Low-altitude logistics unmanned aerial vehicle path planning method and system

Abstract

The invention discloses a low-altitude logistics unmanned aerial vehicle path planning method and system, and relates to the technical field of unmanned aerial vehicle logistics transportation, and the method comprises the steps: firstly, carrying out the optimization through calculating a preliminary path and combining the terrain and weather information; a sensor is used for detecting and dynamically avoiding obstacles; secondly, data transmission between the unmanned aerial vehicle and the ground control center is achieved, and the ground control center carries out monitoring, control and data processing. According to the low-altitude logistics unmanned aerial vehicle path planning system, efficient path planning is realized through multi-module cooperation. According to the invention, the flight safety, path planning accuracy and energy utilization efficiency of the unmanned aerial vehicle can be improved, the operation cost is reduced, and the system adapts to complex environmental conditions.

Description

Technical Field

[0001] The present application relates to the field of drone logistics transportation technology, and specifically to a low-altitude logistics drone path planning method and system. Background Art

[0002] With the widespread adoption of low-altitude logistics drones in the logistics industry, their path planning methods and systems have become key technologies for improving transportation efficiency. Existing technologies primarily achieve accurate path selection through algorithm optimization. Obstacle avoidance systems, combined with sensor fusion and real-time data analysis, effectively identify static obstacles. Multi-band switching and signal enhancement technologies are employed to ensure communication stability in low-altitude environments. However, in complex transportation scenarios, existing path planning methods lack intelligence and struggle to dynamically identify the optimal path. This not only hinders transportation efficiency but also increases operating costs. Dynamic obstacle perception in dense urban environments is significantly limited, particularly in response to fast-moving or sudden obstacles, which significantly increases flight risks. Communication systems operating at low altitudes are subject to building obstruction and electromagnetic interference. Instable signal transmission can disrupt real-time data exchange between drones and ground control centers, directly impacting mission reliability and flight safety. These technical bottlenecks severely restrict the large-scale deployment of low-altitude logistics drones in complex urban environments. Summary of the Invention

[0003] In view of this, the present application provides a low-altitude logistics UAV path planning method and system, which solves the technical problems of dynamic obstacle avoidance, communication interference, adaptability to meteorological conditions and insufficient energy supply sustainability in the existing low-altitude logistics UAV path planning process.

[0004] To achieve the above object, the present invention provides the following technical solutions: The present invention mainly consists of a low-altitude logistics UAV path planning method and system, which includes: obtaining the UAV's mission requirement information, which includes but is not limited to the coordinates and geographic information of the starting point and destination and the transportation item information.

[0005] A preliminary path is calculated based on the coordinate information of the starting point and destination, and the preliminary path is initially optimized based on the terrain, building height, and fixed obstacle information within the target flight area to obtain the initial optimized path. The UAV power margin threshold is calculated based on the object information. The terrain, building height, and fixed obstacle information within the target flight area includes digital elevation model data, three-dimensional building data, and static obstacle distribution information. Re-optimize the initial optimized path based on real-time or predicted weather information to ultimately obtain the optimal path; Obtain real-time information about the drone's surroundings from ultrasonic sensors, lidar, and image recognition units, identify dynamic obstacles based on this information, and adjust the flight path. The ground control center monitors the drone status in real time and performs manual intervention and path adjustment.

[0006] Furthermore, calculating a preliminary path based on the coordinate information of the starting point and the destination includes: using the Dijkstra algorithm to search for the shortest path between the starting point and the destination, generating a preliminary path connecting the starting point and the destination, the preliminary path consisting of a series of continuous path points, each path point containing longitude and latitude coordinate information.

[0007] Furthermore, the initial optimization of the preliminary path based on the terrain, building height and fixed obstacle information within the target flight area includes: Obtain terrain data, building height information and fixed obstacle information within the target flight area; A three-dimensional straight line trajectory model is established based on the coordinates of the starting point and the destination, and the straight line trajectory model is spatially interpolated and corrected according to the digital elevation model, three-dimensional contour data of buildings and spatial coordinates of fixed obstacles in the target flight area. The formula calculates the minimum safe flight altitude, where To preset a safety margin, Adjust the altitude of the preliminary path to account for building heights, ensuring the path avoids steep terrain and high-altitude areas within a safe range, and obtaining the minimum safe flight altitude for the drone; According to terrain DEM data, building 3D data and static obstacle distribution, set the avoidance path information and generate the initial optimized path that meets the minimum safe flight altitude; The power margin threshold required for the drone to complete the task is calculated based on the item information. The power margin threshold is used for subsequent optimization and flight monitoring to ensure that the drone has sufficient power to deal with disturbances or perform obstacle avoidance maneuvers.

