Autonomous vehicle control method and apparatus

Abstract

The application provides an automatic driving vehicle control method and device, and the method comprises the following steps: obtaining position constraints and rotation speed constraints from a planning module, wherein the position constraints are lateral position boundaries from a current time to a preset target time, and the rotation speed constraints are steering wheel rotation speed ranges from the current time to the preset target time; obtaining a steering wheel rotation angle, a yaw rate and a side slip angle within a target time window; obtaining a control instruction according to the steering wheel rotation angle, the yaw rate and the side slip angle within the target time window, in combination with the position constraints and the rotation speed constraints; and controlling the vehicle according to the control instruction. According to the steering wheel rotation angle, the yaw rate and the side slip angle within the target time window, in combination with the position constraints and the rotation speed constraints obtained from the planning module, the control instruction is obtained, the accuracy of the control instruction is improved, and the safety, economy, durability and comfort of the vehicle when executing the control instruction are ensured.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to an autonomous vehicle control method and apparatus. Background Technology

[0002] Self-driving cars, also known as driverless vehicles, computer-driven vehicles, or wheeled mobile robots, are intelligent vehicles that achieve driverless operation through computer systems. With the increasing prevalence of self-driving cars, they can be used as taxis or public transportation. When using a self-driving car, passengers need to input their destination, and the self-driving car generates a route based on the current location and destination, then travels along the generated route.

[0003] Currently, most systems utilize a planning module to generate trajectory lines and then use a planning control interface to transmit the generated trajectory curves to the control module, so that the control module can track the trajectory lines.

[0004] However, due to numerous boundary conditions in the control of some vehicles, the trajectory planned by the planning module may not be executed. For example, a commercial vehicle fully loaded going uphill may still not maintain its speed even with 100% throttle. Some vehicles can only ensure the safety and accuracy of control, and cannot consider other evaluation criteria. For instance, the planning module cannot plan a coasting speed trajectory for the control module to track, thus failing to consider fuel economy. Furthermore, regarding functional safety, there are control parameters that cannot be perceived by the planning module. For example, under the functional safety constraints of steering wheel angle and speed, lateral planning cannot guarantee its feasibility. Summary of the Invention

[0005] This invention provides a method and apparatus for controlling autonomous vehicles, which addresses the shortcomings of existing technologies where planned trajectories cannot be executed due to limitations imposed by actual conditions, thereby improving the feasibility of planned trajectories while also considering economic efficiency and durability.

[0006] This invention provides an autonomous vehicle control method, comprising: obtaining position constraints and rotational speed constraints from a planning module, wherein the position constraints are the lateral position boundaries from the current time to a preset target time, and the rotational speed constraints are the steering wheel rotational speed range from the current time to the preset target time; obtaining the steering wheel angle, yaw rate, and sideslip angle within a target time window; and obtaining control commands based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with the position constraints and the rotational speed constraints, to control the vehicle according to the control commands.

[0007] According to an autonomous vehicle control method provided by the present invention, control commands are obtained based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with the position constraints and speed constraints. The method includes: obtaining a predicted yaw rate, a predicted heading angle, and a predicted lateral position based on the steering wheel angle, yaw rate, and sideslip angle within the target time window; and obtaining control commands based on the predicted yaw rate, the predicted heading angle, the predicted lateral position, and a pre-constructed cost function, combined with the position constraints and speed constraints.

[0008] According to an autonomous vehicle control method provided by the present invention, the step of obtaining a predicted yaw rate, a predicted heading angle, and a predicted lateral position based on the steering wheel angle, yaw rate, and sideslip angle within the target time window includes: obtaining a predicted yaw rate based on the steering wheel angle and yaw rate within the target time window; obtaining a predicted sideslip angle based on the steering wheel angle and sideslip angle within the target time window; obtaining a predicted heading angle based on the predicted yaw rate; and obtaining a predicted lateral position based on the predicted heading angle and the predicted sideslip angle.

[0009] According to an autonomous vehicle control method provided by the present invention, the step of obtaining a predicted yaw rate based on the steering wheel angle and yaw rate within the target time window includes: inputting the steering wheel angle and yaw rate within the target time window into a pre-established first impulse response model, wherein the first impulse response model is convolved based on the steering wheel angle, yaw rate within the target time window and the unit impulse response of the first impulse response model to obtain the predicted yaw rate.

[0010] According to an autonomous vehicle control method provided by the present invention, before inputting the steering wheel angle and yaw rate within the target time window into a pre-established first impulse response model, the method includes: normalizing the steering wheel angle within the target time window;

[0011] After obtaining the predicted yaw rate, the method further includes: updating the first impulse response model based on the predicted yaw rate, the yaw rate within the target time window, and the normalized steering wheel angle.

