An aerial vehicle multi-sensor fusion path planning method, system, device and storage medium

Abstract

The application discloses a kind of flying car multi-sensor fusion path planning method, system, equipment and storage medium, S1, the surrounding environment information of flying car is acquired, constructs three-dimensional simulation space, establishes the starting point coordinate and target point coordinate of flying car;S2, improvement ant colony algorithm, including setting multi-factor heuristic function, adaptive evaporation coefficient, dynamic weight coefficient and multi-factor pheromone update mechanism;S3, set the safety distance function of artificial potential field method and the trajectory evaluation function of dynamic window method;S4, adjusted ant colony algorithm is based on surrounding environment information and the starting point coordinate and target point coordinate of flying car, carries out global path planning, wherein local path is judged by safety distance function and trajectory evaluation function evaluation, obtains the optimal path of flying car. Significantly improve the efficiency and accuracy of path planning, ensure the safety and stability of flight process.

Description

Technical Field

[0001] This invention belongs to the field of flying cars and relates to a method, system, device and storage medium for multi-sensor fusion path planning of flying cars. Background Technology

[0002] Path planning technology is a key guidance technology for planning the aerial flight path of flying cars from any takeoff point to any landing point in a city. Unlike traditional ground transportation, path planning for urban air transportation takes place in three-dimensional space, requiring consideration of the complex three-dimensional environment and airway structure. This three-dimensional path planning involves selecting appropriate airways, considering airway change nodes, and restrictions on airway direction. The complexity of urban air transportation path planning lies in the fact that it must be carried out in three-dimensional space, making it difficult to plan the optimal path in real time and efficiently. At the same time, takeoff and landing control technology also poses a significant challenge to the safety of flying cars, requiring effective takeoff and prioritizing landing safety. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide a multi-sensor fusion path planning method, system, device and storage medium for flying cars, which significantly improves the efficiency and accuracy of path planning and ensures the safety and stability of the flight process.

[0004] To achieve the above objectives, the present invention employs the following technical solution:

[0005] A multi-sensor fusion path planning method for flying cars includes the following process:

[0006] S1: Obtain information about the surrounding environment of the flying car, construct a three-dimensional simulation space, and establish the starting point coordinates and target point coordinates of the flying car;

[0007] S2, an improved ant colony algorithm, includes setting a multi-factor heuristic function, an adaptive volatility coefficient, a dynamic weight coefficient, and a multi-factor pheromone update mechanism;

[0008] S3, set the safety distance function of the artificial potential field method and the trajectory evaluation function of the dynamic window method;

[0009] S4. The adjusted ant colony algorithm performs global path planning based on the surrounding environment information and the starting and target coordinates of the flying car. The local path is evaluated and judged by the safe distance function and the trajectory evaluation function to obtain the optimal path of the flying car.

[0010] Preferably, the specific process of S1 is as follows: acquire the three-dimensional point cloud of the lidar and the visual information of the camera; process and fuse them with MATLAB to create a three-dimensional space; when the flying car reaches a certain flight altitude, determine the size of the grid map for the flight phase, as well as the starting coordinates and target coordinates of the flying car.

[0011] Preferably, in S2, in the ant colony algorithm, a corrected distance function from the next node to the endpoint and a turning point smoothing factor are added to the heuristic function, and a multi-factor heuristic function is set; an adaptive evaporation coefficient that changes with the number of iterations is set; pheromone weight coefficient and heuristic function weight coefficient are set in the dynamic weight coefficient; and a multi-factor pheromone update mechanism is set.

[0012] Preferably, in S3, the location of the flying car in the safety distance function is set as the origin, and the radius R of the obstacle, the safety distance L between the flying car and the obstacle, the radius M of the obstacle's effective range, and the perpendicular distance S between the obstacle and the line connecting the flying car to the target point are obtained; when R < S < L, the flying car is subjected to the repulsive force of the obstacle, and when L < S < M, the flying car is not affected by the repulsive force of the obstacle.

[0013] Preferably, in S3, the trajectory evaluation function sets an initial average speed and calculates the trajectory evaluation function. Each generated predicted trajectory is quantitatively evaluated by the trajectory evaluation function to determine the optimal trajectory. The trajectory evaluation function used in the dynamic window method is then updated as the evaluation standard for the next path planning.

[0014] Preferably, the specific process of S4 is as follows: S41, set the number of ants and place the ants at the starting point. Move to the next node by selecting the probability. The subsequent path is planned in the same way, such as using the selection probability to make the ants move from the current node to the next node at any time. When the ants complete the path, update the pheromone of each path they have passed until they reach the target point.

[0015] S42, by judging the positional relationship between the current node and the interval nodes and obstacles, it is inferred whether the adjacent nodes can be discarded. If the positional relationship is horizontal, vertical or the distance between the connecting line and the obstacle is less than the range of the obstacle, the adjacent node is discarded. If the node cannot be discarded, the next node is selected as the current key node, the current key node is set as the local target point, and the key node is recorded and continuously iterated and updated.