[0008] Further, re-optimizing the initially optimized path based on real-time or predicted meteorological information includes: Acquire real-time weather data for the target flight area through a weather sensor network, including wind speed, wind direction, precipitation intensity, and visibility parameters. At the same time, access the weather forecast system to obtain weather forecast information for a preset time period in the future. Based on the wind speed information in the meteorological information, the flight speed of the drone is adjusted and the flight altitude is changed to reduce energy consumption; Building a meteorological impact assessment model ,in is the wind speed, is the precipitation intensity, For visibility, 、 、 As the weight coefficient, the initial optimization path is discretized into several path nodes, the meteorological impact assessment value of each node is calculated, and the path adjustment cost function is established. ,in is the path length increment, 、 is the adjustment parameter; Genetic algorithm is used to iteratively search in the neighborhood space of path nodes. Output the optimized path when the minimum value is reached; A sliding time window mechanism is used to update the route every 5 minutes based on the latest weather forecast.

[0009] Furthermore, dynamic obstacles are identified based on environmental information, and path adjustments are made during flight, including: Obtain the distance information of the UAV's close-range obstacles, the three-dimensional point cloud map of the UAV's flight area, the category of mobile obstacles and the movement trajectory information through the onboard sensor system; Use dynamic path planning algorithm based on reinforcement learning to adjust the dynamic path and establish cost function ,in, is the distance to the i-th obstacle, is the path smoothness index, the weight coefficient , , real-time calculation and generation of local obstacle avoidance paths to avoid dynamic obstacles; Automatically adjust the flight path to avoid identified obstacles based on the generated obstacle avoidance path.

[0010] A low-altitude logistics UAV path planning system performs path planning based on the above-mentioned low-altitude logistics UAV path planning method, including: a demand acquisition module, a path planning module, an adaptive adjustment module and a manual control module; The demand acquisition module is used to obtain the mission requirement information of the UAV, which includes but is not limited to the coordinates and geographical information of the starting point and destination and the information of the transported items; The path planning module includes a primary optimization module and a final optimization module. The primary optimization module is used to calculate a preliminary path based on the coordinate information of the starting point and the destination, and to perform a preliminary optimization of the preliminary path based on the terrain, building height, and fixed obstacle information within the target flight area to obtain the primary optimized path. The UAV power margin threshold is calculated based on the object information. The final optimization module is used to further optimize the primary optimized path based on real-time or predicted weather information to finally obtain the optimal path. The adaptive adjustment module is used to obtain the real-time environmental information of the drone detected by the ultrasonic sensor, lidar, and image recognition unit, identify dynamic obstacles based on the environmental information, and adjust the path during flight.

[0011] The adaptive adjustment module collects environmental point cloud data in real time through a multi-sensor fusion system consisting of ultrasonic sensors, lidar, and image recognition units. , create an environmental grid map and dynamic obstacle trajectory prediction model A Bayesian filter is used to update obstacle position predictions, and real-time track correction is achieved through the dynamic obstacle probability grid map constructed by combining lidar point cloud data and visual SLAM.

[0012] The manual control module is used to monitor the status of the drone in real time through the ground control center and perform manual intervention and path adjustment. The low-altitude logistics transportation process is mainly based on the control system carried by the drone and the ground control center. The communication part uses a multi-protocol stack parallel transmission mechanism to maintain the data link with the ground control center. The drone body structure is equipped with a graphics processor unit for three-dimensional path calculation, a solid-state memory for storing terrain data, and a field programmable gate array for processing meteorological data; an environmental perception system composed of a millimeter-wave radar array, a stereo vision sensor, and a laser rangefinder; a communication processor with an integrated software-defined radio architecture and a power module containing a maximum power point tracking controller and a lithium polymer battery pack. The power module carried by the drone adjusts the inclination of the solar panel through the maximum power point tracking algorithm. , to achieve efficient energy conversion and endurance. And based on the remaining power Flight distance Linear relationship Set the return-to-home threshold.

