A path tracking control method and device of a vehicle, a vehicle, and a medium

Abstract

The application discloses a path tracking control method and device of a vehicle, the vehicle and a medium. The method comprises the following steps: traversing each path node in a reference path, obtaining a current vehicle speed and a current pose of a current path node; determining a preview distance corresponding to the current vehicle speed based on a preset mapping rule; and predicting a predicted pose of the vehicle at a next path node according to the preview distance. According to the current pose and the predicted pose, it is determined whether the vehicle deviates. If not, the next path node is traversed. If yes, the current vehicle speed is reduced to obtain a target vehicle speed, and the next path node is traversed. When the last path node is traversed, a vehicle speed sequence of each node is generated, and the vehicle is controlled to track and drive based on the vehicle speed sequence. Thus, the preview distance and the vehicle speed are dynamically associated, the future pose change of the vehicle is predicted in real time, and whether there is a deviation risk is identified in advance. If there is, the deviation of the vehicle in the transverse direction is corrected through longitudinal speed reduction, and accurate tracking is realized.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a method, device, vehicle, and medium for path tracking control of a vehicle. Background Technology

[0002] In the field of vehicle autonomous driving control technology, path tracking performance is a core indicator for measuring the quality of system control, directly determining the vehicle's handling precision, driving smoothness, and the user's driving experience. Especially in complex driving scenarios such as continuous S-curves, where road curvature changes drastically and at a high rate, accurate path tracking is crucial for safe vehicle operation.

[0003] Currently, path tracking primarily uses the Pure Pursuit (PP) algorithm as its underlying control logic. Specifically, the PP algorithm sets a fixed preview point using fixed rules and calculates the desired front wheel steering angle based on the geometric relationship between the vehicle's current position and this preview point, thereby achieving path tracking.

[0004] However, when faced with complex paths with varying curvature, the PP algorithm, based on a fixed aiming distance, cannot adaptively adjust according to changes in the curvature of the path ahead. This results in the vehicle's lateral control easily accumulating tracking errors during the tracking of paths such as continuous S-curves, making it difficult to meet the requirements of high-precision control.

[0005] Therefore, how to improve the accuracy of vehicle path tracking, thereby enhancing vehicle driving safety, is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] In view of this, one aspect of this application provides a path tracking control method for a vehicle, the method comprising: S10: Iterate through each path node in the reference path in sequence. For the current path node, obtain the node information; the node information includes the current vehicle speed and the current pose. S11: Based on preset mapping rules, determine the pre-aiming distance corresponding to the current vehicle speed; S12: Based on the pre-aiming distance, predict the vehicle's predicted pose at the next path node; S13: Based on the current pose and the predicted pose, determine whether the vehicle has deviated from its target position; if not, proceed to step S14; if yes, proceed to step S15. S14: Set the next path node as the current path node and return to step S10; S15: Reduce the current vehicle speed to obtain the target vehicle speed; and return to step S14; S16: When traversing to the last path node, generate the vehicle speed sequence for each path node; and control the vehicle to track and drive on the reference path based on the vehicle speed sequence.

[0007] Optionally, determining whether the vehicle has deviated from its course based on the current pose and the predicted pose includes: Based on the current pose and the predicted pose, determine the vehicle's lateral error and heading error; Based on the lateral error and the heading error, a target error parameter is determined; the target error parameter is used to determine whether the vehicle has veered off course, and the degree of veer-off; the target error parameter is positively correlated with the degree of veer-off. If the target error parameter is greater than the threshold, it is determined that the vehicle has deviated from its intended path. If the target error parameter is not greater than the threshold, it is determined that the vehicle has not deviated from its target position.

[0008] Optionally, determining the target error parameters based on the lateral error and the heading error includes: Configure lateral weights for the lateral error and configure heading weights for the heading error; Obtain the remaining mileage traveled by the vehicle on the reference path; Determine whether the remaining mileage is less than the preset mileage; If it is less than the target weight, increase the heading weight to obtain the target weight; based on the lateral weight and the target weight, perform a weighted sum of the lateral error and the heading error to obtain the target error parameter; If it is not less than, the target error parameter is obtained by weighted summation of the lateral error and the heading error based on the lateral weight and the heading weight.

[0009] Optionally, reducing the current vehicle speed to obtain the target vehicle speed includes: Obtain the rate of curvature change from the current path node to the next path node; Assign a first weight to the rate of change of curvature, configure a second weight to the current vehicle speed, configure a third weight to the target error parameter, and configure a fourth weight to the pre-aiming distance; Based on the first weight, the second weight, the third weight, and the fourth weight, the curvature change rate, the current vehicle speed, the target error parameter, and the pre-aiming distance are weighted and summed to obtain the deceleration amount; The target vehicle speed is obtained by summing the current vehicle speed and the deceleration amount.

[0010] Optionally, the rate of change of curvature is positively correlated with the first weight; the current vehicle speed is positively correlated with the second weight; the target error parameter is positively correlated with the third weight; and the aiming distance is negatively correlated with the fourth weight. Of the first weight, the second weight, the third weight, and the fourth weight, the third weight is the largest.