[0016] S43 generates multiple candidate trajectories near the local target point; each trajectory can be generated by the vehicle's motion model, and the optimal speed control is selected as the output by using the safety distance of the artificial potential field method and the trajectory evaluation function of the dynamic window method.

[0017] S44: Use sensors to monitor the surrounding environment in real time, update environmental information, check whether the current local target point is blocked by new obstacles. If the local target point is unreachable, select the node closest to the vehicle's current position and set the nearest node as the new starting point, then return to S41 to replan the global path.

[0018] S45: Detect whether the current position of the flying car has reached the local target point. If the distance between the current position of the flying car and the local target point is less than the set distance, it is considered that the local target point has been reached. At this time, the next node is selected as the new local target point, and S43 is executed again. If the local target point has not been reached, return to S42 to continue the iteration.

[0019] S46, detect whether the vehicle has reached the global target point. If the distance between the vehicle and the global target point is less than the set distance, it is considered to have reached the global target point; if the vehicle has not reached the global target point, return to S45 until it reaches the global target point.

[0020] Preferably, after obtaining the optimal path for the flying car, B-spline curves are used to smooth the planned path and eliminate more tortuous paths at nodes.

[0021] A multi-sensor fusion path planning method for flying cars includes:

[0022] The coordinate establishment module is used to acquire information about the surrounding environment of the flying car, construct a three-dimensional simulation space, and establish the starting coordinates and target coordinates of the flying car.

[0023] The ant colony algorithm improvement module is used to improve the ant colony algorithm, including setting a multi-factor heuristic function, adaptive volatility coefficient, dynamic weight coefficient and multi-factor pheromone update mechanism;

[0024] The function creation module is used to set the safety distance function for the artificial potential field method and the trajectory evaluation function for the dynamic window method;

[0025] The path planning module is used by the adjusted ant colony algorithm to perform global path planning based on the surrounding environment information and the starting point and target point coordinates of the flying car. The local path is evaluated and judged by the safe distance function and the trajectory evaluation function to obtain the optimal path of the flying car.

[0026] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the flying car multi-sensor fusion path planning method.

[0027] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the multi-sensor fusion path planning method for a flying car.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] This invention effectively overcomes the limitations of a single algorithm by integrating the global search capability of the ant colony algorithm, the local obstacle avoidance advantage of the artificial potential field method, and the real-time trajectory optimization characteristics of the dynamic window method. The collaborative approach of multiple algorithms significantly improves the efficiency and accuracy of path planning, ensuring that the flying car can complete path planning tasks safely, quickly, and efficiently. Attached Figure Description

[0030] Figure 1 This is a schematic diagram of the overall frame of the flying car of the present invention;

[0031] Figure 2 These are three views of the flying car structure of the present invention;

[0032] Figure 3 This is a flowchart of the path planning system of the present invention;

[0033] Figure 4 This is a schematic diagram of the safe distance model for the artificial potential field method of the present invention;

[0034] Figure 5 This is a schematic diagram of the multi-fusion algorithm flow of the present invention;

[0035] Figure 6 This is a schematic diagram illustrating the integration of the multi-fusion algorithm and sensor in this invention;

[0036] Figure 7 This is the global path planning graph for the multi-fusion algorithm of this invention;

[0037] Figure 8 This is a dynamic obstacle path planning diagram for the multi-fusion algorithm of this invention.

[0038] The components include: 1. Fixed device; 2. LiDAR; 3. Camera; 4. GPS; 5. Temperature and humidity sensor; 6. Data processor; 7. Thrust device; 8. Height control mechanism. Detailed Implementation

[0039] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0040] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terms “installation,” “connection,” and “linkage” should be interpreted broadly, for example, as a fixed connection, a detachable connection, or an integral connection; a mechanical connection, an electrical connection, or a connection that allows communication; a direct connection or an indirect connection via an intermediate medium; or a connection within two elements or an interaction between two elements. The term “and / or” as used herein includes any and all combinations of one or more of the associated listed items. Those skilled in the art will understand the specific meaning of the above terms in this invention according to the specific circumstances. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention.

[0042] The following disclosure provides many different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the invention. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, examples of various specific processes and materials are provided in this invention, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0043] like Figure 1The diagram shows the overall frame of the flying car described in this invention. The flying car is equipped with a fixed device 1, a lidar 2, a camera 3, a GPS 4, a temperature and humidity sensor 5, a data processor 6, a thrust device 7, and an altitude control mechanism 8, among other devices. These sensors acquire spatial information about the flight environment and the distribution of obstacles, and transmit the data in a timely manner. A detailed layout is shown below. Figure 2 As shown.

[0044] A lidar sensor 2 is installed on the bottom of the flying car to identify obstacles, buildings, etc., and to provide high-precision map data. Cameras 3 are installed around the flying car to acquire information about the surrounding environment. A GPS 4 is installed in the flying car's fixed device 1 to provide real-time location information and determine the current position of the flying car or dynamic obstacles.

