Self-adaptive cruise control method and system based on model-free self-adaptive algorithm

Abstract

The invention provides an adaptive cruise control method and system based on a model-free adaptive algorithm, and belongs to the technical field of auxiliary driving. A nonlinear autoregressive moving average model of a vehicle is constructed by acquiring a relative vehicle speed, a relative distance and an acceleration parameter of the vehicle at a previous moment; defining a speed control function in the nonlinear autoregressive moving average model, and designing a controller based on the speed control function, so that the controller can track the target vehicle speed and vehicle distance as soon as possible without overshoot; optimizing the optimal acceleration of the speed control function by using a reset algorithm, and finally obtaining the optimal acceleration through iteration; and the optimal acceleration is used as the input of a controller, the vehicle speed or the vehicle distance at the current moment is output, and self-adaptive cruise control over the vehicle is achieved. According to the method, frequent acceleration and deceleration of the vehicle can be avoided on the basis of reducing the computing power burden of the controller, and meanwhile, the method has the self-adaptive capacity to adapt to different driving environments and the system delay problem.

Description

Technical Field

[0001] The present invention belongs to the technical field of assisted driving, and in particular relates to an adaptive cruise control method and system based on a model-free adaptive algorithm. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Adaptive cruise control system (ACC) is an intelligent automatic control system. It is a new system that adds a control function of maintaining a reasonable distance from the vehicle in front on the basis of cruise control at a set speed. The algorithm design of adaptive cruise system (hereinafter referred to as ACC) is a multi-faceted technical challenge. The inventor found that the existing adaptive cruise control generally has the following technical problems:

[0004] (1) With the increasing attention paid to energy conservation and emission reduction, ACC algorithms also need to consider how to improve energy efficiency while maintaining vehicle performance. At present, although the simple PID algorithm can reduce the controller calculation burden, due to its algorithm limitations, it will frequently brake and accelerate, resulting in increased fuel consumption or power loss. Complex control algorithms such as MPC will increase the controller load due to the large amount of calculation;

[0005] (2) High algorithm complexity and system delay: In order to ensure the reliability and safety of the ACC system, the existing adaptive cruise control algorithm needs to process a large amount of input data, including speed, distance, acceleration, etc., while also taking into account the dynamic characteristics of the vehicle and the driver's behavior. This complexity may make it difficult for the algorithm to respond in real time, especially in complex traffic environments; and any control system has a certain reaction time, which may increase the probability that the ACC system will not be able to slow down in time in an emergency, increasing the risk of collision;

[0006] (3) Poor generalization ability: Existing adaptive cruise control systems are difficult to adapt to diverse conditions and have poor generalization ability under different vehicle models, different driving environments, and different driving behaviors. Summary of the invention

[0007] In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides an adaptive cruise control method and system based on a model-free adaptive algorithm, which can avoid frequent acceleration and deceleration of the vehicle on the basis of reducing the computing power burden of the controller, and at the same time has the adaptive ability to adapt to different driving environments and system delay problems.

[0008] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0009] A first aspect of the present invention provides an adaptive cruise control method based on a model-free adaptive algorithm.

[0010] The adaptive cruise control method based on the model-free adaptive algorithm includes:

[0011] Obtain the relative speed, relative distance and acceleration parameters of the vehicle at the previous moment;

[0012] A nonlinear autoregressive moving average model of the vehicle is constructed based on relative vehicle speed, relative distance and acceleration parameters;

[0013] Define the speed control function in the nonlinear autoregressive sliding average model, and design a controller based on the speed control function so that it can track the target vehicle speed and distance as quickly as possible without overshoot; use the reset algorithm to optimize the optimal acceleration of the speed control function, and finally obtain the optimal acceleration through iteration;

[0014] The optimal acceleration is used as the input of the controller to output the current vehicle speed or distance to achieve adaptive cruise control of the vehicle.

[0015] Furthermore, after tracking the target vehicle speed and vehicle distance, the relative distance and relative vehicle speed between the vehicles are judged, and based on the judgment result, speed control or distance control of the vehicle is selected.

