A trajectory planning method and device for a low-altitude survey platform of a city

Abstract

This invention provides a trajectory planning method and apparatus for a low-altitude survey platform in urban areas, comprising: generating an initial task path bundle for a target to be surveyed in the city; determining a dynamic obstacle list in the surrounding environment of the target through the low-altitude survey platform; constructing a probabilistic safety field in three-dimensional space based on the dynamic obstacle list and a static obstacle map; calculating a connected spatiotemporal safe flight corridor for the current planning cycle in the probabilistic safety field based on the initial task path bundle; and optimizing the spatiotemporal safe flight corridor based on the dynamic constraints of the low-altitude survey platform to obtain an optimal spatiotemporal trajectory. Based on task-oriented coverage path and safety obstacle avoidance integrated real-time trajectory planning, this method balances flight safety, survey coverage, trajectory optimization, and environmental adaptability, enabling autonomous trajectory planning for a low-altitude survey platform in complex urban environments.

Description

Technical Field

[0001] This invention relates to the field of low-altitude surveying technology in complex urban environments, specifically to a trajectory planning method and apparatus for a low-altitude surveying platform used in cities. Background Technology

[0002] Low-altitude survey platforms such as drones have been widely used in survey tasks such as infrastructure inspection, 3D modeling, power line inspection and bridge inspection. They need to ensure flight safety while completing efficient and complete target data collection through survey task path planning and environmental obstacle avoidance.

[0003] In existing technologies, the path planning for low-altitude survey missions generally relies on the coordinated cooperation of sensor perception (LiDAR, visual cameras, GNSS / IMU integrated navigation, etc.), path planning algorithms (Coverage Path Planning, Dynamic Window Method (DWA, etc.) and flight control systems.

[0004] To address the complex environments of densely built-up urban areas, complex electromagnetic interference, and numerous dynamic obstacles, low-altitude survey platforms typically employ the following path planning methods: 1. Based on a static map of the area to be surveyed, a global waypoint sequence is pre-planned at a safe altitude far from obstacles. During flight, the platform relies on GNSS and altimeter tracking, avoiding only obstacles marked on the static map, without a real-time dynamic obstacle avoidance strategy. 2. The platform is equipped with forward-looking / surround-looking sensors (visual cameras, lidar, etc.) to collect environmental obstacle information in real time. When an obstacle is detected, obstacle avoidance actions such as sharp turns, hovering, or reversing are performed according to preset rules (artificial potential field method, dynamic window method, etc.). After obstacle avoidance, the original survey path is restored. 3. At the ground station, complex global coverage path planning (such as grid decomposition-based optimization algorithms) is performed based on a high-precision map of the area to be surveyed, generating a fixed optimal survey trajectory and uploading it to the low-altitude survey platform. This trajectory is strictly followed during flight, with only minor local trajectory adjustments made for sudden obstacles, without an overall replanning mechanism.

[0005] During the implementation of this invention, the applicant discovered that when performing close-range high-precision surveying tasks in complex urban environments, the task-driven surveying path and the safety-driven real-time obstacle avoidance are disconnected from each other. It is difficult to generate and execute an optimized flight trajectory that can efficiently and completely cover the surface of the target to be surveyed and conform to the dynamic constraints of the low-altitude surveying platform in real time while ensuring absolute flight safety. This ultimately results in frequent interruptions in surveying operations, uneven data acquisition quality, and low task completion efficiency. Summary of the Invention

[0006] This invention provides a trajectory planning method and apparatus for a low-altitude survey platform in cities, which can solve at least one technical problem of the prior art.

[0007] To achieve the above objectives, in one aspect, embodiments of the present invention provide a trajectory planning method for a low-altitude survey platform in cities, comprising:

[0008] Generate the initial task path bundle for the targets to be surveyed in the city;

[0009] A list of dynamic obstacles in the surrounding environment of the target to be surveyed is determined using a low-altitude survey platform.

[0010] Based on the dynamic obstacle list and static obstacle map, a probabilistic safety field in three-dimensional space based on the timeline is constructed.

[0011] In the probabilistic safety field, based on the initial mission path bundle, a connected spatiotemporal safe flight corridor is calculated for the current planning cycle;

[0012] Based on the dynamic constraints of the low-altitude survey platform, the spatiotemporal safe flight corridor is optimized to obtain the optimal spatiotemporal trajectory.