[0045] Temperature and humidity sensor 5 is installed at the rear of the flying car to measure environmental temperature and humidity data and predict weather changes. Data processor 6 is installed in the center of the flying car to process and manage the data collected by the sensors, performing calculations, storage, and analysis for subsequent applications and decision-making.

[0046] The thrust device 7 is installed at the rear of the flying car to provide the necessary thrust and control its speed and direction. The altitude control mechanism 8 is installed at the center of the flying car's wing to control its altitude, ensuring stable flight and obstacle avoidance.

[0047] like Figure 3 and Figure 6 As shown, the multi-sensor fusion path planning method for flying cars according to the present invention includes the following process:

[0048] Step 1: Initial system parameter setting and initial configuration: Using the environmental information around the flying car obtained by the sensors, a three-dimensional simulation space is constructed using MATLAB to establish the starting point coordinates and target point coordinates of the flying car.

[0049] Step 1: Generate a high-precision 3D point cloud using LiDAR and visual information provided by a camera. Then, process and fuse the sensor data using MATLAB to create a detailed 3D space with a size of [size missing]. .

[0050] Step 2: Once the flying car reaches a certain altitude, the size of the grid map during the flight phase is determined using a GPS coordinate system. and the starting coordinates of the flying car and target point coordinates .

[0051] Step 2: Adjust the basic parameter settings of the ant colony algorithm: Based on the detected environmental information, set parameters such as multi-factor heuristic function, adaptive volatility coefficient, dynamic weight coefficient and multi-factor pheromone update mechanism to update the path in real time and ensure flight efficiency.

[0052] Step 1: Multi-factor Heuristic Function: In the early stages of iteration, larger values ​​for the distance correction function and the turning point smoothing factor function reduce the required number of iterations and path turns. In later stages, the values ​​of these two functions are appropriately reduced to avoid the algorithm getting trapped in local optima. Therefore, a corrected distance function from the next node to the endpoint is added to the heuristic function. and inflection point smoothing factor Set up a multi-factor heuristic function .

[0053] Step 2, Adaptive Volatilization Coefficient: In the early stages of iteration, the adaptive volatile coefficient is relatively large, which improves the ants' pathfinding ability and increases the probability of finding the optimal path. In the later stages of iteration, the adaptive volatile coefficient decreases, reducing pheromone evaporation and improving the convergence speed of the optimal path. Therefore, an adaptive volatile coefficient that varies with the number of iterations is set. .

[0054] Step 3, Dynamic Weight Coefficients: The pheromone weight coefficient and heuristic function weight coefficient change with the number of iterations. In the early stages of the algorithm's iteration, these coefficients are initially set to their minimum values ​​to improve global search capability and increase the probability of finding the global optimum. When the set iteration threshold is reached, the pheromone weight coefficient and heuristic function weight coefficient gradually increase to improve the algorithm's convergence ability. Therefore, setting the pheromone weight coefficient... and heuristic function weight coefficients .

[0055] Step 4, Multi-factor pheromone update mechanism: The path length and number of turns are considered during the pheromone update process to improve the quality of the planned path. Therefore, a multi-factor pheromone update mechanism is implemented. .

[0056] Step 3: Design evaluation functions: Design evaluation functions for the safety distance of the artificial potential field method and the trajectory of the dynamic window method, and determine the score of each path by weighted combination of these factors in order to select the optimal and safest path.

[0057] Step 1: Establish the safety distance function for the artificial potential field method: (e.g.) Figure 4As shown, the location of the flying car (O) is set as the origin; R is the radius of the circular obstacle; L is the safe distance from the obstacle; M is the radius of the obstacle's effective range; and S is the perpendicular distance between the obstacle and the line connecting the flying car to the target point (black pentagram). When R < S < L, the flying car experiences a repulsive force from the obstacle; when L < S < M, the flying car is not affected by the obstacle's repulsive force. Therefore, the flying car can avoid excessive obstacle avoidance, which could lead to an overly long planned path.

[0058] Step 2, Trajectory Evaluation Function: Set the initial average velocity And calculate the trajectory evaluation function. Each generated predicted trajectory needs to undergo quantitative evaluation using a trajectory evaluation function to determine the optimal trajectory. The flying car will then select the optimal trajectory based on its chosen path. The vehicle is driven as a speed control command, and the trajectory evaluation function used in the dynamic window method is updated. This will serve as the evaluation criterion for the next path planning.

[0059] Step 4, as follows Figure 5 As shown, multiple algorithms are integrated for path planning of flying cars: the global path planning of the improved ant colony algorithm is combined with the local obstacle avoidance of the dynamic window method to plan the optimal path of the flying car and perform smoothing processing.

