Path automatic decision optimization method for aircraft tractor

Abstract

The invention discloses an automatic path decision optimization method for an aircraft tractor, and the method comprises the steps: building a local path planning method considering the kinematics constraint of the tractor according to the characteristics that the speed of the aircraft tractor in an actual traction working scene is low, and the aircraft tractor can only move forwards or steer within a certain turning radius; and the turning radius limitation of the planned path and the safety distance between the planned path and the obstacle and the road edge are emphatically considered, so that the planned path conforms to the actual working scene of the tractor. A multi-objective optimization function is established by combining a vehicle anti-collision strategy and the motion constraint conditions, the problem of aircraft tractor traction path planning is solved through a nonlinear optimization method, and finally a safe and feasible track which meets the working requirements of a tractor and is free of collision is obtained. According to the method, path planning is carried out by utilizing an A * algorithm, so that a discretized optimal path which has the lowest cost function result and meets the constraint requirement in the working process of the aircraft tractor is planned.

Description

Technical Field

[0001] The invention relates to the technical field of aviation ground special equipment, and in particular to an automatic path decision optimization method for an aircraft tractor. Background Art

[0002] In order to promote a new departure towing mode, that is, by introducing the power integration with departure taxiing, centralized control and high-speed towing movement, the departure mode relies on the power of the towing vehicle to directly complete the efficient transfer from the berth to the take-off runway. Therefore, the high-speed and heavy-load typical characteristics of the aircraft towing system in this mode have requirements for safety and robustness, which has promoted the development of the automatic decision-making optimization method of the aircraft towing vehicle path.

[0003] During the ground operation of an aircraft, path planning for an aircraft tug is a critical task. Traditional path planning methods are usually based on experience or simple algorithms, which cannot fully consider various factors, resulting in inaccurate path decisions and low efficiency. Therefore, it is necessary to provide an efficient and accurate method for automatic decision-making and optimization of aircraft tug paths. Summary of the invention

[0004] The present invention provides an automatic path decision optimization method for aircraft tugs to solve the problems in the above background technology.

[0005] Preferably, the present invention obtains the current position of the aircraft tractor and the position information of the aircraft, obtains the airport map and environmental information, performs path planning based on the real-time data and environmental information using the A* intelligent algorithm, determines the steps of the optimal path, generates path planning instructions for the aircraft tractor according to the optimal path, sends the path planning instructions to the aircraft tractor control system, and monitors the execution status, and continuously optimizes the path planning according to the real-time data and feedback information to adapt to dynamic environmental changes.

[0006] Preferably, the A* intelligent algorithm includes machine learning algorithms, data analysis and optimization algorithms, etc. In view of the relatively regular working area of ​​the aircraft tractor, the algorithm sampling range and randomness are restricted, and the motion constraints and anti-collision functions are combined to realize the planning of the working path of the aircraft tractor.

[0007] Preferably, in the anti-collision processing, an anti-collision safety area is added to the original position and range of the curbs and obstacles in the grid map, so that the aircraft tractor-aircraft system can be regarded as a particle at its center of mass position in the grid map for path planning to ensure the safety of the planned path.

[0008] Preferably, by calculating the minimum turning radius at each location of the smoothed path, the limit of the minimum turning radius is calculated, and the minimum turning radius is set as a hard constraint for path planning to ensure that the turning radius at each location of the path meets the traction work requirements of the aircraft tug.

[0009] Preferably, the airport map and environmental information are obtained to model the airport ground handling area as a two-dimensional grid map, where each grid represents a drivable area. Through map modeling, the airport ground handling area is converted into a graph to facilitate subsequent path search and decision-making.

[0010] Preferably, according to the actual situation, a heuristic function is designed to evaluate the cost of each grid. The heuristic function can consider the following factors: the straight-line distance from the target, the traffic capacity of the grid, avoiding collisions, etc. The A algorithm is used to search the path on the map. The A* algorithm is a heuristic search algorithm that finds the optimal path by comprehensively considering the heuristic function and the cost of the path that has been searched.

[0011] Preferably, due to the real-time requirements of airport ground handling operations, the path needs to be updated in real time. When new information or events occur, the path search and decision optimization steps are re-executed.

[0012] The beneficial effects of the present invention are as follows: (1) by applying the A* algorithm, high efficiency and accuracy of path planning are achieved; (2) factors such as path length, time cost, and vehicle power consumption are comprehensively considered to improve the accuracy of path decision-making; (3) it can be adjusted according to actual needs and has high flexibility and adaptability; (4) the efficiency of aircraft ground operations is improved and operating costs are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Attached Figure 1 A schematic diagram of an automatic path decision optimization method for an aircraft tug;

[0014] Attached Figure 2 This is a diagram of the specific implementation steps of the A* algorithm; DETAILED DESCRIPTION

[0015] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings.