[0013] On the other hand, embodiments of the present invention provide a trajectory planning device for a low-altitude survey platform in cities, comprising:

[0014] The high-level task planning module is used to generate the initial task path bundle for the targets to be surveyed in the city.

[0015] A low-altitude survey platform for determining a list of dynamic obstacles in the surrounding environment of the target to be surveyed;

[0016] The middle-level behavioral decision layer is used to construct a probabilistic safety field in three-dimensional space based on the dynamic obstacle list and the static obstacle map.

[0017] The safe flight corridor construction module is used to calculate a connected spatiotemporal safe flight corridor for the current planning cycle based on the initial mission path bundle in a probabilistic safety field.

[0018] The trajectory optimization module is used to optimize the spatiotemporal safety flight corridor based on the dynamic constraints of the low-altitude survey platform to obtain the optimal spatiotemporal trajectory.

[0019] The above technical solution has the following beneficial effects:

[0020] Using the initial mission path bundle as the survey framework, a spatiotemporally safe flight corridor with spatiotemporal constraints is constructed online in real time, achieving integrated planning of mission-oriented coverage paths and safe obstacle avoidance. The safe flight corridor is generated guided by the initial mission path bundle, minimizing deviations from the original survey intent during obstacle avoidance actions. This avoids the separation of mission and obstacle avoidance, ensuring continuous and complete coverage of the target area and preventing data gaps and mission interruptions. Based on real-time trajectory planning that integrates mission-oriented coverage paths and safe obstacle avoidance, flight safety, survey coverage, trajectory optimization, and environmental adaptability are considered, enabling autonomous trajectory planning for low-altitude survey platforms in complex urban environments. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a trajectory planning method for a low-altitude survey platform for cities according to an embodiment of the present invention.

[0023] Figure 2 This is a structural diagram of a trajectory planning device for a low-altitude survey platform in a city, according to an embodiment of the present invention.

[0024] Figure 3 This is a schematic diagram of the trajectory planning method for a low-altitude survey platform for cities according to an embodiment of the present invention;

[0025] Figure 4 This is a flowchart illustrating the sequential steps of a trajectory planning method for a low-altitude survey platform for cities, according to an embodiment of the present invention.

[0026] Figure 5 This is a logic diagram for generating the probabilistic safety field and safe flight corridor according to an embodiment of the present invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] like Figure 1 As shown, in conjunction with embodiments of the present invention, a trajectory planning method for a low-altitude survey platform in urban areas is provided, comprising:

[0029] S101: Generate the initial task path bundle for the targets to be surveyed in the city;

[0030] S102: Determine a list of dynamic obstacles in the surrounding environment of the target to be surveyed using a low-altitude survey platform;

[0031] S103: Based on the dynamic obstacle list and the static obstacle map, construct a probabilistic safety field in three-dimensional space based on the timeline;

[0032] S104: In the probabilistic safety field, based on the initial mission path bundle, calculate a connected spatiotemporal safe flight corridor for the current planning cycle;

[0033] S105: Based on the dynamic constraints of the low-altitude survey platform, the spatiotemporal safe flight corridor is optimized to obtain the optimal spatiotemporal trajectory.

[0034] Preferably, S101: Generating the initial task path bundle for the city's survey targets, including:

[0035] Based on the geometric features of the target to be surveyed and the three-dimensional real-world map of the target to be surveyed, a set of coarse waypoint sequences that can completely cover the surface of the target to be surveyed are generated as the initial mission path bundle.

[0036] Preferably, S102: Determining a list of dynamic obstacles in the surrounding environment of the target to be surveyed using a low-altitude survey platform, including:

[0037] S102-1: The perception module of the low-altitude survey platform collects multi-source perception data of the surrounding environment of the target to be surveyed and the pose of the low-altitude survey platform in real time at a preset frequency. The multi-source perception data includes at least two of the following: surrounding environment point cloud, surrounding environment image, and dynamic obstacle speed.

[0038] S102-2: Obstacles in multi-source perception data are semantically classified using a semantic segmentation neural network to obtain obstacles and their corresponding categories. The categories of obstacles include static obstacles, low-speed moving obstacles, and high-speed moving obstacles.

[0039] S102-3: By predicting the motion states of low-speed and high-speed moving obstacles, output a list of dynamic obstacles with semantic labels and predicted trajectories.