[0012] According to an autonomous vehicle control method provided by the present invention, before inputting the steering wheel angle and yaw rate within the target time window into a pre-established first impulse response model, the method further includes: obtaining the corresponding average steering wheel angle and average yaw rate based on the steering wheel angle and yaw rate within the target time window; reducing each steering wheel angle within the target time window based on the average steering wheel angle; and reducing each yaw rate within the target time window based on the average yaw rate.

[0013] According to an autonomous vehicle control method provided by the present invention, after receiving the control command, the method further includes: controlling the vehicle according to the control command and receiving the vehicle execution state returned by the vehicle based on the execution of the control command; obtaining the vehicle boundary according to the vehicle execution state; and sending the vehicle boundary to the planning module.

[0014] The present invention also provides an autonomous vehicle control device, comprising: a constraint acquisition module for acquiring position constraints and rotational speed constraints from a planning module, wherein the position constraints are the lateral position boundaries from the current time to a preset target time, and the rotational speed constraints are the steering wheel rotational speed range from the current time to the preset target time; a data acquisition module for acquiring steering wheel angle, yaw rate, and sideslip angle within a target time window; and a command generation module for obtaining control commands based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with the position constraints and the rotational speed constraints, to control the vehicle according to the control commands.

[0015] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the above-described autonomous vehicle control methods.

[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described autonomous vehicle control methods.

[0017] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described autonomous vehicle control methods.

[0018] The autonomous vehicle control method and apparatus provided by this invention obtain control commands based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with position constraints and speed constraints obtained from the planning module. This improves the accuracy of the control commands and ensures the vehicle meets requirements for safety, economy, durability, and comfort when executing the control commands. Furthermore, by utilizing the control module to obtain control commands, the planning module can apply more complex algorithms, extending the original millisecond-level planning to second-level planning, thereby enabling planning for complex scenarios. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this invention 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 some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is one of the flowcharts of the autonomous vehicle control method provided by the present invention;

[0021] Figure 2 This is the second flowchart of the autonomous vehicle control method provided by the present invention;

[0022] Figure 3 This is a schematic diagram of the structure of the autonomous vehicle control device provided by the present invention;

[0023] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0025] Figure 1 A flowchart illustrating an autonomous vehicle control method according to the present invention is shown. The main execution component of the method is a control module, and the method includes:

[0026] S11, obtain position constraints and speed constraints from the planning module. The position constraint is the lateral position boundary from the current time to the preset target time, and the speed constraint is the steering wheel speed range from the current time to the preset target time.

[0027] S12, obtain the steering wheel angle, yaw rate and sideslip angle within the target time window.

[0028] S13: Based on the steering wheel angle, yaw rate and sideslip angle within the target time window, and combined with position constraints and speed constraints, control commands are obtained to control the vehicle according to the control commands.

[0029] It should be noted that S1N in this manual does not represent the sequence of control methods for autonomous vehicles. The following details will explain this in conjunction with... Figure 2 The present invention describes an autonomous vehicle control method.

[0030] Step S11: Obtain position constraints and speed constraints from the planning module. The position constraint is the lateral position boundary from the current time to the preset target time, and the speed constraint is the steering wheel speed range from the current time to the preset target time.

[0031] In this embodiment, obtaining position constraints and rotational speed constraints from the planning module includes: sending a constraint acquisition request to the planning module; and receiving the corresponding constraints returned by the planning module based on the constraint acquisition request. In this embodiment, the corresponding constraints include position constraints and rotational speed constraints, and the preset target time represents any preset time T in the future, wherein:

[0032] Lateral position constraints:

[0033]

[0034] Where T represents the preset target time, y(t) is the lateral position of the vehicle at time t, Y(t) is the lateral position constraint at time t, and y(t)∈Y(t) means that all trajectory points within the target time window from time 0 to time T satisfy the lateral position constraint.

[0035] Speed ​​constraint:

[0036]

[0037] The steering wheel has a functionally safe speed limit at different speeds, so it is necessary to ensure that the speed at any given time does not exceed the functionally safe speed. r represents the speed at which the control command is executed, and R represents the functionally safe speed range.

[0038] Step S12: Obtain the steering wheel angle, yaw rate, and sideslip angle within the target time window.