[0016] Furthermore, when the relative distance between the vehicles is greater than the target vehicle distance, if the speed of the host vehicle relative to the target vehicle is greater than 0, the speed of the host vehicle is controlled; otherwise, the distance of the host vehicle is controlled.

[0017] Furthermore, when the relative distance between the vehicles is less than the target vehicle distance, if the speed of the host vehicle relative to the target vehicle is greater than 0, the host vehicle is subject to distance control; otherwise, the host vehicle is subject to speed control.

[0018] Further, when the relative distance between the vehicles is equal to the target vehicle distance, the speed of the host vehicle is selected to be controlled.

[0019] Furthermore, a controller is designed based on the speed control function, and a weight factor is introduced into the control input criterion function to avoid sudden changes in the acceleration obtained in subsequent iterations.

[0020] Furthermore, the optimal acceleration is used as the input of the controller to output the vehicle speed or vehicle distance at the current moment. Specifically: after the acceleration is input into the controller, the acceleration is converted into the corresponding motor driving torque and braking force through vehicle power conversion.

[0021] A second aspect of the present invention provides an adaptive cruise control system based on a model-free adaptive algorithm.

[0022] Adaptive cruise control system based on model-free adaptive algorithm, including:

[0023] The data acquisition module is configured to: acquire the relative speed, relative distance and acceleration parameters of the vehicle at the previous moment;

[0024] The controller design module is configured to: construct a nonlinear autoregressive sliding average model of the vehicle based on relative vehicle speed, relative distance and acceleration parameters; define a speed control function in the nonlinear autoregressive sliding average model, and design a controller based on the speed control function so that the controller can track the target vehicle speed and distance as quickly as possible without overshoot;

[0025] The adaptive cruise control module is configured to: use a reset algorithm to optimize the optimal acceleration of the speed control function, and finally obtain the optimal acceleration through iteration; use the optimal acceleration as the input of the controller, output the current vehicle speed or vehicle distance, and realize the vehicle's adaptive cruise control.

[0026] A third aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the adaptive cruise control method based on a model-free adaptive algorithm as described in the first aspect of the present invention.

[0027] A fourth aspect of the present invention provides an electronic device, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the adaptive cruise control method based on the model-free adaptive algorithm as described in the first aspect of the present invention are implemented.

[0028] One or more of the above technical solutions have the following beneficial effects:

[0029] (1) The present invention defines a speed control function in a nonlinear autoregressive sliding average model, and designs a controller based on the speed control function, so that the controller can track the target vehicle speed and distance as quickly as possible and without overshoot; after tracking the target vehicle speed and distance, the relative distance and relative speed between the vehicles are judged, and based on the judgment result, the speed control or distance control of the vehicle is selected. That is, by judging the relative distance and relative speed in turn, it is selected whether to control the speed of the vehicle or the distance. Through this multiple comparison judgment logic, the present invention can effectively avoid frequent braking or acceleration and deceleration of the vehicle, and reduce fuel consumption or power loss.

[0030] (2) The present invention designs a controller based on a speed control function, and in this process introduces an important parameter criterion function, and uses a reset algorithm to optimize the optimal acceleration of the speed control function, and finally obtains the optimal acceleration through iteration; by resetting important parameters, it is possible to prevent it from iterating to a very large number. Therefore, the present invention can, to a certain extent, avoid significantly increasing the computing power burden of the controller, reduce the complexity of the algorithm, and then improve the real-time response rate of the adaptive cruise control algorithm in complex traffic environments.

[0031] (3) The adaptive cruise control method based on the model-free adaptive algorithm provided by the present invention is controlled directly based on the actual input and output data of the system, which contains rich system dynamics information, including unmodeled dynamics and unknown system interference. Therefore, the present invention can overcome the high dependence of model-based adaptive control on the system mechanism model, thereby improving the generalization ability of the algorithm.

[0032] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0034] Figure 1 The figure is a flow chart of an adaptive cruise control method based on a model-free adaptive algorithm in the first embodiment of the present invention.

