Unmanned vehicle path planning method, device and equipment and storage medium

Abstract

The invention discloses an unmanned vehicle path planning method. The method comprises the following steps: S1, initializing a current position and a target position of an unmanned vehicle; s2, performing path optimization through multiple iterations based on a Runge-Kutta optimization algorithm, and during each iteration, obtaining an optimal path from the current position to the target position according to the calculated gradient direction and the control input adjustment path; and S3, sensing the environment in real time and detecting obstacles through a multi-sensor data fusion technology, dynamically adjusting the path to avoid the obstacles according to real-time sensor data when the unmanned vehicle detects the obstacles, returning to the step S2 to update the path plan, and obtaining the updated optimal path. The invention further discloses an unmanned vehicle path planning device, corresponding equipment and a storage medium. According to the unmanned vehicle path planning method provided by the invention, the path planning efficiency and the obstacle avoidance capability of the unmanned vehicle in a complex urban environment can be improved.

Description

Technical Field

[0001] The present application relates to the field of new generation information technology, and more specifically, to a method, device, equipment and storage medium for unmanned vehicle path planning. Background Art

[0002] With the rapid development of driverless technology, intelligent transportation systems have become an important part of modern urban traffic management. As a key element, driverless cars can effectively improve urban traffic efficiency and reduce traffic accidents and congestion with their features such as automatic driving, path planning, and obstacle avoidance. However, although the current driverless technology has made significant progress in some environments, it still faces many technical challenges in complex urban road environments.

[0003] In urban environments, especially in densely populated areas, unmanned vehicles need to deal with not only complex road conditions, but also dynamic changes of various obstacles, such as pedestrians, other vehicles, buildings, etc. This places higher demands on the road path planning and obstacle avoidance technology of unmanned vehicles. Most of the existing path planning algorithms rely on traditional rule-based models or simple heuristic search methods, which often cannot handle complex, uncertain and dynamically changing urban environments well. Many algorithms are prone to fall into local optimal solutions and cannot achieve global optimal path planning, or lack flexibility when dealing with dynamic obstacles or emergencies, resulting in weak obstacle avoidance capabilities. At the same time, the existing path planning methods have high computational overhead and low efficiency when dealing with complex environments. These problems limit the path planning capabilities of unmanned vehicles in complex urban environments, and optimizing the obstacle avoidance process has become the main technical challenge facing current unmanned driving technology. Therefore, developing new path planning and obstacle avoidance technologies to improve the safety and efficiency of unmanned vehicles in urban environments is the key to the development of unmanned driving technology. Summary of the invention

[0004] In response to at least one defect or improvement need in the prior art, the present invention provides a method, device, equipment and storage medium for unmanned vehicle path planning, which can solve at least one of the technical problems existing in the above-mentioned background technology.

[0005] To achieve the above object, according to a first aspect of the present invention, a method for unmanned vehicle path planning is provided, the method comprising: S1 initializes the current position and target position of the unmanned vehicle; S2 performs path optimization through multiple iterations based on the Runge-Kutta optimization algorithm. In each iteration, the path is adjusted according to the calculated gradient direction and control input to obtain the optimal path from the current position to the target position. S3 uses multi-sensor data fusion technology to perceive the environment and detect obstacles in real time. When the unmanned vehicle detects an obstacle, it dynamically adjusts the path to avoid the obstacle based on the real-time sensor data, returns to step S2 to update the path planning, and obtains the updated optimal path.

[0006] Furthermore, in the above-mentioned unmanned vehicle path planning method, the initializing the current position and target position of the unmanned vehicle specifically includes: Set the initial position of the unmanned vehicle to , the target location is , the path optimization process is

[0007] in, is the current position vector, is the control input, is the time step, is the state equation of the unmanned vehicle, which represents the relationship between the current position and the control input.

[0008] Furthermore, in the above-mentioned unmanned vehicle path planning method, the path optimization is performed through multiple iterations based on the Runge-Kutta optimization algorithm, specifically including:

[0009]

[0010]

[0011]

[0012] in, is the initial state equation of the unmanned vehicle The first derivative of , and are their second-order, third-order and fourth-order derivatives respectively, and the path optimization is performed through an iterative method to obtain the optimal path from the current position to the target position.