[0039] In this embodiment, obtaining the steering wheel angle, yaw rate, and sideslip angle within a target time window includes: obtaining trajectory points within the target time window; and obtaining the corresponding steering wheel angle, yaw rate, and sideslip angle for each trajectory point. It should be noted that the length of the target time window can be determined based on actual design requirements or prior experience. For example, if the target time window is 3 seconds, then the steering wheel angle, yaw rate, and sideslip angle within the corresponding historical 3 seconds are obtained based on the target time window. If the system sampling frequency is 50 Hz, then the steering wheel angle, yaw rate, and sideslip angle of 150 trajectory points are taken as model input. The steering wheel angle, yaw rate, and sideslip angle of the first trajectory point are the model input for the current time, and the steering wheel angle, yaw rate, and sideslip angle of the 2nd to 150th trajectory points are the model input for the historical 0.02 to historical 3 seconds. By obtaining the steering wheel angle, yaw rate, and sideslip angle within the target time window, online real-time data acquisition is facilitated, thereby facilitating subsequent acquisition of control commands.

[0040] Step S13: Based on the steering wheel angle, yaw rate and sideslip angle within the target time window, and in combination with position constraints and speed constraints, a control command is obtained to control the vehicle according to the control command.

[0041] In this embodiment, control commands are obtained based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with position constraints and speed constraints, to control the vehicle. This includes: obtaining predicted yaw rate, predicted heading angle, and predicted lateral position based on the steering wheel angle, yaw rate, and sideslip angle within the target time window; and obtaining control commands based on the predicted yaw rate, predicted heading angle, and predicted lateral position, a pre-constructed cost function, and combined with position constraints and speed constraints.

[0042] Specifically, based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, the predicted yaw rate, predicted heading angle, and predicted lateral position are obtained, including: obtaining the predicted yaw rate based on the steering wheel angle and yaw rate within the target time window; obtaining the predicted sideslip angle based on the steering wheel angle and sideslip angle within the target time window; obtaining the predicted heading angle based on the predicted yaw rate; and obtaining the predicted lateral position based on the predicted heading angle and predicted sideslip angle.

[0043] Further, based on the steering wheel angle and yaw rate within the target time window, the predicted yaw rate is obtained, including: inputting the steering wheel angle and yaw rate within the target time window into a pre-established first impulse response model, and convolving the first impulse response model with the steering wheel angle, yaw rate within the target time window and the unit impulse response of the first impulse response model to obtain the predicted yaw rate.

[0044] In this embodiment, the predicted yaw rate is expressed as:

[0045]

[0046] Where ω represents the predicted yaw rate, m represents the length of the first impulse response model, and hω represents the unit impulse response h of the first impulse response model with respect to the yaw rate. φ represents the i-th h value in the first impulse response model. m-i This represents the steering wheel angle at the mi-th trajectory point within the target time window. It should be noted that the first impulse response model can be an existing FIR model or a customized model for predicting yaw rate.

[0047] In an optional embodiment, before inputting the steering wheel angle and yaw rate within the target time window into the pre-established first impulse response model, the method includes: normalizing the steering wheel angle within the target time window. Correspondingly, after obtaining the predicted yaw rate, the method further includes: updating the first impulse response model based on the predicted yaw rate, the yaw rate within the target time window, and the normalized steering wheel angle. It should be noted that by normalizing the obtained steering wheel angle within the target time window before updating the first impulse response model, the steering wheel angle after the influence of the steering wheel dead zone on the steering wheel angle is obtained, i.e., the normalized steering wheel angle, thereby improving the accuracy of subsequent updates to the first impulse response model. Furthermore, the steering wheel has a dead zone, which is a certain angular range in the center of the steering wheel, within which rotation of the steering wheel will not cause vehicle movement.

[0048] Specifically, the steering wheel angle within the target time window is normalized, including: obtaining the torque corresponding to the steering wheel angle within the target time window; obtaining the median steering wheel torque based on the steering wheel angle within the target time window, the torque corresponding to the steering wheel angle, and the pre-established second impulse response model; and obtaining the normalized steering wheel angle based on the median steering wheel torque and the corresponding steering wheel angle.

[0049] In this embodiment, the second impulse response model is expressed as:

[0050] y1=h2 T *P+b

[0051] Where y1 represents the output of the second impulse response model, i.e., the steering wheel angle; P represents the input of the second impulse response model, i.e., the torque corresponding to the steering wheel angle within the target time window, represented as a row vector; h2 represents the unit impulse response of the second impulse response model, h2 TLet represent the transpose of h2. When the torque is 0, 'b' represents the center of the steering wheel torque. It should be noted that since h2 is a column vector, it needs to be transposed into its corresponding row vector h2 for easier calculation. T .

[0052] It should be noted that the second impulse response model is also an online-updated FIR model. During vehicle operation, both h2 and b will be updated according to the input steering angle and torque. For details, please refer to the update method of the first impulse response model below, which will not be described here.

