An automatic driving multi-target lateral trajectory tracking optimization control method and device

Abstract

The application provides an automatic driving multi-target lateral trajectory tracking optimization control method and device, relates to the automatic driving vehicle dynamics control technical field, and the method comprises the following steps: obtaining control input information of an automatic driving vehicle; the control input information comprises target planning trajectory information, vehicle state information and external environment information; a comprehensive weight coefficient model is constructed according to the target planning trajectory information and the external environment information; effective tracking coordinate information is generated according to the target planning trajectory information, the comprehensive weight coefficient model, a pre-constructed cumulative lateral displacement difference target model and a pre-constructed cumulative lateral velocity difference target model; and a target steering wheel angle of the automatic driving vehicle is generated according to the effective tracking coordinate information and the vehicle state information to control the automatic driving vehicle. The application realizes high-precision, strong robustness and high real-time lateral tracking control of the target trajectory of the automatic driving vehicle in a complex environment.

Description

Technical Field

[0001] This application relates to the field of autonomous vehicle dynamics control technology, and in particular to an autonomous driving multi-target lateral trajectory tracking optimization control method and device. Background Technology

[0002] In recent years, autonomous driving technology has developed rapidly, and trajectory tracking control, as one of the core technologies for achieving autonomous driving path execution and vehicle stability control, has received widespread attention. Existing trajectory tracking control methods mainly fall into two categories: model-free control methods and model-based control methods.

[0003] Among them, the PID (Proportional-Integral-Derivative) control method, as a typical model-free method, has advantages such as simple structure, good real-time performance, and low cost, and is suitable for some low-speed, simple scenarios. However, because this method cannot effectively integrate the influence of multiple factors such as future road information and planned trajectory, it is difficult to meet the trajectory tracking accuracy requirements in high-speed, nonlinear, or dynamic complex environments.

[0004] In contrast, MPC (Model Predictive Control), as an advanced model-based control strategy, possesses online optimization and prediction capabilities as well as the ability to handle multiple constraints simultaneously, thus improving control accuracy and safety in complex scenarios. However, its high computational complexity and large system resource requirements limit its real-time application in resource-constrained systems. These issues urgently need to be addressed. Summary of the Invention

[0005] To address the problems in the prior art, this application provides an autonomous driving multi-target lateral trajectory tracking optimization control method and apparatus, which can solve the problems existing in the prior art.

[0006] In a first aspect, this application provides an optimized control method for multi-target lateral trajectory tracking in autonomous driving, comprising:

[0007] Acquire control input information for autonomous vehicles; the control input information includes target planning trajectory information, vehicle status information, and external environment information.

[0008] A comprehensive weight coefficient model is constructed based on the target planning trajectory information and the external environment information;

[0009] Effective tracking coordinate information is generated based on the target trajectory information, the comprehensive weight coefficient model, the pre-constructed cumulative lateral displacement difference target model, and the pre-constructed cumulative lateral velocity difference target model.

[0010] The target steering wheel angle of the autonomous vehicle is generated based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle.

[0011] Furthermore, the target planning trajectory information includes pre-aiming segment information and trajectory curvature information; the step of constructing a comprehensive weight coefficient model based on the target planning trajectory information and the external environment information includes:

[0012] A first weight coefficient model is generated based on the pre-aimed segment information;

[0013] A second weighting coefficient model is generated based on the trajectory curvature information and the pre-aiming segment information;

[0014] A third weighting coefficient model is generated based on the external environment information and the pre-aimed segment information;

[0015] The comprehensive weight coefficient model is constructed using the first weight coefficient model, the second weight coefficient model, and the third weight coefficient model.

[0016] Further, the external environment information includes obstacle-trajectory distance information and obstacle-vehicle time distance information; the step of generating a third weighting coefficient model based on the external environment information and the pre-aiming segment information includes:

[0017] A first obstacle weight coefficient model is generated based on the obstacle-trajectory distance information;

[0018] A second obstacle weight coefficient model is generated based on the obstacle-vehicle time-distance information and the pre-aiming section information;

[0019] The third weight coefficient model is constructed using the first obstacle weight coefficient model and the second obstacle weight coefficient model.

[0020] Further, the step of generating effective tracking coordinate information based on the target trajectory information, the comprehensive weight coefficient model, the pre-constructed cumulative lateral displacement difference target model, and the pre-constructed cumulative lateral velocity difference target model includes:

[0021] An effective tracking coordinate model is generated using the cumulative lateral displacement difference target model and the cumulative lateral velocity difference target model; the cumulative lateral displacement difference target model is constructed based on the lateral displacement parameters of the target's planned trajectory within the pre-aiming section and the lateral displacement parameters of the vehicle; the cumulative lateral velocity difference target model is constructed based on the lateral velocity parameters of the target's planned trajectory within the pre-aiming section and the lateral velocity parameters of the vehicle.

[0022] Extract trajectory tracking point information from the target planned trajectory information;

[0023] The comprehensive weight coefficient of the trajectory tracking point is calculated using the trajectory tracking point information and the comprehensive weight coefficient model.

[0024] The effective tracking coordinate information is calculated using the effective tracking coordinate model, the trajectory tracking point information, and the comprehensive weight coefficient of the trajectory tracking points.

[0025] Further, the step of generating the target steering wheel angle of the autonomous vehicle based on the effective tracking coordinate information and the vehicle state information to control the autonomous vehicle includes:

[0026] The target lateral acceleration of the autonomous vehicle is calculated using the effective tracking coordinate information and the vehicle state information.

[0027] The target steering wheel angle is calculated based on the target's lateral acceleration.

[0028] Secondly, this application provides an autonomous driving multi-target lateral trajectory tracking optimization control device, comprising:

[0029] An information acquisition unit is used to acquire control input information of an autonomous vehicle; the control input information includes target planning trajectory information, vehicle status information, and external environment information.

[0030] The comprehensive weighting coefficient model construction unit is used to construct a comprehensive weighting coefficient model based on the target planning trajectory information and the external environment information.

[0031] An effective tracking coordinate information generation unit is used to generate effective tracking coordinate information based on the target planning trajectory information, the comprehensive weight coefficient model, the pre-constructed cumulative lateral displacement difference target model, and the pre-constructed cumulative lateral velocity difference target model.

[0032] The target steering wheel angle generation unit is used to generate the target steering wheel angle of the autonomous vehicle based on the effective tracking coordinate information and the vehicle status information in order to control the autonomous vehicle.

[0033] Furthermore, the target planning trajectory information includes pre-aiming segment information and trajectory curvature information; the comprehensive weight coefficient model construction unit includes:

[0034] The first weight coefficient model generation module is used to generate a first weight coefficient model based on the pre-aiming segment information.

[0035] The second weighting coefficient model generation module is used to generate a second weighting coefficient model based on the trajectory curvature information and the pre-aiming segment information.

[0036] The third weighting coefficient model generation module is used to generate a third weighting coefficient model based on the external environment information and the pre-aiming segment information.

[0037] The comprehensive weight coefficient model construction module is used to construct the comprehensive weight coefficient model using the first weight coefficient model, the second weight coefficient model and the third weight coefficient model.