[0060] Step 1: Set the number of ants to m, and place the ants at the starting point. By choosing probability Move to the next node Subsequent paths are planned in the same way, such as by using selection probability. Make the ant start from the current node at time t. Move to the next node After the ant completes its path, it updates the pheromones of each path it traversed. until the target point is reached. .

[0061] Step 2: Determine the current node With interval nodes Based on the positional relationships of obstacles, infer whether neighboring nodes can be discarded. If the positional relationship is horizontal, vertical, or the distance between the connecting line and the obstacle is less than the obstacle's effective range, then the adjacent nodes are discarded. If a node cannot be discarded, select the next node as the current critical node. The current key nodes Set as local target point It records key nodes and continuously iterates and updates them.

[0062] Step 3, at the local target point M candidate trajectories are generated from the vicinity. Each trajectory can be generated using the vehicle's motion model. The optimal speed is selected using a trajectory evaluation function based on the safety distance of the artificial potential field method and the dynamic window method. Control is the output.

[0063] Step 4: Use sensors to monitor the surrounding environment in real time, update environmental information, and check the current local target points. Is it obstructed by new obstacles? If the target point is unreachable, then the node closest to the vehicle's current location is selected. and will Set this as the new starting point and return to step 1 to replan the global path.

[0064] Step 5: Check if the flying car's current position has reached the local target point. If the distance between the flying car's current position and the local target point is less than 5m, it is considered to have reached the local target point. At this time, select the next node as the new local target point and repeat step 3. If the local target point has not been reached, return to step 2 and continue iterating.

[0065] Step 6: Check if the vehicle has reached the global target point. If the distance between the vehicle and the global target point is less than 2m, it is considered to have reached the global target point. If the vehicle has not reached the global target point, return to step 5 until it reaches the global target point.

[0066] Step 7: Use B-spline curves to smooth the planned path and eliminate more tortuous paths at nodes, making the path more continuous and smooth.

[0067] Step 5: Execute the planned path of the flying car: Generate flight control commands based on the planned path, and guide the operation of the flying car in real time through sensor feedback, including takeoff, flight process, and landing, to ensure that the flying car can safely take off, fly and land according to the planned path.

[0068] Step 1: During the takeoff execution phase, the system performs self-checks and environmental monitoring to ensure all systems are functioning properly and the takeoff area is free of obstructions. After confirming safety, the system generates detailed takeoff commands using a PID controller based on the planned path, gradually increasing altitude and maintaining a stable flight state by controlling thrust and attitude to ensure a smooth takeoff and entry into cruise altitude.

[0069] Step 2: The system uses a PID controller to generate detailed flight control commands based on the optimal path, covering parameters such as position and speed at each node to ensure smooth operation of the flying car throughout the flight. A data processor receives and analyzes the control command parameters, converting them into recognizable signals that are accurately transmitted to the flying car's control system. Finally, the commands processed by the data processor are passed to the control system, guiding the flying car to adjust its attitude and speed, thereby precisely executing flight operations and safely reaching its destination along the planned path.

[0070] Step 3: During the descent phase, the system performs a self-check and environmental monitoring, using a PID controller to generate detailed descent commands, gradually decreasing altitude and controlling speed to smoothly approach the ground. Upon approaching the ground, a final speed adjustment is made to ensure a safe landing and complete stop.

[0071] Step Six: Real-time Path Monitoring and Adjustment: Monitor the surrounding environment in real time using sensor data, identify and predict the position and movement of obstacles, and automatically adjust the flight trajectory.

[0072] Step 1: When a dynamic obstacle is detected, the system combines data from lidar and cameras to identify the obstacle and predict its trajectory. If the obstacle is less than a set safe distance from the flying car, the system will issue an alarm in a timely manner and automatically adjust the flight trajectory to ensure flight safety.

[0073] Step 2: In case of special weather conditions, the temperature and humidity sensors will monitor the ambient temperature and humidity in real time, while the aerodynamic sensors will measure the ambient wind speed, air pressure, and air density in real time. If high humidity is detected, the system will automatically adjust its flight path to cope with the changing weather conditions.

[0074] The above method will be explained in detail below with specific examples:

[0075] Design and construct the structural framework of the flying car: such as Figure 1 As shown, the flying car is equipped with a fixed device 1, a lidar 2, a camera 3, a GPS 4, a temperature and humidity sensor 5, a data processor 6, a thrust device 7, and an altitude control mechanism 8. These devices are used to acquire spatial information about the flight environment and the distribution of obstacles, and to transmit the data in a timely manner. The layout is as follows: Figure 2 As shown.

[0076] A lidar sensor 2 is installed on the bottom of the flying car to identify obstacles, buildings, etc., and to provide high-precision map data. Cameras 3 are installed around the flying car to acquire information about the surrounding environment. A GPS 4 is installed in the flying car's fixed device 1 to provide real-time location information and determine the current position of the flying car or dynamic obstacles.

[0077] Temperature and humidity sensor 5 is installed at the rear of the flying car to measure environmental temperature and humidity data and predict weather changes. Data processor 6 is installed in the center of the flying car to process and manage the data collected by the sensors, performing calculations, storage, and analysis for subsequent applications and decision-making.