[0011] Optionally, after reducing the current vehicle speed to obtain the target vehicle speed, the method further includes: Based on the mapping rules, the target aiming distance corresponding to the target vehicle speed is determined; Based on the target pre-aiming distance, predict the target's predicted pose for the next path node; Based on the current pose and the target predicted pose, determine whether the vehicle has deviated from its target position; If not, return to step S14; If so, reduce the historical speed of the previous path node to obtain the target historical speed; Based on the target historical vehicle speed, adjust the current vehicle speed to obtain the target current vehicle speed; and return to step S11.

[0012] Optionally, adjusting the current vehicle speed based on the target historical vehicle speed to obtain the target current vehicle speed includes: Obtain the deceleration and displacement between the previous path node and the current path node; Determine the product of the deceleration and the displacement; The target current vehicle speed is determined based on the target parameter being equal to a preset multiple of the product; the target parameter is used to characterize the degree of speed difference between the target historical vehicle speed and the target current vehicle speed.

[0013] Another aspect of this application provides a vehicle path tracking control device, the device comprising: The information acquisition module is used to sequentially traverse each path node in the reference path and acquire node information for the current path node; the node information includes the current vehicle speed and the current pose. The aiming distance determination module is used to determine the aiming distance corresponding to the current vehicle speed based on a preset mapping rule; The pose prediction module is used to predict the vehicle's pose at the next path node based on the pre-aiming distance. The vehicle deviation determination module is used to determine whether the vehicle has deviated from its target position based on the current pose and the predicted pose; if not, the first processing module is invoked; if so, the second processing module is invoked. The first processing module is used to take the next path node as the current path node and return to call the information acquisition module; The second processing module is used to reduce the current vehicle speed to obtain the target vehicle speed; and then return to call the first processing module. The vehicle speed sequence generation module is used to generate a vehicle speed sequence for each path node when traversing to the last path node; and to control the vehicle to track and drive on the reference path based on the vehicle speed sequence.

[0014] Another aspect of this application provides a vehicle including a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the computer program to implement the steps of a path tracking control method for the vehicle.

[0015] Another aspect of this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the path tracking control method for the vehicle.

[0016] The vehicle path tracking control method, device, vehicle, and medium provided in this application have the following beneficial effects: They dynamically correlate the pre-aiming distance with the vehicle speed, eliminating reliance on a fixed pre-aiming distance. Instead, they combine the vehicle's actual speed at different path nodes to predict the pose of the next node in real time, i.e., dynamically predicting the future pose change trend of the vehicle and identifying potential follow-alteration risks in the reference path in advance. Furthermore, if a follow-alteration risk is predicted, the combination of longitudinal speed and lateral control—specifically, longitudinal speed reduction—corrects the lateral follow-alteration, thereby ensuring the achievement of the lateral control target, improving vehicle tracking accuracy, and guaranteeing vehicle driving safety. Attached Figure Description

[0017] Figure 1 A schematic flowchart of a vehicle path tracking control method provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the effect of vehicle path tracking provided in an embodiment of this application. Figure 3 A schematic diagram illustrating the principle of pose prediction provided in an embodiment of this application; Figure 4 A schematic diagram illustrating the principle of a vehicle path tracking control method provided in an embodiment of this application; Figure 5 A schematic diagram illustrating the principle of another vehicle path tracking control method provided in this application embodiment; Figure 6 A schematic diagram of the structure of a vehicle path tracking control device provided in an embodiment of this application; Figure 7 This is a structural schematic diagram of a vehicle provided in an embodiment of this application.

[0018] The reference numerals in the attached diagram are as follows: 60 is the information acquisition module, 61 is the pre-aiming distance determination module, 62 is the pose prediction module, 63 is the following deviation determination module, 64 is the first processing module, 65 is the second processing module, 66 is the vehicle speed sequence generation module, 70 is the memory, 71 is the processor, 72 is the display screen, 73 is the input / output interface, 74 is the communication interface, 75 is the power supply, 76 is the communication bus, 701 is the computer program, 702 is the operating system, and 703 is the data. Detailed Implementation

[0019] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0020] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0021] Figure 1 This is a schematic flowchart of a vehicle path tracking control method provided in an embodiment of this application, as shown below. Figure 1 As shown, the method includes: S10: Iterate through each path node in the reference path in sequence. For the current path node, obtain the node information, which includes the current vehicle speed and current pose. Figure 2 This is a schematic diagram illustrating the effect of vehicle path tracking provided in an embodiment of this application. In a specific embodiment, vehicles are generated periodically. Figure 2 The reference path shown guides the vehicle's movement along it. The reference path consists of multiple path nodes, each including node information about the vehicle's current driving state. In a specific embodiment, the node information may include, but is not limited to, vehicle speed, vehicle posture, steering wheel angle, and the rate of curvature change between adjacent nodes.