[0038] Furthermore, the external environment information includes obstacle-trajectory distance information and obstacle-vehicle time-distance information; the third weighting coefficient model generation module includes:

[0039] The first obstacle weight coefficient model generation submodule is used to generate a first obstacle weight coefficient model based on the obstacle-trajectory distance information.

[0040] The second obstacle weight coefficient model generation submodule is used to generate a second obstacle weight coefficient model based on the obstacle-vehicle time distance information and the pre-aiming section information.

[0041] The third weight coefficient model generation submodule is used to construct the third weight coefficient model using the first obstacle weight coefficient model and the second obstacle weight coefficient model.

[0042] Furthermore, the effective tracking coordinate information generation unit includes:

[0043] An effective tracking coordinate model generation module is used to generate an effective tracking coordinate model using the cumulative lateral displacement difference target model and the cumulative lateral velocity difference target model; the cumulative lateral displacement difference target model is constructed based on the lateral displacement parameters of the target planned trajectory in the pre-aiming section and the lateral displacement parameters of the vehicle; the cumulative lateral velocity difference target model is constructed based on the lateral velocity parameters of the target planned trajectory in the pre-aiming section and the lateral velocity parameters of the vehicle.

[0044] The trajectory tracking point information extraction module is used to extract trajectory tracking point information from the target planned trajectory information;

[0045] The comprehensive weighting coefficient calculation module is used to calculate the comprehensive weighting coefficient of the trajectory tracking point using the trajectory tracking point information and the comprehensive weighting coefficient model.

[0046] The effective tracking coordinate information calculation module is used to calculate the effective tracking coordinate information using the effective tracking coordinate model, the trajectory tracking point information, and the comprehensive weight coefficient of the trajectory tracking points.

[0047] Furthermore, the target steering wheel angle generation unit includes:

[0048] The target lateral acceleration calculation module is used to calculate the target lateral acceleration of the autonomous vehicle using the effective tracking coordinate information and the vehicle state information;

[0049] The target steering wheel angle calculation module is used to calculate the target steering wheel angle based on the target lateral acceleration.

[0050] Thirdly, this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the autonomous driving multi-target lateral trajectory tracking optimization control method described in any of the above embodiments.

[0051] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the autonomous driving multi-target lateral trajectory tracking optimization control method described in any of the above embodiments.

[0052] Fifthly, this application provides a computer program product, which includes a computer program that, when executed by a processor, implements the autonomous driving multi-target lateral trajectory tracking optimization control method described in any of the above embodiments.

[0053] This application provides an optimized control method and apparatus for multi-target lateral trajectory tracking in autonomous driving. The method acquires control input information from the autonomous vehicle, including target trajectory planning information, vehicle status information, and external environment information. A comprehensive weighting coefficient model is constructed based on the target trajectory planning information and the external environment information. Effective tracking coordinate information is generated based on the target trajectory planning information, the comprehensive weighting coefficient model, a pre-constructed cumulative lateral displacement difference target model, and a pre-constructed cumulative lateral velocity difference target model. The target steering wheel angle of the autonomous vehicle is generated based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle. This achieves high-precision, robust, and real-time lateral tracking control of the autonomous vehicle in complex environments.

[0054] Specifically, by acquiring control input information from the autonomous vehicle, including target trajectory information, vehicle status information, and external environment information, the system provides a multi-dimensional input foundation for the control system, including the global path, current vehicle status, and environmental perception, ensuring the comprehensiveness and real-time nature of subsequent control strategies. A comprehensive weighting coefficient model is constructed based on the target trajectory information and the external environment information to achieve dynamic evaluation and differentiated control of the importance of different aiming points, improving the control system's adaptability to complex scenarios and its ability to prioritize responses. Effective tracking coordinate information is generated based on the target trajectory information, the comprehensive weighting coefficient model, a pre-constructed cumulative lateral displacement difference target model, and a pre-constructed cumulative lateral velocity difference target model, optimizing tracking point selection and minimizing trajectory deviation, achieving a balance between trajectory tracking accuracy and vehicle dynamic behavior. Finally, the target steering wheel angle of the autonomous vehicle is generated based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle, achieving precise steering control based on minimizing trajectory error, and improving the vehicle's operational stability and safety in dynamic and complex environments.

[0055] This application develops trajectory tracking control based on a vehicle dynamics model, considering the influence of multiple factors including the target trajectory and external environmental information. By discretizing key trajectory tracking points within the pre-aiming time range, the computational resource requirements are reduced and the real-time performance is improved, resulting in a multi-target lateral trajectory tracking optimization control method that considers future trajectory characteristics. By employing far, medium, and near discretized trajectory tracking points, the computational burden during trajectory tracking is effectively reduced, ensuring the real-time performance of the control system. Simultaneously, the trajectory tracking algorithm comprehensively considers the target trajectory and external environmental information, achieving a dynamic trade-off between multi-target constraints and significantly improving the safety of the tracking process. Furthermore, the lateral displacement and velocity differences between the vehicle trajectory and the target trajectory are introduced as optimization criteria during the control process to obtain the optimal lateral acceleration, thereby ensuring high-precision trajectory tracking. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a flowchart illustrating an embodiment of the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application;

[0058] Figure 2This is a flowchart illustrating an embodiment of the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application;

[0059] Figure 3 This is a flowchart illustrating an embodiment of the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application;

[0060] Figure 4 This is a flowchart illustrating an embodiment of the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application;

[0061] Figure 5 This is a flowchart illustrating an embodiment of the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application;

[0062] Figure 6 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device provided in an embodiment of this application;

[0063] Figure 7 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device provided in an embodiment of this application;

[0064] Figure 8 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device provided in an embodiment of this application;

[0065] Figure 9 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device provided in an embodiment of this application;

[0066] Figure 10 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device provided in an embodiment of this application;

[0067] Figure 11 This is a schematic block diagram of the system configuration of an electronic device provided in an embodiment of this application;

[0068] Figure 12 This is a flowchart illustrating a method for calculating comprehensive weight coefficients according to an embodiment of this application;

[0069] Figure 13 This is a logic block diagram of multi-target lateral trajectory tracking control provided in an embodiment of this application. Detailed Implementation

[0070] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments and their descriptions are used to explain this application, but are not intended to limit this application. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0071] The following describes the specific implementation process of the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application embodiment, taking the server as the execution subject as an example.

[0072] Figure 1 This is a flowchart illustrating an embodiment of the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application, as shown below. Figure 1 As shown, the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application includes:

[0073] S101: Obtain control input information for the autonomous vehicle; the control input information includes target planning trajectory information, vehicle status information, and external environment information.

[0074] S102: Construct a comprehensive weight coefficient model based on the target planning trajectory information and the external environment information;

[0075] S103: Generate effective tracking coordinate information based on the target planning trajectory information, the comprehensive weight coefficient model, the pre-constructed cumulative lateral displacement difference target model, and the pre-constructed cumulative lateral velocity difference target model;

[0076] S104: Generate the target steering wheel angle of the autonomous vehicle based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle.

