively controlled. These constraints ensure that the route planning is physically feasible, thereby avoiding unrealistic route selection in planning and enhancing the operational safety of the drone. Therefore, the above solution is convenient for improving the accuracy of route planning.

[0008] Optionally, the calculating of the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions specifically includes: ; in, is the route length cost, is the three-dimensional coordinate of the UAV at time t, is the three-dimensional coordinate of the target location.

[0009] By adopting the above technical solutions, the calculation of route length cost provides a clear quantitative indicator for the flight route of the drone. Through the clear cost function, the efficiency of different route options can be clearly evaluated, which drives the optimization algorithm to develop in the direction of the shortest route, ensuring that the drone can shorten the flight distance as much as possible when performing tasks. Minimizing route length is directly related to the reduction of flight time, which helps to improve the overall operating efficiency of the drone. The shorter the flight distance, the less time the drone needs to complete the task, which means that more tasks can be completed per unit time, thereby improving the efficiency of resource utilization. Route length is positively correlated with energy consumption. Shorter routes usually mean lower energy consumption, which is especially important for battery-powered drones. By optimizing the route length, the flight time of the drone can be extended while reducing the frequency of charging, thereby improving the economy of the flight mission. By calculating the route length cost, the time the drone stays in the air can be reduced, thereby reducing the risk of collisions and accidents. During the flight, a shorter route can reduce the time the drone is exposed to potentially dangerous environments, such as avoiding flying in crowded areas or near uncertain obstacles.

[0010] Optionally, the calculating of the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions specifically includes: ; in, is the energy cost, is the weight coefficient, v(t) is the speed of the drone, in m / s, and a(t) is the acceleration of the drone, in m / s 2 , u(t) is the control input vector, including the control items of the thrust and angular velocity of the UAV.

[0011] By adopting the above technical solutions, the calculation of energy cost enables the UAV to better control energy consumption when performing tasks. By optimizing the route to reduce energy consumption, the flight time of the UAV can be significantly extended and the frequency of charging or replacing batteries can be reduced. This economy is particularly important for long-term missions and helps to reduce overall operating costs. Reducing energy consumption is not only for economic reasons, but also helps to reduce environmental impact. The less energy a UAV uses during flight, the lower the carbon emissions and other environmental impacts. By optimizing energy cost, the sustainable development of UAVs can be promoted. By considering the impact of speed and acceleration on energy consumption, it can be ensured that the UAV operates in the optimal way at different stages of flight. Appropriate speed and acceleration control can not only reduce unnecessary energy consumption, but also improve the overall efficiency of flight, allowing UAVs to complete tasks more quickly. When calculating energy cost, the introduction of control input vectors allows UAVs to flexibly adjust thrust and angular velocity according to real-time status and environmental conditions. This flexibility enables UAVs to better adapt in complex and dynamic environments, thereby improving flight reliability and safety. The calculation of energy cost provides an important data basis for multi-objective optimization in route planning. By combining energy consumption costs with other costs, we can comprehensively consider various needs and achieve a more comprehensive optimization strategy. This integration can make drones more adaptable in different mission scenarios.

[0012] Optionally, the calculating of the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions specifically includes: ; in, is the route smoothness cost, is the heading angle, used to describe horizontal steering, is the climb angle, which is used to describe the up and down pitch of the UAV.

[0013] By adopting the above technical solution, the calculation of the route smoothness cost helps to reduce the sharp turns and drastic up and down changes of the drone during flight by analyzing the heading angle and the climb angle. This smooth route can reduce the dynamic load during flight, improve the flight stability of the drone, and reduce the risk of accidental loss of control. Route smoothness is closely related to energy consumption. Too frequent turns and altitude changes will cause frequent changes in the acceleration and deceleration of the drone, increasing energy consumption. By optimizing the route smoothness, unnecessary energy waste can be reduced and the economy of flight can be improved. The introduction of smoothness cost makes route planning not only focus on the target position and distance, but also consider the operability of the flight. This comprehensive consideration can make the route planning algorithm more intelligent, and the optimized route is not only fast but also more feasible. The optimization of route smoothness can provide important support for the autonomous flight control of the drone. By monitoring and adjusting the heading angle and the climb angle, it is ensured that the drone can autonomously select a smooth route in a changing environment, thereby improving its autonomous decision-making ability. Frequent turns and rapid pitch changes will cause greater wear on the motor and mechanical structure of the drone. By optimizing the smoothness of the flight path, this unnecessary mechanical burden can be reduced, extending the service life of the drone and reducing maintenance costs.

[0014] Optionally, the calculating of the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions specifically includes: ; in, For obstacle avoidance cost, is the space area where the drone is located, is the probability distribution of the existence of obstacles, is the expected position of the obstacle.

[0015] By adopting the above technical solutions, the calculation of obstacle avoidance cost can effectively reduce the risk of UAV colliding with obstacles during flight. By considering the probability of existence and expected position of obstacles, route planning can select safer flight routes for UAVs to ensure flight safety, especially in complex and dynamic environments. The introduction of obstacle avoidance cost allows UAVs to flexibly adjust flight routes when facing unforeseen obstacles. Dynamic planning based on the probability distribution of obstacles can ensure that UAVs can adapt to environmental changes and maintain good operational flexibility when performing tasks. By calculating the obstacle avoidance cost, routes that keep a safe distance from obstacles can be given priority in the planning process. This preventive strategy can effectively reduce the incidence of flight accidents and improve the operational reliability of UAVs. The evaluation of obstacle avoidance cost provides an important decision-making basis for the autonomous navigation of UAVs. UAVs can adjust flight routes based on real-time environmental information, achieve autonomous obstacle avoidance in complex environments, and improve the overall intelligence level.