[0040] Preferably, S103: Based on the dynamic obstacle list and the static obstacle map, a probabilistic safety field based on a timeline in three-dimensional space is constructed, including:

[0041] S103-1: Based on the dynamic obstacle list and combined with the static obstacle map, assign a corresponding risk probability distribution and predicted trajectory to each type of obstacle;

[0042] S103-2: Calculate the probability distribution of each of the obstacles occupying space within a preset time period in the future to obtain a probabilistic safety field in three-dimensional space based on the timeline.

[0043] Preferably, S104: In the probabilistic safety field, based on the initial mission path bundle, a connected spatiotemporal safe flight corridor is calculated for the current planning period, including:

[0044] Based on the initial mission path bundle, in the probabilistic safety field, a connected spatiotemporal safe flight corridor is calculated for the current planning cycle according to the risk probability distribution and predicted trajectory of each obstacle; wherein, the spatiotemporal safe flight corridor meets the preset safety probability threshold and can be as close as possible to the initial mission path bundle while ensuring safety.

[0045] S105: Based on the dynamic constraints of the low-altitude survey platform, the spatiotemporal safe flight corridor is optimized to obtain the optimal spatiotemporal trajectory, including:

[0046] Under the constraints of a safe flight corridor, and with the optimization objectives of satisfying the dynamic constraints of the low-altitude survey platform, minimizing energy consumption, and achieving a smooth trajectory, a smooth and trackable optimal spatiotemporal trajectory is generated.

[0047] like Figure 2 As shown, in conjunction with an embodiment of the present invention, a trajectory planning device for a low-altitude survey platform in a city is provided, comprising:

[0048] High-level task planning module 21 is used to generate the initial task path bundle for the targets to be surveyed in the city;

[0049] The low-altitude survey platform 22 is used to determine a list of dynamic obstacles in the surrounding environment of the target to be surveyed;

[0050] The middle-level behavioral decision layer 23 is used to construct a probabilistic safety field in three-dimensional space based on the dynamic obstacle list and the static obstacle map.

[0051] The safe flight corridor construction module 24 is used to calculate a connected spatiotemporal safe flight corridor for the current planning period based on the initial mission path bundle in a probabilistic safety field.

[0052] The trajectory optimization module 25 is used to optimize the spatiotemporal safe flight corridor based on the dynamic constraints of the low-altitude survey platform to obtain the optimal spatiotemporal trajectory.

[0053] Preferably, the high-level task planning module 21 is specifically used for:

[0054] Based on the geometric features of the target to be surveyed and the three-dimensional real-world map of the target to be surveyed, a set of coarse waypoint sequences that can completely cover the surface of the target to be surveyed are generated as the initial mission path bundle.

[0055] Preferably, the low-altitude survey platform 22 includes:

[0056] The sensing module collects multi-source sensing data of the surrounding environment of the target to be surveyed and the pose of the low-altitude survey platform in real time at a preset frequency. The multi-source sensing data includes at least two of the following: surrounding environment point cloud, surrounding environment image, and dynamic obstacle speed.

[0057] A semantic segmentation neural network is used to semantically classify obstacles in multi-source perception data to obtain obstacles and their corresponding categories. The categories of obstacles include static obstacles, low-speed moving obstacles, and high-speed moving obstacles.

[0058] The prediction model is used to predict the motion state of each obstacle and outputs a dynamic list of obstacles with semantic labels and predicted trajectories.

[0059] Preferably, the middle-level behavioral decision layer 23 is specifically used for:

[0060] Based on the dynamic obstacle list and combined with the static obstacle map, each obstacle is assigned a corresponding risk probability distribution and predicted trajectory.

[0061] Calculate the probability distribution of each obstacle occupying space within a preset time period in the future to obtain a probabilistic safety field in three-dimensional space based on the timeline.

[0062] Preferably, the safe flight corridor construction module 24 is specifically used for:

[0063] Based on the initial mission path bundle, in the probabilistic safety field, a connected spatiotemporal safe flight corridor is calculated for the current planning cycle according to the risk probability distribution and predicted trajectory of each obstacle; wherein, the spatiotemporal safe flight corridor meets the preset safety probability threshold and can be as close as possible to the initial mission path bundle while ensuring safety.

[0064] Trajectory optimization module 25 is specifically used for:

[0065] Under the constraints of a safe flight corridor, and with the optimization objectives of satisfying the dynamic constraints of the low-altitude survey platform, minimizing energy consumption, and achieving a smooth trajectory, a smooth and trackable optimal spatiotemporal trajectory is generated.

