Lateral control method, device and equipment for autonomous vehicle and storage medium

Abstract

The invention provides a transverse control method, device and equipment of an automatic driving vehicle and a storage medium, and relates to the technical field of automatic driving, and the method comprises the steps: obtaining the variance of the steering control quantity of the automatic driving vehicle in a preset number of continuous control periods, the steering control quantity being obtained through LQR based on the driving information of the automatic driving vehicle, the LQR is obtained based on a vehicle dynamics model; according to the variance, determining whether to adjust a weighting matrix R of the LQR; if yes, adjusting a weighting matrix R of the LQR according to the variance to obtain an adjusted weighting matrix R '; and according to the adjusted weighting matrix R'and the driving information of the automatic driving vehicle, the target steering control quantity of the automatic driving vehicle is obtained through the LQR, so that a steering actuator of the automatic driving vehicle is controlled to execute the target steering control quantity. The problem of shaking of the steering wheel can be effectively solved, and the driving stability and comfort of the whole vehicle are improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a lateral control method, device, equipment and storage medium for an autonomous driving vehicle. Background Art

[0002] The lateral control method of an autonomous vehicle refers to the technology used to control the autonomous vehicle to maintain the correct lane position on the road. It mainly involves controlling the steering system of the autonomous vehicle to ensure that the autonomous vehicle travels along the predetermined path and ensures driving stability and comfort.

[0003] At present, in some scenarios, when performing lateral control on an autonomous driving vehicle, there is a problem of large shaking of the steering wheel of the autonomous driving vehicle. Therefore, an effective solution for lateral control of the autonomous driving vehicle is urgently needed. Summary of the invention

[0004] The purpose of the present invention is to provide a lateral control method, device, equipment and storage medium for an autonomous driving vehicle to solve the problem of large steering wheel shaking of the autonomous driving vehicle when the autonomous driving vehicle is laterally controlled in some scenarios.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A lateral control method for an autonomous driving vehicle comprises: obtaining a variance of a steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles, wherein the steering control amount is obtained through a linear quadratic regulator LQR based on driving information of the autonomous driving vehicle, and the LQR is obtained based on a vehicle dynamics model; determining whether to adjust a weighted matrix R of the LQR according to the variance; if so, adjusting the weighted matrix R of the LQR according to the variance to obtain an adjusted weighted matrix R ′ ; According to the adjusted weight matrix R ′ and the driving information of the autonomous driving vehicle, and obtain the target steering control amount of the autonomous driving vehicle through LQR to control the steering actuator of the autonomous driving vehicle to execute the target steering control amount.

[0007] According to the above technical means, based on the variance of the steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles, the weighting matrix R of LQR is dynamically adjusted, so that according to the adjusted weighting matrix R ′And the driving information of the autonomous driving vehicle, the target steering control amount of the autonomous driving vehicle is obtained through LQR, so as to control the steering actuator of the autonomous driving vehicle to execute the target steering control amount; it can effectively reduce the problem of steering wheel shaking, especially in the case of large changes in path curvature. The target steering control amount obtained by LQR is smoother, thereby improving the driving stability and comfort of the whole vehicle.

[0008] Further, according to the variance, determining whether to adjust the weighting matrix R of the LQR includes: if the variance is greater than or equal to the angle threshold, determining to adjust the weighting matrix R of the LQR; if the variance is less than the angle threshold, determining not to adjust the weighting matrix R of the LQR.

[0009] Further, according to the variance, the weight matrix R of LQR is adjusted to obtain the adjusted weight matrix R ′ , including: the adjusted weight matrix R ′ Satisfies the following formula:

[0010] R ′ =min(R*(σ 2 -threshold)*a,b)

[0011] Among them, σ 2 represents variance; threshold represents angle threshold; a represents scaling factor; b represents the upper limit of weighting matrix R.

[0012] Furthermore, the driving information includes vehicle state information, vehicle planned trajectory and vehicle position information of the autonomous driving vehicle, and the steering control amount is obtained in the following manner: coordinate transformation is performed according to the vehicle position information and the vehicle planned trajectory to obtain a local path in the vehicle body coordinate system corresponding to the autonomous driving vehicle; based on the vehicle state information, vehicle position information and local path, the steering control amount is obtained through LQR.

[0013] Furthermore, based on the vehicle state information, the vehicle position information and the local path, the steering control amount is obtained through LQR, including: determining the lateral deviation and heading deviation corresponding to the autonomous driving vehicle according to the vehicle position information and the local path; based on the vehicle state information, the lateral deviation and the heading deviation, the steering control amount is obtained through LQR.

[0014] Furthermore, the vehicle dynamics model is determined based on the lateral deviation, the heading deviation and the vehicle state information, and the vehicle state information includes the front wheel cornering stiffness, the rear wheel cornering stiffness, the moment of inertia, the distance from the center of mass to the front axle, the distance from the center of mass to the rear axle, the mass of the autonomous driving vehicle, the longitudinal speed and the front wheel turning angle.