[0016] Optionally, the minimization comprehensive cost function is determined based on the route length cost, the energy consumption cost, the route smoothness cost and the obstacle avoidance cost, and specifically adopts the following calculation formula: ; in, To minimize the comprehensive cost function, is the route length cost, is the energy cost, is the route smoothness cost, is the obstacle avoidance cost, w1, w2, w3, w4 are the function weight coefficients corresponding to each cost, u(t) is the control input vector, including the control items of the thrust and angular velocity of the drone, t f is the end time of the UAV flight, which is used to indicate the end point of the time range for route planning and optimization, and t0 is the start time of the UAV flight.

[0017] By adopting the above technical solutions, the design of the comprehensive cost function allows multiple key factors such as route length, energy consumption, route smoothness and obstacle avoidance to be considered simultaneously during the route planning process. This multi-dimensional consideration makes the final planned route more reasonable and effective, and can balance the relationship between different objectives. By introducing weight coefficients for different costs, route planning can flexibly adjust the importance of each cost according to specific mission requirements. This flexibility allows UAVs to perform personalized optimization in specific application scenarios, significantly improving the efficiency of route optimization. The calculation process of minimizing the comprehensive cost function enables UAVs to make flexible decisions in a dynamic environment. Based on the real-time collected data and changing environmental conditions, UAVs can adjust their flight strategies in real time to optimize routes and ensure flight safety and efficiency under complex conditions. By considering obstacle avoidance costs and route smoothness, the comprehensive cost function adds safety guarantees in route planning. The optimized route can effectively avoid obstacles and reduce the risk of accidental collisions, thereby improving the operational safety of UAVs.

[0018] Optionally, the determining of the constraint condition of the drone specifically adopts the following calculation formula: ; in, Used to express dynamic constraints, is the state vector, is the control input vector; ; in, Used to indicate control input limits, and are the minimum and maximum values ​​of the control input respectively; ; in, Used to represent environmental constraints, Used to indicate safe spaces to prevent drones from entering dangerous areas.

[0019] By adopting the above technical solutions, constraints can effectively limit the behavior of drones during flight and ensure that they operate within a safe range. Environmental constraints can prevent drones from entering dangerous areas, reduce the risk of accidents or collisions, and thus ensure flight safety. Through dynamic constraints, route planning can fully consider the physical characteristics and motion limitations of drones. This consideration can ensure that the planned route is feasible in actual operation, thereby avoiding control failure caused by excessive speed or excessive maneuvering. Setting control input limits can ensure the stability and controllability of drones during operation. Such constraints help prevent flight loss due to excessive manipulation and improve the operational safety of drones. The introduction of constraints helps to narrow the search range of feasible solutions, allowing the route planning algorithm to find a suitable flight route more quickly. By limiting the space of feasible solutions, computational efficiency can be improved and planning time can be reduced.

[0020] Optionally, generating a refined route for the UAV by minimizing the comprehensive cost function and the constraint conditions specifically includes: obtaining an initial route, wherein the initial route is constructed according to the initial position of the UAV and the target location; under the constraint conditions, solving the minimized comprehensive cost function using a non-dominated sorting genetic algorithm to obtain an optimal route; optimizing the initial route using the optimal route to generate a refined route for the UAV, wherein the refined route of the UAV consists of multiple waypoints, and each waypoint satisfies the constraint conditions.

[0021] By adopting the above technical solution, the construction of the initial route is based on the actual initial position and target location of the UAV, which ensures the rationality of the route. By optimizing the comprehensive cost function using the non-dominated sorting genetic algorithm, a more accurate route planning can be obtained, which improves the success rate of the overall mission. The non-dominated sorting genetic algorithm can simultaneously consider the route length, energy consumption, route smoothness and obstacle avoidance cost, and find the optimal solution. This multi-objective optimization capability enables the planned route to show high performance in all aspects. Optimizing the initial route under constraints enables the generated refined route to adapt to complex environments and changing conditions. Such flexibility is crucial for UAVs to perform various tasks, ensuring that they can respond to different situations efficiently. By optimizing the route, especially in terms of energy consumption, the operating cost of the UAV can be significantly reduced. The planned route is optimized to reduce unnecessary energy consumption, improve flight efficiency, and save resources for the long-term operation of the UAV. The generated refined route follows the preset constraints to ensure that the UAV will not enter the dangerous area during flight. This improvement in safety can reduce the risk of accidents and provide protection for the operation of UAVs in complex environments.

[0022] In a second aspect of the present application, a device for fine-grained route planning of an unmanned aerial vehicle is provided, and the device for fine-grained route planning of an unmanned aerial vehicle includes an acquisition module and a processing module, wherein the acquisition module is used to acquire the three-dimensional coordinates of the target location of the unmanned aerial vehicle flight, the initial position and state of the unmanned aerial vehicle, environmental information and flight conditions; the processing module is used to calculate the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the unmanned aerial vehicle according to the three-dimensional coordinates of the target location, the initial position and state of the unmanned aerial vehicle, environmental information and flight conditions; the processing module is also used to determine the minimized comprehensive cost function based on the route length cost, the energy consumption cost, the route smoothness cost and the obstacle avoidance cost; the processing module is also used to determine the constraints of the unmanned aerial vehicle, and the constraints include dynamic constraints, control input restrictions and environmental constraints; the processing module is also used to generate the refined route of the unmanned aerial vehicle by minimizing the comprehensive cost function and the constraints.