[0013] The system's ground control center includes a monitoring and display unit, a remote control unit, and a data processing unit. These units monitor the drone's status in real time and support manual intervention. The monitoring and display unit displays the drone's flight status, flight path, obstacle information, and bird flight path density distribution in real time, allowing operators to intuitively understand the drone's flight status. The remote control unit receives commands from the operator and transmits them to the drone via a wireless communication module to control parameters such as the drone's flight path, altitude, and speed. The data processing unit processes sensor data transmitted from the drone, including obstacle information, bird signature information, and flight trajectory data. It then performs path planning, obstacle avoidance analysis, and flight trajectory optimization based on preset algorithms. After generating the optimal planned path, it sends it to the drone for execution. Furthermore, the ground control center includes a communication module for real-time data exchange with the drone, ensuring the timeliness of data transmission and control commands during flight.

[0014] It can be seen from the above technical solution that the advantages of the present invention are: 1. This invention generates a preliminary path by acquiring mission requirement information and performing path calculations, then performs multi-level optimization based on terrain analysis and meteorological analysis, while simultaneously detecting dynamic obstacles in real time. This significantly improves the intelligence level of path planning, and can accurately identify the optimal path, especially in complex transportation scenarios, effectively reducing operating costs and improving overall transportation efficiency.

[0015] 2. Based on the recognition of dynamic obstacles, especially fast-moving objects, the drone achieves millisecond-level obstacle avoidance response through a safety recognition algorithm, significantly reducing flight risks in dense urban environments. A multi-mode redundant communication system consisting of satellite communications and cellular networks effectively overcomes signal attenuation caused by building obstructions and electromagnetic interference, ensuring stable data exchange between the drone and ground control, and guaranteeing the reliability and safety of mission execution. The drone also integrates dynamic solar panel adjustment and optimizes energy consumption based on meteorological data, significantly extending its continuous operation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings that constitute a part of this application are used to provide further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute improper limitations on this application.

[0017] Figure 1 Schematic diagram of the steps of the low-altitude logistics drone path planning method of this application.

[0018] Figure 2 Schematic diagram of the structure of step S3 of this embodiment.

[0019] Figure 3 Schematic diagram of the dynamic obstacle avoidance process of this embodiment.

[0020] Figure 4 This is a schematic diagram of the structure of a low-altitude logistics drone path planning system in this embodiment. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail in conjunction with the embodiments and drawings. Here, the illustrative embodiments of this application and their descriptions are used to explain this application, but are not intended to limit this application.

[0022] refer to Figures 1 to 4 This embodiment provides a low-altitude logistics UAV path planning method and system, which obtains mission requirement information and generates a preliminary path, and then combines terrain and meteorological analysis units for multi-level optimization, while detecting dynamic obstacles in real time, and adopts a multi-mode redundant communication system composed of satellite communication units and cellular network units. It realizes a multi-level path optimization mechanism based on real-time terrain and meteorological data, improves the intelligent level of path planning, enhances the three-dimensional perception ability of dynamic obstacles, ensures that the UAV and the ground control center maintain stable data interaction, can accurately identify the optimal path in complex transportation scenarios, effectively reduces flight risks and operating costs, and significantly improves overall transportation efficiency. Figure 1 As shown, the method includes: Step S1: obtaining the mission requirement information of the UAV, the mission requirement information including but not limited to the coordinates and geographic information of the starting point and the destination and the transported item information.

[0023] Determine the drone's starting and destination locations. The starting point is the starting point of the drone's mission, and the destination is the ending point of the drone's mission. Based on the starting and destination locations, determine the drone's mission flight area. The mission flight area is the collection of all potential flight paths between the starting point and the destination. By obtaining the drone's mission requirements information, the drone's flight range can be clarified, providing basic data support for subsequent path planning, ensuring that the drone can complete its mission efficiently and safely.

[0024] Step S2: Calculate a preliminary path based on the coordinate information of the starting point and the destination, and perform a preliminary optimization on the preliminary path based on the terrain, building height, and fixed obstacle information within the target flight area to obtain a primary optimized path. Calculate the UAV power margin threshold based on the item information. The terrain, building height, and fixed obstacle information within the target flight area include digital elevation model data, three-dimensional building data, and static obstacle distribution information.