[0015] Furthermore, the lateral deviation and the heading deviation are the lateral deviation and the heading deviation at a preset distance in front of the center of the rear axle of the autonomous driving vehicle.

[0016] Furthermore, the vehicle body coordinate system takes the center point of the rear axle of the autonomous driving vehicle as its origin.

[0017] A lateral control device for an autonomous driving vehicle, comprising:

[0018] A first acquisition module is used to obtain the variance of the steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles, where the steering control amount is obtained based on the driving information of the autonomous driving vehicle through a linear quadratic regulator LQR, where the LQR is obtained based on a vehicle dynamics model;

[0019] A determination module, used for determining whether to adjust the weight matrix R of the LQR according to the variance;

[0020] The adjustment module is used to adjust the weight matrix R of LQR according to the variance to obtain the adjusted weight matrix R ′ ;

[0021] The second acquisition module is used to adjust the weight matrix R ′ and the driving information of the autonomous driving vehicle, and obtain the target steering control amount of the autonomous driving vehicle through LQR to control the steering actuator of the autonomous driving vehicle to execute the target steering control amount.

[0022] Further, the determination module is specifically used to: if the variance is greater than or equal to the angle threshold, determine to adjust the weighted matrix R of the LQR; if the variance is less than the angle threshold, determine not to adjust the weighted matrix R of the LQR.

[0023] Furthermore, the adjustment module is specifically used to: adjust the weight matrix R ′ Satisfies the following formula:

[0024] R ′ =min(R*(σ 2 -threshold)*a,b)

[0025] Among them, σ 2 represents variance; threshold represents angle threshold; a represents scaling factor; b represents the upper limit of weighting matrix R.

[0026] Furthermore, the driving information includes vehicle status information, vehicle planned trajectory and vehicle position information of the autonomous driving vehicle. The lateral control device of the autonomous driving vehicle also includes a third acquisition module, which is used to obtain the steering control amount in the following manner: coordinate conversion is performed according to the vehicle position information and the vehicle planned trajectory to obtain the local path in the vehicle body coordinate system corresponding to the autonomous driving vehicle; based on the vehicle status information, vehicle position information and the local path, the steering control amount is obtained through LQR.

[0027] Furthermore, when the third acquisition module is used to acquire the steering control amount through LQR based on the vehicle status information, the vehicle position information and the local path, it is specifically used to: determine the lateral deviation and heading deviation corresponding to the autonomous driving vehicle according to the vehicle position information and the local path; acquire the steering control amount through LQR based on the vehicle status information, the lateral deviation and the heading deviation.

[0028] Furthermore, the vehicle dynamics model is determined based on the lateral deviation, the heading deviation and the vehicle state information, and the vehicle state information includes the front wheel cornering stiffness, the rear wheel cornering stiffness, the moment of inertia, the distance from the center of mass to the front axle, the distance from the center of mass to the rear axle, the mass of the autonomous driving vehicle, the longitudinal speed and the front wheel turning angle.

[0029] Furthermore, the lateral deviation and the heading deviation are the lateral deviation and the heading deviation at a preset distance in front of the center of the rear axle of the autonomous driving vehicle.

[0030] Furthermore, the vehicle body coordinate system takes the center point of the rear axle of the autonomous driving vehicle as its origin.

[0031] A vehicle comprises a vehicle body, front wheels and rear wheels, wherein the vehicle body is arranged between the front wheels and the rear wheels; the vehicle also comprises a lateral control device of the automatic driving vehicle as described above in the present invention arranged on the vehicle body.

[0032] An electronic device comprises: a processor, and a memory connected to the processor in communication; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the lateral control method of the autonomous driving vehicle as described above in the present invention.

[0033] A computer-readable storage medium stores computer program instructions, which, when executed, implement the lateral control method of the autonomous driving vehicle as described above in the present invention.

[0034] A computer program product includes a computer program, and when the computer program is executed, the lateral control method of the autonomous driving vehicle as described above in the present invention is implemented.

[0035] Beneficial effects of the present invention: The lateral control method, device, equipment and storage medium of the autonomous driving vehicle provided by the present invention dynamically adjust the weighting matrix R of LQR according to the variance of the steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles; thereby, according to the adjusted weighting matrix R ′And the driving information of the autonomous driving vehicle, the target steering control amount of the autonomous driving vehicle is obtained through LQR, so as to control the steering actuator of the autonomous driving vehicle to execute the target steering control amount; it can effectively reduce the problem of steering wheel shaking, especially when the path curvature changes greatly. The target steering control amount obtained by LQR is smoother, thereby improving the driving stability and comfort of the whole vehicle, and at the same time, the computing power requirements for the hardware are also low. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of the global path of an autonomous vehicle in a garage provided for related technologies;