[0023] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.

[0024] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.

[0025] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: By obtaining the three-dimensional coordinates, initial position, environmental information and flight conditions of the target location of the drone, the route planning can be ensured to be more in line with the actual situation. This method avoids the planning errors caused by using static or overly simple map information, can improve the accuracy and safety of the route, and ensure that the drone can effectively avoid obstacles during flight. In the process of calculating the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost, multiple optimization objectives are considered. This multi-objective optimization method helps to balance the requirements of different tasks, and can reduce energy consumption and improve safety while minimizing flight time, ensuring the efficiency and economy of task execution. Through real-time acquisition and analysis of environmental information, the planning process can better cope with dynamic environmental changes. This means that the drone can adjust its flight strategy based on real-time data and respond to emergencies in a timely manner. By clarifying dynamic constraints, control input restrictions and environmental constraints, the flight behavior of the drone can be effectively controlled. These constraints ensure that route planning is physically feasible, thereby avoiding unrealistic route selection in planning and enhancing the operational safety of the drone. Therefore, the above scheme is convenient for improving the accuracy of route planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A flowchart of a method for refined route planning for an unmanned aerial vehicle provided in an embodiment of the present application.

[0027] Figure 2 Another flowchart of a method for refined route planning for unmanned aerial vehicles provided in an embodiment of the present application.

[0028] Figure 3 A schematic diagram of a module of a drone refined route planning device provided in an embodiment of the present application.

[0029] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0030] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION

[0031] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0032] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0033] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0034] With the rapid development of drone technology, this advanced technology is increasingly being used in various industries, covering a variety of fields such as agricultural monitoring, environmental protection, logistics distribution and public safety. In these applications, drones not only improve work efficiency, but also enhance the flexibility and feasibility of tasks.

[0035] However, in the application of drones in specific fields such as chemical industry, electric power, and fire inspection, traditional route planning methods generally rely on preset flight routes or real-time adjustments based on simple map information. The limitation of this method is that the method based on static map data is too single, and static map data cannot effectively reflect the dynamic changes in the environment. This information lag often leads to a large difference between the planned route and the actual environment, which seriously reduces the accuracy and effectiveness of route planning.

[0036] In order to solve the above technical problems, this application provides a method for fine-grained route planning of unmanned aerial vehicles. Figure 1 , Figure 1 A flowchart of a method for fine-grained route planning of a drone provided in an embodiment of the present application is provided. The method for fine-grained route planning of a drone is applied to a server, and includes steps S110 to S150. The steps are as follows: S110, obtaining the three-dimensional coordinates of the target location of the UAV flight, the initial position and state of the UAV, environmental information and flight conditions.

[0037] Specifically, the server is a computer system or server cluster, which plays a core computing and decision-making role in drone route planning. It is not only responsible for collecting and processing various key data, but also generates refined routes through analysis and optimization. In addition, the server can monitor the execution of tasks in real time and make dynamic adjustments according to environmental changes, thereby improving the success rate and safety of drone missions. Among them, the three-dimensional coordinates of the target location are the end point of the drone flight mission and define the location where the drone needs to reach. This coordinate usually includes longitude, latitude and altitude information to accurately locate the target of the drone. For example, in agricultural monitoring, the target location may be a specific area of ​​a farmland, while in power inspection, it may be the location of a certain electric tower. The initial position refers to the three-dimensional position coordinates of the drone when it takes off, which also includes longitude, latitude and altitude. The initial state of the drone describes its current conditions and flight status, such as battery power, speed, direction, attitude, such as pitch angle and roll angle, etc. Understanding the initial position and state of the drone is the basis for planning routes and controlling flight. For example, if the drone is located on the roof of a warehouse, the initial state information will tell the server whether the battery power is sufficient for the mission or whether the take-off direction needs to be adjusted. Environmental information covers the environmental conditions in the drone's flight area, such as weather factors such as wind speed and direction, temperature, humidity, and air pressure. In addition, it also includes the location and distribution of surrounding obstacles, such as buildings and trees. Real-time environmental data helps drones avoid obstacles and choose safer and more energy-efficient routes. For example, if the wind speed in a certain area is too high, the drone may need to take a detour or lower its flight altitude to reduce the impact of the wind. Flight conditions refer to the specific requirements and restrictions that drones need to meet when performing missions, such as maximum flight altitude, minimum safety distance, flight speed range, etc. These conditions are determined by mission requirements or local flight regulations. For example, in a fire inspection mission, flight conditions may require the drone to maintain stable flight in a high temperature or smoky environment and comply with the prescribed flight altitude.

[0038] For example, suppose a drone is performing an electric inspection mission. The server first obtains the three-dimensional coordinates of the target location, for example, the target is the location of a high-voltage power tower, with longitude 120.4321°, latitude 31.1234°, and height 50 meters. Next, the server records the initial location of the drone, such as the roof of the power company headquarters, with coordinates of 120.4000°, 31.1000°, and 10 meters. In addition, the initial state of the drone may include a battery charge of 90%, a current speed of 0m / s (stationary), a direction of 30° north by east, and a stable attitude. Then, the server also needs to obtain environmental information, such as the current wind speed of 10km / h, the wind direction of 20° south by west, the temperature of 30°C, and tall trees and buildings around. Finally, the server records the flight conditions, such as the maximum allowable height of the drone is 100 meters, the minimum safety distance is 5 meters, and the maximum flight speed is 20m / s. All of this data will be used by the server to calculate the best flight route, ensuring that the drone completes its power inspection mission safely and efficiently.

