A low-altitude flight trajectory optimization method and system

Abstract

The application relates to the technical field of low-altitude flight, and discloses a low-altitude flight trajectory optimization method and system, which comprises the following steps: obtaining obstacle data of a test area, determining a region complexity parameter according to the obstacle data of the test area, and determining a trajectory constraint parameter set according to the region complexity parameter; establishing a flying car trajectory simulation model according to the trajectory constraint parameter set to simulate a flying car obstacle trajectory test process, and outputting a trajectory loss parameter set corresponding to a plurality of trajectory strategies; constructing a fitness function according to the trajectory loss parameter set, optimizing the fitness function based on a particle swarm algorithm, and obtaining an optimal trajectory strategy. The safety adaptability, target diversity and solution accuracy in low-altitude flight trajectory planning of the flying car can be effectively ensured.

Description

Technical Field

[0001] This application relates to the field of low-altitude flight technology, and more specifically, to a method and system for optimizing low-altitude flight trajectories. Background Technology

[0002] With the booming development of urban air traffic and the low-altitude economy, low-altitude aircraft, represented by flying cars and electric vertical take-off and landing aircraft, are gradually becoming key transportation tools for solving ground traffic congestion and expanding urban three-dimensional space.

[0003] Existing low-altitude aircraft, especially in urban low-altitude environments, face unprecedented challenges to operational safety due to dense obstacles, numerous dynamic interferences, and complex airflow conditions. How to plan an efficient and economical flight path while ensuring absolute safety is a core technical challenge that must be overcome for the commercial operation of low-altitude aircraft. Summary of the Invention

[0004] This invention provides a method and system for optimizing low-altitude flight trajectories, addressing the problem in the prior art of planning an efficient and economical flight trajectory for low-altitude aircraft while ensuring absolute safety. The method includes:

[0005] Obstacle data of the test area is acquired, and the area complexity parameter is determined based on the obstacle data. The trajectory constraint parameter set is then determined based on the area complexity parameter. The obstacle data includes the static obstacle area and the dynamic obstacle parameter set. A flight car trajectory simulation model is established based on the trajectory constraint parameter set to simulate the flight car obstacle trajectory test process, and a trajectory loss parameter set corresponding to multiple trajectory strategies is output. A fitness function is constructed based on the trajectory loss parameter set, and the fitness function is optimized based on the particle swarm optimization algorithm to obtain the optimal trajectory strategy.

[0006] Furthermore, the region complexity parameters are determined based on the obstacle data of the test area, including:

[0007] A preset grid is obtained, and the test area is divided into several sub-test areas according to the preset grid. The static obstacle area and dynamic obstacle parameter set in the sub-test areas are statistically analyzed. The sub-complexity parameter of the sub-test area is determined based on the static obstacle area and dynamic obstacle parameter set, where the dynamic obstacle parameter set includes the area, speed, and heading change rate of the dynamic obstacles. Any target sub-test area is selected, and the sub-complexity parameter in a preset neighborhood of any target sub-test area is statistically analyzed. Sub-test areas with sub-complexity parameters greater than a first preset threshold are taken as obstacle association areas of the target sub-test area, and the sum of the sub-complexity parameters of the obstacle association areas is calculated. The sum of the sub-complexity parameters of the obstacle association areas is used to correct the sub-complexity parameter of the target sub-test area, and the average value of the corrected sub-complexity parameters of all sub-test areas is calculated to obtain the regional complexity parameter of the test area.

[0008] Furthermore, the sub-complexity parameters of the sub-test region are determined based on the static obstacle area and the dynamic obstacle parameter set, including: determining the sub-complexity parameters of the sub-test region according to the sub-complexity parameter calculation formula, whereby the sub-complexity parameter calculation formula is as follows:

[0009] ,

[0010] in, For sub-complexity parameters, The area of ​​the static obstacle. The area of ​​the sub-test region. For the preset range coefficient, For the area of ​​the dynamic obstacle, Let be the velocity of the i-th dynamic obstacle within the sub-test area. Let i be the rate of change of heading of the i-th dynamic obstacle within the sub-test area. The average velocity of all dynamic obstacles within the sub-test area. This represents the total number of dynamic obstacles within the sub-test area.