[0022] In a specific embodiment, when the vehicle obtains a reference path, each path node includes the vehicle speed at which it should travel and the steering wheel angle, thereby enabling it to track the reference path. However, see... Figure 2 When a vehicle approaches a curve (i.e., the tangent point), if the vehicle speed is too high, it may not have enough time to adjust the steering angle, causing the vehicle to veer lateral. See [link to other documentation]. Figure 2 If the vehicle is tracked using the originally set speed and other node information, the actual blue driving path may deviate from the red reference path.

[0023] Therefore, in order to avoid the above-mentioned technical problems, this application provides a path tracking control method that predicts the tracking status of each path node in advance and adjusts the vehicle speed of each path node according to the prediction results, thereby improving the tracking accuracy.

[0024] Specifically, in this embodiment, the vehicle acquires a reference path in real time and traverses the path nodes on the reference path sequentially according to the vehicle's direction of travel. During the traversal, for the currently traversed path node, node information including at least the current vehicle speed and current pose is acquired for subsequent deviation judgment.

[0025] It should be noted that the vehicles provided in this application may include, but are not limited to, sedans, sport utility vehicles (SUVs), multi-purpose vehicles (MPVs), off-road vehicles, pickup trucks, or other power-driven, non-rail-borne vehicles. Furthermore, it should be noted that the execution entity of the vehicle path tracking control method provided in this application may be a vehicle controller or a domain controller; this application does not limit the scope of the implementation.

[0026] S11: Determine the aiming distance corresponding to the current vehicle speed based on preset mapping rules; Understandably, current path tracking methods are all based on a fixed aiming distance, which cannot adaptively adjust to changes in path curvature in real-world scenarios. This leads to potential issues with lateral vehicle control in complex paths such as continuous S-curves. Figure 2 The tracking deviation is shown.

[0027] To address this technical issue, this application embodiment dynamically correlates vehicle speed with the pre-aiming distance, selecting different pre-aiming distances based on different scenarios. Specifically, for high-speed driving, a long pre-aiming strategy is employed to ensure tracking stability. For low-speed driving, a short pre-aiming strategy is switched to improve the precision of path tracking.

[0028] In an alternative embodiment, the aiming distance corresponding to the current vehicle speed can be determined according to formula (1): (1) in, Pre-aiming distance, This represents the current vehicle speed.

[0029] As can be seen from the above calculation formula, in the preset mapping relationship (i.e., the above mapping formula), the current vehicle speed is positively correlated with the aiming distance. Different vehicle speeds can calculate different aiming distances, thus realizing the dynamic adjustment of the aiming distance.

[0030] S12: Based on the pre-aiming distance, predict the vehicle's pose at the next path node; Furthermore, based on the pre-aiming distance This can predict the vehicle's pose at the next path node. For example, see... Figure 2 The current path node is S1, and the next path node is S2. In a specific embodiment, before the vehicle reaches nodes S1 and S2, the vehicle's deviation is assessed and its speed is adjusted in advance. Specifically, after determining the pre-aiming distance of node S1 according to the above steps, the vehicle's pose when it reaches node S2 can be predicted based on this pre-aiming distance.

[0031] Figure 3 This is a schematic diagram illustrating the principle of pose prediction provided in an embodiment of this application. In an optional embodiment, the predicted pose of the next path node S2 can be calculated using the PP algorithm. For details, see... Figure 3 In a specific embodiment, the aiming distance at the current vehicle speed can be determined according to the above calculation formula (1). At the same time, obtain the vehicle's wheelbase. And the historical lateral deviation generated when a vehicle travels from the previous path node to the current path node. At this point, the steering wheel angle required for the vehicle to travel from the current path node to the next path node is determined by formula (2): (2) in, For steering wheel angle, Wheelbase This represents historical horizontal deviation.

[0032] In a specific embodiment, see Figure 3 The vehicle can directly obtain the tangent of the next path node in the reference path, and thus the PP algorithm can determine the steering wheel angle through the above calculation formula (2). Furthermore, it can be based on the steering wheel angle. This predicts the vehicle's pose after it travels from node S1 to node S2. The pose is determined based on the steering wheel angle. This application does not limit the method for determining the predicted pose.

[0033] It should be noted that algorithms such as sliding mode control can also be used to predict the pose of the next path node based on the pre-aiming distance, and this application does not limit this. From the perspective of computational efficiency, the prediction is preferably performed using the aforementioned PP algorithm.

[0034] S13: Based on the current pose and the predicted pose, determine whether the vehicle has deviated from its intended position; if not, proceed to step S14; if yes, proceed to step S15. S14: Set the next path node as the current path node and return to step S10; S15: Reduce the current vehicle speed to obtain the target vehicle speed; and return to step S14; It is understandable that, in specific embodiments, the current pose of the current path node... Since these are known quantities, they can be obtained directly. The predicted pose of the next path node... Prediction can be made using the methods described above. Therefore, it is possible to predict based on the current pose. and predicted pose The resulting offset can be used to determine whether the vehicle will deviate from its path at the next path node.

[0035] In an optional embodiment, if the vehicle does not deviate from its path, and the vehicle tracking data, such as the current vehicle speed and steering wheel angle, representing the current path node are set reasonably, the vehicle can track the current path node to the next path node. At this point, the control loop determines whether to enter the next path node. That is, the next path node is taken as the current path node, and steps S10 to S13 are repeated.