[0039] In an embodiment of the present application, the three-dimensional coordinates of the target location can be input by the user through the software interface of the drone task management system, and the server receives the input data and converts it into three-dimensional coordinates. For example, in an agricultural monitoring task, the user can specify the boundary points of the farmland, and the system will generate the target coordinates. The initial position and state of the drone can be monitored by sensors on the drone, such as accelerometers, gyroscopes, attitude sensors, etc., to monitor the flight status, such as speed, acceleration, flight attitude, etc., and send these data to the server. For example, if the speed of the drone exceeds the set value, the server can adjust the route accordingly. The way to obtain environmental information includes: the server can obtain real-time weather information by accessing an online weather service interface, such as a meteorological bureau or a commercial weather service provider. For example, in a fire inspection task, the server needs to understand the wind speed and wind direction in the current area to determine whether the drone is suitable for flight. The server can also access digital maps and geographic information systems to obtain information about the terrain and obstacle distribution of the flight area. For example, in a power inspection task, the server can obtain terrain data and potential obstacle locations around the transmission line. In addition, for dynamic environments, the server can use sensor networks, such as real-time information provided by lidar or cameras, to understand the distribution of surrounding obstacles.

[0040] S120, calculating the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions.

[0041] Specifically, the route length cost refers to the length of the route required for the drone to fly from the starting point to the target location. The route length cost is used to evaluate the distance the drone flies, which directly affects the speed of mission completion and the overall flight time. Among them, a shorter route means faster mission completion, but other cost factors must be balanced. The route length is calculated by the initial position of the drone and the three-dimensional coordinates of the target location. The longer the route, the higher the cost. The energy consumption cost reflects the energy consumed by the drone during the flight. Factors affecting the energy consumption cost include flight speed, acceleration, load, weather conditions, etc. Optimizing the energy consumption cost can extend the flight time of the drone, which is especially important in long-term inspections or multi-task scenarios. The total energy consumption is estimated by the speed, acceleration, and control input of the drone. High speed or frequent acceleration and deceleration will increase energy consumption. The route smoothness cost refers to the smoothness of the drone on the flight route. Route smoothness is related to the steering angle and climb angle of the drone. A smooth route can not only reduce the physical stress of the body, but also reduce energy consumption and improve flight stability. Steep climbs or sharp turns will result in higher smoothness costs. The smoothness of the route is evaluated based on the heading angle and climb angle of the drone. The more dramatic the angle change, the higher the cost. Obstacle avoidance cost refers to the price the drone pays to avoid obstacles during flight. The obstacle avoidance cost is related to the environmental information around the drone, including the distribution of obstacles and their possible movement trajectories. A higher obstacle avoidance cost indicates that the drone needs to bypass multiple obstacles, which may extend the flight time or increase energy consumption. The server evaluates the additional length or complexity of the obstacle avoidance route based on the distribution of obstacles in the environment and their impact range. Areas with dense obstacles will result in higher obstacle avoidance costs.

[0042] For example, suppose a drone is performing a forest fire monitoring mission, and its target location is in the middle of a forest. The server needs to calculate the cost of the route based on a variety of factors to plan a safe and efficient flight route. The drone's initial position is at the edge of the forest, and the target location is in the central area 3 kilometers away from the starting point. The server calculates the straight-line distance from the drone's initial position to the target location and uses the length of this route as part of the route length cost. When calculating energy consumption, the server considers the drone's flight speed and acceleration. For example, if the drone needs to fly at a speed of 10 meters per second and frequently accelerates and decelerates to cope with air flow changes in the forest, the energy cost will increase. In addition, the server will evaluate whether the mission will exceed the drone's battery capacity and adjust the route planning based on the remaining battery. When flying inside the forest, the drone needs to bypass many large trees and other natural obstacles, and may change flight direction and altitude many times. The server calculates the horizontal turning angle and climb angle of the drone on the route to evaluate the smoothness of the route. If the route contains many sharp turns or steep climbs, the route smoothness cost will be higher, which may affect flight stability. The server analyzes obstacle information in the forest, including the location and density of trees. If there are large areas of dense trees or cliffs, the obstacle avoidance cost increases significantly. The server estimates the additional routes the drone needs to take to get around these obstacles and factors that into the cost.

[0043] In a possible implementation, the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone are calculated based on the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions, specifically including: ; in, is the route length cost, is the three-dimensional coordinate of the UAV at time t, is the three-dimensional coordinate of the target location.

[0044] Specifically, the above formula calculates the straight-line distance between the current position of the drone and the target location, based on the distance formula. This method measures the shortest straight-line route from the starting point to the end point, which is calculated in three-dimensional space using the square root of the sum of the squares of the coordinate differences. By calculating the route length cost, the system can evaluate the distance of different flight routes, so that shorter routes can be given priority in route planning to save energy and time. Through this formula, the server can effectively evaluate the length of the flight route and make optimal choices in route planning, which can save energy and improve the efficiency of the task.

[0045] In a possible implementation, the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone are calculated based on the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions, specifically including: ; in, is the energy cost, is the weight coefficient, v(t) is the speed of the drone, in m / s, and a(t) is the acceleration of the drone, in m / s 2 , u(t) is the control input vector, including the control items of the thrust and angular velocity of the UAV.

