Automatic driving preview point selection method, system and device, storage medium and vehicle
The fuzzy algorithm model combines the driver's style, vehicle speed and road curvature to select the pre-sight point of the autonomous driving, which solves the problem of inaccurate selection of pre-sight point in the existing technology, and achieves high accuracy and reliability of autonomous driving.
Patent Information
- Application Number
- CN202410069765.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-18
- Publication Date
- 2025-07-25
AI Technical Summary
The existing pre-targeting method for autonomous driving lacks effective mathematical model support, resulting in misjudgment and misjudgment, which cannot meet the needs of different drivers, affecting the accuracy and reliability of autonomous driving.
The fuzzy algorithm model is used to obtain the driver's driving style, vehicle speed and road curvature as inputs, output the pre-sight distance, and determine the trajectory point that best matches the distance in the local trajectory as the pre-sight point.
It improves the accuracy and reliability of autonomous driving, and realizes real-time pre-aiming point selection based on different drivers, speeds and road curvature, which has strong adaptability and real-time performance to ensure the smooth and safe operation of autonomous driving.
Smart Images

Figure CN120363941A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of autonomous driving, and particularly to a method, a system, a device, a storage medium, and a vehicle for selecting a preview point of autonomous driving. Background Art
[0002] During the autonomous driving process of a vehicle, the selection of the preview point for autonomous driving is one of the key technologies. Traditional methods for selecting preview points usually rely on existing rules or experience, lacking the support of an effective mathematical model, and are prone to misjudgment and missed judgment.
[0003] In the prior art, the methods for selecting preview points of autonomous driving are generally divided into the following two categories: Firstly, a preview point selection strategy based on a single variable factor. This method selects the preview point for autonomous driving through a single variable, such as using the turning radius method; this method selects the preview point position according to the driving state of the vehicle and the curvature radius of the road ahead. The advantage of this method is that it can adaptively adjust the preview point position according to the road curvature change. However, this method requires accurate measurement of the road curvature radius and ignores other obstacles on the road ahead, which will result in a weak adaptability of the selected preview point, thus leading to a poor tracking effect of the unmanned driving algorithm; Secondly, a method based on manual experience calibration. This method controls a single variable to select a preview point for real-time calibration by setting vehicle speed and road curvature factors. However, it is difficult to implement the method of selecting a preview point based on experience calibration, and different driving styles of each person will result in the inability of the calibrated preview point selection strategy to meet the needs of different drivers, thus easily leading to misjudgment and missed judgment, and reducing the driving experience of passengers. Summary of the Invention
[0004] The technical problem to be solved by the present invention is to provide a method, a system, a device, a storage medium, and a vehicle for selecting a preview point of autonomous driving, which can improve the accuracy and reliability of autonomous driving.
[0005] To solve the above technical problem, as one aspect of the present invention, there is provided a method for selecting a preview point of autonomous driving, which at least includes the following steps: Obtain the current local trajectory; Take the current driving style of the driver, the current vehicle speed, and the road curvature as inputs, input them into a pre-set fuzzy algorithm model, and output the current preview distance obtained through fuzzy calculation; Determine the local trajectory point in the local trajectory that most conforms to the preview distance, and take the local trajectory point as the current preview point of autonomous driving.
[0006] As another aspect of the present invention, there is provided a system for selecting a preview point of autonomous driving, which at least includes: A local trajectory acquisition module for acquiring the current local trajectory; A preview distance acquisition module for taking the current driving style of the driver, the current vehicle speed, and the road curvature as inputs, inputting them into a pre-set fuzzy algorithm model, and outputting the current preview distance obtained through fuzzy calculation; A preview point selection module for determining the local trajectory point that best matches the preview distance in the local trajectory, and taking the local trajectory point as the current autonomous driving preview point.
[0007] Correspondingly, in another aspect of the present invention, there is also provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method as described above are implemented.
[0008] Correspondingly, in yet another aspect of the present invention, there is also provided a computing device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the steps of the method as described above are implemented.
[0009] Correspondingly, in another aspect of the present invention, there is also a vehicle, on which at least an autonomous driving planning device is provided, and the system as described above is deployed in the autonomous driving planning device.