[0011] Further, determining the trajectory constraint parameter set based on the regional complexity parameter includes: obtaining a preset mapping relationship between the regional complexity parameter and the complexity level; determining the complexity level corresponding to the current regional complexity parameter based on the preset mapping relationship; and determining the corresponding trajectory constraint parameter set based on the complexity level corresponding to the current regional complexity parameter.

[0012] Furthermore, a flight car trajectory simulation model is established based on the trajectory constraint parameter set to simulate the flight car obstacle trajectory test process, and outputs a trajectory loss parameter set corresponding to multiple trajectory strategies. This includes: acquiring obstacle data of the test area; establishing a flight car trajectory simulation model based on the obstacle data and the trajectory constraint parameter set; inputting each trajectory strategy into the flight car trajectory simulation model to simulate the flight car obstacle trajectory test process and obtain simulation results; and determining collision hazard parameters, trajectory time, and trajectory consumption based on the simulation results to obtain the trajectory loss parameter set.

[0013] Furthermore, collision hazard parameters, trajectory time, and trajectory consumption are determined based on the simulation results, including: determining the distance between the flying car and obstacles during the flying car test based on the simulation results; determining the collision hazard parameters based on the distance between the flying car and obstacles during the flying car test; determining the total time of the flying car test based on the simulation results; determining the trajectory time based on the total time of the flying car test; determining the fuel consumption and pollutant emission data during the flying car test based on the simulation results; and determining the trajectory consumption based on the fuel consumption and pollutant emission data.

[0014] Furthermore, collision hazard parameters are determined based on the distances between the flying car and obstacles during the flying car test, including: statistically analyzing the average distances between the flying car and all obstacles during the flying car test, and performing a negative correlation mapping on the average distances between the flying car and all obstacles during the flying car test to obtain collision hazard parameters.

[0015] Furthermore, the step of constructing a fitness function based on the trajectory loss parameter set includes: constructing a fitness function based on the collision hazard parameters, trajectory time, and trajectory consumption of the trajectory loss parameter set, the expression of which is:

[0016]

[0017] in, For collision hazard parameters, For trajectory time, For trajectory consumption, , , These are the preset first weight, preset second weight, and preset third weight, respectively.

[0018] Furthermore, the optimization of the fitness function based on the particle swarm optimization algorithm to obtain the optimal trajectory strategy includes: Step 1, randomly initializing the velocity and position of each particle in the search space, calculating the fitness function value of each particle, and the position of the particle with the minimum fitness function value is the global optimal position; Step 2, correcting the particle's flight direction using velocity update formulas and position update formulas; Step 3, evaluating the particle's fitness function value, and updating the individual optimal position and the global optimal position of the particle; Step 4, determining whether the particle swarm optimization algorithm meets the convergence condition. If it does, outputting the global optimal position and ending the process, and determining the particle corresponding to the global optimal position as the optimal trajectory strategy; otherwise, repeating steps 1 to 3.

[0019] To achieve the above objectives, the present invention also provides a low-altitude flight trajectory optimization system, comprising:

[0020] The acquisition module is used to acquire obstacle data of the test area, determine the area complexity parameter based on the obstacle data, and determine the trajectory constraint parameter set based on the area complexity parameter. The simulation module is used to build a flight car trajectory simulation model based on the trajectory constraint parameter set to simulate the flight car obstacle trajectory test process and output the trajectory loss parameter set corresponding to multiple trajectory strategies. The optimization module is used to construct a fitness function based on the trajectory loss parameter set, optimize the fitness function based on the particle swarm optimization algorithm, and obtain the optimal trajectory strategy.

[0021] The beneficial effects of this invention are as follows:

[0022] By applying the above technical solutions, this invention dynamically generates the constraints for trajectory planning through quantified regional complexity parameters, and uses intelligent optimization algorithms to solve for the optimal trajectory based on the multi-objective loss function of the simulation model. It can deeply integrate complex environment perception, adaptively generate constraints, and achieve a balance among multiple optimization objectives. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 The overall flowchart of a low-altitude flight trajectory optimization method proposed in an embodiment of the present invention is shown;

[0025] Figure 2 A schematic diagram of a low-altitude flight trajectory optimization system proposed in an embodiment of the present invention is shown. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] This application provides a method for optimizing low-altitude flight trajectories, such as... Figure 1 As shown, it includes:

[0028] S101, Obtain obstacle data of the test area, determine the area complexity parameter based on the obstacle data of the test area, and determine the trajectory constraint parameter set based on the area complexity parameter. The obstacle data includes the static obstacle area and the dynamic obstacle parameter set.