[0046] Specifically, the formula measures the square integral of the drone's speed during the entire flight process. The higher the speed, the greater the energy cost, especially when flying at high speed for a long time. The formula measures the square integral of the acceleration to reflect the drastic change of the drone's speed during flight. If the drone accelerates or decelerates frequently, this part of the cost will increase. The formula measures the square integral of the control input to reflect the energy consumption of the drone's control system. Greater thrust or more drastic angular velocity adjustments will result in higher energy consumption. This calculation method helps to effectively manage and optimize energy consumption in route planning, and improve the drone's flight efficiency and mission completion capabilities. Among them, the weight coefficient can be customized according to the user's actual ability to bear the cost.

[0047] In a possible implementation, the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone are calculated based on the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions, specifically including: ; in, is the route smoothness cost, is the heading angle, used to describe horizontal steering, is the climb angle, which is used to describe the up and down pitch of the UAV.

[0048] Specifically, frequent horizontal turns will increase this cost, resulting in unstable flight. Frequent climbing and descending actions will also increase this cost. The greater the rate of change of the heading angle and the climb angle, the more drastic the change in the drone's route, affecting the smoothness of the flight. In addition, the formula can also add weight coefficients, and different weight coefficients can be adjusted according to specific task requirements. For example, for some tasks, horizontal smoothness may be more emphasized, while for other tasks, vertical stability may be more concerned. For example, in power inspection tasks, a stable route can improve the accuracy of data collection, especially when the drone needs to fly close to high-voltage towers, stability is crucial. This calculation method can effectively evaluate and optimize the flight trajectory of the drone, making it more suitable for complex environments and mission requirements, thereby improving flight efficiency and safety.

[0049] In a possible implementation, the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone are calculated based on the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions, specifically including: ; in, For obstacle avoidance cost, is the space area where the drone is located, is the probability distribution of the existence of obstacles, is the expected position of the obstacle.

[0050] Specifically, the obstacle avoidance cost is calculated by integrating all potential obstacle risks in the UAV's flight space, combining the probability distribution of obstacles and the expected position. Through this method, the UAV can evaluate the risks of different routes and select the route with the lowest obstacle avoidance cost to ensure safety. Among them, the expected position can be obtained by the following methods: the UAV is equipped with laser radar, ultrasonic sensors, cameras and other equipment to detect the environment in real time and determine the actual position of obstacles. The scanning results of the sensors provide high-precision obstacle position information, which is used to update and correct the expected position; the pre-built three-dimensional map of the environment contains information about fixed obstacles, such as buildings, trees, terrain, etc. The UAV can use this map information to predict the possible obstacle position. For mobile obstacles, such as pedestrians, vehicles or other aircraft, the server will dynamically adjust the expected position in combination with the real-time data of the sensors. This dynamic update mechanism ensures that the UAV can respond to environmental changes in a timely manner. For example, in a rescue mission, the UAV can quickly identify obstacles such as collapsed buildings or flying debris and choose a low-risk route. This obstacle avoidance cost calculation method makes the UAV safer and more reliable when flying in complex environments. By effectively utilizing sensor and map data, drones can quickly respond to environmental changes, optimize flight routes, and minimize the risk of collision.

[0051] S130, determining a minimized comprehensive cost function based on the route length cost, energy consumption cost, route smoothness cost, and obstacle avoidance cost.

[0052] Specifically, the server uses a comprehensive cost function to combine these cost factors, and the goal is to minimize this comprehensive cost function. Each cost item will be set with different weight coefficients according to the specific situation to determine their relative importance in the optimization process.

[0053] For example, suppose a drone is performing a building facade inspection mission. It needs to take off from the ground, fly around the building, and finally return to the ground. During the flight, the server needs to plan a safe and efficient route. The server calculates the length of all possible routes from the starting point to the end point. If a route is long, the route length cost will be high, which affects the flight efficiency of the drone. Therefore, the server tends to choose shorter routes. For example, a flight route length of 500 meters is more ideal than a route of 800 meters. Drones consume more energy when accelerating, decelerating, and ascending. The server calculates the energy consumption of each route and selects the route with less energy consumption. For example, route A requires multiple ascents and accelerations, and the total energy consumption is high, while route B is a smooth horizontal flight with lower energy consumption. The server will prefer route B. If the drone needs to turn frequently or pitch up and down during the route, this will reduce flight stability. The server calculates the smoothness cost of the route and selects the smooth route. For example, route C includes several sharp turns, while route D is a smooth arc. Route D has a lower smoothness cost and is therefore more popular. There may be obstacles around the building, such as scaffolding, cranes, or other aircraft. The server calculates the obstacle avoidance cost and selects the less risky route. For example, route E passes through densely built areas and has a higher obstacle avoidance cost, while route F bypasses these areas and has a lower obstacle avoidance cost. Finally, the server combines all cost items and uses an optimization algorithm to minimize the comprehensive cost function. Therefore, the server selects a route with the lowest comprehensive cost, ensuring that the drone flies safely, efficiently, and saves as much energy as possible.

[0054] In a possible implementation, based on the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost, a minimized comprehensive cost function is determined, specifically using the following calculation formula: ; in, To minimize the comprehensive cost function, is the route length cost, is the energy cost, is the route smoothness cost, is the obstacle avoidance cost, w1, w2, w3, w4 are the function weight coefficients corresponding to each cost, u(t) is the control input vector, including the control items of the thrust and angular velocity of the drone, t f is the end time of the UAV flight, which is used to indicate the end point of the time range for route planning and optimization, and t0 is the start time of the UAV flight.