[0078] The thrust device 7 is installed at the rear of the flying car to provide the necessary thrust and control its speed and direction. The altitude control mechanism 8 is installed at the center of the flying car's wing to control its altitude, ensuring stable flight and obstacle avoidance.

[0079] Step 1: Initial system parameter setting and initial configuration: Using environmental information acquired by sensors, a three-dimensional simulation space is constructed using MATLAB to establish the starting and target positions of the flying car.

[0080] Step 1: Generate a high-precision 3D point cloud using LiDAR and visual information provided by a camera. Then, process and fuse the sensor data using MATLAB to create a detailed 3D space with a size of [size missing]. All units are in km.

[0081] Step 2: The flying car reaches a certain flight altitude, such as... Use GPS coordinate system to determine the size of the grid map during the flight phase. and the starting coordinates of the flying car and target point coordinates All units are in km.

[0082] Step 2: Adjust the basic parameter settings of the ant colony algorithm: Based on the detected environmental information, set parameters such as multi-factor heuristic function, adaptive volatility coefficient, dynamic weight coefficient and multi-factor pheromone update mechanism to update the path in real time and ensure flight efficiency.

[0083] Step 1: Multi-factor Heuristic Function: In the early stages of iteration, larger values ​​for the distance correction function and the turning point smoothing factor function reduce the required number of iterations and path turns. In later stages, the values ​​of these two functions are appropriately reduced to avoid the algorithm getting trapped in local optima. Therefore, a corrected distance function from the next node to the endpoint is added to the heuristic function. and inflection point smoothing factor Set up a multi-factor heuristic function The calculation formula is as follows:

[0084] (1)

[0085] (2)

[0086] (3)

[0087] (4)

[0088] In the formula, This represents the maximum distance from the next node adjacent to the current node to the destination. It is the minimum distance from the next node adjacent to the current node to the destination. This represents the distance from the next node to the destination. This represents the current iteration number; Since it is a positive integer, we set it to 0.01. This is an adjustment coefficient for the function expression, usually set to a positive number, such as 10. The correction factor is set to 2; The length of the set of the next possible adjacent nodes; The previous node of the current node With the current node The angle between the direction of the transition and the x-axis; Current node With the next node The angle between the direction of the transition and the x-axis; Set the path-inspired constant to 10; The importance coefficient for ants walking in a straight line is usually set to a positive constant less than 1, such as 0.5. For the current node With the next node The distance; For the current node The coordinates; For the next node The coordinates.

[0089] Step 2, Adaptive Volatilization Coefficient: In the early stages of iteration, the adaptive volatile coefficient is relatively large, which improves the ants' pathfinding ability and increases the probability of finding the optimal path. In the later stages of iteration, the adaptive volatile coefficient decreases, reducing pheromone evaporation and improving the convergence speed of the optimal path. Therefore, an adaptive volatile coefficient that varies with the number of iterations is set. The calculation formula is as follows:

[0090] (5)

[0091] In the formula, the adaptive volatility coefficient .

[0092] Step 3, Dynamic Weight Coefficients: The pheromone weight coefficient and heuristic function weight coefficient change with the number of iterations. In the early stages of the algorithm's iteration, these coefficients are initially set to their minimum values ​​to improve global search capability and increase the probability of finding the global optimum. When the set iteration threshold is reached, the pheromone weight coefficient and heuristic function weight coefficient gradually increase to improve the algorithm's convergence ability. Therefore, setting the pheromone weight coefficient... and heuristic function weight coefficients The calculation formula is as follows:

[0093] (6)

[0094] (7)

[0095] In the formula, Pheromone weighting coefficient The maximum value is set to 4; Pheromone weighting coefficient The minimum value is set to 1. Weight coefficients of the heuristic function The maximum value is set to 8; Weight coefficients of the heuristic function The minimum value is set to 3; This is the limit value for the number of iterations, usually a constant, set to 30; Let be the total number of iterations, set to 100.

[0096] Step 4, Multi-factor pheromone update mechanism: The path length and number of turns are considered during the pheromone update process to improve the quality of the planned path. Therefore, a multi-factor pheromone update mechanism is implemented. The calculation formula is as follows:

[0097] (8)

[0098] (9)

[0099] In the formula, This represents the distance along the ant's path. This represents the number of turns made on the ant's path. This is a comprehensive indicator of ant path.

[0100] Step 3: Design evaluation functions: Design evaluation functions for the safety distance of the artificial potential field method and the trajectory of the dynamic window method, and determine the score of each path by weighted combination of these factors in order to select the optimal and safest path.