[0013] Furthermore, the above-mentioned unmanned vehicle path planning method, when the unmanned vehicle detects an obstacle, dynamically adjusts the path to avoid the obstacle according to real-time sensor data, specifically includes: When the autonomous vehicle detects an obstacle, it automatically adjusts the control input and path Avoid obstacles and update path planning

[0014] in, To avoid obstacles, a new path is generated. is the adjustment term caused by the obstacle, which can be obtained by the following formula

[0015] in, is the gradient effect of the current obstacle position on the path, It is the adjustment coefficient, indicating the strength of avoiding obstacles.

[0016] Furthermore, the above-mentioned unmanned vehicle path planning method further includes: After the first time step, the cost of the current path is re-evaluated and the path continues to be optimized based on the new environmental data.

[0017] Furthermore, in the above-mentioned unmanned vehicle path planning method, the re-evaluation of the cost of the current path specifically includes:

[0018] in, is the total length of the path, For the The location of the obstacle, For current location With obstacles The distance is the weight coefficient for obstacle avoidance.

[0019] Furthermore, the above-mentioned unmanned vehicle path planning method further includes: By integrating data from lidar, cameras, and ultrasonic sensors, the Kalman filter algorithm is used to update and fuse multi-sensor data in real time to obtain environmental perception information, and real-time adjustments to the path are made based on real-time sensor data and a dynamic feedback mechanism.

[0020] According to a second aspect of the present invention, there is also provided an unmanned vehicle path planning device, comprising: Initialization module, used to initialize the current position and target position of the unmanned vehicle; The path optimization module is used to perform path optimization through multiple iterations based on the Runge-Kutta optimization algorithm. In each iteration, the path is adjusted according to the calculated gradient direction and control input to obtain the optimal path from the current position to the target position; The obstacle avoidance module is used to perceive the environment and detect obstacles in real time through multi-sensor data fusion technology. When the unmanned vehicle detects an obstacle, it dynamically adjusts the path according to the real-time sensor data to avoid the obstacle, returns to the path planning, and obtains the updated optimal path.

[0021] According to the third aspect of the present invention, there is also provided an unmanned vehicle path planning device, which includes at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit executes the steps of any one of the above methods.

[0022] According to the fourth aspect of the present invention, a storage medium is also provided, which stores a computer program that can be executed by an unmanned vehicle path planning device. When the computer program runs on the unmanned vehicle path planning device, the unmanned vehicle path planning device executes the steps of any of the above-mentioned methods.

[0023] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art: (1) The unmanned vehicle path planning method provided by the present invention can improve the path planning efficiency and obstacle avoidance capability of the unmanned vehicle in a complex urban environment by introducing an unmanned vehicle intelligent path planning and obstacle avoidance method based on the Runge-Kutta optimization algorithm. Through real-time sensor data fusion and dynamic path adjustment mechanism, it can achieve rapid response to environmental changes, effectively avoid the local optimal solution problem in path planning, and enhance dynamic adaptability.

[0024] (2) The unmanned vehicle path planning method provided by the present invention uses multi-sensor data fusion technology to improve the accuracy of environmental perception, reduce dependence on a single sensor, and enhance the safety of path planning. Through the comprehensive decision support of the smart city environment, path selection is optimized, traffic congestion is avoided, and the overall travel efficiency of the unmanned vehicle is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 A flowchart of a method for unmanned vehicle path planning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0028] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0029] Figure 1 A flow chart of a method for unmanned vehicle path planning provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, an unmanned vehicle path planning method provided in an embodiment of the present application includes: S1 initializes the current position and target position of the unmanned vehicle; S2 performs path optimization through multiple iterations based on the Runge-Kutta optimization algorithm. In each iteration, the path is adjusted according to the calculated gradient direction and control input to obtain the optimal path from the current position to the target position. S3 uses multi-sensor data fusion technology to perceive the environment and detect obstacles in real time. When the unmanned vehicle detects an obstacle, it dynamically adjusts the path to avoid the obstacle based on the real-time sensor data, returns to step S2 to update the path planning, and obtains the updated optimal path.

[0030] Specifically, the initial state of the unmanned vehicle is initialized, including its current position on the map and the target position to be reached. This information can be obtained through the unmanned vehicle's built-in GPS system, map database, or pre-set route. Initialization is the basis of path planning, ensuring that the algorithm has a clear starting point and end point.

[0031] Path optimization is performed using the Runge-Kutta optimization algorithm, which gradually approaches the optimal path from the current position to the target position through multiple iterations. In each iteration, the algorithm adjusts the path based on the calculated gradient direction and control inputs (such as vehicle speed, steering angle, etc.). This process involves mathematical calculations, including but not limited to solving the vehicle state equation, and gradient-based path adjustment strategies. In this way, the algorithm can effectively handle dynamically changing environments and update the path planning in real time to adapt to environmental changes.