[0053] Because the steering wheel has a dead zone—a certain angular range within the center of the steering wheel where turning the wheel will not cause vehicle movement—it is necessary to first determine the median steering wheel torque. Then, based on the distance between the steering wheel angle and the median torque, the influence of the dead zone on the steering wheel angle is determined, resulting in the steering wheel angle affected by the dead zone, i.e., the normalized steering wheel angle mentioned above. Further, based on the median steering wheel torque and the corresponding steering wheel angle, the normalized steering wheel angle is obtained, including: determining the degree of influence of the dead zone on the steering wheel angle based on the median steering wheel torque and the corresponding steering wheel angle, combined with vehicle weight and a preset dead zone sensitivity; and obtaining the normalized steering wheel angle based on the preset dead zone width, the steering wheel angle, and the degree of influence of the dead zone on the steering wheel angle.

[0054] Additionally, the normalized steering wheel angle is represented as:

[0055]

[0056] Where y2 represents the normalized steering wheel angle, u1 represents the steering wheel angle acquired within the target time window, c represents the median steering wheel torque, m represents the vehicle weight, k1 represents the dead zone width, and k2 represents the dead zone sensitivity. This indicates the degree to which the dead zone affects the steering wheel angle. For example, there exists... When y2 = y3 = d, we obtain the corresponding u1 and u2, where k1 represents the distance between u1 and u2, and k2 represents the steepness of the y2 curve at point (c,0). It should be noted that the tanh function changes rapidly near the point (c,0) and approaches plus or minus 1 when the input is relatively large. Therefore, subtracting a value of k1*1 for large angles ensures that the angle change is not within the dead zone. For small angles, the value obtained by the tanh function is closer to the original small angle; subtracting it brings it close to 0, thus linking the dead zone to the center of the steering wheel torque.

[0057] In an optional embodiment, since some types of vehicles, such as trucks, exhibit zero bias and nonlinearity, the steering wheel angle and yaw rate within the target time window are preprocessed before being input into the pre-established impulse response model. Specifically, this includes: obtaining the corresponding average steering wheel angle and average yaw rate based on the steering wheel angle and yaw rate within the target time window; reducing each steering wheel angle within the target time window based on the average steering wheel angle; and reducing each yaw rate within the target time window based on the average yaw rate.

[0058] It should be noted that, based on the average steering wheel angle, each steering wheel angle within the target time window is reduced, which means subtracting the average steering wheel angle from each steering wheel angle within the target time window, thus achieving preprocessing of the steering wheel angles within the acquired target time window.

[0059] Similarly, based on the average yaw rate, each yaw rate within the target time window is reduced, which means subtracting the average yaw rate from each yaw rate within the target time window.

[0060] It should be noted that the preprocessing of the steering wheel angle and yaw rate within the target time window can be performed before or after the normalization of the steering wheel angle within the target time window; no further restrictions are imposed here.

[0061] It should be noted that if the steering wheel angle and yaw rate within the target time window are preprocessed before normalization, then the preprocessed steering wheel angle will be normalized during the subsequent normalization process. Similarly, if the steering wheel angle and yaw rate within the target time window are preprocessed after normalization, then the normalized steering wheel angle will be preprocessed after the preprocessing of the steering wheel angle and yaw rate within the target time window.

[0062] In one optional embodiment, updating the first impulse response model based on the predicted yaw rate, the yaw rate within the target time window, and the normalized steering wheel angle includes: obtaining the yaw rate error based on the predicted yaw rate and the yaw rate within the target time window; updating the first impulse response model based on the normalized steering wheel angle, a first preset value, and the yaw rate error; determining the response intensity of the updated first impulse response model, where the response intensity is the sum of all weight values ​​of the updated first impulse response model; determining whether the response intensity is within a preset interval, and determining whether to update the first impulse response model based on the determination result.

[0063] Furthermore, based on the normalized steering wheel angle, the first preset value, and the yaw rate error, the unit impulse response of the first impulse response model is updated, thereby updating the first impulse response model. The updated unit impulse response of the first impulse response model is expressed as:

[0064] h new (k)=h1(k)+Δh

[0065]

[0066] Among them, h new (k) represents the unit impulse response of the updated first impulse response model, h(k) represents the unit impulse response of the first impulse response model before the update, k3 represents the first preset value, δ represents the second preset value, e represents the yaw rate error, and u represents the steering wheel angle after preprocessing and normalization within the target time window. It should be noted that the first and second preset values ​​can be set according to actual design requirements or prior experience, and are not further limited here.