[0066] The beneficial technical effects achieved by the embodiments of the present invention are as follows:

[0067] It adopts a closed-loop architecture of real-time perception, modeling, trajectory planning, optimization, and trajectory execution, combined with probabilistic safety field modeling based on semantic perception and probability prediction, and real-time trajectory planning based on task-oriented coverage path and safety obstacle avoidance integration, taking into account flight safety, survey coverage, trajectory optimization and environmental adaptability, while meeting the dynamic constraints of the low-altitude survey platform; and realizes autonomous trajectory planning of the low-altitude survey platform in complex urban environments.

[0068] Using the initial mission path bundle as the survey framework, a spatiotemporal safe flight corridor with spatiotemporal constraints is constructed online in real time. Within the spatiotemporal safe flight corridor, smooth trajectory optimization that meets platform dynamic constraints is completed. The core is the online real-time construction of the safe flight corridor and the flexible deformation mechanism of the mission path, realizing the integrated planning of mission-oriented coverage path and safe obstacle avoidance.

[0069] The safe flight corridor is generated based on the initial mission path bundle. Obstacle avoidance actions minimize deviation from the original survey intent, thereby avoiding the separation of mission and obstacle avoidance, ensuring continuous and complete coverage of the target area, and avoiding data gaps and mission interruptions.

[0070] Closed-loop processing ensures uninterrupted operation, avoiding survey pauses during trajectory execution and improving the continuity of data acquisition and task completion efficiency.

[0071] Each planning cycle replans the trajectory based on the latest environment and platform status, achieving online real-time trajectory replanning. This ensures that each replanned trajectory meets both safety and mission requirements, without additional survey quality loss, rather than the fixed trajectory execution or minor local adjustments of existing technologies.

[0072] By continuously updating environmental and platform status data, the real-time performance and accuracy of trajectory planning are ensured. When the environment does not match the initial model, the system can be quickly adapted to improve its environmental robustness.

[0073] The technical solutions of the present invention will be described in detail below with reference to specific application examples. For technical details not described in the implementation process, please refer to the relevant descriptions above.

[0074] The technical problems that the embodiments of the present invention can solve in view of the technical problems of the prior art are as follows:

[0075] 1. This technology addresses the technical problems of "poor flexibility, low survey quality, and reliance on high-precision prior maps" in existing technologies. It enables real-time response to unforeseen dynamic obstacles (vehicles, birds, etc.), ensures that the survey path closely follows the target to improve data resolution, reduces reliance on high-precision static prior maps, and adapts to dynamic changes in the urban environment.

[0076] 2. Address the technical problems of "frequent task interruptions, non-optimized trajectories, and high energy consumption with low efficiency" in existing technologies. Avoid local oscillations / deadlocks caused by purely reactive obstacle avoidance, ensure continuous and complete observation of the survey target during obstacle avoidance, reduce energy consumption caused by frequent sudden stops / turns, and improve task execution efficiency.

[0077] 3. Address the technical problems of existing technologies, such as "high computational load and long time consumption, weak environmental adaptability, and weak dynamic obstacle handling." Simplify complex offline global optimization calculations, improve the efficiency of utilizing online perception information, and achieve proactive and predictive handling of dynamic obstacles, rather than reactive remediation, adapting to sudden scenarios where the environment does not match the offline model.

[0078] The principle of trajectory planning methods for low-altitude survey platforms used in cities is as follows: Figure 3 As shown, the sequential steps are as follows: Figure 4 As shown, the generation logic of the probabilistic safety field and the safe flight corridor is as follows: Figure 5 As shown, the sequential steps are as follows:

[0079] S1: Initialization

[0080] The steps to obtain initial data for the targets to be surveyed in a city include:

[0081] Input the survey task information, which includes the target to be surveyed and the resolution required for data acquisition;

[0082] Input a 3D real-world map of the target to be surveyed;

[0083] The initial state of the low-altitude survey platform is recorded, including its initial position, initial attitude, and remaining battery power.

[0084] Specifically, input a 3D real-world map of the area to be surveyed (high precision is not required) and survey task information (including the target area to be surveyed and the resolution required for data acquisition) into the system, and at the same time input the initial status of the low-altitude survey platform (initial position, initial attitude, remaining power, etc.) to complete the parameter initialization before planning.

[0085] S2: Generate the initial task path bundle

[0086] The high-level mission planning submodule generates a set of coarse waypoint sequences that can completely cover the surface of the target to be surveyed, based on the geometric features (height, width, elevation flatness, etc.). This set of waypoints is the initial mission path bundle. The path bundle provides the framework for subsequent trajectory planning, ensuring the coverage of the survey mission.