[0032] Use multi-sensor data fusion technology to perceive the environment around the unmanned vehicle in real time and detect possible obstacles. These sensors may include lidar, cameras, ultrasonic sensors, etc., each of which provides different environmental information. By fusing this data, the unmanned vehicle can obtain a more comprehensive and accurate environmental perception and improve the accuracy and reliability of obstacle detection. When an obstacle is detected, the unmanned vehicle will dynamically adjust the path based on the real-time sensor data to avoid the obstacle, and return to step S2 to update the path planning to obtain the updated optimal path.

[0033] The unmanned vehicle path planning method provided in the embodiment of the present application can improve the path planning efficiency and obstacle avoidance capability of the unmanned vehicle in complex urban environments by introducing an unmanned vehicle intelligent path planning and obstacle avoidance method based on the Runge-Kutta optimization algorithm. Through real-time sensor data fusion and dynamic path adjustment mechanism, it achieves rapid response to environmental changes, effectively avoids the problem of local optimal solution in path planning, and enhances dynamic adaptability.

[0034] Optionally, in the unmanned vehicle path planning method provided in the embodiment of the present application, the initializing the current position and the target position of the unmanned vehicle specifically includes: Set the initial position of the unmanned vehicle to , the target location is , the path optimization process is

[0035] in, is the current position vector, is the control input, is the time step, is the state equation of the unmanned vehicle, which represents the relationship between the current position and the control input.

[0036] Specifically, the initial position of the unmanned vehicle is set to and the target location is , these two positions are the basis of path planning, where It can be obtained through the unmanned vehicle's built-in GPS system, map database or pre-set route. The unmanned vehicle needs to reach a large destination location.

[0037] The path optimization process is based on the Runge-Kutta optimization algorithm, and the specific formula is:

[0038] in: is the current position vector, indicating the position of the unmanned vehicle on the map. Control inputs, including vehicle speed and steering angle, are used to guide the movement of the unmanned vehicle. is the time step, which indicates the time interval between each optimization update. is the state equation of the unmanned vehicle, which represents the relationship between the current position and the control input and is used to calculate the new position of the unmanned vehicle after the next time step.

[0039] Equation of state It is the core of path planning and describes the motion model of the unmanned vehicle under given control input. This equation can be defined based on the specific dynamic and kinematic characteristics of the unmanned vehicle, usually including factors such as the speed, acceleration, and steering dynamics of the unmanned vehicle.

[0040] Path optimization is an iterative process that takes successive time steps. Update the position of the unmanned vehicle until it reaches the target position Or other stopping conditions are met. In each iteration, a new position is calculated based on the current position and control input, gradually approaching the optimal path.

[0041] Optionally, the unmanned vehicle path planning method provided in the embodiment of the present application, wherein the path optimization is performed through multiple iterations based on the Runge-Kutta optimization algorithm, specifically comprising:

[0042]

[0043]

[0044]

[0045] in, is the initial state equation of the unmanned vehicle The first derivative of , and are their second-order, third-order and fourth-order derivatives respectively, and the path optimization is performed through an iterative method to obtain the optimal path from the current position to the target position.

[0046] Specifically, through the iterative calculation of the above four steps, the Runge-Kutta algorithm can provide high-precision prediction of the movement of the unmanned vehicle. Each iteration will update the position estimate of the unmanned vehicle, thereby gradually approaching the optimal path.

[0047] Optionally, the unmanned vehicle path planning method provided in the embodiment of the present application, when the unmanned vehicle detects an obstacle, dynamically adjusts the path to avoid the obstacle according to real-time sensor data, specifically comprising: When the autonomous vehicle detects an obstacle, it automatically adjusts the control input and path Avoid obstacles and update path planning

[0048] in, To avoid obstacles, a new path is generated. is the adjustment term caused by the obstacle, which can be obtained by the following formula

[0049] in, is the gradient effect of the current obstacle position on the path, It is the adjustment coefficient, indicating the strength of avoiding obstacles.

[0050] Specifically, when the unmanned vehicle detects an obstacle, it automatically adjusts the control input and path To avoid obstacles and update the path planning. The specific calculation steps include: Generate New Path

[0051] Calculate adjustments due to obstacles

[0052] in, is the gradient effect of the current obstacle position on the path, indicating the degree of influence of the obstacle on path planning; It is an adjustment coefficient, which indicates the intensity of obstacle avoidance, that is, the priority and strength of obstacle avoidance.