[0077] from Figure 1 As shown in the flowchart, this application provides an optimized control method for multi-target lateral trajectory tracking in autonomous driving. This method acquires control input information from the autonomous vehicle, including target trajectory planning information, vehicle status information, and external environment information. A comprehensive weighting coefficient model is constructed based on the target trajectory planning information and the external environment information. Effective tracking coordinate information is generated based on the target trajectory planning information, the comprehensive weighting coefficient model, a pre-constructed cumulative lateral displacement difference target model, and a pre-constructed cumulative lateral velocity difference target model. The target steering wheel angle of the autonomous vehicle is generated based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle. This method achieves high-precision, robust, and real-time lateral tracking control of the autonomous vehicle in complex environments.

[0078] Each step is explained in detail below.

[0079] S101: Obtain control input information for the autonomous vehicle; the control input information includes target planning trajectory information, vehicle status information, and external environment information.

[0080] Specifically, the server first acquires the control input information of the autonomous vehicle, which includes target trajectory information, vehicle status information, and external environment information. The target trajectory information describes the path the vehicle intends to follow, including the coordinates of trajectory points and direction information. The vehicle status information reflects the vehicle's current position and speed, among other dynamic states. The external environment information describes factors in the vehicle's surrounding environment that may affect trajectory tracking.

[0081] S102: Construct a comprehensive weight coefficient model based on the target planning trajectory information and the external environment information;

[0082] Specifically, after acquiring the above information, the server constructs a comprehensive weighting coefficient model to quantify the importance of different trajectory points based on the target trajectory planning information and external environment information. This model is used to evaluate which aiming points or trajectory points are more worthy of attention under the current environment and trajectory structure during trajectory tracking control, so as to assign different control priorities.

[0083] Figure 2 This is a flowchart illustrating an embodiment of an autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application. The target planning trajectory information includes pre-aiming segment information and trajectory curvature information; as shown... Figure 2 As shown, S102 includes:

[0084] S201: Generate a first weight coefficient model based on the pre-aimed section information;

[0085] Specifically, the target planning trajectory information includes not only the basic location data of trajectory points, but also pre-aiming segment information and trajectory curvature information, which are used to support the construction and dynamic adjustment of subsequent weight coefficients.

[0086] The forward-aiming segment information refers to the trajectory segment extracted from the target planned trajectory, located within a certain time or distance range ahead of the vehicle's current position, used for forward-looking control. This segment can cover multiple future trajectory points, reflecting the path the vehicle will take and environmental characteristics in the short term.

[0087] The trajectory curvature information is obtained by calculating the curvature of each trajectory point within the pre-aiming section, and is used to measure the degree of curvature of the trajectory. The greater the trajectory curvature, the more drastic the trajectory change, and the more difficult the vehicle's steering control is in that area, thus requiring higher tracking control accuracy.

[0088] Based on the pre-aiming segment information and trajectory curvature information, the server further constructs a comprehensive weighting coefficient model. First, based on the time distance between the pre-aiming point and the vehicle, a first weighting coefficient model is constructed. This model reflects the impact of the distance between the trajectory point and the current vehicle position on control priority. Points closer to the vehicle have higher weights to ensure that the vehicle responds preferentially to upcoming control requests.

[0089] In one embodiment, the time interval between the pre-aiming point and the vehicle's position The shorter the time it takes for the vehicle to reach the aiming point, the closer the aiming point is to the vehicle. This has a significant impact, as the first weighting factor is [not specified]. The larger the selected value, the longer it takes for the vehicle to reach the aiming point, indicating that the aiming point is farther from the vehicle. (First weighting coefficient) The smaller the selected value, the more specific the first weight coefficient model is as shown in equation (1):

[0090] (1)

[0091] in, The time interval between the nearest preview point and the vehicle's position. The time interval between the farthest aiming point and the vehicle's position.

[0092] S202: Generate a second weighting coefficient model based on the trajectory curvature information and the pre-aiming segment information;

[0093] Specifically, the server constructs a second weighting coefficient model based on the magnitude of the trajectory curvature and the distribution of the curvature's location within the pre-aiming segment. This model reflects the impact of the trajectory's drastic changes on the required control response accuracy. The greater the curvature, the higher the required control accuracy, and the greater the weight of the corresponding trajectory points.

[0094] In one embodiment, influenced by the magnitude of trajectory curvature, a greater trajectory curvature at the aiming point indicates a more drastic trajectory change, and the second weighting coefficient... The larger the selected value, the smaller the trajectory curvature at the aiming point, indicating a smoother trajectory change. (Second weighting coefficient) The smaller the selected value, the more specific the second weighting coefficient model is as shown in equation (2):

[0095] (2)

[0096] Where k is the trajectory curvature, a parameter used to describe the degree of curvature of the trajectory curve. The larger the value, the more severe the curvature of the curve.

[0097] S203: Generate a third weighting coefficient model based on the external environment information and the pre-aimed section information;

[0098] Specifically, a third weighting coefficient model is constructed based on the correspondence between external environmental information (such as obstacle information) and the pre-aiming section position to describe the impact of environmental complexity on the trajectory control strategy.

[0099] Figure 3 This is a flowchart illustrating an embodiment of an autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application. The external environment information includes obstacle-trajectory distance information and obstacle-vehicle time distance information; such as Figure 3 As shown, S203 includes:

[0100] S301: Generate a first obstacle weight coefficient model based on the obstacle-trajectory distance information;

[0101] Specifically, the external environment information includes obstacle-trajectory distance information and obstacle-vehicle time distance information, which are used to characterize the spatiotemporal relationship between obstacles and the vehicle and target trajectory, thereby more precisely assessing the potential impact of obstacles on trajectory tracking safety.

[0102] The obstacle-track distance information includes the distance from the obstacle to the target tracking trajectory, the minimum permissible distance from the obstacle to the target tracking trajectory, and the maximum distance of interest from the obstacle to the target tracking trajectory. This reflects whether the obstacle is close to the trajectory the vehicle is about to travel on in the lateral direction. If the distance from the obstacle to the target tracking trajectory is less than the minimum permissible distance, the obstacle is considered to pose a high risk of interference to trajectory tracking, and the control attention of the corresponding trajectory point needs to be increased.

[0103] Obstacle-vehicle time-distance information refers to the time interval (i.e., distance) required for the vehicle to travel from its current position to the obstacle's location at the current speed and predicted path. A shorter time-distance indicates that the vehicle will approach the obstacle more quickly, requiring the control system to prepare for obstacle avoidance in advance. Therefore, this information can be used to identify areas with significant risks in the near future.

[0104] To construct a more reasonable weighting strategy, the server establishes two obstacle weighting coefficient models based on the two types of information mentioned above. First, based on the distance information between the obstacle and the trajectory, a first obstacle weighting coefficient model is constructed. In this model, the smaller the distance, the higher the weight assigned, in order to enhance the tracking accuracy and path constraint capability of the control system when the trajectory approaches an obstacle.