[0087] S3: Real-time perception, dynamic obstacle semantic recognition, and motion state prediction

[0088] The perception module collects multi-source perception data (point cloud, image, velocity, pose, etc.) of the surrounding environment in real time at a preset frequency (e.g., 10Hz) and transmits it to the data processing and fusion module. This module performs semantic classification of dynamic obstacles (at least into static obstacles, low-speed moving obstacles, and high-speed moving obstacles, with low-speed moving obstacles and high-speed moving obstacles being dynamic obstacles) through a semantic segmentation neural network. It then uses target detection and tracking algorithms combined with a prediction model (Kalman filter / LSTM) to predict the motion state of dynamic obstacles (low-speed moving obstacles and high-speed moving obstacles) and outputs a list of dynamic obstacles with semantic labels and predicted trajectories.

[0089] S4: Constructing a 4D probabilistic safety field that evolves over time

[0090] The mid-level behavioral decision-making and safe corridor construction submodule, based on a dynamic obstacle list and combined with a static obstacle map, assigns differentiated risk probability distributions and predicted trajectories to obstacles of different semantic categories (e.g., the risk probability of static buildings is fixed at 1, the risk probability of low-speed moving obstacles decreases with distance, and the risk probability of high-speed moving obstacles increases with speed). It calculates the probability distribution of dynamic obstacles occupying space in the next few seconds and constructs a 4D probabilistic safety field that combines three-dimensional space and time. This probabilistic safety field represents the probability that different locations will be occupied by obstacles at different times, replacing the traditional binary obstacle map.

[0091] S5: Real-time generation of spatiotemporally safe flight corridors

[0092] Using the initial mission path bundle as the framework, a connected, low-probability collision spatiotemporal corridor, i.e., a spatiotemporal safe flight corridor, is calculated in a 4D probabilistic safety field for the current planning period (e.g., 0.5s). The generation of the spatiotemporal safe flight corridor must meet the preset safety probability threshold. Based on the semantic category of dynamic obstacles and their predicted trajectories, the risk probability threshold and the attenuation parameters (attenuation coefficient) of the safety field are set differently. The spatiotemporal safe flight corridor is dynamically adjusted to be as close as possible to the initial mission path bundle while ensuring safety, thereby reducing deviation from the survey mission.

[0093] S6: Corridor Trajectory Optimization

[0094] Under the constraints of the spatiotemporal safe flight corridor, the underlying trajectory optimization submodule aims to meet the dynamic constraints of the low-altitude survey platform (maximum flight speed, maximum acceleration, etc.), minimize energy consumption, and achieve a smooth trajectory. It generates a smooth and trackable optimal spatiotemporal trajectory through trajectory optimization algorithms (such as Bernstein polynomials and MINVO basis functions).

[0095] S7: Execute the trajectory and iteratively replan.

[0096] The flight control module calculates the optimal spatiotemporal trajectory into control commands, driving the low-altitude survey platform to execute the trajectory. During trajectory execution, the system does not interrupt the perception process, and re-plans in the next planning cycle, realizing a closed-loop iteration of perception, planning, and execution until the survey mission is completed.

[0097] The following is a description of each module:

[0098] 1. Sensing Module

[0099] Components: LiDAR, visual camera, millimeter-wave radar, GNSS / IMU integrated navigation unit;

[0100] Functions: Real-time acquisition of environmental point clouds, environmental images, obstacle velocity information, and the platform's own pose (position, attitude) information, providing raw perception data for subsequent data processing and trajectory planning. Specifically, the lidar acquires a 3D point cloud, with each point containing precise X, Y, Z 3D coordinates and reflection intensity information. The visual camera acquires environmental images / video streams. The millimeter-wave radar acquires an obstacle list, including obstacle distance, radial velocity (via Doppler effect), azimuth angle, and obstacle reflection intensity. The GNSS / IMU integrated navigation unit acquires the platform's own status data, including global position (latitude, longitude, and elevation), 3D velocity, 3D attitude (roll, pitch, and yaw angles), and precise timestamps.

[0101] 2. Data Processing and Fusion Module

[0102] Components: Semantic segmentation neural network, target detection and tracking algorithm, multi-sensor fusion localization algorithm;

[0103] Function: Cleans, parses, and fuses the raw data from the perception module, outputting a dynamic obstacle list with semantic labels and predicted trajectories, a static obstacle map, and the platform's own high-precision pose, providing processed environmental and platform status data for trajectory planning.