[0029] In this embodiment, obstacle data such as static obstacles like buildings and mountains and dynamic obstacles like aircraft and birds in the test area are acquired by airborne sensors, and a set of trajectory constraint parameters is constructed based on the obstacle data.

[0030] In some embodiments of this application, determining the region complexity parameter based on obstacle data of the test area includes: obtaining a preset grid; dividing the test area into several sub-test areas based on the preset grid; calculating the static obstacle area and dynamic obstacle parameter set in the sub-test areas; determining the sub-complexity parameter of the sub-test areas based on the static obstacle area and dynamic obstacle parameter set, wherein the dynamic obstacle parameter set includes the area, speed, and heading change rate of the dynamic obstacles; selecting any target sub-test area; calculating the sub-complexity parameter within a preset neighborhood of any target sub-test area; taking the sub-test areas with sub-complexity parameters greater than a first preset threshold as obstacle association areas of the target sub-test area; calculating the sum of the sub-complexity parameters of the obstacle association areas; correcting the sub-complexity parameter of the target sub-test area based on the sum of the sub-complexity parameters of the obstacle association areas; and calculating the average value of the corrected sub-complexity parameters of all sub-test areas to obtain the region complexity parameter of the test area.

[0031] In some embodiments of this application, determining the sub-complexity parameter of a sub-test region based on the static obstacle area and the dynamic obstacle parameter set includes: determining the sub-complexity parameter of the sub-test region according to a sub-complexity parameter calculation formula, wherein the sub-complexity parameter calculation formula is as follows:

[0032] ,

[0033] in, For sub-complexity parameters, The area of ​​the static obstacle. The area of ​​the sub-test region. For the preset range coefficient, For the area of ​​the dynamic obstacle, Let be the velocity of the i-th dynamic obstacle within the sub-test area. Let i be the rate of change of heading of the i-th dynamic obstacle within the sub-test area. The average velocity of all dynamic obstacles within the sub-test area. This represents the total number of dynamic obstacles within the sub-test area.

[0034] In this embodiment, static risk is... This measure represents the physical occupancy rate of space. Dynamic risk is amplified using the exponential function exp(), whose internal parameters... This represents the instantaneous spatial occupancy of dynamic obstacles, while This is a dimensionless dynamic disturbance factor that measures the average velocity-weighted maneuverability of dynamic obstacles within a region. When there are many dynamic obstacles in the region, and they are fast and highly maneuverable, this factor increases. Through exponential function mapping, this causes a sharp increase in dynamic risk, in order to adapt to the objective law of nonlinear risk growth in complex dynamic airspace.

[0035] S102, Establish a flight car trajectory simulation model based on the trajectory constraint parameter set to simulate the flight car obstacle trajectory test process, and output the trajectory loss parameter set corresponding to multiple trajectory strategies;

[0036] In some embodiments of this application, determining the trajectory constraint parameter set based on the region complexity parameter includes: obtaining a preset mapping relationship between the region complexity parameter and the complexity level; determining the complexity level corresponding to the current region complexity parameter based on the preset mapping relationship; and determining the corresponding trajectory constraint parameter set based on the complexity level corresponding to the current region complexity parameter.

[0037] In this embodiment, a pre-defined mapping table between region complexity parameters and complexity levels is used. Based on the calculated current region complexity parameters, its complexity level (e.g., low, medium, high) is determined, and then a trajectory constraint parameter set matching that level is invoked. This trajectory constraint parameter set includes safety thresholds and performance boundaries that need to be followed in subsequent simulations, such as the minimum safe distance coefficient, the maximum permissible rate of change of heading, and speed adjustment weights.

[0038] In some embodiments of this application, a flight car trajectory simulation model is established based on a trajectory constraint parameter set to simulate the flight car obstacle trajectory test process, and a trajectory loss parameter set corresponding to multiple trajectory strategies is output. This includes: acquiring obstacle data of the test area; establishing a flight car trajectory simulation model based on the obstacle data and the trajectory constraint parameter set; inputting each trajectory strategy into the flight car trajectory simulation model to simulate the flight car obstacle trajectory test process and obtain simulation results; and determining collision hazard parameters, trajectory time, and trajectory consumption based on the simulation results to obtain a trajectory loss parameter set.