[0037] Figure 2 A schematic diagram of an autonomous vehicle meeting another vehicle in an underground garage provided for related technologies;

[0038] Figure 3 A schematic diagram of an application scenario provided by an embodiment of the present invention;

[0039] Figure 4 A flowchart of a lateral control method for an autonomous driving vehicle provided by an embodiment of the present invention;

[0040] Figure 5 A flowchart of a method for obtaining a steering control amount of an automatic driving vehicle provided by an embodiment of the present invention;

[0041] Figure 6 A schematic diagram of coordinate conversion provided by an embodiment of the present invention;

[0042] Figure 7 A schematic diagram of the structure of a lateral control device for an autonomous driving vehicle provided by an embodiment of the present invention;

[0043] Figure 8 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0045] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0046] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and corresponding operation entrances shall be provided for users to choose to authorize or refuse.

[0047] The lateral control method of an autonomous vehicle can control the steering system of the autonomous vehicle to ensure that the autonomous vehicle travels along the predetermined path and ensures driving stability and comfort. There are many different lateral control methods for autonomous vehicles, and common lateral control methods include proportional-integral-derivative controller (PID), LQR, model predictive control (MPC), and pure tracking control.

[0048] At present, the following method is usually used to control the lateral direction of the autonomous driving vehicle: determine the optimal matrix according to LQR, and control the steering actuator of the autonomous driving vehicle to execute the steering control amount obtained by multiplying the optimal matrix and the state matrix. However, in some scenarios, such as the autonomous driving scenario in the underground garage, due to the complex roads in the underground garage, most of the garage roads have a small turning radius, and at the same time, oncoming vehicles and parking of vehicles in front will cause large changes in the local path curvature. Therefore, by using the above method to control the lateral direction of the autonomous driving vehicle, the steering wheel of the autonomous driving vehicle often switches frequently between small angles and large angles, and there is a problem of large steering wheel shaking, which in turn affects the riding experience and comfort.

[0049] In one example, Figure 1 A schematic diagram of the global path of an autonomous vehicle in a garage provided for related technologies, such as Figure 1 As shown, 101 is the global path of the autonomous vehicle in the garage. Due to the complex environment of the garage, the autonomous vehicle often makes large-angle turns, which easily causes the steering wheel to shake, affecting the riding comfort. In another example, Figure 2 A schematic diagram of an autonomous driving vehicle meeting another vehicle in an underground garage provided for related technologies, such as Figure 2As shown, due to the relatively narrow roads and small path curvature radius of the underground garage, the path curvature provided by the local path planning of the autonomous driving vehicle (i.e., this vehicle) varies greatly, resulting in a sudden change in the steering wheel, which can easily cause the steering wheel to shake.

[0050] In addition, LQR is a widely used control method for lateral control of autonomous vehicles, but it has the disadvantages of poor robustness and overshoot when the curvature of the trajectory changes rapidly, which is mainly manifested in large shaking of the steering wheel. This will cause body instability when the autonomous vehicle is traveling at a high speed, affecting the riding experience and comfort.

[0051] Based on the above problems, the present invention provides a lateral control method for an autonomous driving vehicle, which dynamically adjusts the weighted matrix R of LQR based on the variance of the steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles, so as to effectively reduce the problem of steering wheel shaking, especially in the case of large changes in path curvature. The output of LQR control can be made smoother, thereby improving the driving stability and comfort of the entire vehicle; at the same time, the computing power requirements for the hardware are relatively low.

[0052] It can be seen that the present invention can be applied to the Automated Valet Parking (AVP) system, and its main application scenario is the underground garage. The present invention can be applied to the lateral control of complex garage environments, and can ensure the stability of the steering wheel of the autonomous driving vehicle when the path curvature changes greatly, thereby improving the driving stability of the autonomous driving vehicle.

[0053] In the following, the application scenario of the solution provided by the present invention is firstly described by way of example.

[0054] Figure 3 Schematic diagram of an application scenario provided by an embodiment of the present invention. Figure 3 As shown, in this application scenario, when the autonomous driving vehicle automatically parks in an underground garage, the target steering control amount is obtained according to the lateral control method of the autonomous driving vehicle provided by the present invention, and the steering actuator of the autonomous driving vehicle is controlled to execute the target steering control amount, so that the autonomous driving vehicle smoothly enters the parking space and completes the parking process.

[0055] It should be noted that Figure 3 This is only a schematic diagram of an application scenario provided by an embodiment of the present invention. Figure 3 does not limit the equipment included in Figure 3 The positional relationship between the devices is limited.

[0056] The technical solution of the present invention is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0057] Figure 4 A flowchart of a lateral control method for an autonomous driving vehicle provided by an embodiment of the present invention. The lateral control method for an autonomous driving vehicle may be executed by software and / or hardware devices. For example, the hardware device may be a lateral control device for an autonomous driving vehicle, and the lateral control device for an autonomous driving vehicle may be an electronic device or a processing chip in an electronic device. Figure 4 As shown, the method of the embodiment of the present invention includes:

[0058] S401. Obtain the variance of the steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles, where the steering control amount is obtained based on driving information of the autonomous driving vehicle through LQR, and the LQR is obtained based on a vehicle dynamics model.