[0025] Among them, based on the coordinates of the starting point and destination of the drone, the Dijkstra algorithm is used to search for the shortest path between the starting point and the destination, and a preliminary path connecting the starting point and the destination is generated. The preliminary path consists of a series of continuous path points, and each path point contains longitude and latitude coordinate information. By calculating the initial optimized path, a basic reference is provided for subsequent path optimization, ensuring that the drone can fly efficiently from the starting point to the destination. For example, in an urban environment, the starting point is set to the roof of Building A (longitude 116.404°E, latitude 39.915°N), and the destination is set to the center of Park B (longitude 116.412°E, latitude 39.922°N). A node network is constructed through map data, and the shortest driving route passing through three intersections is calculated as the preliminary path. This technical solution significantly improves the efficiency and accuracy of drone mission planning through automated path calculation, laying an important foundation for path optimization in complex environments.

[0026] Terrain analysis begins by acquiring terrain data, building heights, and other fixed obstacle information within the target flight area. Terrain data includes the altitude and terrain undulations within the target flight area. Building heights include the height of building tops, and fixed obstacle information includes parameters such as location, size, and shape. Next, an initial optimization of the preliminary path is performed.

[0027] Specifically, the altitude of the preliminary path is adjusted based on the terrain fluctuations within the target flight area, ensuring that the path avoids steep terrain and high-altitude areas within a safe range and ensuring the stability and safety of the drone during flight. Building height information is used to correct the preliminary path to avoid taller buildings, ensuring that the drone does not collide with or interfere with buildings during flight. At the same time, avoidance areas are added to the preliminary path based on the location, size, and shape of fixed obstacles to ensure that the path avoids all fixed obstacles, generating a preliminary optimized path. This initial optimization of the preliminary path through terrain analysis ensures terrain safety, building avoidance, and fixed obstacle avoidance of the drone's flight path, thereby improving the safety and efficiency of drone flight.

[0028] Specifically, the initial optimization of the preliminary path based on the terrain, building height and fixed obstacle information in the target flight area includes: obtaining the terrain data, building height information and fixed obstacle information in the target flight area; establishing a three-dimensional space straight line trajectory model based on the starting point and destination coordinates, and performing spatial interpolation correction on the straight line trajectory model based on the digital elevation model, building three-dimensional contour data and fixed obstacle space coordinates in the target flight area, using The formula calculates the minimum safe flight altitude, where To preset a safety margin, The altitude of the preliminary path is adjusted to the building height to ensure that the path avoids steep terrain and high-altitude areas within a safe range and obtains the minimum safe flight altitude of the UAV; according to the terrain DEM data, building 3D data and static obstacle distribution, the avoidance path information is set to generate the initial optimized path that meets the minimum safe flight altitude; and based on the object information, the power margin threshold required for the UAV to complete the task is calculated. The power margin threshold is used for subsequent optimization and flight monitoring to ensure that the UAV has sufficient power to deal with disturbances or perform obstacle avoidance maneuvers.

[0029] In this embodiment, for example, the application scenario is urban logistics distribution. When a drone transports medical supplies from a storage center to a hospital, it is necessary to plan the route based on the height distribution of the building complex. Calculate the drone power margin threshold based on the cargo weight ,in is the dynamic coefficient, is the benchmark power; secondly, the terrain gradient matrix is ​​generated according to the digital elevation model . Construct a multi-objective optimization function ,in is the flight time, is energy consumption, is the risk factor; the improved ant colony algorithm is used to search for paths. In the cold chain logistics scenario in coastal areas, it is necessary to avoid strong wind areas and residential areas at the same time, and generate a three-dimensional waypoint sequence ; Then, a weather optimization and real-time replanning module is embedded to trigger local path optimization when sudden obstacles are detected.

[0030] The embodiment of the present invention further introduces meteorological analysis to perform path optimization. Step S3 specifically includes: re-optimizing the initially optimized path according to real-time or predicted meteorological information to finally obtain the optimal path.

[0031] Specifically, if Figure 2 As shown, step S30: obtain real-time meteorological data of the target flight area through the meteorological sensor network, including wind speed, wind direction, precipitation intensity and visibility parameters, and access the meteorological forecast system to obtain meteorological forecast information for the future preset period; step S31: adjust the flight speed of the drone and change the flight altitude to reduce energy consumption based on the wind speed information in the meteorological information; step S32: build a meteorological impact assessment model ,in is the wind speed, is the precipitation intensity, For visibility, 、 、 As the weight coefficient, the initial optimization path is discretized into several path nodes, the meteorological impact assessment value of each node is calculated, and the path adjustment cost function is established. ,in is the path length increment, 、 To adjust the parameters; Step S33: Use genetic algorithm to iteratively search in the path node neighborhood space. When the minimum value is reached, the optimized path is output. Specific application scenarios include urban logistics delivery, where drones adjust their original paths to areas with less rainfall impact based on real-time thunderstorm warnings, while avoiding transient strong winds.