[0010] Implementing the embodiments of the present invention has the following beneficial effects: The present invention provides a method, system, device, storage medium, and vehicle for selecting an autonomous driving preview point. By first collecting global trajectory information (such as speed, longitude and latitude, road curvature, etc.); then using the method of cubic spline interpolation to smooth the trajectory points of the collected trajectory, and embedding the trajectory points into the autonomous driving algorithm through tools such as Dspace, generating a local trajectory according to its own positioning and trajectory prediction algorithm; then selecting the driving style of the driver, vehicle speed, road curvature, etc. as fuzzy variables to select the preview distance, and combining the preview distance based on the distance between the local trajectory point and the host vehicle to select the current preview point; finally, by sending the information of the preview point to the downstream control, the stable and safe operation of autonomous driving can be achieved.
[0011] The present invention selects the main factors (driving style, vehicle speed, road curvature) affecting the autonomous driving preview distance as fuzzy variables, takes the preview distance as the output variable, and selects the autonomous driving preview point in the way of fuzzy principle, greatly improving the applicability of the method. By online controlling the driving style, speed, and curvature of the driver in the system, the preview point can be selected in real time according to different drivers, different speeds, and different road curvatures, with strong real-time performance.
[0012] The preview point selection method provided by the present invention only adopts the principle of single fuzzy control, selects the main factors affecting the preview point as variables, and realizes the strong self - adaptability requirement of algorithm preview point selection, thus avoiding problems such as high control difficulty caused by combining multiple complex preview point selection models. Brief Description of the Drawings
[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, obtaining other drawings based on these drawings still belongs to the scope of the present invention; Figure 1 It is a schematic diagram of the main process of an embodiment of a method for selecting a preview point of an autonomous driving provided by the present invention; Figure 2 It is a schematic diagram of the principle of fuzzy calculation involved in the present invention; Figure 3 It is a more complete schematic diagram of the process of selecting a preview point and making a decision in the method provided by the present invention; Figure 4 It is a schematic diagram of the structure of an embodiment of a system for selecting a preview point of an autonomous driving provided by the present invention; Figure 5 For Figure 4 it is a schematic diagram of the structure of the local trajectory acquisition module in Figure 6 For Figure 4 it is a schematic diagram of the structure of the preview distance acquisition module in Figure 7 For Figure 4 it is a schematic diagram of the structure of the preview point selection module in Detailed Embodiment
[0014] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will further describe the present invention in detail with reference to the drawings.
[0015] As Figure 1 shown, it shows a schematic diagram of the main process of an embodiment of a method for selecting a preview point of an autonomous driving provided by the present invention; in combination with Figure 2 shown, in this embodiment, the method at least includes the following steps: Step S11, obtain the current local trajectory; Specifically, it includes: Step S110, obtain the global trajectory that the autonomous driving vehicle needs to run; In a specific example, the step S110 further includes: Collect the trajectory point information on the road in the selected autonomous driving test area. For example, an autonomous driving vehicle equipped with devices such as GPS and gyroscopes can be used to collect the trajectory point information on the road in the selected autonomous driving test area in the way of manual driving; the trajectory point information includes: longitude and latitude, speed, acceleration and road curvature; Smooth the collected trajectory points by the method of cubic spline curve interpolation to generate global trajectory points. More specifically, the above trajectory point information can be stored in the form of a computer-readable file, and the trajectory points are read into the algorithm through methods such as Dspace (a simulation software) to generate global trajectory points.
[0016] It can be understood that through this step, the global trajectory required for the autonomous driving vehicle to run can be generated, which is a prerequisite for the selection of preview points.
[0017] Step S111, obtain the current local trajectory in the global trajectory according to the positioning information of the vehicle; In a specific example, the step S111 further includes: When the vehicle starts, the autonomous driving module imports the global trajectory, performs coordinate conversion processing, and converts the longitude and latitude coordinate system into a local coordinate system; According to the positioning of the vehicle and in combination with the trajectory prediction algorithm in the autonomous driving module, search the global trajectory to generate a series of local trajectory points to form a local trajectory, where the local trajectory points correspond to the imported global trajectory.
[0018] It can be understood that through this step, the real-time local trajectory is determined, which provides a reference for the selection of the preview point distance.