[0036] Of course, in another optional embodiment, if the vehicle deviates from its path, it indicates that the vehicle tracking data, such as the current speed and steering wheel angle of the current path node, is set incorrectly, making it impossible to track the vehicle from the current path node to the next path node, and this will result in... Figure 2 The control shown is biased. At this point, the bias needs to be corrected; specifically, the current speed of the vehicle at the current path node needs to be reduced.

[0037] It is understandable that reducing the current vehicle speed is essentially to control the vehicle's longitudinal deceleration when it laterally deviates from its target. Based on the mapping rule of the above calculation formula (1), the aiming distance can be shortened, thereby correcting the vehicle's deviation.

[0038] In other words, by deeply integrating longitudinal speed planning with lateral control strategies, the path tracking process not only focuses on correcting lateral deviations but also considers the matching relationship between steering wheel response and current vehicle speed. When a risk of following the vehicle off course is predicted, the longitudinal speed is actively reduced to provide sufficient steering response time, ensuring that the vehicle has enough time to turn the steering wheel to the corresponding angle. This ensures the achievement of lateral control objectives and improves path tracking accuracy in complex tracking scenarios such as S-curves.

[0039] S16: When traversing to the last path node, generate the vehicle speed sequence for each path node; and control the vehicle to track and drive on the reference path based on the vehicle speed sequence.

[0040] After traversing all path nodes in the reference path based on steps S10 to S15, the vehicle speeds after judgment and / or adjustment are used to form a vehicle speed sequence so that the vehicle can perform path tracking control based on the corrected vehicle speed sequence during actual driving on the reference path.

[0041] Therefore, the vehicle path tracking control method provided in this application dynamically correlates the aiming distance with the vehicle speed, no longer relying on a fixed aiming distance. Instead, it combines the actual vehicle speed at different path nodes to predict the pose of the next node in real time, that is, dynamically predicts the future pose change trend of the vehicle and identifies in advance whether there is a risk of following deviation in the reference path. Furthermore, if a risk of following deviation is predicted, the method combines longitudinal speed and lateral control, that is, corrects the lateral vehicle deviation by reducing longitudinal speed, thereby ensuring the achievement of the lateral control target, improving vehicle tracking accuracy, and ensuring vehicle driving safety.

[0042] In one optional embodiment, determining whether the vehicle has veered off course based on the current pose and the predicted pose includes: Based on the current pose and the predicted pose, determine the vehicle's lateral error and heading error; Based on the lateral error and heading error, the target error parameters are determined; the target error parameters are used to determine whether the vehicle has followed the lane and the degree of following the lane; the target error parameters are positively correlated with the degree of following the lane. If the target error parameter is greater than the threshold, it is determined that the vehicle has deviated from its intended path. If the target error parameter is not greater than the threshold, it is determined that the vehicle has not deviated from its target position.

[0043] Based on the above embodiments, the current pose can be obtained. and predicted pose At this point, the lateral error and heading error of the vehicle can be determined according to formulas (3) and (4): (3) (4) in, For lateral error, This represents the heading error.

[0044] Furthermore, to determine whether the vehicle has veered off course, lateral error is considered. and heading error Calculate the target error parameters The target error parameter Used to determine whether a vehicle has pulled to one side and the degree of such pulling.

[0045] Specifically, if the target error parameter A value greater than a threshold (e.g., greater than 0.05) indicates that the vehicle has engaged in follow-alley maneuvering, and the target error parameter... The larger the value, the more severe the bias in the representation. If the target error parameter... If the value is not greater than a threshold, it indicates that the vehicle has not engaged in follow-alone maneuvering. In a specific embodiment, the target error parameter is calculated... The method can be calculated by summation or other means, and this application does not limit this.

[0046] Based on the above embodiments, as an optional embodiment, the target error parameters are determined according to the lateral error and heading error, including: Configure lateral weights for lateral errors and lateral weights for heading errors; Obtain the remaining mileage of the vehicle on the reference path; Determine if the remaining mileage is less than the preset mileage; If it is less than the target weight, increase the heading weight to obtain the target weight; based on the lateral weight and the target weight, perform a weighted sum of the lateral error and the heading error to obtain the target error parameter; If it is not less than, the target error parameter is obtained by weighted summation of the lateral error and the heading error based on the lateral weight and the heading weight.

[0047] In actual vehicle control, when determining the target error parameter, as an optional implementation, it can be the lateral error. and heading error Configure different weights separately, specifically including horizontal weights. and heading weight In a specific embodiment, horizontal weights are configured. and heading weight The weights can be set based on experience values ​​and continuously adjusted based on the tracking results during the historical tracking process.

[0048] Furthermore, see calculation formula (5), based on horizontal weights. and heading weight For lateral error and heading error By performing a weighted summation, the target error parameters can be determined: (5) It is important to note that as the vehicle continuously travels and tracks the reference path, the target error parameters need to be calculated in real time. During the calculation process, since the vehicle pays more attention to heading deviation when entering the end of the reference path, it is necessary to increase the heading weight. This is to meet the tracking accuracy requirements at the end of the vehicle's journey.