[0032] The path is dynamically updated based on the provided meteorological data, using a sliding time window mechanism to update the path every 5 minutes based on the latest weather forecast. In the embodiment, an electronic device and a computer-readable storage medium are also included. When the processor of the electronic device executes the meteorological optimization instruction, it synchronously calls the GPU to accelerate matrix operations, so that the time consumption of meteorological impact assessment is controlled within 50ms. The meteorological optimization program stored in the computer-readable storage medium includes a Kalman filter subroutine for eliminating measurement noise in meteorological sensor data. The present invention improves the flight safety factor of the UAV by integrating meteorological elements for secondary path optimization and reduces energy consumption by 12%.

[0033] This embodiment also provides a method for dynamic obstacle avoidance for a UAV. Step S4 specifically includes: obtaining real-time environmental information about the UAV detected by ultrasonic sensors, laser radar, and image recognition units, identifying dynamic obstacles based on the environmental information, and adjusting the flight path.

[0034] In this embodiment, if Figure 3 As shown, the ultrasonic sensor array is used to obtain the distance information of close-range obstacles within a range of 0.1-5 meters around the drone, and the lidar scanning is used to construct a three-dimensional point cloud map of the drone's flight area. The spatial coordinates of dynamic obstacles are updated in real time, and the convolutional neural network in the image recognition unit is used to semantically segment the visual data collected by the camera to identify the category and motion trajectory of mobile obstacles. Then, based on the fused data, a dynamic path planning algorithm based on reinforcement learning is used to generate an obstacle avoidance path in real time. For example, the ultrasonic sensor array emits 40kHz ultrasonic pulses at a frequency of 20Hz, and calculates the obstacle distance by the time-of-flight method with a measurement accuracy of ±2cm. The lidar uses a 905nm wavelength, a scanning frequency of 10Hz, a horizontal field of view of 270°, a vertical field of view of 30°, and a point cloud density of 0.1°×0.1°. The convolutional neural network uses the ResNet-50 architecture, and uses a data set of 10 types of dynamic obstacles including pedestrians, vehicles, and birds during training, with an identification accuracy of 98.7%. When performing dynamic path planning, a cost function is established. ,in is the distance to the i-th obstacle, is the path smoothness index, the weight coefficient , When running the obstacle avoidance program in this embodiment, the following steps are implemented: the radial velocity of obstacles within a range of 80m is acquired through the millimeter-wave radar, and an obstacle motion prediction model is established by fusing the lidar point cloud with the visual recognition results; and the obstacle avoidance path parameters are updated at a period of 10ms.

[0035] Step S5: The ground control center monitors the status of the UAV in real time and performs manual intervention and path adjustment.

[0036] Specifically, the communication module's satellite communication unit and cellular network unit maintain communication between the drone and the ground control center. The satellite communication unit is used to maintain the drone's connection to the ground control center in high-altitude or remote areas, while the cellular network unit is used to maintain the drone's connection to the ground control center within base station coverage areas such as cities or suburbs. The satellite communication unit utilizes L-band satellite communication technology and is equipped with a high-gain directional antenna. During flight, the drone establishes a communication link with the ground control center via geostationary satellites, ensuring communication continuity in remote areas or beyond visual range. The cellular network unit integrates a 4G / 5G multi-mode communication chipset and enables broadband data transmission within low-altitude areas via a network of ground base stations. It supports two-way transmission of high-definition video streams and flight control commands. In one application scenario, when a drone performs a city inspection, the cellular network unit prioritizes establishing a communication connection. If it enters a signal blind spot, it automatically switches to the satellite communication unit. Adaptive bit rate adjustment technology dynamically adjusts the transmission rate based on channel quality, ensuring a minimum 99.9% success rate for flight data packet transmission. In this embodiment, when the processor of the electronic device executes the program, the communication module is controlled to: establish a handshake connection between the satellite communication unit and the Inmarsat satellite system, initialize the IMSI authentication process of the cellular network unit, and merge the control instructions from the two communication links through a dual-channel data fusion algorithm. The computer-readable storage medium stores program code that, when executed, causes the communication module to: periodically detect the satellite signal strength. and cellular network signal strength , compare the results according to the threshold Select the optimal communication channel, where The communication module of the present invention significantly improves the communication reliability of the UAV in complex environments through dual-mode redundancy design, and is particularly suitable for cross-regional long-duration flight missions.