[0104] This module uses a semantic segmentation neural network to perform semantic classification (static obstacles, low-speed moving obstacles, and high-speed moving obstacles) and motion state prediction of dynamic obstacles. It assigns differentiated risk probability distributions and predicted trajectories to different types of obstacles, and constructs a 4D probabilistic safety field (3D space + time) that evolves over time on a 3D real-world map, replacing the traditional binary obstacle map and realizing probabilistic and spatiotemporal modeling of obstacles.

[0105] It enables predictive and smooth avoidance of dynamic obstacles, rather than the passive reactive obstacle avoidance of existing technologies, thus avoiding the high energy consumption and low efficiency caused by frequent sudden stops / turns, and improving flight safety and mission execution efficiency.

[0106] By extracting features and semantically classifying the obstacle avoidance requirements of airspace rules and natural language, and combining them with differentiated risk threshold settings, the system can understand the behavioral characteristics of obstacles, adopt targeted obstacle avoidance strategies, improve environmental adaptability, and respond in real time to unpredictable dynamic obstacles and dynamic changes in the urban environment.

[0107] 4D probabilistic modeling reduces the reliance on high-precision prior maps, requiring only a 3D real-world map to complete planning. This solves the problem of existing technologies relying on high-precision prior maps and is suitable for real-world application scenarios in complex urban environments.

[0108] During the generation of the spatiotemporal safe flight corridor, the corresponding risk probability threshold and the attenuation parameter of the 4D probabilistic safety field are set differently according to the semantic category of the dynamic obstacle and its predicted trajectory. The spatiotemporal safe flight corridor is dynamically adjusted. For example, a higher safety probability threshold is set for high-speed moving obstacles, and a normal threshold is set for low-speed moving obstacles.

[0109] It enables precise obstacle avoidance for different types of obstacles, avoids trajectory deviation caused by excessive obstacle avoidance of low-risk obstacles, and strictly avoids high-risk obstacles to ensure flight safety, balancing safety and efficiency.

[0110] Dynamically adjusting the spatiotemporal safety flight corridor makes the trajectory planning more in line with the actual situation of the complex urban environment, thereby improving the practicality and engineering application value of the solution.

[0111] Differentiated parameter settings simplify calculations, eliminating the need to apply uniform high safety standards to all obstacles, further reducing the computational burden and improving the real-time performance of planning.

[0112] 3. Integrated trajectory planning module

[0113] Composition: High-level task planning submodule, mid-level behavioral decision-making and safety corridor construction submodule, trajectory optimization submodule;

[0114] Function: Receives output data from the data processing and fusion module and the target of the survey mission, and generates a smooth, safe, executable spatiotemporal trajectory that conforms to the platform's dynamic constraints through hierarchical planning, providing trajectory instructions to the flight control module.

[0115] Using the initial mission path bundle as the survey framework, a spatiotemporal safe flight corridor with spatiotemporal constraints is constructed online in real time. Within the spatiotemporal safe flight corridor, smooth trajectory optimization that meets platform dynamic constraints is completed. The core is the online real-time construction of the safe flight corridor and the flexible deformation mechanism of the mission path, realizing the integrated planning of mission-oriented coverage path and safe obstacle avoidance.

[0116] The safe flight corridor is generated based on the initial mission path bundle. Obstacle avoidance actions minimize deviation from the original survey intent, thereby avoiding the separation of mission and obstacle avoidance, ensuring continuous and complete coverage of the target area, and avoiding data gaps and mission interruptions.

[0117] The layered architecture decomposes complex global optimization problems into online local optimizations, which can significantly reduce the computational burden and eliminate the need for time-consuming offline global optimization; it also improves the real-time performance of trajectory planning and adapts to task changes and environmental changes.

[0118] The system adopts dynamic adjustment of the spatiotemporal safety flight corridor, which takes into account both flight safety and trajectory optimization, avoids the problem of low survey quality caused by conservative obstacle avoidance, and meets the platform dynamics constraints to ensure the feasibility of the trajectory.

[0119] 4. Flight Control Module

[0120] Composition: Trajectory calculation unit, platform execution mechanism drive unit;

[0121] Function: Receives the planned trajectory output by the integrated trajectory planning module, converts it into control commands for each actuator of the low-altitude survey platform, and drives the platform to execute the trajectory; at the same time, it continuously feeds back the platform status during trajectory execution to achieve closed-loop planning.