[0019] Step S12, take the current driving style of the driver, the current vehicle speed and the road curvature as inputs, input them into a pre-set fuzzy algorithm model, and output the current preview distance obtained through fuzzy calculation; In a specific example, the step S12 further includes: Step S120, obtain the current vehicle speed and the road curvature through the CAN bus, take the current driving style of the driver, the current vehicle speed and the road curvature as inputs, and input them into a pre-set fuzzy algorithm model; among them, the current driving style of the driver can be input and operated through the in-vehicle HMI (Human Machine Interface) interface; Step S121, perform variable fuzzification processing in the pre-set fuzzy algorithm model.
[0020] It is understandable that according to daily life experience, the faster the vehicle speed, the more the driver pays attention to the state of the road in the farther distance, and the longer the preview distance; the more radical the driving style of the driver, the faster the vehicle speed during normal driving, and the relatively longer the preview distance; the more conservative the driving style of the driver, the relatively slower the vehicle speed during normal driving, and the relatively shorter the preview distance. At the same time, the road curvature also affects the driver's preview point. When the road curvature is larger (the road radius is smaller), the preview distance is shorter.
[0021] Therefore, in the present invention, factors affecting the preview distance such as the driver's driving style, vehicle speed, and road curvature are used as fuzzy inputs, and their universes of discourse are [a, b], [e, f] km / h, and [g, h] respectively , and the output variable is the preview distance , and the universe of discourse is [x, y] m. In order to simplify the calculation model and ensure the control accuracy, the universes of discourse of the input and output fuzzy sets are divided into n grades. The driver's driving style is determined as a i (i = 1…n; i represents the grading of the driver's style universe), the vehicle speed is determined as V q (q = 1…n; q represents the grading of the vehicle speed universe), the road curvature is determined as T r (r = 1…n, r represents the grading of the road curvature universe), and the preview distance is determined as L s (s = 1…n; s represents the grading of the driver's reaction time universe);
[0022] In the present invention, the trapezoidal membership function, triangular membership function, and Gaussian membership function are combined to select the membership function; In the present invention, fuzzy rules need to be generated in advance. It can be seen from the fuzzy conditional statement that there are fuzzy rule bases composed of rules. In the present invention, Mamdani method (a linguistic fuzzy system) is used for fuzzy inference, and the rules can be expressed as follows:
[0023] If: age = a i & driving age = d j & V = V q & tired = T r , then: t = t s In the formula, are the linguistic variables of the input and output variables respectively.
[0024] At the same time, the centroid method is selected for defuzzification processing; Step S121, obtain the preview distance data value and output it.
[0025] Step S13: Determine the local trajectory point in the local trajectory that best matches the preview distance, and use this local trajectory point as the current automatic driving preview point.
[0026] After determining the automatic driving preview distance by the method based on the fuzzy principle, it is first necessary to determine which trajectory point on the local trajectory the preview point specifically is according to the preview distance; In a specific example, step S13 further includes: Step S130: Calculate the distance value between each trajectory point in the local trajectory and the host vehicle in real time; it can be understood that the local coordinates of the host vehicle , , and the coordinates on the global trajectory point are , (i = 1, 2, 3…, the number of the trajectory point), calculate the distance between each trajectory point and the host vehicle in real time , as follows:
[0027]
[0028] Step S131: By comparing the preview distance data value with each distance value, use the local trajectory point with the smallest difference as the current automatic driving preview point. More specifically, by comparing the preview distance L with and taking the trajectory point number corresponding to the minimum value, and select the local trajectory point under this number as the automatic driving preview point.
[0029] It can be understood that through step S12 and step S13, the preview distance is output by the method based on the fuzzy principle, and then the preview point is selected by combining the preview distance on the basis of the distance between the local trajectory point and the host vehicle.
[0030] It can be understood that in the method provided by the present invention, since a vehicle may be operated by different drivers, the driving style information of the driver is constantly changing. In the method provided by the present invention, whenever the driver starts to drive this vehicle, the driver inputs his own driving to the control algorithm embedded in the vehicle through this interface; the speed of the vehicle is obtained through sensors and input to the control algorithm through the CAN line; the road curvature is obtained through the road curvature information on the global trajectory point, and finally the reaction time of the driver is obtained through fuzzy inference to formulate a preview distance suitable for each driver.