[0059] In the embodiment of the present invention, the preset number is, for example, 10. It can be understood that if the preset number is too small, the change trend of the steering control amount (steering wheel angle) may not be accurately obtained, and the obtained variance may also be a random deviation. The control period is, for example, 10ms. The driving information of the autonomous driving vehicle may include, for example, the vehicle state information, the vehicle planning trajectory and the vehicle position information of the autonomous driving vehicle, wherein the vehicle state information may include, for example, the longitudinal speed of the autonomous driving vehicle, the state of the whole vehicle, etc.; the vehicle planning trajectory is obtained based on the current path and the environmental information of the autonomous driving vehicle, and the environmental information of the autonomous driving vehicle may include, for example, the perception information obtained by forward vision, perimeter vision, surround vision and two laser radars arranged on both sides of the front of the vehicle, and output free space (FS) points (i.e., passable boundary points), target information (such as vehicle information in front of the autonomous driving vehicle, meeting information, etc.) and ultrasonic ranging information after sensor fusion processing; the vehicle position information is the vehicle positioning information, such as the latitude and longitude of the current point output by the global positioning system (GPS), and the plane coordinate points obtained by internal conversion. LQR is obtained based on the vehicle dynamics model. For the specific vehicle dynamics model and how to obtain LQR based on the vehicle dynamics model, please refer to the subsequent embodiments. The steering control amount can be obtained through LQR based on the driving information of the autonomous driving vehicle. For how to obtain the steering control amount, please refer to the subsequent embodiments.

[0060] In this step, for example, the steering control amount of the autonomous driving vehicle in 10 consecutive control cycles can be obtained, and the variance of the steering control amount in the 10 consecutive control cycles can be obtained. It can be understood that the variance of the steering control amount in the 10 consecutive control cycles can be obtained in sequence in a sliding window manner according to the chronological order.

[0061] S402: Determine whether to adjust the weighting matrix R of LQR according to the variance.

[0062] It can be understood that the control parameters of LQR include weighting matrix R and weighting matrix Q. The embodiment of the present invention adjusts the weighting matrix R of LQR. In this step, after the variance is obtained, it can be determined whether to adjust the weighting matrix R of LQR according to the variance.

[0063] Further, optionally, determining whether to adjust the weighting matrix R of the LQR according to the variance may include: if the variance is greater than or equal to an angle threshold, determining to adjust the weighting matrix R of the LQR; if the variance is less than the angle threshold, determining not to adjust the weighting matrix R of the LQR.

[0064] For example, the angle threshold is 200 degrees. If the variance is greater than or equal to 200 degrees, the weighted matrix R of the LQR is adjusted; if the variance is less than 200 degrees, the weighted matrix R of the LQR is not adjusted, that is, R = [1], which can ensure the tracking accuracy of the lateral error and heading error of the autonomous driving vehicle.

[0065] S403: If yes, adjust the weight matrix R of LQR according to the variance to obtain the adjusted weight matrix R ′ .

[0066] In this step, after determining the weighted matrix R of the adjusted LQR, the weighted matrix R of the LQR can be adjusted according to the variance to obtain the adjusted weighted matrix R ′ .

[0067] Further, optionally, the adjusted weight matrix R ′ Satisfy the following formula 1:

[0068] R ′ =min(R*(σ 2 -threshold)*a,b) Formula 1

[0069] Among them, σ 2 represents variance; threshold represents angle threshold; a represents scaling factor; b represents the upper limit of weighting matrix R.

[0070] For example, if threshold is 200 degrees, a is 1 / 50, and b is 15, then the weight matrix R and variance σ of LQR are2 Enter the above formula 1 to get the adjusted weight matrix R ′ It can be understood that when the weighted matrix R is increased, the requested angle of the steering wheel of the autonomous driving vehicle will be smoother, thereby improving the comfort of lateral control. The embodiment of the present invention recommends that the threshold is 200 degrees, a is 1 / 50, and b is 15.

[0071] S404, according to the adjusted weight matrix R ′ and the driving information of the autonomous driving vehicle, and obtain the target steering control amount of the autonomous driving vehicle through LQR to control the steering actuator of the autonomous driving vehicle to execute the target steering control amount.

[0072] In this step, after obtaining the adjusted weight matrix R ′ After that, the weight matrix R of LQR can be replaced by the adjusted weight matrix R ′ , so that according to the adjusted weight matrix R ′ The target steering control amount of the autonomous vehicle is obtained through LQR based on the driving information of the autonomous vehicle. After the target steering control amount is obtained, the target steering control amount can be output to the steering actuator of the autonomous vehicle through the Controller Area Network (CAN) bus, thereby controlling the steering actuator to execute the target steering control amount, effectively reducing the problem of steering wheel shaking, improving the smoothness and comfort of the whole vehicle, and at the same time, the computing power requirements of the hardware are also relatively low.