[0039] In this embodiment, after determining a trajectory constraint parameter set that matches the complexity of the current environment, a high-fidelity flying car trajectory simulation model is constructed. This model not only integrates the six-degree-of-freedom dynamics and kinematic equations of the flying car, but also incorporates obstacle data and a dynamically generated trajectory constraint parameter set. Multiple pre-designed candidate trajectory strategies are input into the simulation model one by one to simulate the entire flight process of the flying car from the starting point to the destination. During the simulation, the model records data such as the interaction between the aircraft and obstacles, flight time, and energy consumption in real time. After the simulation, the trajectory loss parameters corresponding to each trajectory strategy are extracted based on the simulation results, including: collision hazard parameters, trajectory time, and trajectory consumption.

[0040] In some embodiments of this application, determining collision hazard parameters, trajectory time, and trajectory consumption based on simulation results includes: determining the distance between the flying car and obstacles during the flying car test based on simulation results; determining collision hazard parameters based on the distance between the flying car and obstacles during the flying car test; determining the total time of the flying car test process based on simulation results; determining trajectory time based on the total time of the flying car test process; determining fuel consumption and pollutant emission data during the flying car test process based on simulation results; and determining trajectory consumption based on fuel consumption and pollutant emission data.

[0041] In some embodiments of this application, collision hazard parameters are determined based on the distance between the flying car and obstacles during the flying car test, including: calculating the average distance between the flying car and all obstacles during the flying car test, and performing a negative correlation mapping on the average distance between the flying car and all obstacles during the flying car test to obtain collision hazard parameters.

[0042] In this embodiment, the collision hazard parameters are determined by the negative correlation mapping method. That is, the smaller the average distance, the greater the hazard parameter. The trajectory time is directly determined by the total time of the simulation process, and the trajectory consumption is obtained by weighted summation of the simulated flying car fuel consumption and pollutant emission data.

[0043] S103: Construct a fitness function based on the trajectory loss parameter set, and optimize the fitness function based on the particle swarm optimization algorithm to obtain the optimal trajectory strategy.

[0044] In some embodiments of this application, constructing a fitness function based on the trajectory loss parameter set includes: constructing a fitness function based on the collision hazard parameters, trajectory time, and trajectory consumption of the trajectory loss parameter set, the expression of which is:

[0045]

[0046] in, For collision hazard parameters, For trajectory time, For trajectory consumption, , , These are the preset first weight, preset second weight, and preset third weight, respectively.

[0047] In some embodiments of this application, the optimization of the fitness function based on the particle swarm optimization algorithm to obtain the optimal trajectory strategy includes: Step 1, randomly initializing the velocity and position of each particle in the search space, calculating the fitness function value of each particle, and the position of the particle with the minimum fitness function value is the global optimal position; Step 2, correcting the particle's flight direction using velocity update formulas and position update formulas; Step 3, evaluating the particle's fitness function value, and updating the individual optimal position and the global optimal position of the particle; Step 4, determining whether the particle swarm optimization algorithm meets the convergence condition. If it does, outputting the global optimal position and ending the process, and determining the particle corresponding to the global optimal position as the optimal trajectory strategy; otherwise, repeating steps 1 to 3.

[0048] In this embodiment, the particle swarm optimization algorithm is used to optimize each trajectory strategy to obtain the optimal trajectory strategy, which can effectively ensure the safety adaptability, target diversity and solution accuracy in the low-altitude flight trajectory planning of flying cars.

[0049] Based on the same technological concept, such as Figure 2 As shown, the present invention also provides a low-altitude flight trajectory optimization system, comprising:

[0050] The acquisition module is used to acquire obstacle data of the test area, determine the area complexity parameter based on the obstacle data, and determine the trajectory constraint parameter set based on the area complexity parameter. The simulation module is used to build a flight car trajectory simulation model based on the trajectory constraint parameter set to simulate the flight car obstacle trajectory test process and output the trajectory loss parameter set corresponding to multiple trajectory strategies. The optimization module is used to construct a fitness function based on the trajectory loss parameter set, optimize the fitness function based on the particle swarm optimization algorithm, and obtain the optimal trajectory strategy.