[0055] Specifically, the calculation principle of minimizing the comprehensive cost function is to combine multiple related cost factors to form a single optimization goal. This method enables the drone to consider multiple influencing factors at the same time when planning the route, so as to select the best route. Among them, the weight coefficient reflects the relative importance of each cost factor in the overall optimization. By adjusting these coefficients, one aspect can be emphasized. For example, in a high-risk environment, the weight of the obstacle avoidance cost can be increased, thereby affecting the final route selection. The solution uses optimization algorithms such as genetic algorithms, particle swarm optimization, gradient descent method, etc., and finds the route that minimizes the comprehensiveness by continuously adjusting the route and related parameters. By limiting the time range of optimization, the drone can complete the flight mission within the set time. This helps to make timely adjustments in a dynamic environment.

[0056] S140. Determine the constraints of the UAV, where the constraints include dynamic constraints, control input limitations, and environmental constraints.

[0057] Specifically, dynamic constraints refer to the physical limitations imposed on a drone during flight. These limitations are mainly related to factors such as the drone's equation of motion, mass, thrust, and gravity. Dynamic constraints ensure that a drone operates within its feasible flight performance range. For example, assuming a drone has a maximum thrust of 10 Newtons and a mass of 1 kg, its maximum acceleration is 10 m / s. 2 This means that the drone cannot accelerate more than 10m / s at any time. 2. In addition, the climb rate, i.e. the vertical speed, and the rate of change of the heading angle need to be considered, which are also part of the dynamic constraints. Control input limits refer to the constraints imposed on the drone control system to ensure that the drone's operations and responses are within a safe and effective range. This includes limits on thrust, steering, and other control variables. For example, the effective range of thrust may be 0 to 10 Newtons, and the limit of angular velocity may be ±3rad / s. This means that during the flight of the drone, the thrust cannot be less than 0 Newtons, that is, it cannot hover, and it cannot exceed 10 Newtons to prevent damage to the motor or loss of control. Environmental constraints refer to the external conditions that the drone must comply with during flight. These conditions are usually related to the environmental characteristics of the flight area, such as obstacles, flight altitude restrictions, meteorological conditions, etc. These constraints ensure the safety of the drone's flight and effectively avoid conflicts with the surrounding environment. For example, suppose there are high-rise buildings, trees, or other obstacles in the area where the drone is flying. In such a case, environmental constraints may include: the drone's flight altitude must be higher than a certain height, such as 50 meters, to avoid the top of the building; the flight route must not pass through certain areas, such as during emergency rescue or firefighting activities, some areas may be designated as prohibited flight areas. Therefore, these constraints ensure that the flight of the drone not only meets the technical and physical characteristics, but also takes into account safety and operational effectiveness in the drone route planning. By setting and processing these constraints reasonably, the server can generate effective, reliable and safe flight routes, thereby improving the application efficiency of the drone and ensuring the smooth completion of the mission.

[0058] In a possible implementation, the constraint conditions of the drone are determined by using the following calculation formula: ; in, Used to express dynamic constraints, is the state vector, is the control input vector; ; in, Used to indicate control input limits, and are the minimum and maximum values ​​of the control input respectively; ; in, Used to represent environmental constraints, Used to indicate safe spaces to prevent drones from entering dangerous areas.

[0059] Specifically, constraints play a vital role in the flight process of drones, effectively restricting their behavior and ensuring that drones always operate within a safe range. The setting of environmental constraints can effectively prevent drones from entering dangerous areas, thereby significantly reducing the risk of accidents or collisions and ensuring flight safety. By introducing dynamic constraints, route planning can fully consider the physical characteristics and motion limitations of drones. This consideration ensures that the planned route is feasible in actual operation and avoids control failure caused by excessive speed or excessive maneuvering. At the same time, setting control input limits ensures the stability and controllability of the drone during operation. Such constraints help prevent flight loss caused by excessive manipulation, thereby improving the safety of drone operations. In addition, the introduction of these constraints can effectively narrow the search range of feasible solutions, allowing the route planning algorithm to find a suitable flight route more quickly. By limiting the space of feasible solutions, not only is the computational efficiency improved, but the time required for planning is also significantly reduced.

[0060] S150, generating a refined route for the UAV by minimizing the comprehensive cost function and constraints.

[0061] Specifically, minimizing the comprehensive cost function takes into account a variety of cost factors, including route length cost, energy consumption cost, route smoothness cost, and obstacle avoidance cost. By minimizing these costs, the goal is to find an optimal route so that the drone consumes less time, energy, and improves flight safety while meeting mission requirements. Constraints ensure that the drone's flight route is physically feasible and does not enter dangerous areas or violate other safety regulations. Through these constraints, it can be ensured that the generated route is safe and reliable in actual operation. Based on minimizing the comprehensive cost function and satisfying the constraints, the algorithm will output a specific flight route, namely the refined route.

[0062] In one possible implementation, a refined route for the UAV is generated by minimizing the comprehensive cost function and the constraints, referring to Figure 2 , Figure 2 Another flow chart of a method for refined route planning of a UAV provided in an embodiment of the present application specifically includes steps S210 to S230, and the above steps are as follows: S210, obtaining an initial route, the initial route is constructed according to the initial position and target location of the UAV; S220, under constraints, using a non-dominated sorting genetic algorithm to solve the minimized comprehensive cost function to obtain an optimal route; S230, using the optimal route to optimize the initial route to generate a refined route of the UAV, the refined route of the UAV consists of multiple waypoints, and each waypoint satisfies the constraints.