[0016] As attached Figure 1 This system uses the site and obstacle information to generate an electronic map, and on this basis uses the A* algorithm combined with anti-collision constraints and motion constraints for path planning, planning a discretized optimal path that meets the constraint requirements with the lowest cost function result, and obtains the optimal path by using the curve fitting optimization method for the discrete trajectory points obtained after calculation.

[0017] As attached Figure 2 , the specific implementation method of this system is as follows:

[0018] In step 2, the division of the ground operation area can be adjusted according to actual needs, and can be divided into different grids according to the characteristics of the ground operation area to improve the accuracy of path planning.

[0019] In step 3, sensors may include depth cameras, lidars, etc., to obtain real-time data of the ground operation area.

[0020] In step 4, the A* algorithm can perform calculations based on the gridded representation of the ground operation area and find the optimal path through heuristic search.

[0021] In step 5, the automatic path decision optimization can be adjusted according to actual needs, and different weight coefficients can be set to achieve flexibility in path planning, while adaptive parameter control can be performed according to different aircraft models.

[0022] Anti-collision processing is a crucial part to ensure the safety of the planned path. The path planning algorithm proposed in the present invention first rasterizes the aircraft tractor work site and obstacles, discretizes the continuous space into discrete grids, and reflects the road features of the aircraft tractor work site such as airport runways and corridors in the grid map.

[0023] By calculating the minimum turning radius at each location on the smoothed path, the limit of the calculated minimum turning radius is set as a hard constraint for path planning to ensure that the turning radius at each location on the path meets the requirements of the aircraft tug.

[0024] For the discrete path points obtained by the improved A* algorithm planning, the least squares method and gradient descent method are used for curve fitting respectively. The common working scenarios of aircraft tugs (airport curves and airport straights) are used to fit the discrete path points to achieve path smoothing, so that the system outputs a path that can enable the aircraft tug to move forward smoothly.

[0025] In summary, the above are only preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A path automatic decision optimization method for an aircraft tractor, characterized in that: The steps of obtaining the current position of the aircraft tractor and the position information of the aircraft, obtaining the airport map and environmental information, performing path planning using the A* intelligent algorithm based on the real-time data and environmental information, and determining the optimal path, generating path planning instructions for the aircraft tractor according to the optimal path, sending the path planning instructions to the aircraft tractor control system, and monitoring the execution status, and continuously optimizing the path planning according to the real-time data and feedback information to adapt to the dynamic environmental changes.

2. The automatic path decision optimization method for aircraft tractors according to claim 1, characterized in that: The A* intelligent algorithm includes machine learning algorithms, data analysis and optimization algorithms, etc. In view of the relatively regular working area of ​​the aircraft tractor, the algorithm sampling range and randomness are restricted, and the motion constraints and anti-collision functions are combined to realize the planning of the working path of the aircraft tractor, including the following steps: Step 1: Get the current position and target position of the aircraft tug; Step 2: Build a map network and divide the ground operation area into multiple grids; Step 3: Use sensors to obtain real-time data of the ground operation area, including obstacle locations, vehicle power consumption, etc. Step 4: Calculate the optimal path based on the A* algorithm; Step 5: Comprehensively consider factors such as path length, time cost, and vehicle power consumption to automatically optimize the path decision; Step 6: Output the optimal path and execute it.

3. The automatic path decision optimization method for aircraft tugs according to claim 1, characterized in that: The A* algorithm has anti-collision processing, that is, an anti-collision safety area is added to the original position and range of the curbs and obstacles in the grid map. In this way, the aircraft tractor-aircraft system can be regarded as a particle at its center of mass position in the grid map for path planning to ensure the safety of the planned path.

4. The automatic path decision optimization method for aircraft tractors according to claim 2, characterized in that: In step 2, the division of the ground operation area is adjusted according to actual needs to improve the accuracy of path planning.

5. The automatic path decision optimization method for aircraft tractors according to claim 2, characterized in that: In step 3, sensors include depth cameras, lidars, etc., which are used to obtain real-time data of the ground operation area, wherein the environmental information obtained includes aprons, runways, obstacles, etc.

6. The automatic path decision optimization method for aircraft tractors according to claim 2, characterized in that: In step 4, the A* algorithm performs calculations based on the grid representation of the ground operation area and finds the optimal path through heuristic search. The path planning instructions include the driving direction, speed, turning radius, etc. of the aircraft tractor.

7. The automatic path decision optimization method for aircraft tractors according to claim 2, characterized in that: In step 5, the automatic path decision optimization is adjusted according to actual needs, with high flexibility and adaptability.

8. The automatic path decision optimization method for aircraft tractors according to claim 1, characterized in that: By implementing the aircraft tractor path automatic decision optimization method provided by the present invention, the aircraft ground operation efficiency is improved and the operation cost is reduced.

Images