[0067] Further, determining whether to update the first impulse response model based on the judgment result includes: adjusting the first preset value based on the response intensity being outside the preset range; updating the first impulse response model again using the adjusted first preset value, combined with the normalized steering wheel angle and yaw rate errors; redetermining the response intensity based on the updated first impulse response model; and re-judging whether the re-determined response intensity is within the preset range, so as to redetermine the updated first impulse response model based on the judgment result.

[0068] It should be noted that, based on the response intensity being outside the preset range, the first preset value is adjusted in several ways: decreasing the first preset value when the response intensity is greater than the maximum boundary value of the preset range; and increasing the first preset value when the response intensity is less than the minimum boundary value of the preset range. By adjusting the magnitude of the first preset value, the response intensity of the updated first impulse response model is made to fall within the preset range. Furthermore, the preset range can be determined based on actual design requirements or prior experience; no further limitations are imposed here.

[0069] In an optional embodiment, the process of re-determining the updated first impulse response model based on the judgment result further includes: determining the currently updated first impulse response model as the updated model based on the response intensity being within a preset range.

[0070] Additionally, the predicted sideslip angle is expressed as:

[0071]

[0072] Where β represents the predicted side slip angle, m represents the length of the model corresponding to the predicted side slip angle, and h β This represents the unit impulse response h of the corresponding model with respect to the sideslip angle. φ represents the i-th h value in the corresponding model. m-i This represents the steering wheel angle at the mi-th trajectory point within the target time window.

[0073] It should be noted that the method for obtaining the predicted sideslip angle and the model for updating the corresponding predicted sideslip angle can refer to the method for obtaining the predicted yaw rate and updating the first impulse response model described above, and will not be elaborated further here.

[0074] The predicted heading angle is expressed as:

[0075]

[0076] Where ω represents the predicted yaw rate and θ represents the predicted yaw angle. Similarly, the method for obtaining the predicted heading angle can refer to the method for obtaining the predicted yaw rate described above, and will not be elaborated further here.

[0077] The predicted lateral position is represented as:

[0078]

[0079] Where y represents the predicted lateral position, θ represents the predicted yaw angle, β represents the predicted sideslip angle, and v x This represents the vehicle's velocity along the first direction of the x-axis in the vehicle coordinate system. The first direction of the x-axis indicates the vehicle's heading, and can be either positive or negative, depending on the setting of the positive or negative x-axis direction in the vehicle coordinate system. No further limitations are made here. Similarly, the method for obtaining the predicted lateral position can refer to the method for obtaining the predicted yaw rate described above, and will not be elaborated further here.

[0080] Furthermore, based on the predicted yaw rate, predicted heading angle, predicted lateral position, and a pre-constructed cost function, combined with position and speed constraints, control commands are obtained. In this embodiment, the cost function is expressed as:

[0081]

[0082] Among them, J cont Let ω represent the cost function, T represent the future time T, ω represent the predicted yaw rate, θ represent the predicted heading angle, y represent the predicted lateral position, u represent the predicted steering wheel angle (i.e., the control command), and k represent the predicted yaw rate. ω k θ k y k s k aThese represent the weights of yaw rate, heading angle, lateral position, steering wheel speed, and steering wheel angular acceleration in the cost function, respectively, and are all positive numbers. It should be noted that the cost function is a standard quadratic function, where each term is kx. 2 The format ensures that each term is positive, where x is the square of the physical quantity and k represents the weight of that term. For example, suppose k... ω The value is 10, and the other four are k. θ k y k s and k a If all values ​​are 0.001, then the first term, ω (yaw rate), will be the dominant term in the cost function. Therefore, the five weighting coefficients k are adjusted. ω k θ k y k s and k a This allows for the achievement of ideal vehicle dynamics.

[0083] Additionally, by adjusting k ω k θ k y k s and k a Parameters such as position and speed are used to obtain the predicted steering wheel angle u, i.e., the control command, by minimizing the cost function under position and speed constraints, so as to control the vehicle according to the control command.

[0084] In one alternative embodiment, reference Figure 2 After sending control commands to the vehicle, the process also includes: controlling the vehicle according to the control commands and receiving the vehicle execution status returned by the vehicle based on the executed control commands; obtaining the vehicle boundary based on the vehicle execution status; and sending the vehicle boundary to the planning module. It should be noted that the vehicle execution status includes the vehicle's speed, acceleration, heading angle, yaw rate, sideslip angle, steering wheel angle, steering wheel angular velocity, and steering wheel angular acceleration, etc., which facilitates the subsequent determination of the vehicle's current position boundary, i.e., the vehicle boundary, based on the vehicle execution status. Furthermore, by receiving the vehicle execution status returned by the vehicle based on the control commands and returning the vehicle execution status to the planning module, the planning module can make timely adjustments based on the vehicle execution status, thereby improving the accuracy of vehicle control.