[0063] Specifically, the initial route is constructed based on the starting position and target location of the drone. This route can be preliminarily determined by a simple straight line connection. The initial route provides the basis for subsequent optimization. During the optimization process, it is necessary to ensure that the route follows certain specific constraints, such as the flight altitude, speed limit, and prohibited flight areas of the drone. These constraints are the key to ensuring flight safety and efficiency. In order to solve the problem of minimizing the comprehensive cost function, the embodiment of the present application adopts a non-dominated sorting genetic algorithm, which can consider multiple objectives at the same time and find the optimal solution. The algorithm gradually improves in the population of potential solutions through mechanisms such as selection, crossover, and mutation, and finally obtains the optimal route that meets the constraints. The optimal route is based on the result of the optimization algorithm. This route is used to further optimize the initial route and generate a refined route. The refined route consists of multiple waypoints to ensure that each waypoint meets the previously set constraints.

[0064] For example, suppose the initial position of the drone is at a distribution center with coordinates (0, 0, 0), and the target location is the customer location with coordinates (30, 40, 10). Here are the specific steps: First, the server connects the initial position and the target location with a simple straight line to derive an initial route, such as a route from (0, 0, 0) to (30, 40, 10). Constraints may include: the drone cannot be lower than 20 meters in a certain area; the maximum speed is limited to 10 meters / second and the minimum speed is 2 meters / second; no-fly zones, such as near airports or other sensitive areas. Next, the server uses a non-dominated sorting genetic algorithm, which starts from the initial route, considers multiple costs, and optimizes under the premise of satisfying the above constraints. The algorithm may go through multiple generations of iterations to generate multiple candidate routes. Suppose the algorithm finally derives a new route, from (0, 0, 25) to (15, 20, 30) to (30, 40, 10), which is smoother and safer than the initial route. Finally, the optimal route is used to optimize the initial route. The resulting refined route includes multiple waypoints, such as (0, 0, 25), (15, 20, 30), (30, 40, 10), and ensures that the height and position of each waypoint meet the set constraints. Through the above steps, the drone finally obtains a safe and efficient refined route, and can effectively perform the mission by flying according to each waypoint.

[0065] This application also provides a UAV refined route planning device, referring to Figure 3 , Figure 3A module schematic diagram of a drone refined route planning device provided in an embodiment of the present application. The drone refined route planning device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 acquires the three-dimensional coordinates of the target location of the drone flight, the initial position and state of the drone, environmental information, and flight conditions; the processing module 32 calculates the route length cost, energy consumption cost, route smoothness cost, and obstacle avoidance cost of the drone based on the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information, and flight conditions; the processing module 32 determines the minimized comprehensive cost function based on the route length cost, energy consumption cost, route smoothness cost, and obstacle avoidance cost; the processing module 32 determines the constraints of the drone, which include dynamic constraints, control input restrictions, and environmental constraints; the processing module 32 generates a refined route for the drone by minimizing the comprehensive cost function and the constraints.

[0066] In a possible implementation, the processing module 32 calculates the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions, specifically including: ; in, is the route length cost, is the three-dimensional coordinate of the UAV at time t, is the three-dimensional coordinate of the target location.

[0067] In a possible implementation, the processing module 32 calculates the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions, specifically including: ; in, is the energy cost, is the weight coefficient, v(t) is the speed of the drone, in m / s, and a(t) is the acceleration of the drone, in m / s 2 , u(t) is the control input vector, including the control items of the thrust and angular velocity of the UAV.

[0068] In a possible implementation, the processing module 32 calculates the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions, specifically including: ; in, is the route smoothness cost, is the heading angle, used to describe horizontal steering, is the climb angle, which is used to describe the up and down pitch of the UAV.

[0069] In a possible implementation, the processing module 32 calculates the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions, specifically including: ; in, For obstacle avoidance cost, is the space area where the drone is located, is the probability distribution of the existence of obstacles, is the expected position of the obstacle.

[0070] In a possible implementation, the processing module 32 determines the minimum comprehensive cost function based on the route length cost, energy consumption cost, route smoothness cost, and obstacle avoidance cost, specifically using the following calculation formula: ; in, To minimize the comprehensive cost function, is the route length cost, is the energy cost, is the route smoothness cost, is the obstacle avoidance cost, w1, w2, w3, w4 are the function weight coefficients corresponding to each cost, u(t) is the control input vector, including the control items of the thrust and angular velocity of the drone, t f is the end time of the UAV flight, which is used to indicate the end point of the time range for route planning and optimization, and t0 is the start time of the UAV flight.

[0071] In a possible implementation, the processing module 32 determines the constraint conditions of the drone by specifically using the following calculation formula: ; in, Used to express dynamic constraints, is the state vector, is the control input vector; ; in, Used to indicate control input limits, and are the minimum and maximum values ​​of the control input respectively; ; in, Used to represent environmental constraints, Used to indicate safe spaces to prevent drones from entering dangerous areas.