[0122] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0123] In the above detailed description, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features of the single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, wherein each claim stands alone as a preferred embodiment of the invention.

[0124] The disclosed embodiments have been described above to enable any person skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments without departing from the spirit and scope of this disclosure. Therefore, this disclosure is not limited to the embodiments given herein, but is consistent with the broadest scope of the principles and novel features disclosed in this application.

[0125] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

[0126] Those skilled in the art will also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention can be implemented by electronic hardware, computer software, or a combination of both. To clearly demonstrate the interchangeability of hardware and software, the functions of the various illustrative components, units, and steps described above have been generally described. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functions using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of the present invention.

[0127] The various illustrative logic blocks or units described in the embodiments of this invention can be implemented or operate the described functions using a general-purpose processor, digital signal processor, application-specific integrated circuit (ASIC), field-programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general-purpose processor can be a microprocessor; alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented using a combination of computing devices, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0128] The steps of the methods or algorithms described in the embodiments of this invention can be directly embedded in hardware, a software module executed by a processor, or a combination of both. The software module can be stored in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from and write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and storage medium can be housed in an ASIC, which can be housed in a user terminal. Optionally, the processor and storage medium can also be housed in different components of the user terminal.

[0129] In one or more exemplary designs, the functions described in the embodiments of the present invention can be implemented in hardware, software, firmware, or any combination of these three. If implemented in software, these functions can be stored on a computer-readable medium or transmitted on a computer-readable medium in the form of one or more instructions or code. Computer-readable media include computer storage media and communication media that facilitate the transfer of computer programs from one place to another. Storage media can be any available media that can be accessed by a general-purpose or special-purpose computer. For example, such computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store program code in the form of instructions or data structures and other forms that can be read by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Furthermore, any connection can be suitably defined as a computer-readable medium, for example, if the software is transmitted from a website, server, or other remote resource via a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wirelessly, such as infrared, wireless, and microwave, it is also included in the defined computer-readable medium. The disks and discs mentioned include compressed disks, laser discs, optical discs, DVDs, floppy disks, and Blu-ray discs. Disks typically copy data magnetically, while discs typically copy data optically using lasers. Combinations of the above can also be contained in computer-readable media.

[0130] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A trajectory planning method for a low-altitude survey platform in urban areas, characterized in that, include: Generate the initial task path bundle for the targets to be surveyed in the city; A list of dynamic obstacles in the surrounding environment of the target to be surveyed is determined using a low-altitude survey platform. Based on the dynamic obstacle list and static obstacle map, a probabilistic safety field in three-dimensional space based on the timeline is constructed. In the probabilistic safety field, based on the initial mission path bundle, a connected spatiotemporal safe flight corridor is calculated for the current planning cycle; Based on the dynamic constraints of the low-altitude survey platform, the spatiotemporal safe flight corridor is optimized to obtain the optimal spatiotemporal trajectory.

2. The trajectory planning method for a low-altitude survey platform for cities according to claim 1, characterized in that, The initial task path bundle for generating the targets to be surveyed in the city includes: Based on the geometric features of the target to be surveyed and the three-dimensional real-world map of the target to be surveyed, a set of coarse waypoint sequences that can completely cover the surface of the target to be surveyed are generated as the initial mission path bundle.

3. The trajectory planning method for a low-altitude survey platform for cities according to claim 2, characterized in that, A list of dynamic obstacles in the surrounding environment of the target to be surveyed is determined using a low-altitude survey platform, including: The sensing module of the low-altitude survey platform collects multi-source sensing data of the surrounding environment of the target to be surveyed and the pose of the low-altitude survey platform in real time at a preset frequency. The multi-source sensing data includes at least two of the following: surrounding environment point cloud, surrounding environment image, and dynamic obstacle speed. Obstacles in multi-source perception data are semantically classified using a semantic segmentation neural network to obtain obstacles and their corresponding categories. The categories of obstacles include static obstacles, low-speed moving obstacles, and high-speed moving obstacles. By predicting the motion states of slow-moving and fast-moving obstacles, a dynamic list of obstacles with semantic labels and predicted trajectories is output.