[0037] like Figure 4 As shown, the present application also discloses a low-altitude logistics UAV path planning system, which performs path planning based on the above-mentioned low-altitude logistics UAV path planning method, including: a demand acquisition module, a path planning module, an adaptive adjustment module and a manual control module; The demand acquisition module is used to obtain the mission requirement information of the UAV, which includes but is not limited to the coordinates and geographic information of the starting point and destination and the transport item information, which includes weight, size, and value; The path planning module includes a primary optimization module and a final optimization module. The primary optimization module is used to calculate a preliminary path based on the coordinate information of the starting point and the destination, and to perform a preliminary optimization of the preliminary path based on the terrain, building height, and fixed obstacle information within the target flight area to obtain the primary optimized path. The UAV power margin threshold is calculated based on the object information. The final optimization module is used to further optimize the primary optimized path based on real-time or predicted weather information to finally obtain the optimal path. The adaptive adjustment module is used to obtain the real-time environmental information of the drone detected by the ultrasonic sensor, lidar, and image recognition unit, identify dynamic obstacles based on the environmental information, and adjust the path during flight.

[0038] In this embodiment, obstacle identification involves obtaining information on multiple obstacles within the target flight area, as well as collecting characteristic information on birds within the target flight area. Obstacles include buildings and trees, and the target flight area is the area to be flown through. Specifically, obstacle location information, obstacle model information, and obstacle category information are scanned and obtained for multiple obstacles within the target flight area, including obstacle category information on buildings and trees. The obstacle location information, obstacle model information, and obstacle category information are then integrated to obtain information on multiple obstacles within the target flight area.

[0039] The average number of birds within the target flight area is then collected as bird characteristic information. Specifically, the target flight area of ​​the drone is first determined. The target flight area is the area to be flown through, i.e., the range of the flight path the drone is scheduled to traverse. For example, the departure and destination locations of the drone are determined based on the mission requirements. Based on the departure and destination locations, the area containing all potential path selections is set as the target flight area. Next, within the target flight area, detailed information about each obstacle is collected using scanning or sensing technology to obtain obstacle location information, obstacle model information, and obstacle category information for each of the multiple obstacles. Obstacle location information refers to the geographic coordinates of each obstacle to determine its specific location within the flight area. Obstacle model information refers to the three-dimensional model or parameters of the obstacle obtained through scanning technology, such as the height, width, and structure of buildings, and the shape and height of trees. Obstacle category information includes buildings and trees. Buildings include all man-made structures within the target flight area, such as residential buildings, office buildings, and industrial buildings. Trees include all natural vegetation structures within the target area, such as trees. The system then integrates multiple obstacles, their location information, model information, and category information. Specifically, each obstacle's location information (coordinates), model information (shape, height, dimensions, and other parameters), and category information (building or tree) are combined to form a complete entry for each obstacle. For example, for each building, the entry includes its specific location, height, width, and shape parameters. This provides information on multiple obstacles within the target flight area. Determining this information provides intuitive obstacle distribution data for flight path planning, ensuring that drones can effectively perceive and avoid obstacles, thereby improving flight safety. Furthermore, bird activity data is collected within the target flight area, and the average number of birds seen over a predetermined time period is calculated as bird signature information. For example, the daily bird counts over the past 10 days are calculated and averaged. Obtaining this information provides detailed data support for drone path planning, enabling drones to select the optimal path while avoiding obstacles and bird activity areas, thereby improving flight safety and efficiency.

[0040] Among them, the manual control module is used to monitor the status of the drone in real time through the ground control center and perform manual intervention and path adjustment.