[0085] In summary, this embodiment of the invention obtains control commands based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with the position and speed constraints obtained from the planning module. This improves the accuracy of the control commands and ensures the vehicle meets requirements for safety, economy, durability, and comfort when executing them. Furthermore, by utilizing the control module to obtain control commands, the planning module can apply more complex algorithms, extending the original millisecond-level planning to second-level planning, thereby enabling planning for complex scenarios.

[0086] The autonomous vehicle control device provided by the present invention is described below. The autonomous vehicle control device described below can be referred to in correspondence with the autonomous vehicle control method described above.

[0087] Figure 3 A schematic diagram of an autonomous vehicle control device is shown, the device comprising:

[0088] The constraint acquisition module 31 acquires position constraints and rotation speed constraints from the planning module. The position constraint is the lateral position boundary from the current time to the preset target time, and the rotation speed constraint is the steering wheel rotation speed range from the current time to the preset target time.

[0089] Data acquisition module 32 acquires the steering wheel angle, yaw rate and sideslip angle of the vehicle within the target time window;

[0090] The instruction generation module 33 generates control instructions based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with position constraints and speed constraints, so as to control the vehicle according to the control instructions.

[0091] In this embodiment, the constraint acquisition module 31 includes: a request sending unit for sending a constraint acquisition request to the planning module; and a constraint receiving unit for receiving the corresponding constraints returned by the planning module based on the constraint acquisition request. In this embodiment, the corresponding constraints include position constraints and rotational speed constraints.

[0092] The data acquisition module 32 includes: a trajectory point acquisition unit, which acquires trajectory points within the target time window; and a data acquisition unit, which acquires the steering wheel angle, yaw rate and sideslip angle corresponding to each trajectory point.

[0093] The instruction generation module 33 includes: a prediction unit, which obtains the predicted yaw rate, predicted heading angle and predicted lateral position based on the steering wheel angle, yaw rate and sideslip angle within the target time window; and an instruction generation unit, which obtains the control instructions based on the predicted yaw rate, predicted heading angle and predicted lateral position and a pre-constructed cost function, combined with position constraints and speed constraints.

[0094] Specifically, the prediction unit includes: a first prediction unit that obtains the predicted yaw rate based on the steering wheel angle and yaw rate within the target time window; a second prediction unit that obtains the predicted sideslip angle based on the steering wheel angle and sideslip angle within the target time window; a third prediction unit that obtains the predicted heading angle based on the predicted yaw rate; and obtains the predicted lateral position based on the predicted heading angle and the predicted sideslip angle.

[0095] Furthermore, the first prediction unit includes: inputting the steering wheel angle and yaw rate within the target time window into a pre-established first impulse response model, wherein the first impulse response model is convolved with the steering wheel angle, yaw rate within the target time window and the unit impulse response of the first impulse response model to obtain the predicted yaw rate.

[0096] In an optional embodiment, the instruction generation module 33 further includes: a normalization processing unit, which normalizes the steering wheel angle within the target time window before inputting the steering wheel angle and yaw rate within the target time window into the pre-established first impulse response model; and a model update unit, which updates the first impulse response model based on the predicted yaw rate, the yaw rate within the target time window, and the normalized steering wheel angle after obtaining the predicted yaw rate.

[0097] Specifically, the normalization processing unit includes: a torque acquisition subunit, which acquires the torque corresponding to the steering wheel angle within the target time window; a median acquisition subunit, which obtains the median steering wheel torque based on the steering wheel angle within the target time window, the torque corresponding to the steering wheel angle, and a pre-established second impulse response model; and a normalization processing subunit, which obtains the normalized steering wheel angle based on the median steering wheel torque and the corresponding steering wheel angle.

[0098] Furthermore, the normalization processing subunit includes: an influence degree determination subunit, which determines the influence degree of the dead zone on the steering wheel angle based on the median steering wheel torque and the corresponding steering wheel angle, combined with the vehicle weight and the preset dead zone sensitivity; and a normalization processing subunit, which obtains the normalized steering wheel angle based on the preset dead zone width, the steering wheel angle, and the influence degree of the dead zone on the steering wheel angle.

[0099] In an optional embodiment, the normalization processing unit further includes an impulse response model update unit for updating the second impulse response model. It should be noted that the second impulse response model update unit can be referred to in the section on model update unit, and will not be further described here.