[0105] In one embodiment, when an obstacle enters the pre-aiming range, the obstacle weight is determined from two perspectives: the distance from the obstacle to the target tracking trajectory and the time distance between the obstacle and the vehicle. Regarding the distance from the obstacle to the target tracking trajectory, the closer the obstacle is to the target trajectory, the higher the first obstacle weight coefficient. The larger the value, the better the tracking accuracy of the vehicle at this point. The specific model of the first obstacle weight coefficient is shown in equation (3):

[0106] (3)

[0107] Where d is the distance from the obstacle to the target tracking trajectory, d1 is the minimum allowable distance from the obstacle to the target tracking trajectory, and d2 is the maximum distance of interest from the obstacle to the target tracking trajectory.

[0108] S302: Generate a second obstacle weight coefficient model based on the obstacle-vehicle time-distance information and the pre-aiming section information;

[0109] Specifically, the server constructs a second obstacle weighting coefficient model based on the time distance between the obstacle and the vehicle, as well as their positional relationship within the pre-aiming section. In this model, the smaller the time distance between the obstacle and the vehicle, and the closer the obstacle is to the current control window, the larger the weighting coefficient, thereby guiding the system to improve its response speed to short-term threats and its obstacle avoidance priority.

[0110] In one embodiment, regarding the time distance between the obstacle and the vehicle, a smaller time distance between the obstacle and the vehicle indicates that the obstacle is closer to the vehicle, and the second obstacle weighting coefficient is used. The larger the value, the better the tracking accuracy of the vehicle at this point. The specific model of the second obstacle weight coefficient is shown in equation (4):

[0111] (4)

[0112] in, This is the time interval between the obstacle and the vehicle's position.

[0113] S303: Construct the third weight coefficient model using the first obstacle weight coefficient model and the second obstacle weight coefficient model.

[0114] Specifically, by integrating the outputs of the two models mentioned above, a final third weighting coefficient model is formed, which serves as part of the input to the comprehensive weighting coefficient model. This enables the control system to have higher judgment and control flexibility when facing obstacle risks, thereby improving the safety and robustness of autonomous vehicles in complex traffic environments.

[0115] In one embodiment, taking into account both the distance from the obstacle to the target tracking trajectory and the time distance between the obstacle and the vehicle, the third weighting coefficient model is specifically shown in equation (5):

[0116] (5)

[0117] S204: Construct the comprehensive weight coefficient model using the first weight coefficient model, the second weight coefficient model, and the third weight coefficient model.

[0118] Specifically, by integrating the first weight coefficient model, the second weight coefficient model, and the third weight coefficient model, the final comprehensive weight coefficient model is constructed. This model will play a key role in subsequent trajectory error optimization and steering wheel control decisions, thereby achieving multi-objective dynamic trade-off control and improving the system's adaptability and safety response capability to complex environments.

[0119] In one embodiment, the process of calculating the comprehensive weighting coefficient is as follows: Figure 12 As shown, the comprehensive weighting coefficient model is specifically shown in equation (6):

[0120] (6)

[0121] S103: Generate effective tracking coordinate information based on the target planning trajectory information, the comprehensive weight coefficient model, the pre-constructed cumulative lateral displacement difference target model, and the pre-constructed cumulative lateral velocity difference target model;

[0122] Specifically, the server generates effective tracking coordinate information for trajectory control based on the target trajectory planning information, the comprehensive weight coefficient model, and the pre-built cumulative lateral displacement difference target model and cumulative lateral velocity difference target model. By minimizing the error between the vehicle trajectory and the target trajectory in the lateral displacement and velocity directions, and combining the weights for weighted optimization, a trajectory tracking point that better meets the needs of multiple objectives (such as the balance between accuracy and obstacle avoidance) is obtained.

[0123] Figure 4 This is a flowchart illustrating an embodiment of the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application, as shown below. Figure 4 As shown, S103 includes:

[0124] S401: Generate an effective tracking coordinate model using the cumulative lateral displacement difference target model and the cumulative lateral velocity difference target model; the cumulative lateral displacement difference target model is constructed based on the lateral displacement parameters of the target planned trajectory in the pre-aiming section and the lateral displacement parameters of the vehicle; the cumulative lateral velocity difference target model is constructed based on the lateral velocity parameters of the target planned trajectory in the pre-aiming section and the lateral velocity parameters of the vehicle.

[0125] Specifically, the server pre-constructs a target model for the cumulative lateral displacement difference based on the lateral displacement parameters of the planned trajectory within the pre-aiming section and the current lateral displacement parameters of the vehicle; simultaneously, it constructs a target model for the cumulative lateral velocity difference based on the lateral velocity parameters of the planned trajectory within the pre-aiming section and the current lateral velocity parameters of the vehicle. These two models together constitute the optimization objectives for the vehicle's lateral error, respectively measuring the differences between the vehicle and the ideal trajectory in terms of lateral position and lateral dynamic response.

[0126] Based on the above model, the server generates an effective tracking coordinate model. Under the premise of minimizing the lateral displacement difference and lateral velocity difference between the vehicle's trajectory and the target planned trajectory, the weights of the three trajectory tracking points (near, middle, and far) are weighed to obtain the effective tracking abscissa value.

[0127] In one embodiment, the cumulative lateral displacement difference target model It takes into account the time distance For any time interval τ within the vehicle, based on the vehicle's current lateral displacement y(t), the lateral displacement difference can be obtained by using a third-order spline curve to track the target trajectory. This difference is due to the vehicle's lateral acceleration. As a controllable variable, it can be utilized right The minimum value is obtained by taking the derivative. The target model for the cumulative lateral displacement difference is shown in equation (7):

[0128] (7)

[0129] In the formula, f(t+τ) is the lateral displacement of the target trajectory at time interval τ.

[0130] In one embodiment, the objective function for accumulating lateral velocity difference is... It takes into account the time distance Any time interval within Based on the vehicle's current lateral speed By using a third-order spline curve to track the target trajectory, the lateral velocity difference can be obtained, due to the lateral acceleration of the vehicle. As a controllable variable, it can be utilized right The minimum value is obtained by taking the derivative. The target model of the cumulative lateral velocity difference is shown in equation (8):

[0131] (8)

[0132] In the formula, Plan the lateral velocity of the target trajectory at time interval τ.

[0133] In one embodiment, the optimal value is obtained by combining equations (7) and (8), and the results are eliminated simultaneously. Considering the cumulative lateral displacement difference between the target planned trajectory and the vehicle's running trajectory in the target model and cumulative lateral velocity difference target model In the case of minimum value, the optimal lateral acceleration is obtained. Continuous effective tracking of the horizontal coordinate value f e(t), the effective tracking abscissa value is obtained by comprehensively considering the minimum lateral displacement difference and lateral velocity difference within the pre-aiming time range, combined with the weighting coefficient. The effective tracking coordinate model is shown in equation (9):

[0134] (9)

[0135] S402: Extract trajectory tracking point information from the target planned trajectory information;

[0136] Specifically, the server extracts multiple trajectory tracking point information from the target planned trajectory. These points are located within the pre-aiming time range and represent the positions that the vehicle should track in different predicted time periods.

[0137] In one embodiment, the distant tracking point is selected as the time interval. The target tracking point places greater emphasis on the smoothness of the vehicle during trajectory tracking; the nearby tracking point is selected based on time distance. The target tracking point places greater emphasis on the vehicle obstacle avoidance requirements during the trajectory tracking process; the tracking point in the middle is selected based on time distance. The target tracking point is used to balance vehicle smoothness and obstacle avoidance requirements.