[0041] The low-altitude logistics transportation process is mainly based on the control system carried by the drone and the ground control center. The communication part uses a multi-protocol stack parallel transmission mechanism to maintain the data link with the ground control center. The drone body structure is equipped with a graphics processor unit for three-dimensional path calculation, a solid-state memory for storing terrain data, and a field programmable gate array for processing meteorological data; an environmental perception system composed of a millimeter-wave radar array, a stereo vision sensor, and a laser rangefinder; a communication processor with an integrated software-defined radio architecture and a power module containing a maximum power point tracking controller and a lithium polymer battery pack. The power module carried by the drone adjusts the inclination of the solar panel through the maximum power point tracking algorithm. , under sufficient sunlight, it can significantly extend the flight time of the drone, achieve efficient energy conversion and endurance. And based on the remaining power Flight distance Linear relationship Set the return-to-home threshold. Through the coordinated operation of the battery management system, charging unit, and solar panels, efficient energy management and continuous supply are achieved during the drone's mission execution, ensuring that the drone can operate stably in complex environments and complete its scheduled missions. The charging unit can quickly recharge the battery when the drone lands, shortening the time between missions. The solar panels fully utilize sunlight for energy replenishment during daytime flight, further enhancing the drone's mission execution capabilities. This technical solution effectively solves the problem of mission interruption or failure caused by insufficient energy during drone missions, significantly improving the drone's mission execution efficiency and reliability.

[0042] The system's ground control center includes a monitoring and display unit, a remote control unit, and a data processing unit. These units monitor the drone's status in real time and support manual intervention. The monitoring and display unit displays the drone's flight status, flight path, obstacle information, and bird flight path density distribution in real time, allowing the operator to intuitively understand the drone's flight status. The remote control unit receives commands from the operator and transmits them to the drone via a wireless communication module to control parameters such as the drone's flight path, altitude, and speed. The data processing unit processes sensor data transmitted from the drone, including obstacle information, bird characteristics, and flight trajectory data. It performs path planning, obstacle avoidance analysis, and flight trajectory optimization based on pre-set algorithms. The optimal planned path is then transmitted to the drone for execution. The ground control center also includes a communication module for real-time data exchange with the drone, ensuring timely data transmission and control commands during flight. This technical solution enables the ground control center to achieve comprehensive remote monitoring and control of the drone, improving the safety and efficiency of drone flight missions.

[0043] In view of the problems in the existing technology such as insufficient intelligence in path planning leading to low transportation efficiency, limited dynamic obstacle perception capability leading to high flight risk, unstable signals caused by building obstruction and electromagnetic interference in the communication system, and low energy management efficiency, the present invention provides a low-altitude logistics UAV path planning method and system, which obtains mission requirement information and generates a preliminary path through a path calculation unit, and then combines terrain analysis and meteorological analysis for multi-level optimization, while detecting dynamic obstacles in real time. A multi-mode redundant communication system consisting of a satellite communication unit and a cellular network unit is adopted, and an intelligent power management system and a solar panel dynamic adjustment function are configured to realize a multi-level path optimization mechanism based on real-time terrain and meteorological data, improve the intelligence level of path planning, enhance the three-dimensional perception capability of dynamic obstacles, ensure stable data interaction between the UAV and the ground control center, improve energy management efficiency, accurately identify the optimal path in complex transportation scenarios, effectively reduce flight risks and operating costs, significantly improve overall transportation efficiency, and solve the technical bottleneck that limits the large-scale application of low-altitude logistics UAVs in complex urban environments.

[0044] The present application also provides an electronic device comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the method in the first aspect above.

[0045] The present application also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the steps of the method in the first aspect are implemented.

[0046] It should be noted that the order of the above-mentioned embodiments of this application is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. In some cases, the actions or steps described in the specification and claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require a specific order or continuous order to achieve the desired results. In some embodiments, multitasking and parallel processing are also feasible or advantageous.

[0047] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0048] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Those skilled in the art will appreciate that various modifications and variations of the present embodiment are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A low-altitude logistics UAV path planning method, characterized in that: include: Obtaining mission requirement information of the UAV, including but not limited to coordinates and geographic information of the starting point and destination and information of transported items; Calculate a preliminary path based on the coordinate information of the starting point and the destination, and perform a preliminary optimization on the preliminary path based on the terrain, building height, and fixed obstacle information within the target flight area to obtain a primary optimized path. Calculate the UAV power margin threshold based on the object information. Re-optimizing the initially optimized path according to real-time or predicted meteorological information to ultimately obtain the optimal path; Obtaining real-time environmental information about the drone from ultrasonic sensors, lidar, and image recognition units, identifying dynamic obstacles based on this environmental information, and making in-flight path adjustments; The ground control center monitors the drone status in real time and performs manual intervention and path adjustment.