[0101] Step 1: Design the safety distance function for the artificial potential field method: (e.g.) Figure 3As shown, O represents the location of the flying car, set as the origin; R is the radius of the circular obstacle; L is the safety distance, set at 5m; M is the radius of the obstacle's effective range; and S is the perpendicular distance between the obstacle and the line connecting the flying car to the target point (black pentagram). When R < S < L, the flying car experiences a repulsive force from the obstacle; when L < S < M, the flying car is not affected by the obstacle's repulsive force. Therefore, the flying car can avoid excessive obstacle avoidance, which could lead to an overly long planned path.

[0102] Step 2, Trajectory Evaluation Function: Set the initial average velocity And calculate the trajectory evaluation function. Each generated predicted trajectory needs to undergo quantitative evaluation using a trajectory evaluation function to determine the optimal trajectory. The flying car will then select the optimal trajectory based on its chosen path. The vehicle is driven as a speed control command, and the trajectory evaluation function used in the dynamic window method is updated. As the evaluation criterion for the next path planning, the calculation formula is as follows:

[0103] (10)

[0104] (11)

[0105] In the formula, The distance between the vehicle at the end of the trajectory and the target point; The coordinates of the target point; The coordinates of the end point of the vehicle trajectory; This is a sub-function for evaluating the vehicle target distance.

[0106] Step 4: Multi-algorithm fusion for flying car path planning: The improved ant colony algorithm for global path planning is combined with the dynamic window method for local obstacle avoidance to plan the optimal path for the flying car and perform smoothing processing.

[0107] Step 1: Set the number of ants to m=50 and place the ants at the starting point. By choosing probability Move to the next node Subsequent paths are planned in the same way, such as by using selection probability. Make the ant start from the current node at time t. Move to the next node After the ant completes its path, it updates the pheromones of each path it traversed. until the target point is reached. ,like Figure 7 As shown, the selection probability The calculation formula is as follows:

[0108] (12)

[0109] (13)

[0110] in, This is the set of the next feasible nodes; This is a distance heuristic function.

[0111] Step 2: Determine the current node With interval nodes Based on the positional relationships of obstacles, infer whether neighboring nodes can be discarded. If the positional relationship is horizontal, vertical, or the distance between the connecting line and the obstacle is less than the obstacle's effective range, then the adjacent nodes are discarded. If a node cannot be discarded, select the next node as the current critical node. The current key nodes Set as local target point It records key nodes and continuously iterates and updates them.

[0112] Step 3, at the local target point M candidate trajectories are generated from the vicinity. Each trajectory can be generated using the vehicle's motion model. The optimal speed is selected using a trajectory evaluation function based on the safety distance of the artificial potential field method and the dynamic window method. Control is the output.

[0113] Step 4: Use sensors to monitor the surrounding environment in real time, update environmental information, and check the current local target points. Is it obstructed by new obstacles? If the target point is unreachable, then the node closest to the vehicle's current location is selected. and will Set this as the new starting point and return to step 1 to replan the global path.

[0114] Step 5: Check if the flying car's current position has reached the local target point. If the distance between the flying car's current position and the local target point is less than 5m, it is considered to have reached the local target point. At this time, select the next node as the new local target point and repeat step 3. If the local target point has not been reached, return to step 2 and continue iterating.

[0115] Step 6: Check if the vehicle has reached the global target point. If the distance between the vehicle and the global target point is less than 2m, it is considered to have reached the global target point. If the vehicle has not reached the global target point, return to step 5 until it reaches the global target point.

[0116] Step 7: Use B-spline curves to smooth the planned path and eliminate more winding paths at nodes, making the path more continuous and smooth, such as... Figure 8 As shown.

[0117] Step 5: Execute the planned path of the flying car: Generate flight control commands based on the planned path, and guide the operation of the flying car in real time through sensor feedback, including takeoff, flight process, and landing, to ensure that the flying car can safely take off, fly and land according to the planned path.

[0118] Step 1: During the takeoff execution phase, the system performs self-checks and environmental monitoring to ensure all systems are functioning properly and the takeoff area is free of obstructions. After confirming safety, the system generates detailed takeoff commands using a PID controller based on the planned path, gradually increasing altitude and maintaining a stable flight state by controlling thrust and attitude to ensure a smooth takeoff and entry into cruise altitude.

[0119] Step 2: The system uses a PID controller to generate detailed flight control commands based on the optimal path, covering parameters such as position and speed at each node to ensure smooth operation of the flying car throughout the flight. A data processor receives and analyzes the control command parameters, converting them into recognizable signals that are accurately transmitted to the flying car's control system. Finally, the commands processed by the data processor are passed to the control system, guiding the flying car to adjust its attitude and speed, thereby precisely executing flight operations and safely reaching its destination along the planned path.

[0120] Step 3: During the descent phase, the system performs a self-check and environmental monitoring, using a PID controller to generate detailed descent commands, gradually decreasing altitude and controlling speed to smoothly approach the ground. Upon approaching the ground, a final speed adjustment is made to ensure a safe landing and complete stop.

[0121] Step Six: Real-time Path Monitoring and Adjustment: Monitor the surrounding environment in real time using sensor data, identify and predict the position and movement of obstacles, and automatically adjust the flight trajectory.