[0049] Specifically, in each calculation of the target error parameter In a specific embodiment, the remaining mileage traveled by the vehicle on the reference path is first obtained. If the remaining mileage is less than a preset mileage, it indicates that the vehicle has entered the final tracking stage, and at this time, the heading weight is increased. And based on the increased heading weight The target error parameter is calculated using the above formula (5). .

[0050] For example, in vehicle parking tracking control, the preset distance is 1 meter. If the remaining distance is less than 1 meter, it indicates that the vehicle has entered the final stage of tracking, at which point the heading weight is increased. This allows vehicle control to focus more on heading deviation, ensuring that the vehicle accurately tracks the path.

[0051] In one optional embodiment, reducing the current vehicle speed to obtain the target vehicle speed includes: Obtain the rate of curvature change from the current path node to the next path node; Assign a first weight to the rate of curvature change, a second weight to the current vehicle speed, a third weight to the target error parameter, and a fourth weight to the aiming distance; Based on the first weight, second weight, third weight, and fourth weight, the rate of curvature change, current vehicle speed, target error parameters, and pre-aiming distance are weighted and summed to obtain the deceleration amount; The target speed is obtained by summing the current speed and the amount of deceleration.

[0052] When reducing the current vehicle speed, the main factor to consider is the degree of vehicle yaw, that is, the target error parameter. The resulting impact. Therefore, in an alternative embodiment, when performing deceleration control, the target error parameter can be... Define a coefficient that is related to the target error parameter. The product of the two is used as the deceleration amount, and the current vehicle speed is further reduced based on the deceleration amount.

[0053] Of course, it is understandable that significantly reducing the vehicle's speed could cause severe jerking, affecting the user's riding experience. Therefore, considering the issue of ride comfort after speed reduction, multiple influencing factors can be introduced to determine the amount of deceleration, based on the above embodiments.

[0054] Specifically, the rate of curvature change between the current path node and the next path node is obtained, and different weights are assigned to the rate of curvature change, current vehicle speed, target error parameter, and aiming distance. Further, the deceleration amount for the current path node is determined according to formula (6): (5) in, This is the amount of deceleration. As the first weight, The rate of change of curvature, As the second weight, As the third weight, It is the fourth weight.

[0055] In a specific embodiment, the rate of change of curvature indicates that the greater the abrupt change in curvature and the higher the vehicle speed, the greater the trajectory deviation represented by the target error parameter, and the corresponding required deceleration amount should also increase. Conversely, the shorter the preview distance, the more sensitive the system response, allowing for a smaller deceleration amount to maintain smoothness and control accuracy. That is, the rate of change of curvature is positively correlated with the first weight; the current vehicle speed is positively correlated with the second weight; the target error parameter is positively correlated with the third weight; and the preview distance is negatively correlated with the fourth weight.

[0056] In addition, it should be noted that in specific embodiments, the most important influencing factor of deceleration is the target error parameter, while factors such as the rate of change of curvature are mainly used to improve comfort. Therefore, among the four weights assigned, the third weight is the largest.

[0057] Based on the above formula (5), the reference path of this application can be, but is not limited to, a straight line tangent to a circular arc, a circular arc tangent to a straight line, an S-bend, and other diverse paths. For different path segments, the curve change rate is different, and precise control of graded deceleration can be achieved, thereby improving the generalization ability of path tracking control.

[0058] Figure 4 This is a schematic diagram illustrating the principle of a vehicle path tracking control method provided in this application embodiment. Based on the above embodiment, as an optional embodiment, after reducing the current vehicle speed to obtain the target vehicle speed, the method further includes: Based on the mapping rules, determine the target aiming distance corresponding to the target vehicle speed; Based on the target's pre-aiming distance, predict the target's pose at the next path node; Based on the current pose and the target predicted pose, determine whether the vehicle has deviated from its target position; If not, return to step S14; If so, reduce the historical speed of the previous path node to obtain the target historical speed; Adjust the current vehicle speed according to the target historical vehicle speed to obtain the target current vehicle speed; and return to step S11.

[0059] It is understandable that in the above embodiments, if the target error parameter corresponding to the current path node is greater than the threshold, it indicates that the vehicle has deviated from its intended path, and the current vehicle speed needs to be reduced. After the speed reduction, it is necessary to re-verify whether the target speed after the speed reduction meets the deviating requirement, that is, to determine whether deviating will still occur when the vehicle travels from the current path node to the next path node at the target speed. Specifically, in conjunction with... Figure 4 Please provide a detailed explanation.

[0060] See Figure 4 Node n is the current path node, node n+1 is the next path node, and node n-1 is the previous path node. In a specific embodiment, it is first determined whether the target error parameter determined based on the current vehicle speed when the vehicle is at node n is greater than a threshold. If it is greater, it indicates that the vehicle has deviated from its path. At this time, the current vehicle speed at node n is reduced to obtain the target vehicle speed.