2. The low-altitude logistics UAV path planning method according to claim 1 is characterized in that: Calculating a preliminary path based on the coordinate information of the starting point and the destination includes: using the Dijkstra algorithm to search for the shortest path between the starting point and the destination, generating a preliminary path connecting the starting point and the destination, the preliminary path consisting of a series of continuous path points, each path point containing latitude and longitude coordinate information.

3. The low-altitude logistics UAV path planning method according to claim 1 is characterized in that: The initial optimization of the preliminary path based on the terrain, building height and fixed obstacle information within the target flight area includes: Obtain terrain data, building height information and fixed obstacle information within the target flight area; A three-dimensional straight line trajectory model is established based on the coordinates of the starting point and the destination, and the straight line trajectory model is spatially interpolated and corrected according to the digital elevation model, three-dimensional contour data of buildings and spatial coordinates of fixed obstacles in the target flight area. The formula calculates the minimum safe flight altitude, where To preset a safety margin, Adjust the altitude of the preliminary path to account for building heights, ensuring the path avoids steep terrain and high-altitude areas within a safe range, and obtaining the minimum safe flight altitude for the drone; According to terrain DEM data, building 3D data and static obstacle distribution, set the avoidance path information and generate the initial optimized path that meets the minimum safe flight altitude; The power margin threshold required for the drone to complete the task is calculated based on the item information. The power margin threshold is used for subsequent optimization and flight monitoring to ensure that the drone has sufficient power to deal with disturbances or perform obstacle avoidance maneuvers.

4. The low-altitude logistics UAV path planning method according to claim 1 is characterized in that: The re-optimization of the initially optimized path according to the real-time or predicted meteorological information includes: Acquire real-time weather data for the target flight area through a weather sensor network, including wind speed, wind direction, precipitation intensity, and visibility parameters. At the same time, access the weather forecast system to obtain weather forecast information for a preset time period in the future. Based on the wind speed information in the meteorological information, the flight speed of the drone is adjusted and the flight altitude is changed to reduce energy consumption; Building a meteorological impact assessment model ,in is the wind speed, is the precipitation intensity, For visibility, 、 、 As the weight coefficient, the initial optimization path is discretized into several path nodes, the meteorological impact assessment value of each node is calculated, and the path adjustment cost function is established. ,in is the path length increment, 、 is the adjustment parameter; Genetic algorithm is used to iteratively search in the neighborhood space of path nodes. Output the optimized path when the minimum value is reached; A sliding time window mechanism is used to update the route every 5 minutes based on the latest weather forecast.

5. The low-altitude logistics UAV path planning method according to claim 3 is characterized in that: Identifying dynamic obstacles based on the environmental information and adjusting the flight path include: Obtain the distance information of the UAV's close-range obstacles, the three-dimensional point cloud map of the UAV's flight area, the category of mobile obstacles and the movement trajectory information through the onboard sensor system; Use dynamic path planning algorithm based on reinforcement learning to adjust the dynamic path and establish cost function ,in, is the distance to the i-th obstacle, is the path smoothness index, the weight coefficient , , real-time calculation and generation of local obstacle avoidance paths to avoid dynamic obstacles; Automatically adjust the flight path to avoid identified obstacles based on the generated obstacle avoidance path.

6. A low-altitude logistics UAV path planning system, which performs path planning based on the low-altitude logistics UAV path planning method described in claims 1-5 above, characterized in that: include: Demand acquisition module, path planning module, adaptive adjustment module and manual control module; The demand acquisition module is used to obtain the mission requirement information of the UAV, and the mission requirement information includes but is not limited to the coordinates and geographical information of the starting point and the destination and the transport item information; The path planning module includes a primary optimization module and a final optimization module. The primary optimization module is used to calculate a preliminary path based on the coordinate information of the starting point and the destination, and to perform a preliminary optimization on the preliminary path based on the terrain, building height, and fixed obstacle information within the target flight area to obtain a preliminary optimized path. The UAV power margin threshold is calculated based on the object information. The final optimization module is used to further optimize the preliminary optimized path based on real-time or predicted weather information to ultimately obtain the optimal path. The adaptive adjustment module is used to obtain the surrounding environment information of the drone detected in real time by the ultrasonic sensor, laser radar, and image recognition unit, and identify dynamic obstacles based on the environmental information to adjust the flight path; The manual control module is used to monitor the status of the UAV in real time through the ground control center and perform manual intervention and path adjustment.

Images