[0138] S403: Calculate the comprehensive weight coefficient of the trajectory tracking point using the trajectory tracking point information and the comprehensive weight coefficient model;

[0139] Specifically, the server calculates the comprehensive weight coefficient for each selected trajectory tracking point using the constructed comprehensive weight coefficient model. This weight takes into account not only the trajectory geometry and environmental interference factors, but also the aiming distance and control priority, thus reflecting the relative importance of each trajectory point in the control process.

[0140] S404: Calculate the effective tracking coordinate information using the effective tracking coordinate model, the trajectory tracking point information, and the comprehensive weight coefficient of the trajectory tracking points.

[0141] Specifically, the server uses the aforementioned effective tracking coordinate model, trajectory tracking point information, and comprehensive weighting coefficients of the trajectory tracking points to calculate and generate effective tracking coordinate information. This takes into account the varying trajectory tracking requirements of different target trajectory tracking points and aims to improve computational speed. A weighting correction scheme for near, medium, and far tracking points is adopted, adjusting the continuous effective tracking horizontal coordinate value f. e (t) Discretization yields the discrete effective tracking abscissa value f. e (T i Effective tracking coordinate information is used as input to the controller. It represents the current optimal tracking point determined by the server after comprehensively considering the error optimization objective and multi-objective constraints, and is used to guide the vehicle in generating subsequent control commands.

[0142] In one embodiment, the effective tracking coordinate information after far-to-mid-to-near weight correction is calculated as shown in equation (10):

[0143] (10)

[0144] In the formula, T i Discrete time interval points, i.e., the time intervals of the selected trajectory tracking points. , , ;ω i This represents the magnitude of the weight coefficients corresponding to the discrete time interval points.

[0145] S104: Generate the target steering wheel angle of the autonomous vehicle based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle.

[0146] Specifically, based on the effective tracking coordinate information and the vehicle's state information, the target steering wheel angle of the autonomous vehicle is calculated and sent as the final control output command to the actuator, thereby driving the vehicle to perform precise trajectory tracking control. Through this method, the autonomous driving system can achieve dynamic, efficient, and accurate tracking of the planned trajectory in complex traffic environments, improving operational safety and stability.

[0147] In one embodiment, the multi-target lateral trajectory tracking control logic block diagram is as follows: Figure 13 As shown.

[0148] Figure 5 This is a flowchart illustrating an embodiment of the autonomous driving multi-target lateral trajectory tracking optimization control method provided in this application, as shown below. Figure 5 As shown, S104 includes:

[0149] S501: Calculate the target lateral acceleration of the autonomous vehicle using the effective tracking coordinate information and the vehicle status information;

[0150] Specifically, to achieve precise steering control of autonomous vehicles, the server further calculates the target steering wheel angle based on the generated valid tracking coordinate information and vehicle status information, which serves as the final control output command.

[0151] First, using effective tracking coordinate information and vehicle status information, the target lateral acceleration that the vehicle should achieve within the current control cycle is calculated. During this calculation, the server comprehensively considers the current lateral offset of the vehicle, its lateral motion state, and the position of the target tracking point, calculating the desired acceleration value that minimizes tracking error through a control law or mapping relationship. This acceleration value not only reflects the direction and intensity of the vehicle's required deflection but also indirectly reflects the requirements of multiple factors such as trajectory curvature and environmental complexity on the vehicle's dynamic response.

[0152] In one embodiment, influenced by the lateral displacement difference and the vehicle's lateral velocity, a larger lateral acceleration is required to reduce trajectory tracking error when the lateral displacement difference is large, and a smaller lateral acceleration can be appropriately reduced when the vehicle's lateral velocity is large to avoid lateral trajectory tracking overshoot. Simultaneously, the target lateral acceleration needs to consider the combined influence of the weights at different trajectory tracking points on the lateral displacement difference and the vehicle's lateral velocity, as shown in equation (11), which allows the calculation of the vehicle's target lateral acceleration. :

[0153] (11)

[0154] In the formula, k1 is the influence coefficient of lateral displacement difference on lateral acceleration; k2 is the influence coefficient of lateral velocity on lateral acceleration. Specifically, k1 and k2, which are affected by the weight of the trajectory tracking points, are:

[0155] (12)

[0156] S502: Calculate the target steering wheel angle based on the target lateral acceleration.

[0157] Specifically, based on the aforementioned target lateral acceleration, the required target steering wheel angle for the vehicle is further derived. This process incorporates calculations using the vehicle's dynamics model, such as a linear single-track model or a steering response model obtained through experimental fitting, to map the desired lateral acceleration into a steering wheel angle output value. To ensure control accuracy and response stability, the nonlinear characteristics of the vehicle's steering system and the hysteresis effect of the actuators can also be considered during this mapping process. The final generated target steering wheel angle can be directly used as a control command, outputting to the vehicle's steering execution system to drive the vehicle to achieve high-precision tracking of the target trajectory. This method effectively improves the vehicle's path control accuracy, response speed, and handling stability in dynamic scenarios, enhancing the adaptability of autonomous driving systems to complex traffic environments.

[0158] In one embodiment, in order to achieve real-time tracking of the vehicle's actual lateral acceleration to meet the target lateral acceleration requirement, the influence of vehicle dynamics and actuator hysteresis needs to be fully considered during the control response process.

[0159] The vehicle dynamics model was obtained through steering transient response tests, establishing the direct target steering wheel angle value. Lateral acceleration of the vehicle target The transfer function relationship is shown in equation (13).

[0160] (13)

[0161] In the formula, It is the steady-state gain of lateral acceleration; T1, T y1 The time constant for fitting the transfer function is obtained from experiments, and s is the Laplace transform variable.

[0162] Next, considering the effect of actuator inertia causing lag in the actuator response, the target steering wheel angle is obtained using a first-order differential element. As shown in equation (14).

[0163] (14)

[0164] Among them, T h The time constant is obtained by fitting the transfer function of the actuator's inertial response hysteresis.

[0165] This application provides an optimized control method for multi-target lateral trajectory tracking in autonomous driving. The method acquires control input information from the autonomous vehicle, including target trajectory planning information, vehicle status information, and external environment information. A comprehensive weighting coefficient model is constructed based on the target trajectory planning information and the external environment information. Effective tracking coordinate information is generated based on the target trajectory planning information, the comprehensive weighting coefficient model, a pre-constructed cumulative lateral displacement difference target model, and a pre-constructed cumulative lateral velocity difference target model. The target steering wheel angle of the autonomous vehicle is generated based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle. This method achieves high-precision, robust, and real-time lateral tracking control of the autonomous vehicle in complex environments.