[0100] In an optional embodiment, since some types of vehicles, such as trucks, exhibit zero bias and nonlinearity, the instruction generation module 33 further includes a preprocessing unit that preprocesses the steering wheel angle and yaw rate within the target time window before inputting them into the pre-established impulse response model. Specifically, the preprocessing unit includes: an average value acquisition subunit that obtains the corresponding average steering wheel angle and average yaw rate based on the steering wheel angle and yaw rate within the target time window; and a preprocessing subunit that reduces each steering wheel angle within the target time window based on the average steering wheel angle and reduces each yaw rate within the target time window based on the average yaw rate.

[0101] It should be noted that the preprocessing module can perform the preprocessing of the steering wheel angle and yaw rate within the target time window before or after the normalization module performs the normalization of the steering wheel angle within the target time window; no further restrictions are imposed here.

[0102] In one optional embodiment, the model update unit includes: an error acquisition subunit, which obtains the yaw rate error based on the predicted yaw rate and the yaw rate within the target time window; a model update subunit, which updates the first impulse response model based on the normalized steering wheel angle, a first preset value, and the yaw rate error; an intensity determination subunit, which determines the response intensity of the updated first impulse response model, wherein the response intensity is the sum of all weight values ​​of the updated first impulse response model; and a model determination subunit, which determines whether the response intensity is within a preset interval and determines whether to update the first impulse response model based on the determination result.

[0103] Furthermore, the model determines the sub-units, including: judging the grandchild unit to determine whether the response intensity is within a preset range; the first model determines the grandchild unit, based on the response intensity being within the preset range, determining the currently updated first impulse response model as the updated model; adjusting the grandchild unit, based on the response intensity being outside the preset range, adjusting the first preset value; updating the grandchild unit, using the adjusted first preset value, combined with the normalized steering wheel angle and yaw rate errors, to re-update the first impulse response model; updating the grandchild unit, based on the re-updated first impulse response model, redetermining the response intensity; and the second model determines the grandchild unit, re-judging whether the re-determined response intensity is within the preset range, so as to redetermine the updated first impulse response model based on the judgment result.

[0104] It should be noted that adjusting the grandchild unit includes: first adjusting the great-grandchild unit by decreasing the first preset value based on the maximum boundary value of the response intensity being greater than the preset interval; and second adjusting the great-grandchild unit by increasing the first preset value based on the minimum boundary value of the response intensity being less than the preset interval.

[0105] In an optional embodiment, the device further includes a constraint receiving module, which receives position constraints and speed constraints sent by the planning module before obtaining control commands based on the predicted yaw rate, predicted heading angle, predicted lateral position, and a pre-built cost function, combined with position constraints and speed constraints.

[0106] In an optional embodiment, the device further includes: a status receiving module, which controls the vehicle according to the control command after sending the control command to the vehicle, and receives the vehicle execution status returned by the vehicle based on the execution control command; a boundary determination module, which obtains the vehicle boundary according to the vehicle execution status; and a data sending module, which sends the vehicle boundary to the planning module.

[0107] In summary, this embodiment of the invention utilizes the instruction generation module to obtain control instructions based on the steering wheel angle, yaw rate, and sideslip angle within the target time window acquired by the data acquisition module, combined with the position constraints and speed constraints obtained from the planning module by the constraint acquisition module. This improves the accuracy of the control instructions and ensures the vehicle meets requirements for safety, economy, durability, and comfort when executing them. Furthermore, by utilizing the control module to obtain control instructions, the planning module can apply more complex algorithms, extending the original millisecond-level planning to second-level planning, thereby enabling planning for complex scenarios.

[0108] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 41, a communication interface 42, a memory 43, and a communication bus 44. The processor 41, communication interface 42, and memory 43 communicate with each other via the communication bus 44. The processor 41 can call logical instructions from the memory 43 to execute an autonomous vehicle control method. This method includes: obtaining position constraints and speed constraints from a planning module; the position constraints being the lateral position boundary from the current time to a preset target time, and the speed constraints being the steering wheel speed range from the current time to the preset target time; obtaining the steering wheel angle, yaw rate, and sideslip angle within a target time window; and obtaining control commands based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with the position constraints and speed constraints, to control the vehicle according to the control commands.

[0109] Furthermore, the logical instructions in the aforementioned memory 43 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0110] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the autonomous vehicle control method provided by the above methods. The method includes: obtaining position constraints and rotational speed constraints from a planning module, wherein the position constraints are the lateral position boundaries from the current time to a preset target time, and the rotational speed constraints are the steering wheel rotational speed range from the current time to the preset target time; obtaining the steering wheel angle, yaw rate, and sideslip angle within a target time window; and obtaining control commands based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with the position constraints and rotational speed constraints, so as to control the vehicle according to the control commands.