[0073] The lateral control method of the autonomous driving vehicle provided in the embodiment of the present invention dynamically adjusts the weighting matrix R of LQR according to the variance of the steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles; thereby, according to the adjusted weighting matrix R ′ And the driving information of the autonomous driving vehicle, the target steering control amount of the autonomous driving vehicle is obtained through LQR, so as to control the steering actuator of the autonomous driving vehicle to execute the target steering control amount; it can effectively reduce the problem of steering wheel shaking, especially when the path curvature changes greatly. The target steering control amount obtained by LQR is smoother, thereby improving the driving stability and comfort of the whole vehicle, and at the same time, the computing power requirements for the hardware are also low.

[0074] Based on the above embodiments, Figure 5 This is a flow chart of a method for obtaining a steering control amount of an automatic driving vehicle provided by an embodiment of the present invention. Figure 5 As shown, the method of the embodiment of the present invention may include:

[0075] S501. Obtain driving information of the autonomous driving vehicle, where the driving information includes vehicle status information, vehicle planning trajectory, and vehicle position information of the autonomous driving vehicle.

[0076] Exemplarily, the vehicle status information of the autonomous driving vehicle may include, for example, the longitudinal speed of the autonomous driving vehicle, the vehicle status, etc. The vehicle planning trajectory is obtained based on the current path and the environmental information of the autonomous driving vehicle. The environmental information of the autonomous driving vehicle may include, for example, the perception information obtained through forward vision, peripheral vision, surround vision and two laser radars arranged on both sides of the front of the vehicle, and after sensor fusion processing, the output FS point (i.e., passable boundary point), target information (such as vehicle information in front of the autonomous driving vehicle, meeting information, etc.) and ultrasonic ranging information, etc. The vehicle position information is the vehicle positioning information, such as the plane coordinate point obtained by internal conversion based on the latitude and longitude of the current point output by the GPS.

[0077] S502: Perform coordinate conversion according to the vehicle position information and the vehicle planned trajectory to obtain a local path in the vehicle body coordinate system corresponding to the autonomous driving vehicle.

[0078] It can be understood that the coordinate transformation of the vehicle planned trajectory is performed according to the vehicle position information, and the trajectory coordinate points (corresponding to the local path) are converted from the global coordinate system (corresponding to the global path) in the vehicle body coordinate system, which can be used more conveniently to obtain the corresponding lateral deviation and heading deviation of the autonomous driving vehicle.

[0079] Optionally, the vehicle body coordinate system takes the center point of the rear axle of the autonomous driving vehicle as its origin.

[0080] For example, the center point of the rear axle of the autonomous driving vehicle is used as the origin of the vehicle body coordinate system, so that the coordinate transformation can be performed according to the vehicle position information and the vehicle planning trajectory to obtain the local path in the vehicle body coordinate system corresponding to the autonomous driving vehicle. The specific coordinate transformation formula is the following formula 2:

[0081]

[0082] Where X represents the horizontal coordinate of the autonomous driving vehicle in the global coordinate system; Y represents the vertical coordinate of the autonomous driving vehicle in the global coordinate system; p Represents the horizontal coordinate of the positioning of the autonomous driving vehicle in the global coordinate system; y p represents the positioning ordinate of the autonomous driving vehicle in the global coordinate system; h represents the heading angle of the autonomous driving vehicle in the global coordinate system; x v Represents the horizontal coordinate of the autonomous driving vehicle in the vehicle body coordinate system; y v Represents the vertical coordinate of the autonomous driving vehicle in the vehicle body coordinate system.

[0083] For example, Figure 6 A schematic diagram of coordinate conversion provided by an embodiment of the present invention is shown in FIG. Figure 6As shown in the figure, X represents the horizontal coordinate of the autonomous driving vehicle in the global coordinate system, and Y represents the vertical coordinate of the autonomous driving vehicle in the global coordinate system. x represents the horizontal coordinate of the autonomous driving vehicle in the vehicle body coordinate system, and y represents the vertical coordinate of the autonomous driving vehicle in the vehicle body coordinate system. h represents the heading angle of the autonomous driving vehicle in the global coordinate system. The vehicle planning trajectory can be converted from the global coordinate system to the trajectory coordinate point in the vehicle body coordinate system according to the vehicle position information.

[0084] S503 . Based on the vehicle state information, the vehicle position information and the local path, obtain the steering control amount through LQR.

[0085] In this step, after obtaining the local path in the vehicle body coordinate system corresponding to the autonomous driving vehicle, the steering control amount can be obtained through LQR based on the vehicle state information, vehicle position information and local path.