[0166] Specifically, by acquiring control input information from the autonomous vehicle, including target trajectory information, vehicle status information, and external environment information, the system provides a multi-dimensional input foundation for the control system, including the global path, current vehicle status, and environmental perception, ensuring the comprehensiveness and real-time nature of subsequent control strategies. A comprehensive weighting coefficient model is constructed based on the target trajectory information and the external environment information to achieve dynamic evaluation and differentiated control of the importance of different aiming points, improving the control system's adaptability to complex scenarios and its ability to prioritize responses. Effective tracking coordinate information is generated based on the target trajectory information, the comprehensive weighting coefficient model, a pre-constructed cumulative lateral displacement difference target model, and a pre-constructed cumulative lateral velocity difference target model, optimizing tracking point selection and minimizing trajectory deviation, achieving a balance between trajectory tracking accuracy and vehicle dynamic behavior. Finally, the target steering wheel angle of the autonomous vehicle is generated based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle, achieving precise steering control based on minimizing trajectory error, and improving the vehicle's operational stability and safety in dynamic and complex environments.

[0167] This application develops trajectory tracking control based on a vehicle dynamics model, considering the influence of multiple factors including the target trajectory and external environmental information. By discretizing key trajectory tracking points within the pre-aiming time range, the computational resource requirements are reduced and the real-time performance is improved, resulting in a multi-target lateral trajectory tracking optimization control method that considers future trajectory characteristics. By employing far, medium, and near discretized trajectory tracking points, the computational burden during trajectory tracking is effectively reduced, ensuring the real-time performance of the control system. Simultaneously, the trajectory tracking algorithm comprehensively considers the target trajectory and external environmental information, achieving a dynamic trade-off between multi-target constraints and significantly improving the safety of the tracking process. Furthermore, the lateral displacement and velocity differences between the vehicle trajectory and the target trajectory are introduced as optimization criteria during the control process to obtain the optimal lateral acceleration, thereby ensuring high-precision trajectory tracking.

[0168] Based on the same inventive concept, this application also provides an autonomous driving multi-target lateral trajectory tracking optimization control device, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of the autonomous driving multi-target lateral trajectory tracking optimization control device in solving the problem is similar to that of the autonomous driving multi-target lateral trajectory tracking optimization control method, the implementation of the autonomous driving multi-target lateral trajectory tracking optimization control device can refer to the implementation of the software performance benchmark determination method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0169] Figure 6 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device according to an embodiment of this application, as shown below. Figure 6 As shown, the autonomous driving multi-target lateral trajectory tracking optimization control device provided in this application includes:

[0170] The information acquisition unit 601 is used to acquire control input information of the autonomous vehicle; the control input information includes target planning trajectory information, vehicle status information and external environment information.

[0171] The comprehensive weight coefficient model construction unit 602 is used to construct a comprehensive weight coefficient model based on the target planning trajectory information and the external environment information.

[0172] The effective tracking coordinate information generation unit 603 is used to generate effective tracking coordinate information based on the target planning trajectory information, the comprehensive weight coefficient model, the pre-constructed cumulative lateral displacement difference target model, and the pre-constructed cumulative lateral velocity difference target model.

[0173] The target steering wheel angle generation unit 604 is used to generate the target steering wheel angle of the autonomous vehicle based on the effective tracking coordinate information and the vehicle status information in order to control the autonomous vehicle.

[0174] Figure 7 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device according to an embodiment of this application. Figure 6 Based on the embodiments, further, such as Figure 7 As shown, the comprehensive weight coefficient model construction unit 602 includes:

[0175] The first weight coefficient model generation module 701 is used to generate a first weight coefficient model based on the pre-aiming segment information.

[0176] The second weighting coefficient model generation module 702 is used to generate a second weighting coefficient model based on the trajectory curvature information and the pre-aiming segment information.

[0177] The third weighting coefficient model generation module 703 is used to generate a third weighting coefficient model based on the external environment information and the pre-aiming section information.

[0178] The comprehensive weight coefficient model construction module 704 is used to construct the comprehensive weight coefficient model using the first weight coefficient model, the second weight coefficient model and the third weight coefficient model.

[0179] Figure 8 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device according to an embodiment of this application. Figure 7 Based on the embodiments, further, such as Figure 8 As shown, the third weighting coefficient model generation module 703 includes:

[0180] The first obstacle weight coefficient model generation submodule 801 is used to generate a first obstacle weight coefficient model based on the obstacle-trajectory distance information.

[0181] The second obstacle weight coefficient model generation submodule 802 is used to generate a second obstacle weight coefficient model based on the obstacle-vehicle time distance information and the pre-aiming section information.

[0182] The third weight coefficient model generation submodule 803 is used to construct the third weight coefficient model using the first obstacle weight coefficient model and the second obstacle weight coefficient model.

[0183] Figure 9 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device according to an embodiment of this application. Figure 6Based on the embodiments, further, such as Figure 9 As shown, the effective tracking coordinate information generation unit 603 includes:

[0184] The effective tracking coordinate model generation module 901 is used to generate an effective tracking coordinate model using the cumulative lateral displacement difference target model and the cumulative lateral velocity difference target model; the cumulative lateral displacement difference target model is constructed based on the lateral displacement parameters of the target planned trajectory in the pre-aiming section and the lateral displacement parameters of the vehicle; the cumulative lateral velocity difference target model is constructed based on the lateral velocity parameters of the target planned trajectory in the pre-aiming section and the lateral velocity parameters of the vehicle.

[0185] The trajectory tracking point information extraction module 902 is used to extract trajectory tracking point information from the target planned trajectory information;

[0186] The comprehensive weight coefficient calculation module 903 is used to calculate the comprehensive weight coefficient of the trajectory tracking point using the trajectory tracking point information and the comprehensive weight coefficient model.

[0187] The effective tracking coordinate information calculation module 904 is used to calculate the effective tracking coordinate information using the effective tracking coordinate model, the trajectory tracking point information, and the comprehensive weight coefficient of the trajectory tracking points.

[0188] Figure 10 This is a schematic diagram of the structure of an autonomous driving multi-target lateral trajectory tracking optimization control device according to an embodiment of this application. Figure 6 Based on the embodiments, further, such as Figure 10 As shown, the target steering wheel angle generation unit 604 includes:

[0189] The target lateral acceleration calculation module 1001 is used to calculate the target lateral acceleration of the autonomous vehicle using the effective tracking coordinate information and the vehicle state information;

[0190] The target steering wheel angle calculation module 1002 is used to calculate the target steering wheel angle based on the target lateral acceleration.

[0191] This application provides an optimized control method and apparatus for multi-target lateral trajectory tracking in autonomous driving. The method acquires control input information from the autonomous vehicle, including target trajectory planning information, vehicle status information, and external environment information. A comprehensive weighting coefficient model is constructed based on the target trajectory planning information and the external environment information. Effective tracking coordinate information is generated based on the target trajectory planning information, the comprehensive weighting coefficient model, a pre-constructed cumulative lateral displacement difference target model, and a pre-constructed cumulative lateral velocity difference target model. The target steering wheel angle of the autonomous vehicle is generated based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle. This achieves high-precision, robust, and real-time lateral tracking control of the autonomous vehicle in complex environments.