[0111] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the autonomous vehicle control method provided by the above methods. The method includes: obtaining position constraints and rotational speed constraints from a planning module, wherein the position constraints are the lateral position boundaries from the current time to a preset target time, and the rotational speed constraints are the steering wheel rotational speed range from the current time to the preset target time; obtaining the steering wheel angle, yaw rate, and sideslip angle within a target time window; and obtaining control commands based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with the position constraints and rotational speed constraints, to control the vehicle according to the control commands.

[0112] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0113] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling an autonomous vehicle, characterized in that, include: The position constraint and rotation speed constraint are obtained from the planning module. The position constraint is the lateral position boundary from the current time to the preset target time, and the rotation speed constraint is the range of steering wheel rotation speed from the current time to the preset target time. Obtain the steering wheel angle, yaw rate, and sideslip angle within the target time window; Based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, and in conjunction with the position constraints and the speed constraints, control commands are obtained to control the vehicle according to the control commands. The preset target time refers to a future preset time relative to the current time, and the target time window refers to a historical time relative to the current time that meets the length of the target time window.

2. The autonomous vehicle control method according to claim 1, characterized in that, Based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, and in conjunction with the position and speed constraints, control commands are obtained, including: Based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, the predicted yaw rate, predicted heading angle, and predicted lateral position are obtained. Based on the predicted yaw rate, the predicted heading angle, the predicted lateral position, and the pre-constructed cost function, combined with the position constraints and the rotational speed constraints, control commands are obtained.

3. The autonomous vehicle control method according to claim 2, characterized in that, The step of obtaining the predicted yaw rate, predicted heading angle, and predicted lateral position based on the steering wheel angle, yaw rate, and sideslip angle within the target time window includes: The predicted yaw rate is obtained based on the steering wheel angle and yaw rate within the target time window; The predicted sideslip angle is obtained based on the steering wheel angle and sideslip angle within the target time window; Based on the predicted yaw rate, the predicted heading angle is obtained; The predicted lateral position is obtained based on the predicted heading angle and the predicted sideslip angle.

4. The autonomous vehicle control method according to claim 3, characterized in that, The step of obtaining the predicted yaw rate based on the steering wheel angle and yaw rate within the target time window includes: The steering wheel angle and yaw rate within the target time window are input into a pre-established first impulse response model. The first impulse response model is convolved with the steering wheel angle, yaw rate within the target time window and the unit impulse response of the first impulse response model to obtain the predicted yaw rate.

5. The autonomous vehicle control method according to claim 4, characterized in that, Before inputting the steering wheel angle and yaw rate within the target time window into the pre-established first impulse response model, the following steps are included: The steering wheel angle within the target time window is normalized. After obtaining the predicted yaw rate, the process also includes: The first impulse response model is updated based on the predicted yaw rate, the yaw rate within the target time window, and the normalized steering wheel angle.

6. The autonomous vehicle control method according to claim 4, characterized in that, Before inputting the steering wheel angle and yaw rate within the target time window into the pre-established first impulse response model, the process also includes: Based on the steering wheel angle and yaw rate within the target time window, the corresponding average steering wheel angle and average yaw rate are obtained; Based on the average steering wheel angle, reduce the steering wheel angle for each target time window; Based on the average yaw rate, reduce the yaw rate for each time window within the target time window.

7. The autonomous vehicle control method according to claim 1, characterized in that, After receiving the control command, the process also includes: Control the vehicle according to the control command, and receive the vehicle execution status returned by the vehicle based on the execution of the control command; Based on the vehicle's execution state, the vehicle boundary is obtained, whereby the vehicle boundary represents the position boundary corresponding to the vehicle. The vehicle boundary is sent to the planning module.

8. An autonomous vehicle control device, characterized in that, include: The constraint acquisition module acquires position constraints and rotation speed constraints from the planning module. The position constraint is the lateral position boundary from the current time to the preset target time, and the rotation speed constraint is the steering wheel rotation speed range from the current time to the preset target time. The data acquisition module acquires the steering wheel angle, yaw rate, and sideslip angle within the target time window; The instruction generation module generates control instructions based on the steering wheel angle, yaw rate, and sideslip angle within the target time window, combined with the position constraints and the speed constraints, to control the vehicle according to the control instructions. The preset target time refers to a future preset time relative to the current time, and the target time window refers to a historical time relative to the current time that meets the length of the target time window.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the autonomous vehicle control method as described in any one of claims 1 to 7.

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

Images