[0031] In an embodiment of the present invention, by selecting the driving style (aggressive, smooth, etc.) of the driver, the vehicle speed, and the road curvature as fuzzy variables, and the distance of the preview point from the host vehicle as the output variable, by comparing with the predicted trajectory points locally searched, the coordinates (x, y, z) and azimuth information of the preview point are selected and given to the downstream decision control module. The downstream decision control module automatically generates the steering wheel angle / torque control information of the vehicle according to the information of the preview point, and uses the control information to control the vehicle to drive automatically, so as to realize the precise and smooth operation of the autonomous vehicle. For specific details, reference can be made to Figure 3 the details in
[0032] As Figure 4 shown, a schematic structural diagram of an embodiment of a system for selecting a preview point for autonomous driving provided by the present invention is shown; in combination with Figures 5 to 7 shown, in this embodiment, the system 1 at least includes: A local trajectory acquisition module 11, configured to acquire the current local trajectory; A preview distance acquisition module 12, configured to use the current driving style of the driver, the current vehicle speed, and the road curvature as inputs, input a pre-set fuzzy algorithm model, and output the current preview distance obtained through fuzzy calculation; A preview point selection module 13, configured to determine the local trajectory point that most conforms to the preview distance in the local trajectory, and use the local trajectory point as the current preview point for autonomous driving.
[0033] As Figure 5 shown, more specifically, the local trajectory acquisition module 11 further includes: A global trajectory acquisition module 110, configured to acquire the global trajectory required for the autonomous vehicle; A local trajectory generation module 111, configured to obtain the current local trajectory in the global trajectory according to the positioning information of the vehicle; Among them, the global trajectory acquisition module 110 further includes: A trajectory point acquisition unit 1100, configured to acquire the trajectory point information on the road in the selected autonomous driving test area. Specifically, an autonomous vehicle equipped with devices such as GPS and gyroscopes can be used to acquire the trajectory point information on the road in the selected autonomous driving test area by means of manual driving; the trajectory point information includes: longitude and latitude, speed, acceleration, and road curvature; A smoothing processing unit 1101, configured to smooth the acquired trajectory points by means of cubic spline curve interpolation to generate global trajectory points.
[0034] Among them, the local trajectory generation module 111 further includes: An import conversion unit 1110 is used to import the global trajectory, perform coordinate conversion processing, and convert the longitude and latitude coordinate system into a local coordinate system; A search unit 1111 is used to search the global trajectory according to the vehicle's positioning, generate a series of local trajectory points, and form a local trajectory, where the local trajectory points correspond to the imported global trajectory.
[0035] As Figure 6 shown, more specifically, the preview distance acquisition module 12 further includes: An input unit 120 is used to obtain the current vehicle speed and road curvature through the CAN bus, and use the driver's current driving style, the current vehicle speed, and the road curvature as inputs to input a pre-set fuzzy algorithm model; A fuzzy processing unit 121 is used to perform variable fuzzification processing in the pre-set fuzzy algorithm model, divide the input-output fuzzy set domain into n grades, and determine the driver's driving style as a i , the vehicle speed is determined as v q , the road curvature is determined as T r , the preview distance is determined as L s ; where, i represents the grading of the driver style domain, i = 1…n; q represents the grading of the vehicle speed domain, q = 1…n; r represents the grading of the road curvature domain, r = 1…n; s represents the grading of the driver reaction time domain, s = 1…n; and a method combining trapezoidal membership function, triangular membership function and Gaussian membership function is used, the fuzzy inference rule of Mamdani method is adopted, and the centroid method is selected for defuzzification processing; A preview distance output unit 122 is used to obtain the preview distance data value and output it.
[0036] As Figure 7 shown, more specifically, the preview point selection module 13 further includes: A calculation unit 130 is used to calculate the distance value between each trajectory point in the local trajectory and the host vehicle in real time; A selection unit 131 is used to compare the preview distance data value with each distance value, and take the local trajectory point with the smallest difference as the current autonomous driving preview point.
[0037] For more details, please refer to and combine the foregoing description of Figures 1 to 3 , and no further elaboration will be made here.