[0086] Further, optionally, obtaining a steering control amount through LQR based on vehicle status information, vehicle position information and a local path may include: determining a lateral deviation and a heading deviation corresponding to the autonomous driving vehicle according to the vehicle position information and the local path; and obtaining a steering control amount through LQR based on the vehicle status information, the lateral deviation and the heading deviation.

[0087] Exemplarily, the lateral deviation and heading deviation corresponding to the autonomous driving vehicle can be determined based on the vehicle position information and the local path. Optionally, the lateral deviation and heading deviation are the lateral deviation and heading deviation at a preset distance in front of the center of the rear axle of the autonomous driving vehicle. Exemplarily, the preset distance is, for example, 1 meter. It can be understood that in order to obtain the lateral deviation and heading deviation close to the center of mass of the autonomous driving vehicle, the lateral deviation and heading deviation 1 meter in front of the center of the rear axle of the autonomous driving vehicle are usually obtained to be approximately the lateral deviation and heading deviation at the center of mass.

[0088] The LQR is obtained based on a vehicle dynamics model. Optionally, the vehicle dynamics model is determined based on the lateral deviation, the heading deviation, and vehicle state information, the vehicle state information including the front wheel cornering stiffness, the rear wheel cornering stiffness, the moment of inertia, the distance from the center of mass to the front axle, the distance from the center of mass to the rear axle, the mass of the autonomous vehicle, the longitudinal speed, and the front wheel steering angle.

[0089] For example, reference Figure 6 , the vehicle dynamics model can be obtained as follows:

[0090]

[0091] Where e1 represents the lateral deviation between positioning (i.e., vehicle position information) and path (i.e., local path); e2 represents the heading deviation; C αf Indicates the front wheel cornering stiffness; Cαr Represents the rear wheel cornering stiffness; I z represents the moment of inertia of the autonomous driving vehicle; l f Indicates the distance from the center of mass to the front axle; l r represents the distance from the center of mass to the rear axle; m represents the mass of the autonomous vehicle; v x represents the longitudinal speed; δ represents the front wheel turning angle.

[0092] The above formula 3 is simplified as the following formula 4:

[0093]

[0094] Based on the vehicle dynamics model, the objective function of LQR control can be defined as the following formula 5:

[0095]

[0096] Wherein, J represents the function name of the objective function; k represents the kth control cycle; δ(k) represents the steering control amount.

[0097] The optimal control output based on the objective function is as follows:

[0098] δ(k)=-Kx(k) Formula 6

[0099] in, Where P satisfies the following Riccati equation (i.e., Formula 7):

[0100]

[0101] Where T represents transpose; A d represents the discretized form of A; B d Represents the discretized form of B.

[0102] By solving formula 7, P can be obtained, and then K can be obtained, and then the final optimal steering control amount can be obtained through formula 6.

[0103] It can be understood that according to the LQR control theory, the larger the diagonal coefficient of the weighting matrix Q, the larger the corresponding state variable (i.e. )The faster the convergence speed, the smaller the diagonal coefficient of the weighted matrix Q, and the corresponding state variable (i.e. ) The slower the convergence speed. The larger the coefficient of the weighting matrix R, the smaller the control output of the LQR will be, so as to ensure that J in the objective function (Formula 5) obtains the minimum value. In order to make the control output of the LQR smoother, in the present invention, the coefficient size of the weighting matrix R is dynamically adjusted according to the variance of the control output of the LQR (i.e., the steering control amount) within 10 control cycles, so that the variance of the control output is kept below a certain limit, thereby improving the driving stability and comfort of the whole vehicle.

[0104] The method for obtaining the steering control amount of an autonomous driving vehicle provided in an embodiment of the present invention obtains driving information of the autonomous driving vehicle, where the driving information includes vehicle status information, vehicle planned trajectory and vehicle position information of the autonomous driving vehicle; coordinate transformation is performed according to the vehicle position information and the vehicle planned trajectory to obtain a local path in the vehicle body coordinate system corresponding to the autonomous driving vehicle; based on the vehicle status information, the vehicle position information and the local path, the steering control amount is obtained through LQR, so that the steering control amount can be accurately obtained.

[0105] Based on the above embodiments, you can refer to Figure 5 In the embodiment shown, after obtaining the adjusted weighting matrix R ′ Then, replace the weight matrix R in Formula 5 with the adjusted weight matrix R ′ , so that the adjusted weight matrix R ′ The target steering control amount of the autonomous driving vehicle can be obtained through LQR, and then the steering actuator can be controlled to execute the target steering control amount, which can effectively reduce the problem of steering wheel shaking and improve the driving stability and comfort of the whole vehicle.

[0106] The following are embodiments of the device of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments of the present invention, please refer to the method embodiments of the present invention.