[0061] Furthermore, based on the above method and mapping rules, the target preset distance corresponding to the target vehicle speed is determined, and the target prediction pose of node n+1 is re-predicted based on the target preset distance. Finally, the current target error parameters are determined based on the target prediction pose. (See also...) Figure 4 Next, it checks whether the target error parameter corresponding to the target vehicle speed is greater than the threshold, i.e., whether there is still a risk of deviation after the speed reduction. If it is not greater, it indicates that the target vehicle speed after the speed reduction can accurately track the reference path. At this point, it checks whether to traverse to the last node of the reference path. If it is the last node, it generates the vehicle speed sequence corresponding to all nodes on the reference path. If it is not the last node, it takes the next path node as the current path node, i.e., returns to the step of taking node n+1 as node n.

[0062] If the target error parameter corresponding to the target vehicle speed is greater than the threshold, it indicates that even after a speed reduction, the current node still cannot meet the tracking requirements, meaning that tracking deviation will still occur. In this case, node backtracking is performed. Specifically, the previous path node (i.e., node n-1) is returned, and the historical vehicle speed of node n-1 is reduced to obtain the target historical vehicle speed.

[0063] Furthermore, to conserve computing resources, the speed of the current node is quickly determined based on the target historical vehicle speed; that is, the current speed is adjusted based on the target historical vehicle speed to obtain the target current speed. Simultaneously, steps S11 to S13 of the above embodiment are executed again based on the target current speed to re-determine whether the target error parameter corresponding to the current speed of node n is greater than the threshold. This process is repeated cyclically. Figure 4 The nodes shown are traversed until the last node is reached, and the vehicle speed corresponding to all nodes is obtained.

[0064] Figure 5 This is a schematic diagram illustrating the principle of another vehicle path tracking control method provided in this application embodiment. For ease of understanding, it will be described below in conjunction with... Figure 5 Further explanation is needed. For example... Figure 5 As shown, the horizontal axis represents the mileage traveled, and the vertical axis represents the vehicle speed.

[0065] In a specific embodiment, when node S1 travels to node S2, if the target error parameter corresponding to the vehicle speed V10 is not greater than the threshold, then node S2 is taken as the current node, and the determination is made as to whether the target error parameter corresponding to the vehicle speed V20 of that node is greater than the threshold.

[0066] If the target error parameter corresponding to vehicle speed V20 is greater than the threshold, then reduce vehicle speed V20 to vehicle speed V21, and continue to check whether the target error parameter corresponding to vehicle speed V21 is greater than the threshold. If the target error parameter corresponding to vehicle speed V21 is greater than the threshold, then proceed to the next node.

[0067] If the target error parameter corresponding to vehicle speed V21 is greater than the threshold, the system returns to node S1 and reduces vehicle speed V10 to vehicle speed V11. At the same time, the vehicle speed at node S2 is directly determined based on vehicle speed V11, thus obtaining V22.

[0068] In one optional embodiment, adjusting the current vehicle speed based on the target historical vehicle speed to obtain the target current vehicle speed includes: Get the deceleration and displacement between the previous path node and the current path node; Determine the product of deceleration and displacement; The target current speed is determined based on the target parameter being equal to a preset multiple of the product; the target parameter is used to characterize the degree of speed difference between the target's historical speed and the target's current speed.

[0069] In a specific implementation, if the current path node's speed reduction still fails to meet the tracking requirements (i.e., the target error parameter remains greater than the threshold), node backtracking is required, meaning the process returns to the previous path for speed reduction. However, to ensure optimal comfort, the speed difference between adjacent path nodes cannot be too significant.

[0070] Therefore, after reducing the speed of the previous node path, based on the aforementioned comfort requirements, the speed of the current node path can be directly updated. Specifically, the deceleration and displacement between the previous path node and the current path node are obtained, and the target current speed is determined according to formula (6): (5) in, As a preset multiple, in one optional embodiment, it can be set to 2. It is the product of deceleration and displacement. Target historical vehicle speed, The target is the current vehicle speed. The target parameter is used to characterize the degree of speed difference between the target's historical speed and its current speed.

[0071] Therefore, based on the speed difference calculation formula between the above path nodes, it can be ensured that the speed difference between the upper and lower path nodes will not be too large, ensuring that the vehicle will not undergo drastic speed changes and improving the user's riding experience.

[0072] In the above embodiments, the vehicle path tracking control method has been described in detail. This application also provides an embodiment of a vehicle path tracking control device.

[0073] Figure 6 This is a schematic diagram of the structure of a vehicle path tracking control device provided in an embodiment of this application, as shown below. Figure 6 As shown, the device includes: The information acquisition module 60 is used to traverse each path node in the reference path in sequence, and for the current path node, acquire the node information; the node information includes the current vehicle speed and the current pose; The aiming distance determination module 66 is used to determine the aiming distance corresponding to the current vehicle speed based on a preset mapping rule; The pose prediction module 62 is used to predict the vehicle's pose at the next path node based on the pre-aiming distance. The vehicle deviation determination module 63 is used to determine whether the vehicle has deviated from its target position based on the current pose and the predicted pose; if not, the first processing module 64 is called; if so, the second processing module 65 is called. The first processing module 64 is used to take the next path node as the current path node and return the call information acquisition module 60. The second processing module 65 is used to reduce the current vehicle speed, obtain the target vehicle speed, and then return to call the first processing module 64. The vehicle speed sequence generation module 66 is used to generate the vehicle speed sequence of each path node when traversing to the last path node; and to control the vehicle to track and drive on the reference path based on the vehicle speed sequence.