[0053] Gradient Effect This item indicates the degree of influence of obstacles on the current path of the unmanned vehicle. By calculating the path function The gradient in the direction of the obstacle is obtained. The direction of the gradient points to the direction where the path function grows fastest, so the opposite direction is the direction of obstacle avoidance.

[0054] Adjustment factor It is used to adjust the intensity of obstacle avoidance, and is dynamically adjusted according to factors such as the relative position of the unmanned vehicle and the obstacle, the speed, and the size of the obstacle. The larger the value, the greater the obstacle avoidance effort, and the autonomous vehicle will be more active in avoiding obstacles.

[0055] Calculating a new path After that, the driverless car will use the new control input It drives along the new path and continues to detect obstacles and adjust the path at the next time step, forming a closed-loop path planning and obstacle avoidance system.

[0056] Optionally, the unmanned vehicle path planning method provided in the embodiment of the present application further includes: After the first time step, the cost of the current path is re-evaluated and the path continues to be optimized based on the new environmental data.

[0057] Specifically, the environment around the unmanned vehicle may change during driving, such as changes in traffic flow, new obstacles or road construction, so after each time step, an evaluation mechanism will be triggered to recalculate the cost of the current path. This cost includes the length of the path, the expected driving time, the number of obstacles encountered, and other factors that may affect driving. After re-evaluating the cost of the current path, the system will optimize the path based on the latest environmental data.

[0058] Optionally, in the unmanned vehicle path planning method provided in the embodiment of the present application, the re-evaluating the cost of the current path specifically includes:

[0059] in, is the total length of the path, For the The location of the obstacle, For current location With obstacles The distance is the weight coefficient for obstacle avoidance.

[0060] Specifically, the unmanned vehicle path planning method provided in the embodiment of the present application includes re-evaluating the cost of the current path, and the specific formula is:

[0061] in, represents the total length of the path, that is, the sum of the distances between adjacent path points, For the The location of the obstacle, For current location With obstacles The distance, when and When the distance between them is less than a certain threshold, The function will output a larger value to indicate that avoidance is required. It is the weight coefficient of obstacle avoidance, which is used to adjust the importance of obstacle avoidance in path cost evaluation.

[0062] Path cost assessment first calculates the total length of the path, which is a basic consideration in path planning and directly affects travel time and energy consumption. Path cost assessment also includes consideration of obstacle avoidance. By calculating the distance between each point on the path and the obstacle and weighting these distances, the impact of obstacle avoidance on path cost can be quantified. Weight coefficient It is used to adjust the proportion of obstacle avoidance in the total cost, and can be dynamically adjusted according to the safety strategy and driving environment of the unmanned vehicle.

[0063] Based on the above cost assessment, the unmanned vehicle can choose a suitable path to minimize the total length of the path, while avoiding or minimizing the approach to obstacles to ensure driving safety.

[0064] Optionally, the unmanned vehicle path planning method provided in the embodiment of the present application further includes: By integrating data from lidar, cameras, and ultrasonic sensors, the Kalman filter algorithm is used to update and fuse multi-sensor data in real time to obtain environmental perception information, and real-time adjustments to the path are made based on real-time sensor data and a dynamic feedback mechanism.

[0065] Specifically, the embodiments of the present application use multiple sensors such as laser radar, camera, ultrasonic sensor, etc. to collect environmental data. These sensors each provide different information, such as laser radar provides accurate distance and shape information, camera provides visual information, and ultrasonic sensor provides close-range distance information. By integrating these data, the unmanned vehicle can obtain more comprehensive and accurate environmental perception.

[0066] The Kalman filter algorithm is used to update and fuse multi-sensor data in real time. Kalman filtering is an efficient recursive filter that can estimate the state of a dynamic system from a series of noisy measurements. In the path planning of unmanned vehicles, Kalman filtering is used to reduce the uncertainty and error of sensor data and provide more accurate environmental perception information.

[0067] While the driverless car is driving, the environment may change, such as sudden obstacles or changes in traffic conditions. The dynamic feedback mechanism allows the driverless car to adjust its path planning based on these real-time data to avoid obstacles and optimize the driving route.

[0068] The unmanned vehicle path planning method provided by the present invention uses multi-sensor data fusion and Kalman filtering algorithm. The multi-sensor data fusion technology improves the accuracy of environmental perception, reduces the dependence on a single sensor, and improves the safety of path planning. Through the comprehensive decision-making support of the smart city environment, the path selection is optimized, traffic congestion is avoided, and the overall travel efficiency of the unmanned vehicle is improved.