[0038] As another aspect of the present invention, a computer-readable storage medium is further provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in Figures 1 to 3 are implemented. For more details, please refer to and combine the foregoing description of Figures 1 to 3The description thereof will not be elaborated herein.
[0039] As another aspect of the present invention, there is also provided a computing device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the method as described in Figures 1 to 3 are implemented. For more details, please refer to and combine the foregoing description of Figures 1 to 3 The description thereof will not be elaborated herein.
[0040] As yet another aspect of the present invention, there is also provided a vehicle provided with an autonomous driving planning device, characterized in that the autonomous driving planning device deploys a system as described in Figures 4 to 7 For more details, please refer to and combine the foregoing description of Figures 4 to 7 The description thereof will not be elaborated herein.
[0041] Implementing the embodiments of the present invention has the following beneficial effects: The present invention provides a method, a system, a device, a storage medium, and a vehicle for selecting an autonomous driving preview point. First, global trajectory information (such as speed, longitude and latitude, road curvature, etc.) is collected; then, the collected trajectory is smoothed by using the cubic spline interpolation method, and the trajectory points are embedded into the autonomous driving algorithm through tools such as Dspace, and local trajectories are generated according to its own positioning and trajectory prediction algorithm; then, by selecting the driver's driving style, vehicle speed, road curvature, etc. as fuzzy variables to select the preview distance, and combining the preview distance based on the distance between the local trajectory points and the host vehicle to select the current preview point; finally, by sending the information of the preview point to the downstream control, the stable and safe operation of autonomous driving can be realized.
[0042] By selecting the main factors (driving style, vehicle speed, road curvature) affecting the autonomous driving preview distance as fuzzy variables and taking the preview distance as the output variable, the present invention selects the autonomous driving preview point by means of the fuzzy principle, greatly improving the applicability of the method. By performing online control on the driving style, speed, and curvature of the driver in the system, the preview point can be selected in real time according to different drivers, different speeds, and different road curvatures, with strong real-time performance.
[0043] The preview point selection method provided by the present invention only adopts the principle of single fuzzy control, selects the main factors affecting the preview point as variables, and realizes the strong self-adaptability requirement of the algorithm for preview point selection, thus avoiding problems such as large control difficulty caused by combining multiple complex preview point selection models.
[0044] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, an apparatus, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.
[0045] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 means for implementing the functions specified in one block or multiple blocks.
[0046] The above-disclosed is only a preferred embodiment of the present invention, and of course, it cannot be used to limit the scope of the rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.
Claims
1. A method for selecting a preview point for autonomous driving, characterized in that, At least include the following steps: Obtain the current local trajectory; Take the driver's current driving style, the current vehicle speed, and the road curvature as inputs, input them into a pre-set fuzzy algorithm model, and output the current preview distance obtained through fuzzy calculation; Determine the local trajectory point in the local trajectory that best matches the preview distance, and use the local trajectory point as the current autonomous driving preview point.
2. The method according to claim 1, wherein The obtaining of the current local trajectory includes: Obtain the global trajectory required for the autonomous vehicle to run; According to the vehicle's positioning information, obtain the current local trajectory in the global trajectory.
3. The method according to claim 2, wherein The obtaining of the global trajectory required for the autonomous vehicle to run includes: Collect trajectory point information on the road in the selected autonomous driving test area, where the trajectory point information includes: longitude and latitude, speed, acceleration, and road curvature; Smoothly process the collected trajectory points by means of cubic spline curve interpolation to generate global trajectory points and form a global trajectory.
4. The method according to claim 1, characterized in that, Obtain the current local trajectory, including: Import the global trajectory and perform coordinate conversion processing to convert the longitude and latitude coordinate system into a local coordinate system; According to the vehicle's positioning, search the global trajectory to generate a series of local trajectory points and form a local trajectory, where the local trajectory points correspond to the imported global trajectory.