[0192] Specifically, by acquiring control input information from the autonomous vehicle, including target trajectory information, vehicle status information, and external environment information, the system provides a multi-dimensional input foundation for the control system, including the global path, current vehicle status, and environmental perception, ensuring the comprehensiveness and real-time nature of subsequent control strategies. A comprehensive weighting coefficient model is constructed based on the target trajectory information and the external environment information to achieve dynamic evaluation and differentiated control of the importance of different aiming points, improving the control system's adaptability to complex scenarios and its ability to prioritize responses. Effective tracking coordinate information is generated based on the target trajectory information, the comprehensive weighting coefficient model, a pre-constructed cumulative lateral displacement difference target model, and a pre-constructed cumulative lateral velocity difference target model, optimizing tracking point selection and minimizing trajectory deviation, achieving a balance between trajectory tracking accuracy and vehicle dynamic behavior. Finally, the target steering wheel angle of the autonomous vehicle is generated based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle, achieving precise steering control based on minimizing trajectory error, and improving the vehicle's operational stability and safety in dynamic and complex environments.

[0193] This application develops trajectory tracking control based on a vehicle dynamics model, considering the influence of multiple factors including the target trajectory and external environmental information. By discretizing key trajectory tracking points within the pre-aiming time range, the computational resource requirements are reduced and the real-time performance is improved, resulting in a multi-target lateral trajectory tracking optimization control method that considers future trajectory characteristics. By employing far, medium, and near discretized trajectory tracking points, the computational burden during trajectory tracking is effectively reduced, ensuring the real-time performance of the control system. Simultaneously, the trajectory tracking algorithm comprehensively considers the target trajectory and external environmental information, achieving a dynamic trade-off between multi-target constraints and significantly improving the safety of the tracking process. Furthermore, the lateral displacement and velocity differences between the vehicle trajectory and the target trajectory are introduced as optimization criteria during the control process to obtain the optimal lateral acceleration, thereby ensuring high-precision trajectory tracking.

[0194] From a hardware perspective, in order to address the problems in the prior art, this application provides an embodiment of an electronic device for implementing all or part of the aforementioned autonomous driving multi-target lateral trajectory tracking optimization control method. The electronic device specifically includes the following components:

[0195] The system comprises a processor, a memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to realize information transmission between the autonomous driving multi-target lateral trajectory tracking optimization control device and core business systems, user terminals, and related databases and other related devices; the logic controller can be a desktop computer, tablet computer, or mobile terminal, etc., and this embodiment is not limited to these. In this embodiment, the logic controller can be implemented with reference to the embodiments of the autonomous driving multi-target lateral trajectory tracking optimization control method and the autonomous driving multi-target lateral trajectory tracking optimization control device, the contents of which are incorporated herein by reference, and repeated details will not be described again.

[0196] It is understood that the user terminal may include smartphones, tablet computers, network set-top boxes, portable computers, desktop computers, personal digital assistants (PDAs), in-vehicle devices, smart wearable devices, etc. Among these, the smart wearable devices may include smart glasses, smartwatches, smart bracelets, etc.

[0197] In practical applications, parts of the autonomous driving multi-target lateral trajectory tracking optimization control method can be executed on the electronic device side as described above, or all operations can be completed in the client device. The choice can be made based on the processing power of the client device and the limitations of the user's usage scenario. This application does not impose any limitations on this. If all operations are completed in the client device, the client device may further include a processor.

[0198] The aforementioned client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission. The server may include a server on the task scheduling center side; in other implementation scenarios, it may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a distributed server structure.

[0199] Figure 11 This is a schematic block diagram illustrating the system configuration of the electronic device 9600 according to an embodiment of this application. Figure 11 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that... Figure 11 This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0200] In one embodiment, the autonomous driving multi-target lateral trajectory tracking optimization control method function can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:

[0201] S101: Obtain control input information for the autonomous vehicle; the control input information includes target planning trajectory information, vehicle status information, and external environment information.

[0202] S102: Construct a comprehensive weight coefficient model based on the target planning trajectory information and the external environment information;

[0203] S103: Generate effective tracking coordinate information based on the target planning trajectory information, the comprehensive weight coefficient model, the pre-constructed cumulative lateral displacement difference target model, and the pre-constructed cumulative lateral velocity difference target model;

[0204] S104: Generate the target steering wheel angle of the autonomous vehicle based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle.

[0205] As described above, the autonomous driving multi-target lateral trajectory tracking optimization control method and device provided in this application, considering the influence of multiple factors such as the target planned trajectory and external environmental information, develops trajectory tracking control based on the vehicle dynamics model. By discretizing and obtaining key trajectory tracking points within the pre-aiming time range, the computational resource requirements can be reduced and the real-time performance can be improved, resulting in a multi-target lateral trajectory tracking optimization control method that considers future trajectory characteristics. By using far, medium, and near discretized trajectory tracking points, the computational burden in the trajectory tracking process is effectively reduced, ensuring the real-time performance of the control system. At the same time, the trajectory tracking algorithm comprehensively considers the target planned trajectory and external environmental information, realizing a dynamic trade-off for multi-target constraints, significantly improving the safety of the tracking process. In addition, the lateral displacement difference and velocity difference between the vehicle trajectory and the target trajectory are introduced as optimization criteria during the control process to obtain the optimal lateral acceleration, thereby ensuring high-precision execution of trajectory tracking.

[0206] In another embodiment, the autonomous driving multi-target lateral trajectory tracking optimization control device can be configured separately from the central processing unit 9100. For example, the data composite transmission device autonomous driving multi-target lateral trajectory tracking optimization control device can be configured as a chip connected to the central processing unit 9100, and the function of the autonomous driving multi-target lateral trajectory tracking optimization control method can be realized through the control of the central processing unit.

[0207] like Figure 11 As shown, the electronic device 9600 may also include: a communication module (transmitter / receiver) 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily need to include these components. Figure 11 All components shown; in addition, the electronic device 9600 may also include Figure 11 For components not shown, please refer to existing technologies.

[0208] like Figure 11 As shown, the central processing unit 9100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device, which receives inputs and controls the operation of various components of the electronic device 9600.

[0209] The memory 9140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 9100 may execute the program stored in the memory 9140 to perform information storage or processing, etc.

[0210] Input unit 9120 provides input to central processing unit 9100. Input unit 9120 may be, for example, a keypad or touch input device. Power supply 9170 provides power to electronic device 9600. Display 9160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0211] The memory 9140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 via the central processing unit 9100.

[0212] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0213] The communication module (transmitter / receiver) 9110 is the communication module (transmitter / receiver) 9110 that transmits and receives signals via the antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processing unit 9100 to provide input signals and receive output signals, which is the same as in a conventional mobile communication terminal.

[0214] Based on different communication technologies, multiple communication modules (transmitters / receivers) 9110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby realizing typical telecommunications functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 9130 is also coupled to a central processing unit 9100, enabling on-device recording via the microphone 9132 and on-device playback of stored sound via the speaker 9131.

[0215] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the autonomous driving multi-target lateral trajectory tracking optimization control method with a server or client as the execution subject in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the autonomous driving multi-target lateral trajectory tracking optimization control method with a server or client as the execution subject in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0216] S101: Obtain control input information for the autonomous vehicle; the control input information includes target planning trajectory information, vehicle status information, and external environment information.