[0051] By applying the above technical solutions, this invention acquires obstacle data from the test area, determines the area complexity parameters based on the obstacle data, and then determines the trajectory constraint parameter set based on the area complexity parameters. A flight car trajectory simulation model is established based on the trajectory constraint parameter set to simulate the flight car obstacle trajectory test process, outputting trajectory loss parameter sets corresponding to multiple trajectory strategies. A fitness function is constructed based on the trajectory loss parameter set, and the fitness function is optimized using a particle swarm optimization algorithm to obtain the optimal trajectory strategy. This effectively ensures the safety adaptability, target diversity, and solution accuracy in the low-altitude flight trajectory planning of the flight car.

[0052] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for optimizing low-altitude flight trajectories, characterized in that, include: Obtain obstacle data for the test area, determine the area complexity parameter based on the obstacle data, and determine the trajectory constraint parameter set based on the area complexity parameter. The obstacle data includes the static obstacle area and the dynamic obstacle parameter set. A flight car trajectory simulation model is established based on the trajectory constraint parameter set to simulate the obstacle trajectory test process of the flight car, and the trajectory loss parameter set corresponding to multiple trajectory strategies is output. A fitness function is constructed based on the trajectory loss parameter set, and the fitness function is optimized based on the particle swarm optimization algorithm to obtain the optimal trajectory strategy. The region complexity parameters are determined based on the obstacle data of the test area, including: Obtain a preset grid, and divide the test area into several sub-test areas based on the preset grid; The area of ​​static obstacles and the set of dynamic obstacle parameters in the sub-test area are statistically analyzed. The sub-complexity parameters of the sub-test area are determined based on the area of ​​static obstacles and the set of dynamic obstacle parameters, wherein the set of dynamic obstacle parameters includes the area, speed and rate of change of heading of the dynamic obstacles. Select any target sub-test region and calculate the sub-complexity parameters within the preset neighborhood of any target sub-test region; Sub-test regions with sub-complexity parameters greater than a first preset threshold are taken as obstacle association regions of the target sub-test region, and the sum of sub-complexity parameters of the obstacle association regions is calculated. The sum of the sub-complexity parameters of the obstacle-related regions is used to correct the sub-complexity parameters of the target sub-test region. The average value of the corrected sub-complexity parameters of all sub-test regions is calculated to obtain the region complexity parameter of the test region. The sub-complexity parameters of the sub-test region are determined based on the static obstacle area and the dynamic obstacle parameter set, including: The sub-complexity parameter of the sub-test region is determined based on the sub-complexity parameter calculation formula, which is as follows: ， in, For sub-complexity parameters, The area of ​​the static obstacle. The area of ​​the sub-test region. For the preset range coefficient, For the area of ​​the dynamic obstacle, Let be the velocity of the i-th dynamic obstacle within the sub-test area. Let i be the rate of change of heading of the i-th dynamic obstacle within the sub-test area. The average velocity of all dynamic obstacles within the sub-test area. This represents the total number of dynamic obstacles within the sub-test area.

2. The low-altitude flight trajectory optimization method according to claim 1, characterized in that, The trajectory constraint parameter set is determined based on the region complexity parameter, including: Obtain the preset mapping relationship between region complexity parameters and complexity levels, and determine the complexity level corresponding to the current region complexity parameter based on the preset mapping relationship; The corresponding set of trajectory constraint parameters is determined based on the complexity level corresponding to the current region complexity parameter.

3. The low-altitude flight trajectory optimization method according to claim 1, characterized in that, A flight car trajectory simulation model is established based on the trajectory constraint parameter set to simulate the obstacle trajectory test process of the flight car, and the trajectory loss parameter set corresponding to multiple trajectory strategies is output, including: Obtain obstacle data for the test area, and establish a flight car trajectory simulation model based on the obstacle data and trajectory constraint parameter set; Each trajectory strategy is input into the flying car trajectory simulation model to simulate the obstacle trajectory test process of the flying car and obtain the simulation results. Based on the simulation results, collision hazard parameters, trajectory time, and trajectory consumption are determined, resulting in a trajectory loss parameter set.