5. The method according to claim 1, wherein Taking the driver's current driving style, the current vehicle speed, and the road curvature as inputs, input them into a pre-set fuzzy algorithm model, and output the current preview distance obtained through fuzzy calculation, including: Obtain the current vehicle speed and road curvature through the CAN bus, take the driver's current driving style, the current vehicle speed, and the road curvature as inputs, and input them into a pre-set fuzzy algorithm model; In the pre-set fuzzy algorithm model, variable fuzzification is performed. The input and output fuzzy set domains are divided into n levels, and the driving style of the driver is determined as a i , the vehicle speed is determined as V q , the road curvature is determined as T r , the preview distance is determined as L s ; where i represents the classification of the driver style domain, i = 1…n; q represents the classification of the vehicle speed domain, q = 1…n; r represents the classification of the road curvature domain, r = 1…n; s represents the classification of the driver reaction time domain, s = 1…n; and a method combining trapezoidal membership function, triangular membership function and Gaussian membership function is used, and the fuzzy inference rule of Mamdani method is adopted, and the centroid method is selected for defuzzification processing; Obtain the preview distance data value and output it.
6. The method according to any one of claims 1 to 5, characterized in that, The determining of the local trajectory point in the local trajectory that is closest according to the preview distance and using the local trajectory point as the current autonomous driving preview point further includes: Calculate in real time the distance value between each trajectory point in the local trajectory and the host vehicle; By comparing the preview distance data value with each distance value, take the local trajectory point with the smallest difference as the current autonomous driving preview point.
7. A system for selecting a preview point for autonomous driving, characterized in that At least include: A local trajectory acquisition unit for obtaining the current local trajectory; A preview distance acquisition module for taking the driver's current driving style, the current vehicle speed, and the road curvature as inputs, inputting them into a pre-set fuzzy algorithm model, and outputting the current preview distance obtained through fuzzy calculation; A preview point selection module for determining the local trajectory point in the local trajectory that best matches the preview distance and using the local trajectory point as the current autonomous driving preview point.
8. The system according to claim 7, wherein The local trajectory acquisition unit includes: A global trajectory acquisition module for obtaining the global trajectory required for the autonomous vehicle to run; A local trajectory generation module for obtaining the current local trajectory in the global trajectory according to the vehicle's positioning information.
9. The system according to claim 8, wherein The global trajectory acquisition module further includes: A trajectory point collection unit for collecting trajectory point information on the road in the selected autonomous driving test area, where the trajectory point information includes: longitude and latitude, speed, acceleration, and road curvature; A smoothing processing unit, configured to smooth the acquired trajectory points by means of cubic spline curve interpolation to generate global trajectory points.
10. The system according to claim 7, wherein The local trajectory generation module further includes: An import and conversion unit, configured to import the global trajectory and perform coordinate conversion processing to convert the longitude and latitude coordinate system into a local coordinate system; A search unit, configured to search the global trajectory according to the vehicle's positioning to generate a series of local trajectory points to form a local trajectory, wherein the local trajectory points correspond to the imported global trajectory.
11. The system according to claim 8, wherein The preview distance acquisition module further includes: An input unit, configured to acquire the current vehicle speed and road curvature through the CAN bus, and use the driver's current driving style, the current vehicle speed, and the road curvature as inputs to input a pre-set fuzzy algorithm model; A fuzzy processing unit, which is used to perform variable fuzzification processing in the pre-set fuzzy algorithm model, divide the input-output fuzzy set universe into n levels, and determine the driver's driving style as a i , determine the vehicle speed as V q , determine the road curvature as T r , determine the preview distance as L s ; where, i represents the grading of the driver style universe, i = 1…n; q represents the grading of the vehicle speed universe, q = 1…n; r represents the grading of the road curvature universe, r = 1…n; s represents the grading of the driver reaction time universe, s = 1…n; and a method combining trapezoidal membership function, triangular membership function and Gaussian membership function is used, the fuzzy inference rule of Mamdani method is adopted, and the centroid method is selected for defuzzification processing; A preview distance output unit, configured to obtain and output the preview distance data value.
12. The system according to any one of claims 7-11, characterized in that, The preview point selection module further includes: A calculation unit, configured to calculate in real time the distance value between each trajectory point in the local trajectory and the host vehicle; A selection unit, configured to compare the preview distance data value with each distance value, and use the local trajectory point with the smallest difference as the current autonomous driving preview point.
13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
14. A computing device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
15. A vehicle is provided with an autonomous driving planning device, characterized in that, The system according to any one of claims 7 to 12 is deployed in the autonomous driving planning device.