[0122] Step 1: When a dynamic obstacle is detected, the system combines data from lidar and cameras to identify the obstacle and predict its trajectory. If the obstacle is less than a set safe distance from the flying car, the system will issue an alarm in a timely manner and automatically adjust the flight trajectory to ensure flight safety.

[0123] Step 2: In case of special weather conditions, the temperature and humidity sensors will monitor the ambient temperature and humidity in real time, while the aerodynamic sensors will measure the ambient wind speed, air pressure, and air density in real time. If high humidity is detected, the system will automatically adjust its flight path to cope with the changing weather conditions.

[0124] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not omitted in the apparatus embodiments, please refer to the embodiments of the method of the present invention.

[0125] In another embodiment of the present invention, a multi-sensor fusion path planning system for flying cars is provided. This multi-sensor fusion path planning system for flying cars can be used to implement the above-mentioned multi-sensor fusion path planning method for flying cars. Specifically, the multi-sensor fusion path planning system for flying cars includes a coordinate establishment module, an ant colony algorithm improvement module, a function establishment module, and a path planning module.

[0126] The coordinate establishment module is used to acquire information about the surrounding environment of the flying car, construct a three-dimensional simulation space, and establish the starting coordinates and target coordinates of the flying car.

[0127] The ant colony algorithm improvement module is used to improve the ant colony algorithm, including setting a multi-factor heuristic function, adaptive volatility coefficient, dynamic weight coefficient and multi-factor pheromone update mechanism.

[0128] The function creation module is used to set the safety distance function for the artificial potential field method and the trajectory evaluation function for the dynamic window method.

[0129] The path planning module is used by the adjusted ant colony algorithm to perform global path planning based on the surrounding environment information and the starting point and target point coordinates of the flying car. The local path is evaluated and judged by the safe distance function and the trajectory evaluation function to obtain the optimal path of the flying car.

[0130] In another embodiment of the present invention, a terminal device is provided, comprising a processor and a memory. The memory stores a computer program, the computer program including program instructions, and the processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), or field-programmable gate arrays (FPGAs). Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., are the computing and control core of the terminal. They are suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to realize the corresponding method flow or corresponding function. The processor described in this embodiment of the invention can be used for the operation of the multi-sensor fusion path planning method for flying cars, including: S1, acquiring the surrounding environment information of the flying car, constructing a three-dimensional simulation space, and establishing the starting point coordinates and target point coordinates of the flying car; S2, improving the ant colony algorithm, including setting a multi-factor heuristic function, adaptive evaporation coefficient, dynamic weight coefficient, and multi-factor pheromone update mechanism; S3, setting a safe distance function of the artificial potential field method and a trajectory evaluation function of the dynamic window method; S4, the adjusted ant colony algorithm performs global path planning based on the surrounding environment information and the starting point coordinates and target point coordinates of the flying car, wherein the local path is evaluated and judged by the safe distance function and the trajectory evaluation function to obtain the optimal path of the flying car.

[0131] In another embodiment, the present invention also provides a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understood that the computer-readable storage medium here may include both the built-in storage medium in the terminal device and extended storage media supported by the terminal device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor, which may be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here may be high-speed RAM or non-volatile memory, such as at least one disk storage device.

[0132] One or more instructions stored in a computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the multi-sensor fusion path planning method for flying cars in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor in the following steps: S1, acquire the surrounding environment information of the flying car, construct a three-dimensional simulation space, and establish the starting point coordinates and target point coordinates of the flying car; S2, improve the ant colony algorithm, including setting a multi-factor heuristic function, an adaptive evaporation coefficient, a dynamic weight coefficient, and a multi-factor pheromone update mechanism; S3, set the safety distance function of the artificial potential field method and the trajectory evaluation function of the dynamic window method; S4, the adjusted ant colony algorithm performs global path planning based on the surrounding environment information and the starting point coordinates and target point coordinates of the flying car, wherein the local path is evaluated and judged by the safety distance function and the trajectory evaluation function to obtain the optimal path of the flying car.

[0133] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0135] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0136] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0137] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0138] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0139] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0140] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

[0142] It should be understood that the above description is for illustrative purposes and not for limitation. Many embodiments and applications beyond the provided examples will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this patent should not be determined by reference to the above description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be construed as an indication that the applicant has not considered that subject matter as part of the disclosed inventive subject matter.