[0035] Figure 2 The figure is a flow chart of the switching logic of the adaptive cruise control target in the first embodiment of the present invention. DETAILED DESCRIPTION

[0036] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0037] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0038] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0039] Embodiment 1

[0040] This embodiment discloses an adaptive cruise control method based on a model-free adaptive algorithm.

[0041] like Figure 1 As shown, the adaptive cruise control method based on the model-free adaptive algorithm includes:

[0042] Step S1, obtaining the relative speed, relative distance and acceleration parameters of the vehicle at the previous moment;

[0043] Step S2: constructing a nonlinear autoregressive sliding average model of the vehicle based on the relative vehicle speed, relative distance and acceleration parameters; defining a speed control function in the nonlinear autoregressive sliding average model, and designing a controller based on the speed control function so that the controller can track the target vehicle speed and distance as quickly as possible without overshoot;

[0044] Step S3: Optimize the optimal acceleration of the speed control function by using a reset algorithm, and finally obtain the optimal acceleration through iteration; use the optimal acceleration as the input of the controller, output the current vehicle speed or vehicle distance, and realize the adaptive cruise control of the vehicle.

[0045] Through the above steps, the present invention can avoid frequent acceleration and deceleration of the vehicle on the basis of reducing the computing power burden of the controller, and at the same time has the adaptive ability to adapt to different driving environments and system delay problems. To facilitate understanding of the technical solution of the present invention, the above process is further explained and illustrated:

[0046] In step S1, the relative speed, relative distance and acceleration parameters of the vehicle at the previous moment are obtained, specifically:

[0047] Before designing the model-free adaptive cruise control algorithm, it is assumed that the relative speed, relative distance and other important parameter data between the vehicle and the target vehicle have been obtained through various sensor tools such as vehicle speed sensors and millimeter wave radars. At the same time, it is assumed that the acceleration obtained by the model-free adaptive algorithm needs to be converted into corresponding motor drive torque and braking torque through different vehicle dynamics. Among them, the target vehicle refers to a vehicle in the same lane as the vehicle. The target vehicle can be identified by millimeter radar waves or camera shooting, and this application does not make specific restrictions on this.

[0048] In order to facilitate the construction of a model-free adaptive algorithm, in step S2 of this embodiment, a nonlinear autoregressive sliding average model of the vehicle is constructed based on the relative vehicle speed, relative distance and acceleration parameters; and a speed control function in the nonlinear autoregressive sliding average model is defined.

[0049] Specifically, for the convenience of calculation, let d(k) represent the control quantity at the current moment, that is, the vehicle speed or the distance between two vehicles, and let U(k) represent the acceleration that needs to be input at the current moment. Since this system is a nonlinear system, the system can be described as a discrete-time nonlinear system, that is, a nonlinear autoregressive sliding average model with external input, and its expression is:

[0050] d(k+1)=f(v(k),…,e(kk v ),U(k),…,U(kk U ));

[0051] in, is an unknown nonlinear speed control function, hereinafter referred to as the speed control system, R represents the control target, k v and k U They represent the speed and input at the kth moment respectively; d(k+1) represents the control quantity at the next moment. Compared with the control quantity d(k) at the current moment, the measurement unit of each moment is a transmission cycle (usually 10 milliseconds or 20 milliseconds). e(k-kv) represents the total speed deviation of the state quantity at the kth moment. The function of the speed control system is to find the appropriate acceleration U(k) so that the total deviation of the state quantity at the kth moment, which is synonymous with e(k), can track the target vehicle speed and distance as quickly as possible without overshoot.

[0052] At the same time, for the speed control system, define U L (k)∈R L is an active time window [k-L+1], and the input signal of all accelerations is: U L (k)=[U(k),…U(k-L+1)] T .