4. The low-altitude flight trajectory optimization method according to claim 3, characterized in that, Based on the simulation results, collision hazard parameters, trajectory time, and trajectory consumption are determined, including: The distance between the flying car and obstacles during the test is determined based on the simulation results, and the collision hazard parameters are determined based on the distance between the flying car and obstacles during the test. The total time for the flying car test process is determined based on the simulation results, and the trajectory time is determined based on the total time for the flying car test process. Based on the simulation results, determine the fuel consumption and pollutant emission data during the flying car test process, and determine the trajectory consumption based on the fuel consumption and pollutant emission data.

5. The low-altitude flight trajectory optimization method according to claim 4, characterized in that, Collision hazard parameters are determined based on the distance between the flying car and obstacles during flight car testing, including: The average distance between the flying car and all obstacles during the test was statistically analyzed, and a negative correlation mapping was performed on the average distance between the flying car and all obstacles during the test to obtain collision hazard parameters.

6. The low-altitude flight trajectory optimization method according to claim 3, characterized in that, The construction of the fitness function based on the trajectory loss parameter set includes: Based on the collision hazard parameters, trajectory time, and trajectory consumption from the trajectory loss parameter set, a fitness function is constructed, the expression of which is: in, For collision hazard parameters, For trajectory time, For trajectory consumption, , , These are the preset first weight, preset second weight, and preset third weight, respectively.

7. The low-altitude flight trajectory optimization method according to claim 1, characterized in that, The optimization of the fitness function based on the particle swarm optimization algorithm to obtain the optimal trajectory strategy includes: Step 1: Randomly initialize the velocity and position of each particle in the search space, calculate the fitness function value of each particle, and the position of the particle with the minimum fitness function value is the global optimal position. Step 2: Correct the particle's flight direction using velocity update formulas and position update formulas; Step 3: Evaluate the fitness function value of the particle and update the individual optimal position and global optimal position of the particle; Step 4: Determine whether the particle swarm optimization algorithm meets the convergence condition. If it does, output the global optimal position and end the process. The particle corresponding to the global optimal position is determined as the optimal trajectory strategy. Otherwise, repeat steps 1 to 3.

8. A low-altitude flight trajectory optimization system, characterized in that, include: The acquisition module is used to acquire obstacle data of the test area, determine the area complexity parameter based on the obstacle data of the test area, and determine the trajectory constraint parameter set based on the area complexity parameter. The obstacle data includes the static obstacle area and the dynamic obstacle parameter set. The simulation module is used to build a flight car trajectory simulation model based on the trajectory constraint parameter set to simulate the obstacle trajectory test process of the flight car and output the trajectory loss parameter set corresponding to multiple trajectory strategies. The optimization module is used to construct a fitness function based on the trajectory loss parameter set, and optimize the fitness function based on the particle swarm optimization algorithm to obtain the optimal trajectory strategy. The acquisition module determines the region complexity parameter based on the obstacle data of the test area, including: Obtain a preset grid, and divide the test area into several sub-test areas based on the preset grid; The area of ​​static obstacles and the set of dynamic obstacle parameters in the sub-test area are statistically analyzed. The sub-complexity parameters of the sub-test area are determined based on the area of ​​static obstacles and the set of dynamic obstacle parameters, wherein the set of dynamic obstacle parameters includes the area, speed and rate of change of heading of the dynamic obstacles. Select any target sub-test region and calculate the sub-complexity parameters within the preset neighborhood of any target sub-test region; Sub-test regions with sub-complexity parameters greater than a first preset threshold are taken as obstacle association regions of the target sub-test region, and the sum of sub-complexity parameters of the obstacle association regions is calculated. The sum of the sub-complexity parameters of the obstacle-related regions is used to correct the sub-complexity parameters of the target sub-test region. The average value of the corrected sub-complexity parameters of all sub-test regions is calculated to obtain the region complexity parameter of the test region. The sub-complexity parameters of the sub-test region are determined based on the static obstacle area and the dynamic obstacle parameter set, including: The sub-complexity parameter of the sub-test region is determined based on the sub-complexity parameter calculation formula, which is as follows: ， in, For sub-complexity parameters, The area of ​​the static obstacle. The area of ​​the sub-test region. For the preset range coefficient, For the area of ​​the dynamic obstacle, Let be the velocity of the i-th dynamic obstacle within the sub-test area. Let i be the rate of change of heading of the i-th dynamic obstacle within the sub-test area. The average velocity of all dynamic obstacles within the sub-test area. This represents the total number of dynamic obstacles within the sub-test area.

Images