[0107] Figure 7 This is a schematic diagram of the structure of a lateral control device for an autonomous driving vehicle provided by an embodiment of the present invention. Figure 7 As shown, the lateral control device 700 of the autonomous driving vehicle according to the embodiment of the present invention includes: a first acquisition module 701, a determination module 702, an adjustment module 703, and a second acquisition module 704. Among them:

[0108] The first acquisition module 701 is used to obtain the variance of the steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles. The steering control amount is based on the driving information of the autonomous driving vehicle and is obtained through a linear quadratic regulator LQR, which is obtained based on a vehicle dynamics model.

[0109] The determination module 702 is used to determine whether to adjust the weight matrix R of the LQR according to the variance.

[0110] Adjustment module 703 is used to adjust the weight matrix R of LQR according to the variance to obtain the adjusted weight matrix R ′ .

[0111] The second acquisition module 704 is used to obtain the weight matrix R ′ and the driving information of the autonomous driving vehicle, and obtain the target steering control amount of the autonomous driving vehicle through LQR to control the steering actuator of the autonomous driving vehicle to execute the target steering control amount.

[0112] Further, the determination module 702 may be specifically configured to: if the variance is greater than or equal to the angle threshold, determine to adjust the weighting matrix R of the LQR; if the variance is less than the angle threshold, determine not to adjust the weighting matrix R of the LQR.

[0113] Furthermore, the adjustment module 703 can be specifically used to: adjust the weight matrix R ′ Satisfies the following formula:

[0114] R ′ =min(R*(σ 2 -threshold)*a,b)

[0115] Among them, σ 2 represents variance; threshold represents angle threshold; a represents scaling factor; b represents the upper limit of weighting matrix R.

[0116] Furthermore, the driving information includes vehicle status information, vehicle planned trajectory and vehicle position information of the autonomous driving vehicle. The lateral control device 700 of the autonomous driving vehicle may also include a third acquisition module (not shown in the figure) for obtaining the steering control amount in the following manner: performing coordinate conversion according to the vehicle position information and the vehicle planned trajectory to obtain the local path in the vehicle body coordinate system corresponding to the autonomous driving vehicle; based on the vehicle status information, vehicle position information and the local path, obtaining the steering control amount through LQR.

[0117] Furthermore, when the third acquisition module is used to acquire the steering control amount through LQR based on the vehicle status information, the vehicle position information and the local path, it can be specifically used to: determine the lateral deviation and heading deviation corresponding to the autonomous driving vehicle according to the vehicle position information and the local path; acquire the steering control amount through LQR based on the vehicle status information, the lateral deviation and the heading deviation.

[0118] Furthermore, the vehicle dynamics model is determined based on the lateral deviation, the heading deviation and the vehicle state information, and the vehicle state information includes the front wheel cornering stiffness, the rear wheel cornering stiffness, the moment of inertia, the distance from the center of mass to the front axle, the distance from the center of mass to the rear axle, the mass of the autonomous driving vehicle, the longitudinal speed and the front wheel turning angle.

[0119] Furthermore, the lateral deviation and the heading deviation are the lateral deviation and the heading deviation at a preset distance in front of the center of the rear axle of the autonomous driving vehicle.

[0120] Furthermore, the vehicle body coordinate system takes the center point of the rear axle of the autonomous driving vehicle as its origin.

[0121] The device of the embodiment of the present invention can be used to execute the technical solution of any of the above-mentioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0122] The present invention also provides a vehicle, comprising a vehicle body, front wheels and rear wheels, wherein the vehicle body is arranged between the front wheels and the rear wheels; the vehicle also includes a lateral control device of the autonomous driving vehicle as described above in the embodiment of the present invention, which is arranged on the vehicle body.

[0123] Figure 8 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 8 As shown, the electronic device 800 may include: at least one processor 801 and a memory 802 .

[0124] The memory 802 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer-executable instructions.

[0125] The memory 802 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0126] The processor 801 is used to execute the computer-executable instructions stored in the memory 802 to implement the lateral control method of the autonomous driving vehicle described in the aforementioned method embodiment. Among them, the processor 801 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. Specifically, when implementing the lateral control method of the autonomous driving vehicle described in the aforementioned method embodiment, the electronic device may be, for example, an electronic power steering system (Electric Power Steering, EPS) of the steering wheel of the autonomous driving vehicle.

[0127] Optionally, the electronic device 800 may further include a communication interface 803. In a specific implementation, if the communication interface 803, the memory 802 and the processor 801 are implemented independently, the communication interface 803, the memory 802 and the processor 801 may be interconnected through a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0128] Optionally, in a specific implementation, if the communication interface 803, the memory 802 and the processor 801 are integrated on a chip, the communication interface 803, the memory 802 and the processor 801 can communicate through an internal interface.

[0129] The present invention also provides a computer-readable storage medium, in which computer program instructions are stored. When a processor executes the computer program instructions, the above-mentioned lateral control method of the autonomous driving vehicle is implemented.

[0130] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned lateral control method for an autonomous driving vehicle.