Claims

1. A flying car multi-sensor fusion path planning method, characterized in that, The process comprises the following steps: S1, obtaining the surrounding environment information of the flying car, constructing a three-dimensional simulation space, and establishing the starting point coordinates and target point coordinates of the flying car; S2, improving the ant colony algorithm, including setting a multi-factor heuristic function, an adaptive evaporation coefficient, a dynamic weight coefficient, and a multi-factor pheromone update mechanism; S3, setting a safety distance function of the artificial potential field method and a trajectory evaluation function of the dynamic window method; In the safety distance function, the position of the flying car is set as the origin, the obstacle radius R, the safety distance L from the obstacle, the obstacle action range radius M, and the vertical distance S from the obstacle to the target point are obtained; when R < S < L, the flying car is subjected to the repulsive force of the obstacle; when L < S < M, the flying car is not affected by the repulsive force of the obstacle; S4, the adjusted ant colony algorithm is used for global path planning based on the surrounding environment information and the starting point coordinates and target point coordinates of the flying car, and the optimal path of the flying car is obtained through the evaluation and judgment of the safety distance function and the trajectory evaluation function. 2.The method according to claim 1, wherein, The specific process of S1 is as follows: obtaining the three-dimensional point cloud of the laser radar and the visual information of the camera; combining MATLAB for processing and fusion to create a three-dimensional space; the flying car reaches a certain flight height, the size of the grid map in the flight stage is determined, and the starting point coordinates and target point coordinates of the flying car are determined. 3.The method according to claim 1, wherein, In S2, in the ant colony algorithm, the modified distance function of the next node to the end point and the turning point smoothing factor are added to the heuristic function, and a multi-factor heuristic function is set; the adaptive evaporation coefficient is set to change with the number of iterations; the pheromone weight coefficient and the heuristic function weight coefficient are set in the dynamic weight coefficient; and a multi-factor pheromone update mechanism is set.

4. The method of claim 1, wherein, In S3, in the trajectory evaluation function, the initial average speed is set, and the trajectory evaluation function is calculated to quantitatively evaluate each generated predicted trajectory to determine the best trajectory, and the trajectory evaluation function used by the dynamic window method is updated as the evaluation standard for the next path planning. 5.The method of claim 1, wherein, The specific process of S4 is as follows: S41, the number of ants is set, and the ants are placed at the starting point and moved to the next node by selecting probability, and the subsequent path is planned in the same way, such as using selection probability to make the ants move from the current node to the next node at a certain time, and the pheromone of each path passed is updated after the ants complete the path until the target point is reached; S42, the position relationship between the current node and the interval node and the obstacle is judged to infer whether the adjacent node can be discarded, if the position relationship is horizontal, vertical, or the distance between the connecting line and the obstacle is less than the action range of the obstacle, the adjacent node is discarded, if the node cannot be discarded, the next node is selected as the current key node, the current key node is set as the local target point, and the key node is recorded and iteratively updated; S43, a plurality of candidate trajectories are generated near the local target point; each trajectory can be generated through the motion model of the vehicle, and the optimal speed control is selected as the output through the safety distance of the artificial potential field method and the trajectory evaluation function of the dynamic window method; S44, real-time monitoring of the surrounding environment using sensors, updating the environment information, checking whether the current local target point is blocked by new obstacles, if the local target point is inaccessible, selecting the node closest to the current position of the vehicle and setting the closest node as a new starting point, returning to S41 to re-plan the global path; S45, detecting whether the current position of the flying car reaches the local target point, if the distance between the current position of the flying car and the local target point is less than the set distance, it is considered to reach the local target point, at this time the next node is selected as a new local target point, and S43 is re-executed; if the local target point is not reached, return to S42 for iteration; S46, detecting whether the vehicle reaches the global target point, if the distance between the vehicle and the global target point is less than the set distance, it is considered to reach the global target point; If the global target point is not reached, return to S45 until the global target point is reached. 6.The method of claim 1, wherein, After obtaining the optimal path of the flying car, the planned path is smoothed and the zigzag path at the node is eliminated using B-spline curve.

7. An air car multi-sensor fusion path planning system, characterized in that, It comprises: A coordinate establishing module for obtaining the surrounding environment information of the flying car, constructing a three-dimensional simulation space, and establishing the starting point coordinates and target point coordinates of the flying car; An improved ant colony algorithm module for improving the ant colony algorithm, including setting a multi-factor heuristic function, an adaptive evaporation coefficient, a dynamic weight coefficient, and a multi-factor pheromone update mechanism; A function establishing module for setting a safety distance function of the artificial potential field method and a trajectory evaluation function of the dynamic window method; In the safety distance function, the position of the flying car is set as the origin, the obstacle radius R, the safety distance L from the obstacle, the obstacle action range radius M, and the perpendicular distance S from the obstacle to the connecting line of the flying car to the target point are obtained; when R < S < L, the flying car is affected by the repulsive force of the obstacle, and when L < S < M, the flying car is not affected by the repulsive force of the obstacle; A path planning module for global path planning based on the surrounding environment information and the starting point coordinates and target point coordinates of the flying car using the adjusted ant colony algorithm, wherein the local path is evaluated and judged by the safety distance function and the trajectory evaluation function to obtain the optimal path of the flying car.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the flying car multi-sensor fusion path planning method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to realize the steps of the flying car multi-sensor fusion path planning method according to any one of claims 1 to 6.

Images