[0072] In a possible implementation, the processing module 32 generates a refined route for the UAV by minimizing the comprehensive cost function and constraints, specifically including: the acquisition module 31 acquires the initial route, and the initial route is constructed according to the initial position and target location of the UAV; the processing module 32 uses a non-dominated sorting genetic algorithm to solve the minimized comprehensive cost function under constraints to obtain the optimal route; the processing module 32 uses the optimal route to optimize the initial route to generate a refined route for the UAV, and the refined route of the UAV consists of multiple waypoints, and each waypoint satisfies the constraints.

[0073] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0074] The present application also provides an electronic device, referring to Figure 4 , Figure 4 The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .

[0075] The communication bus 42 is used to realize the connection and communication between these components.

[0076] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.

[0077] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0078] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.

[0079] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a method for fine-grained route planning of a drone.

[0080] exist Figure 4In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program storing a method for refined route planning of a drone in the memory 45. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0081] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0082] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0083] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0085] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0087] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0088] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for fine-grained route planning of an unmanned aerial vehicle, characterized in that: The method comprises: Obtain the three-dimensional coordinates of the target location of the drone flight, the initial position and status of the drone, environmental information, and flight conditions; Calculate the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the UAV according to the three-dimensional coordinates of the target location, the initial position and state of the UAV, environmental information and flight conditions; Determining a minimized comprehensive cost function based on the route length cost, the energy consumption cost, the route smoothness cost, and the obstacle avoidance cost; Determining constraints of the drone, the constraints comprising dynamic constraints, control input limitations, and environmental constraints; By minimizing the comprehensive cost function and the constraint conditions, a refined route of the UAV is generated.

2. The method for fine-grained UAV route planning according to claim 1, characterized in that: The calculating of the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the UAV according to the three-dimensional coordinates of the target location, the initial position and state of the UAV, environmental information and flight conditions specifically includes: ； in, is the route length cost, is the three-dimensional coordinate of the UAV at time t, is the three-dimensional coordinate of the target location.

3. The method for fine-grained UAV route planning according to claim 1, characterized in that: The calculating of the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the UAV according to the three-dimensional coordinates of the target location, the initial position and state of the UAV, environmental information and flight conditions specifically includes: ； in, is the energy cost, is the weight coefficient, v(t) is the speed of the drone, in m / s, and a(t) is the acceleration of the drone, in m / s 2 , u(t) is the control input vector, including the control items of the thrust and angular velocity of the UAV.

4. The method for fine-grained route planning of a UAV according to claim 1, characterized in that: The calculating of the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the UAV according to the three-dimensional coordinates of the target location, the initial position and state of the UAV, environmental information and flight conditions specifically includes: ； in, is the route smoothness cost, is the heading angle, used to describe horizontal steering, is the climb angle, which is used to describe the up and down pitch of the UAV.

5. The method for fine-grained route planning of a UAV according to claim 1, characterized in that: The calculating of the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the UAV according to the three-dimensional coordinates of the target location, the initial position and state of the UAV, environmental information and flight conditions specifically includes: ； in, For obstacle avoidance cost, is the space area where the drone is located, is the probability distribution of the existence of obstacles, is the expected position of the obstacle.

6. The method for fine-grained UAV route planning according to claim 1, characterized in that: The minimization of the comprehensive cost function is determined based on the route length cost, the energy consumption cost, the route smoothness cost and the obstacle avoidance cost, and specifically adopts the following calculation formula: ； in, To minimize the comprehensive cost function, is the route length cost, is the energy cost, is the route smoothness cost, is the obstacle avoidance cost, w1, w2, w3, w4 are the function weight coefficients corresponding to each cost, u(t) is the control input vector, including the control items of the thrust and angular velocity of the drone, t f is the end time of the UAV flight, which is used to indicate the end point of the time range for route planning and optimization, and t0 is the start time of the UAV flight.

7. The method for fine-grained UAV route planning according to claim 1, characterized in that: The constraint conditions of the UAV are determined by using the following calculation formula: ； in, Used to express dynamic constraints, is the state vector, is the control input vector; ； in, Used to indicate control input limits, and are the minimum and maximum values ​​of the control input respectively; ； in, Used to represent environmental constraints, Used to indicate safe spaces to prevent drones from entering dangerous areas.

8. The method for fine-grained route planning of a UAV according to claim 1, characterized in that: The generating of the refined route of the UAV by minimizing the comprehensive cost function and the constraint condition specifically includes: Acquire an initial route, where the initial route is constructed according to the initial position of the UAV and the target location; Under the constraints, a non-dominated sorting genetic algorithm is used to solve the minimized comprehensive cost function to obtain an optimal route; The initial route is optimized using the optimal route to generate a refined route for the UAV, where the refined route for the UAV consists of a plurality of waypoints, and each of the waypoints satisfies the constraint condition.

9. A device for fine-grained route planning of a drone, characterized in that: The unmanned aerial vehicle refined route planning device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to acquire the three-dimensional coordinates of the target location of the UAV flight, the initial position and state of the UAV, environmental information and flight conditions; The processing module (32) is used to calculate the route length cost, energy consumption cost, route smoothness cost and obstacle avoidance cost of the drone according to the three-dimensional coordinates of the target location, the initial position and state of the drone, environmental information and flight conditions; The processing module (32) is further used to determine a minimized comprehensive cost function based on the route length cost, the energy consumption cost, the route smoothness cost and the obstacle avoidance cost; The processing module (32) is further used to determine the constraints of the drone, wherein the constraints include dynamic constraints, control input limitations and environmental constraints; The processing module (32) is also used to generate a refined route for the drone by minimizing the comprehensive cost function and the constraint conditions.

10. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 8.

Images