[0131] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0132] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in a dedicated integrated circuit. Of course, the processor and the readable storage medium can also be present as discrete components in the lateral control device of the autonomous driving vehicle.

[0133] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0134] Finally, it should be noted that the above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A lateral control method for an autonomous driving vehicle, characterized in that: include: Obtaining a variance of a steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles, wherein the steering control amount is obtained based on driving information of the autonomous driving vehicle through a linear quadratic regulator LQR, wherein the LQR is obtained based on a vehicle dynamics model; Determining whether to adjust the weighting matrix R of the LQR according to the variance; If yes, then adjust the weighting matrix R of the LQR according to the variance to obtain the adjusted weighting matrix R ′ ; According to the adjusted weight matrix R ′ and the driving information of the autonomous driving vehicle, and obtains the target steering control amount of the autonomous driving vehicle through the LQR to control the steering actuator of the autonomous driving vehicle to execute the target steering control amount.

2. The lateral control method of an autonomous driving vehicle according to claim 1, characterized in that: The step of determining whether to adjust the weighting matrix R of the LQR according to the variance includes: If the variance is greater than or equal to the angle threshold, determining to adjust the weighting matrix R of the LQR; If the variance is less than the angle threshold, it is determined not to adjust the weighting matrix R of the LQR.

3. The lateral control method of the automatic driving vehicle according to claim 2, characterized in that: The weighting matrix R of the LQR is adjusted according to the variance to obtain an adjusted weighting matrix R ′ ,include: The adjusted weight matrix R ′ Satisfies the following formula: R ′ =min(R*(σ 2 -threshold)*a,b) Among them, σ 2 represents the variance; threshold represents the angle threshold; a represents the scaling factor; b represents the upper limit value of the weighting matrix R.

4. The lateral control method of an autonomous driving vehicle according to any one of claims 1 to 3, characterized in that: The driving information includes vehicle state information, vehicle planning trajectory and vehicle position information of the autonomous driving vehicle, and the steering control amount is obtained in the following manner: Performing coordinate conversion according to the vehicle position information and the vehicle planned trajectory to obtain a local path in a vehicle body coordinate system corresponding to the autonomous driving vehicle; The steering control amount is acquired through the LQR based on the vehicle state information, the vehicle position information and the local path.

5. The lateral control method of the automatic driving vehicle according to claim 4, characterized in that: The acquiring the steering control amount through the LQR based on the vehicle state information, the vehicle position information and the local path includes: Determining a lateral deviation and a heading deviation corresponding to the autonomous driving vehicle according to the vehicle position information and the local path; The steering control amount is acquired through the LQR based on the vehicle state information, the lateral deviation and the heading deviation.

6. The lateral control method of the automatic driving vehicle according to claim 5, characterized in that: The vehicle dynamics model is determined based on the lateral deviation, the heading deviation and the vehicle state information, wherein the vehicle state information includes the front wheel cornering stiffness, rear wheel cornering stiffness, moment of inertia, distance from the center of mass to the front axle, distance from the center of mass to the rear axle, mass of the autonomous driving vehicle, longitudinal speed and front wheel turning angle.

7. The lateral control method of the automatic driving vehicle according to claim 6, characterized in that: The lateral deviation and the heading deviation are the lateral deviation and the heading deviation at a preset distance in front of the rear axle center of the automatic driving vehicle.

8. The lateral control method of the automatic driving vehicle according to claim 4, characterized in that: The vehicle body coordinate system takes the center point of the rear axle of the autonomous driving vehicle as its origin.

9. A lateral control device for an autonomous driving vehicle, characterized in that: include: A first acquisition module is used to acquire a variance of a steering control amount of the autonomous driving vehicle within a preset number of continuous control cycles, wherein the steering control amount is obtained based on driving information of the autonomous driving vehicle through a linear quadratic regulator LQR, wherein the LQR is obtained based on a vehicle dynamics model; A determination module, used for determining whether to adjust the weighting matrix R of the LQR according to the variance; An adjustment module is used to adjust the weight matrix R of the LQR according to the variance to obtain an adjusted weight matrix R ′ ; The second acquisition module is used to obtain the weight matrix R after adjustment. ′ and the driving information of the autonomous driving vehicle, and obtains the target steering control amount of the autonomous driving vehicle through the LQR to control the steering actuator of the autonomous driving vehicle to execute the target steering control amount.

10. A vehicle, characterized in that: The vehicle comprises a vehicle body, front wheels and rear wheels, wherein the vehicle body is arranged between the front wheels and the rear wheels; the vehicle also comprises a lateral control device for an autonomous driving vehicle as claimed in claim 9 arranged on the vehicle body.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the lateral control method of the autonomous driving vehicle as described in any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, which, when executed, implement the lateral control method of the autonomous driving vehicle as described in any one of claims 1 to 8.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed, the lateral control method of the autonomous driving vehicle according to any one of claims 1 to 8 is implemented.

Images