[0053] like Figure 2 As shown, after tracking the target vehicle speed and distance, the relative distance and relative speed between the vehicles are judged, and the speed control or distance control of the vehicle is selected based on the judgment result. Specifically:

[0054] If the speed of the vehicle relative to the target vehicle is greater than 0, the speed of the vehicle is controlled; otherwise, the distance of the vehicle is controlled. When the relative distance between the vehicles is equal to the target distance, the speed of the vehicle is controlled. When the relative distance between the vehicles is less than the target distance, if the speed of the vehicle relative to the target vehicle is greater than 0, the distance of the vehicle is controlled; otherwise, the speed of the vehicle is controlled.

[0055] In step S2, a controller is designed based on the speed control function so that it can track the target vehicle speed and distance as quickly as possible without overshoot. This can be achieved through the following process:

[0056] Step S2-1, design a control input criterion function to prepare for solving the problem. The control input criterion function is:

[0057]

[0058] Where λ is the weight factor, which is used to prevent the acceleration from abruptly changing; v(k+1)=v(k)+Φ L T (k)ΔU(k),Φ L T (k) is the time-varying parameter vector; d * (k+1) represents the target value at the next moment, d(k+1) represents the actual value at the next moment, and v(k+1) represents the control value at the next moment (which can be speed or distance).

[0059] Let the criterion function be 0 and take the derivative of the acceleration U(k), we get:

[0060]

[0061] Among them, ρ is the compensation factor, ρ∈(0,1]. By introducing the compensation factor, it is easy to adjust the control rate; L represents the control range. Therefore, the introduction of L can make the algorithm more controllable.

[0062] Step S2-2, designing a PG estimation criterion function, wherein the PG estimation criterion function is:

[0063]

[0064] Among them, μ is the weight factor, Φ L (k) is the estimated value of the PG function at the kth moment. L (k) Taking the derivative, we can get the estimated value Φ L The calculation formula of (k) is:

[0065]

[0066] In step S3, the optimal acceleration of the speed control function is optimized by using a reset algorithm, and the optimal acceleration is finally obtained through iteration; the optimal acceleration is used as the input of the controller to output the current vehicle speed or vehicle distance to achieve the vehicle's adaptive cruise control. Specifically, in order to enable the PG estimation criterion function to estimate and better adapt to the actual situation of vehicle speed control, the reset algorithm is set as follows:

[0067] When ‖Φ L (k)‖≤ε or‖ΔU L (k-1)||≤εorsign(Φ L(k))≠sign(Φ L (1)) L (k) = Φ L (1).

[0068] Among them, Φ L (1) is Φ L (k), ε is a small positive number; the optimal acceleration U(k) is finally obtained through iteration. L (k) Initial value parameter can prevent very large numbers from appearing during the iteration process. Therefore, the present invention can avoid significantly increasing the computing power burden of the controller to a certain extent, reduce the complexity of the algorithm, and then improve the real-time response rate of the adaptive cruise control algorithm in a complex traffic environment; moreover, the acceleration of the iterative calculation will not produce sudden changes, and will not cause the vehicle to frequently accelerate and decelerate suddenly, which is conducive to ensuring the stability of the vehicle during the adaptive cruise control process.

[0069] At the same time, the present invention directly controls based on the actual input and output data of the system, which contains rich system dynamics information, including unmodeled dynamics and unknown disturbances of the system. Therefore, the present invention can overcome the high dependence of model-based adaptive control on the system mechanism model, thereby improving the generalization ability of the algorithm.

[0070] Embodiment 2

[0071] This embodiment discloses an adaptive cruise control system based on a model-free adaptive algorithm.

[0072] Adaptive cruise control system based on model-free adaptive algorithm, including:

[0073] The data acquisition module is configured to: acquire the relative speed, relative distance and acceleration parameters of the vehicle at the previous moment;

[0074] The controller design module is configured to: construct a nonlinear autoregressive sliding average model of the vehicle based on relative vehicle speed, relative distance and acceleration parameters; define a speed control function in the nonlinear autoregressive sliding average model, and design a controller based on the speed control function so that the controller can track the target vehicle speed and distance as quickly as possible without overshoot;

[0075] The adaptive cruise control module is configured to: use a reset algorithm to optimize the optimal acceleration of the speed control function, and finally obtain the optimal acceleration through iteration; use the optimal acceleration as the input of the controller, output the current vehicle speed or vehicle distance, and realize the vehicle's adaptive cruise control.