4. The trajectory planning method for a low-altitude survey platform for cities according to claim 3, characterized in that, Based on the dynamic obstacle list and static obstacle map, a probabilistic safety field in three-dimensional space based on a timeline is constructed, including: Based on the dynamic obstacle list and combined with the static obstacle map, each obstacle is assigned a corresponding risk probability distribution and predicted trajectory. Calculate the probability distribution of each obstacle occupying space within a preset time period in the future to obtain a probabilistic safety field in three-dimensional space based on the timeline.

5. The trajectory planning method for a low-altitude survey platform for cities according to claim 4, characterized in that, In the probabilistic safety field, based on the initial mission path bundle, a connected spatiotemporal safe flight corridor is calculated for the current planning period, including: Based on the initial mission path bundle, in the probabilistic safety field, a connected spatiotemporal safe flight corridor is calculated for the current planning cycle according to the risk probability distribution and predicted trajectory of each obstacle; wherein, the spatiotemporal safe flight corridor meets the preset safety probability threshold and can be as close as possible to the initial mission path bundle while ensuring safety. Based on the dynamic constraints of the low-altitude survey platform, the spatiotemporal safe flight corridor is optimized to obtain the optimal spatiotemporal trajectory, including: Under the constraints of a safe flight corridor, and with the optimization objectives of satisfying the dynamic constraints of the low-altitude survey platform, minimizing energy consumption, and achieving a smooth trajectory, a smooth and trackable optimal spatiotemporal trajectory is generated.

6. A trajectory planning device for a low-altitude survey platform in cities, characterized in that, include: The high-level task planning module is used to generate the initial task path bundle for the targets to be surveyed in the city. A low-altitude survey platform for determining a list of dynamic obstacles in the surrounding environment of the target to be surveyed; The middle-level behavioral decision layer is used to construct a probabilistic safety field in three-dimensional space based on the dynamic obstacle list and the static obstacle map. The safe flight corridor construction module is used to calculate a connected spatiotemporal safe flight corridor for the current planning cycle based on the initial mission path bundle in a probabilistic safety field. The trajectory optimization module is used to optimize the spatiotemporal safety flight corridor based on the dynamic constraints of the low-altitude survey platform to obtain the optimal spatiotemporal trajectory.

7. The trajectory planning device for a low-altitude survey platform for cities according to claim 6, characterized in that, The high-level task planning module is specifically used for: Based on the geometric features of the target to be surveyed and the three-dimensional real-world map of the target to be surveyed, a set of coarse waypoint sequences that can completely cover the surface of the target to be surveyed are generated as the initial mission path bundle.

8. The trajectory planning device for a low-altitude survey platform for cities according to claim 7, characterized in that, The low-altitude survey platform includes: The sensing module collects multi-source sensing data of the surrounding environment of the target to be surveyed and the pose of the low-altitude survey platform in real time at a preset frequency. The multi-source sensing data includes at least two of the following: surrounding environment point cloud, surrounding environment image, and dynamic obstacle speed. A semantic segmentation neural network is used to semantically classify obstacles in multi-source perception data to obtain obstacles and their corresponding categories. The categories of obstacles include static obstacles, low-speed moving obstacles, and high-speed moving obstacles. The prediction model is used to predict the motion state of slow-moving and fast-moving obstacles, and outputs a list of dynamic obstacles with semantic labels and predicted trajectories.

9. The trajectory planning device for a low-altitude survey platform for cities according to claim 8, characterized in that, The middle-level behavioral decision-making layer is specifically used for: Based on the dynamic obstacle list and combined with the static obstacle map, each obstacle is assigned a corresponding risk probability distribution and predicted trajectory. Calculate the probability distribution of each obstacle occupying space within a preset time period in the future to obtain a probabilistic safety field in three-dimensional space based on the timeline.

10. The trajectory planning device for a low-altitude survey platform for cities according to claim 9, characterized in that, The safe flight corridor construction module is specifically used for: Based on the initial mission path bundle, in the probabilistic safety field, a connected spatiotemporal safe flight corridor is calculated for the current planning cycle according to the risk probability distribution and predicted trajectory of each obstacle; wherein, the spatiotemporal safe flight corridor meets the preset safety probability threshold and can be as close as possible to the initial mission path bundle while ensuring safety. The trajectory optimization module is specifically used for: Under the constraints of a safe flight corridor, and with the optimization objectives of satisfying the dynamic constraints of the low-altitude survey platform, minimizing energy consumption, and achieving a smooth trajectory, a smooth and trackable optimal spatiotemporal trajectory is generated.

Images