[0074] Furthermore, the vehicle path tracking control device provided in this application embodiment also includes: The error determination module is used to determine the vehicle's lateral error and heading error based on the current pose and the predicted pose. The error judgment module is used to determine the target error parameter based on the lateral error and heading error. The target error parameter is used to determine whether the vehicle has followed the target and the degree of following. The target error parameter is positively correlated with the degree of following. If the target error parameter is greater than the threshold, it is determined that the vehicle has followed the target. If the target error parameter is not greater than the threshold, it is determined that the vehicle has not followed the target.

[0075] The first allocation module is used to configure lateral weights for lateral errors and heading weights for heading errors. The mileage acquisition module is used to obtain the remaining mileage of the vehicle on the reference path; The target error parameter determination module is used to determine whether the remaining mileage is less than the preset mileage; if it is less, the heading weight is increased to obtain the target weight; based on the lateral weight and the target weight, the lateral error and the heading error are weighted and summed to obtain the target error parameter; if it is not less, based on the lateral weight and the heading weight, the lateral error and the heading error are weighted and summed to obtain the target error parameter.

[0076] The curvature change rate acquisition module is used to obtain the curvature change rate from the current path node to the next path node; The second allocation module is used to allocate a first weight to the rate of curvature change, a second weight to the current vehicle speed, a third weight to the target error parameter, and a fourth weight to the aiming distance. The rate of curvature change is positively correlated with the first weight; the current vehicle speed is positively correlated with the second weight; the target error parameter is positively correlated with the third weight; and the aiming distance is negatively correlated with the fourth weight. Among the first, second, third, and fourth weights, the third weight is the largest.

[0077] The weighted summation module is used to perform a weighted summation of the rate of curvature change, current vehicle speed, target error parameters, and pre-aiming distance based on the first weight, second weight, third weight, and fourth weight to obtain the deceleration amount; The summation module is used to sum the current vehicle speed and the amount of deceleration to obtain the target vehicle speed.

[0078] The aiming distance determination module is also used to determine the target aiming distance corresponding to the target vehicle speed based on mapping rules; The pose prediction module is also used to predict the target's pose at the next path node based on the target's pre-aiming distance. The vehicle deviation determination module is also used to determine whether the vehicle has deviated from its target position based on the current position and the target's predicted position. If not, it returns to call the first processing module. If yes, it calls the vehicle speed adjustment module and then returns to call the pre-aiming distance determination module. The vehicle speed adjustment module is used to reduce the historical vehicle speed of the previous path node to obtain the target historical vehicle speed; and adjust the current vehicle speed according to the target historical vehicle speed to obtain the target current vehicle speed.

[0079] The target information acquisition module is used to obtain the deceleration and displacement between the previous path node and the current path node. The product module is used to determine the product of deceleration and displacement. The target current vehicle speed determination module is used to determine the target current vehicle speed based on a preset multiple of the target parameter equal to the product; the target parameter is used to characterize the speed difference between the target's historical vehicle speed and the target's current vehicle speed.

[0080] Figure 7 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application, such as... Figure 7 As shown, the vehicle includes: a memory 70 for storing computer programs; The processor 71 is configured to execute a computer program to implement the steps of the vehicle path tracking control method as described in the above embodiments.

[0081] The processor 71 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 71 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 71 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 71 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 71 may also include an Artificial Intelligence (AI) processor, which is used to handle computational operations related to machine learning.

[0082] The memory 70 may include one or more computer-readable storage media, which may be non-transitory. The memory 70 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 70 is used to store at least the following computer program 701, which, after being loaded and executed by the processor 71, is capable of implementing the relevant steps of the vehicle path tracking control method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 70 may also include an operating system 702 and data 703, and the storage method may be temporary or permanent storage. The operating system 702 may include Windows, Unix, Linux, etc. The data 703 may include, but is not limited to, relevant data involved in the vehicle path tracking control method.

[0083] In some embodiments, the vehicle may also include a display screen 72, an input / output interface 73, a communication interface 74, a power supply 75, and a communication bus 76.

[0084] Those skilled in the art will understand that Figure 7 The structure shown does not constitute a limitation on the vehicle and may include more or fewer components than illustrated.

[0085] The vehicle provided in this application includes a memory and a processor. When the processor executes the program stored in the memory, it can implement the path tracking control method of the vehicle in the above embodiments.