[0076] Embodiment 3

[0077] The purpose of this embodiment is to provide a computer-readable storage medium.

[0078] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the adaptive cruise control method based on a model-free adaptive algorithm as described in the first embodiment of the present disclosure.

[0079] Embodiment 4

[0080] The purpose of this embodiment is to provide an electronic device.

[0081] An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the adaptive cruise control method based on the model-free adaptive algorithm as described in the first embodiment of the present disclosure are implemented.

[0082] The steps involved in the apparatuses of the above embodiments 2, 3 and 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0083] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0084] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. An adaptive cruise control method based on a model-free adaptive algorithm, characterized in that: include: Obtain the relative speed, relative distance and acceleration parameters of the vehicle at the previous moment; A nonlinear autoregressive moving average model of the vehicle is constructed based on relative vehicle speed, relative distance and acceleration parameters; Define the speed control function in the nonlinear autoregressive sliding average model, and design a controller based on the speed control function so that it can track the target vehicle speed and distance as quickly as possible without overshoot; use the reset algorithm to optimize the optimal acceleration of the speed control function, and finally obtain the optimal acceleration through iteration; The optimal acceleration is used as the input of the controller to output the current vehicle speed or distance to achieve adaptive cruise control of the vehicle.

2. The adaptive cruise control method based on the model-free adaptive algorithm according to claim 1, characterized in that: After tracking the target vehicle speed and distance, the relative distance and relative speed between the vehicles are judged, and the speed control or distance control of the vehicle is selected based on the judgment result.

3. The adaptive cruise control method based on the model-free adaptive algorithm as claimed in claim 2, characterized in that: When the relative distance between vehicles is greater than the target vehicle distance, if the speed of the host vehicle relative to the target vehicle is greater than 0, the speed of the host vehicle is controlled; otherwise, the distance of the host vehicle is controlled.

4. The adaptive cruise control method based on the model-free adaptive algorithm as claimed in claim 2, characterized in that: When the relative distance between vehicles is less than the target vehicle distance, if the speed of the host vehicle relative to the target vehicle is greater than 0, the host vehicle is subject to distance control; otherwise, the host vehicle is subject to speed control.

5. The adaptive cruise control method based on the model-free adaptive algorithm as claimed in claim 2, characterized in that: When the relative distance between the vehicles is equal to the target vehicle distance, the speed of the vehicle is controlled.

6. The adaptive cruise control method based on the model-free adaptive algorithm as claimed in claim 1, characterized in that: The controller is designed based on the speed control function. In order to avoid sudden changes in the acceleration obtained in subsequent iterations, a weight factor is introduced into the control input criterion function.

7. The adaptive cruise control method based on the model-free adaptive algorithm as claimed in claim 1, characterized in that: The optimal acceleration is used as the input of the controller to output the current vehicle speed or distance. Specifically, after the acceleration is input into the controller, the acceleration is converted into the corresponding motor driving torque and braking force through vehicle power conversion.

8. An adaptive cruise control system based on a model-free adaptive algorithm, characterized in that: include: The data acquisition module is configured to: acquire the relative speed, relative distance and acceleration parameters of the vehicle at the previous moment; The controller design module is configured to: construct a nonlinear autoregressive sliding average model of the vehicle based on relative vehicle speed, relative distance and acceleration parameters; define a speed control function in the nonlinear autoregressive sliding average model, and design a controller based on the speed control function so that the controller can track the target vehicle speed and distance as quickly as possible without overshoot; The adaptive cruise control module is configured to: use a reset algorithm to optimize the optimal acceleration of the speed control function, and finally obtain the optimal acceleration through iteration; use the optimal acceleration as the input of the controller, output the current vehicle speed or vehicle distance, and realize the vehicle's adaptive cruise control.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps in the adaptive cruise control method based on a model-free adaptive algorithm as described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the adaptive cruise control method based on the model-free adaptive algorithm as described in any one of claims 1 to 7 are implemented.

Images