[0217] S102: Construct a comprehensive weight coefficient model based on the target planning trajectory information and the external environment information;

[0218] S103: Generate effective tracking coordinate information based on the target planning trajectory information, the comprehensive weight coefficient model, the pre-constructed cumulative lateral displacement difference target model, and the pre-constructed cumulative lateral velocity difference target model;

[0219] S104: Generate the target steering wheel angle of the autonomous vehicle based on the effective tracking coordinate information and the vehicle status information to control the autonomous vehicle.

[0220] As described above, the autonomous driving multi-target lateral trajectory tracking optimization control method and device provided in this application, considering the influence of multiple factors such as the target planned trajectory and external environmental information, develops trajectory tracking control based on the vehicle dynamics model. By discretizing and obtaining key trajectory tracking points within the pre-aiming time range, the computational resource requirements can be reduced and the real-time performance can be improved, resulting in a multi-target lateral trajectory tracking optimization control method that considers future trajectory characteristics. By using far, medium, and near discretized trajectory tracking points, the computational burden in the trajectory tracking process is effectively reduced, ensuring the real-time performance of the control system. At the same time, the trajectory tracking algorithm comprehensively considers the target planned trajectory and external environmental information, realizing a dynamic trade-off for multi-target constraints, significantly improving the safety of the tracking process. In addition, the lateral displacement difference and velocity difference between the vehicle trajectory and the target trajectory are introduced as optimization criteria during the control process to obtain the optimal lateral acceleration, thereby ensuring high-precision execution of trajectory tracking.

[0221] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0222] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0223] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0224] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0225] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. An automatic driving multi-target lateral trajectory tracking optimization control method, characterized in that, The method comprises the following steps: acquiring control input information of an autonomous vehicle; the control input information comprises target planning trajectory information, self-vehicle state information and external environment information; constructing a comprehensive weight coefficient model according to the target planning trajectory information and the external environment information; generating effective tracking coordinate information according to the target planning trajectory information, the comprehensive weight coefficient model, a pre-constructed cumulative lateral displacement difference target model and a pre-constructed cumulative lateral velocity difference target model between the target planning trajectory and the self-vehicle running trajectory; generating a target steering wheel angle of the autonomous vehicle according to the effective tracking coordinate information and the self-vehicle state information to control the autonomous vehicle; the target planning trajectory information comprises pre-look-ahead section information and trajectory curvature information; the step of constructing the comprehensive weight coefficient model according to the target planning trajectory information and the external environment information comprises the following steps: generating a first weight coefficient model according to the pre-look-ahead section information; generating a second weight coefficient model according to the trajectory curvature information and the pre-look-ahead section information; generating a third weight coefficient model according to the external environment information and the pre-look-ahead section information; constructing the comprehensive weight coefficient model by using the first weight coefficient model, the second weight coefficient model and the third weight coefficient model; the external environment information comprises obstacle-trajectory distance information and obstacle-self-vehicle time-distance information; the step of generating the third weight coefficient model according to the external environment information and the pre-look-ahead section information comprises the following steps: generating a first obstacle weight coefficient model according to the obstacle-trajectory distance information; generating a second obstacle weight coefficient model according to the obstacle-self-vehicle time-distance information and the pre-look-ahead section information; constructing the third weight coefficient model by using the first obstacle weight coefficient model and the second obstacle weight coefficient model.

2. The automatic driving multi-target lateral trajectory tracking optimization control method according to claim 1, characterized in that, the step of generating the effective tracking coordinate information according to the target planning trajectory information, the comprehensive weight coefficient model, the pre-constructed cumulative lateral displacement difference target model and the pre-constructed cumulative lateral velocity difference target model comprises the following steps: generating an effective tracking coordinate model by using the cumulative lateral displacement difference target model and the cumulative lateral velocity difference target model; the cumulative lateral displacement difference target model is constructed based on a lateral displacement parameter of the target planning trajectory in the pre-look-ahead section and a lateral displacement parameter of the self-vehicle; the cumulative lateral velocity difference target model is constructed based on a lateral velocity parameter of the target planning trajectory in the pre-look-ahead section and a lateral velocity parameter of the self-vehicle; extracting trajectory tracking point information from the target planning trajectory information; calculating a comprehensive weight coefficient of the trajectory tracking point by using the trajectory tracking point information and the comprehensive weight coefficient model; calculating the effective tracking coordinate information by using the effective tracking coordinate model, the trajectory tracking point information and the comprehensive weight coefficient of the trajectory tracking point.

3. The automatic driving multi-target lateral trajectory tracking optimization control method according to claim 1, characterized in that, the step of generating the target steering wheel angle of the autonomous vehicle according to the effective tracking coordinate information and the self-vehicle state information to control the autonomous vehicle comprises the following steps: calculating a target lateral acceleration of the autonomous vehicle by using the effective tracking coordinate information and the self-vehicle state information; The target steering wheel angle is calculated according to the target lateral acceleration.

4. An automatic driving multi-target lateral trajectory tracking optimization control device, characterized by, The method comprises the steps of: an information acquisition unit configured to acquire control input information of an autonomous vehicle; the control input information comprises target planning trajectory information, self-vehicle state information and external environment information; a comprehensive weight coefficient model construction unit configured to construct a comprehensive weight coefficient model according to the target planning trajectory information and the external environment information; an effective tracking coordinate information generation unit configured to generate effective tracking coordinate information according to the target planning trajectory information, the comprehensive weight coefficient model, a pre-constructed cumulative lateral displacement difference target model between a target planning trajectory and a self-vehicle running trajectory and a pre-constructed cumulative lateral velocity difference target model; a target steering wheel angle generation unit configured to generate a target steering wheel angle of the autonomous vehicle according to the effective tracking coordinate information and the self-vehicle state information to control the autonomous vehicle; the target planning trajectory information comprises preview section information and trajectory curvature information; the comprehensive weight coefficient model construction unit comprises: a first weight coefficient model generation module configured to generate a first weight coefficient model according to the preview section information; a second weight coefficient model generation module configured to generate a second weight coefficient model according to the trajectory curvature information and the preview section information; a third weight coefficient model generation module configured to generate a third weight coefficient model according to the external environment information and the preview section information; a comprehensive weight coefficient model construction module configured to construct the comprehensive weight coefficient model by using the first weight coefficient model, the second weight coefficient model and the third weight coefficient model; the external environment information comprises obstacle-trajectory distance information and obstacle-self-vehicle time-distance information; the third weight coefficient model generation module comprises: a first obstacle weight coefficient model generation submodule configured to generate a first obstacle weight coefficient model according to the obstacle-trajectory distance information; a second obstacle weight coefficient model generation submodule configured to generate a second obstacle weight coefficient model according to the obstacle-self-vehicle time-distance information and the preview section information; a third weight coefficient model generation submodule configured to construct the third weight coefficient model by using the first obstacle weight coefficient model and the second obstacle weight coefficient model.

5. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the method of any one of claims 1 to 3.

6. A computer readable storage medium characterized by, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the method of any one of claims 1 to 3.

7. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to realize the method of any one of claims 1 to 3.

Images