[0069] The present application also provides a path planning device for an unmanned vehicle, comprising: Initialization module, used to initialize the current position and target position of the unmanned vehicle; The path optimization module is used to perform path optimization through multiple iterations based on the Runge-Kutta optimization algorithm. In each iteration, the path is adjusted according to the calculated gradient direction and control input to obtain the optimal path from the current position to the target position; The obstacle avoidance module is used to perceive the environment and detect obstacles in real time through multi-sensor data fusion technology. When the unmanned vehicle detects an obstacle, it dynamically adjusts the path according to the real-time sensor data to avoid the obstacle, returns to the path planning, and obtains the updated optimal path.

[0070] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0071] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0072] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0073] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0074] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0075] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0076] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0077] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0078] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0079] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for unmanned vehicle path planning, characterized in that: include: S1 initializes the current position and target position of the unmanned vehicle; S2 performs path optimization through multiple iterations based on the Runge-Kutta optimization algorithm. In each iteration, the path is adjusted according to the calculated gradient direction and control input to obtain the optimal path from the current position to the target position. S3 uses multi-sensor data fusion technology to perceive the environment and detect obstacles in real time. When the unmanned vehicle detects an obstacle, it dynamically adjusts the path to avoid the obstacle based on the real-time sensor data, returns to step S2 to update the path planning, and obtains the updated optimal path.

2. The unmanned vehicle path planning method according to claim 1, characterized in that: Initializing the current position and target position of the unmanned vehicle specifically includes: Set the initial position of the unmanned vehicle to , the target location is , the path optimization process is in, is the current position vector, is the control input, is the time step, is the state equation of the unmanned vehicle, which represents the relationship between the current position and the control input.

3. The unmanned vehicle path planning method according to claim 2, characterized in that: The path optimization is performed through multiple iterations based on the Runge-Kutta optimization algorithm, specifically including: in, is the initial state equation of the unmanned vehicle The first derivative of , and are their second-order, third-order and fourth-order derivatives respectively, and the path optimization is performed through an iterative method to obtain the optimal path from the current position to the target position.

4. The unmanned vehicle path planning method according to claim 3, characterized in that: When the unmanned vehicle detects an obstacle, the path is dynamically adjusted to avoid the obstacle according to real-time sensor data, specifically including: When the autonomous vehicle detects an obstacle, it automatically adjusts the control input and path Avoid obstacles and update path planning in, To avoid obstacles, a new path is generated. is the adjustment term caused by the obstacle, which can be obtained by the following formula in, is the gradient effect of the current obstacle position on the path, It is the adjustment coefficient, indicating the strength of avoiding obstacles.

5. The unmanned vehicle path planning method according to claim 1, characterized in that: Also includes: After the first time step, the cost of the current path is re-evaluated and the path continues to be optimized based on the new environmental data.

6. The unmanned vehicle path planning method according to claim 5, characterized in that: The cost of re-evaluating the current path specifically includes: in, is the total length of the path, For the The location of the obstacle, For current location With obstacles The distance is the weight coefficient for obstacle avoidance.

7. The unmanned vehicle path planning method according to claim 1, characterized in that: Also includes: By integrating data from lidar, cameras, and ultrasonic sensors, the Kalman filter algorithm is used to update and fuse multi-sensor data in real time to obtain environmental perception information, and real-time adjustments to the path are made based on real-time sensor data and a dynamic feedback mechanism.

8. A path planning device for an unmanned vehicle, characterized in that: include: Initialization module, used to initialize the current position and target position of the unmanned vehicle; The path optimization module is used to perform path optimization through multiple iterations based on the Runge-Kutta optimization algorithm. In each iteration, the path is adjusted according to the calculated gradient direction and control input to obtain the optimal path from the current position to the target position; The obstacle avoidance module is used to perceive the environment and detect obstacles in real time through multi-sensor data fusion technology. When the unmanned vehicle detects an obstacle, it dynamically adjusts the path according to the real-time sensor data to avoid the obstacle, returns to the path planning, and obtains the updated optimal path.

9. An unmanned vehicle path planning device, characterized in that: The method comprises at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit executes the steps of the method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: It stores a computer program that can be executed by an unmanned vehicle path planning device. When the computer program runs on the unmanned vehicle path planning device, the unmanned vehicle path planning device executes the steps of the method described in any one of claims 1 to 7.

Images