[0086] It should be noted that although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

Claims

1. A method for path tracking control of a vehicle, characterized in that, The method includes: S10: Iterate through each path node in the reference path in sequence. For the current path node, obtain the node information; the node information includes the current vehicle speed and the current pose. S11: Based on preset mapping rules, determine the pre-aiming distance corresponding to the current vehicle speed; S12: Based on the pre-aiming distance, predict the vehicle's predicted pose at the next path node; S13: Based on the current pose and the predicted pose, determine whether the vehicle has deviated from its course; if not, proceed to step S14; if yes, proceed to step S15. S14: Set the next path node as the current path node and return to step S10; S15: Reduce the current vehicle speed to obtain the target vehicle speed; and return to step S14; S16: When traversing to the last path node, generate the vehicle speed sequence for each path node; and control the vehicle to track and drive on the reference path based on the vehicle speed sequence.

2. The vehicle path tracking control method as described in claim 1, characterized in that, The step of determining whether the vehicle has deviated from its course based on the current pose and the predicted pose includes: Based on the current pose and the predicted pose, determine the vehicle's lateral error and heading error; Based on the lateral error and the heading error, a target error parameter is determined; the target error parameter is used to determine whether the vehicle has drifted off course, and the degree of drift; the target error parameter is positively correlated with the degree of drift. If the target error parameter is greater than the threshold, it is determined that the vehicle has deviated from its intended path. If the target error parameter is not greater than the threshold, it is determined that the vehicle has not deviated from its target position.

3. The vehicle path tracking control method as described in claim 2, characterized in that, The step of determining the target error parameters based on the lateral error and the heading error includes: Configure lateral weights for the lateral error and configure heading weights for the heading error; Obtain the remaining mileage traveled by the vehicle on the reference path; Determine whether the remaining mileage is less than the preset mileage; If it is less than the target weight, increase the heading weight to obtain the target weight; based on the lateral weight and the target weight, perform a weighted sum of the lateral error and the heading error to obtain the target error parameter; If it is not less than, the target error parameter is obtained by weighted summation of the lateral error and the heading error based on the lateral weight and the heading weight.

4. The vehicle path tracking control method as described in claim 2, characterized in that, The step of reducing the current vehicle speed to obtain the target vehicle speed includes: Obtain the rate of curvature change from the current path node to the next path node; Assign a first weight to the rate of change of curvature, configure a second weight to the current vehicle speed, configure a third weight to the target error parameter, and configure a fourth weight to the pre-aiming distance; Based on the first weight, the second weight, the third weight, and the fourth weight, the curvature change rate, the current vehicle speed, the target error parameter, and the pre-aiming distance are weighted and summed to obtain the deceleration amount; The target vehicle speed is obtained by summing the current vehicle speed and the deceleration amount.

5. The vehicle path tracking control method as described in claim 4, characterized in that, The rate of change of curvature is positively correlated with the first weight; the current vehicle speed is positively correlated with the second weight; the target error parameter is positively correlated with the third weight; and the pre-aiming distance is negatively correlated with the fourth weight. Of the first weight, the second weight, the third weight, and the fourth weight, the third weight is the largest.

6. The vehicle path tracking control method as described in claim 1, characterized in that, After reducing the current vehicle speed to obtain the target vehicle speed, the method further includes: Based on the mapping rules, the target aiming distance corresponding to the target vehicle speed is determined; Based on the target pre-aiming distance, predict the target's predicted pose for the next path node; Based on the current pose and the target predicted pose, determine whether the vehicle has deviated from its target position; If not, return to step S14; If so, reduce the historical speed of the previous path node to obtain the target historical speed; Based on the target historical vehicle speed, adjust the current vehicle speed to obtain the target current vehicle speed; and return to step S11.

7. The vehicle path tracking control method as described in claim 6, characterized in that, The step of adjusting the current vehicle speed based on the target historical vehicle speed to obtain the target current vehicle speed includes: Obtain the deceleration and displacement between the previous path node and the current path node; Determine the product of the deceleration and the displacement; The target current vehicle speed is determined based on the target parameter being equal to a preset multiple of the product; the target parameter is used to characterize the degree of speed difference between the target historical vehicle speed and the target current vehicle speed.

8. A vehicle path tracking control device, characterized in that, The device includes: The information acquisition module is used to sequentially traverse each path node in the reference path and acquire node information for the current path node; the node information includes the current vehicle speed and the current pose. The aiming distance determination module is used to determine the aiming distance corresponding to the current vehicle speed based on a preset mapping rule; The pose prediction module is used to predict the vehicle's pose at the next path node based on the pre-aiming distance. The vehicle deviation determination module is used to determine whether the vehicle has deviated from its target position based on the current pose and the predicted pose; if not, the first processing module is invoked; if so, the second processing module is invoked. The first processing module is used to take the next path node as the current path node and return to call the information acquisition module; The second processing module is used to reduce the current vehicle speed to obtain the target vehicle speed; and then return to call the first processing module. The vehicle speed sequence generation module is used to generate a vehicle speed sequence for each path node when traversing to the last path node; and to control the vehicle to track and drive on the reference path based on the vehicle speed sequence.

9. A vehicle comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the path tracking control method for the vehicle according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the path tracking control method for the vehicle according to any one of claims 1 to 7.

Images