Vehicle control method, device and equipment in following state, medium and product

Abstract

The invention provides a vehicle control method and device in a following state, equipment, a medium and a product, and relates to the technical field of automatic driving control. The method comprises the steps of obtaining a first constraint relation model of a current vehicle in a following state; obtaining the actual state and speed information of the current vehicle at the current moment, and substituting the actual state and speed information into the first constraint relation model to obtain a second constraint relation model; acquiring a cost function of the current vehicle at the current moment; and determining the acceleration of the current vehicle at N moments when the cost function outputs the minimum value under the constraint of the second constraint relation model, and controlling the driver and the automatic driving system to accelerate the current vehicle according to the acceleration of the current vehicle at the current moment included in the acceleration of the N moments. The method provided by the invention is used for solving the problem of how to perform cooperative control on the vehicle by a driver and an automatic driving system in a vehicle following state.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving control technology, and in particular to a vehicle control method, device, equipment, medium and product in a following state. Background Art

[0002] The popularization of autonomous driving functions helps reduce driver fatigue and traffic accidents, and is crucial to the safe driving of vehicles.

[0003] In the existing technology, the autonomous driving system is usually unable to fully cope with all scenarios in complex traffic environments, so the driver is required to coordinate control with the autonomous driving system to improve the safety of the vehicle during driving.

[0004] However, the existing technology mainly focuses on the collaborative control method between the driver and the automatic driving system during the vehicle lane changing process. In the vehicle following state, the collaborative control method between the driver and the automatic driving system is relatively lacking. Summary of the invention

[0005] The present application provides a vehicle control method, device, equipment, medium and product in a following state, which are used to solve the problem of how a driver and an automatic driving system can collaboratively control a vehicle in a following state.

[0006] In a first aspect, the present application provides a vehicle control method in a following state, the method comprising:

[0007] Get the first constraint relationship model of the current vehicle in the following state, the first constraint relationship model includes: N state transition models, N+1 reference state models, N+1 relative acceleration definition models, N+1 relative speed definition models, N+1 distance definition models, N is a positive integer greater than or equal to 0, the kth state transition model is used to describe the relationship between the actual state of the current vehicle at the k+1th moment and the actual state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment, k is greater than or equal to 0 and less than or equal to N is an integer, the 0th moment is the current moment, the actual state includes: the actual distance between the current vehicle and the vehicle in front, the actual relative speed between the current vehicle and the vehicle in front, the mth reference state model is used to describe the relationship between the reference state of the current vehicle at the mth moment and the speed information of the current vehicle at the mth moment, m is an integer greater than or equal to 0 and less than or equal to N+1, the reference state includes the reference distance and the reference relative speed, the reference relative speed is 0, and the speed information includes: the relative speed between the current vehicle and the vehicle in front at the mth moment, and the absolute speed of the current vehicle at the mth moment;

[0008] Obtaining the actual state and speed information of the current vehicle at the current moment, and substituting them into the first constraint relationship model to obtain the second constraint relationship model;

[0009] Obtaining a cost function of the current vehicle at the current moment, the cost function being used to indicate the difference and total acceleration between N reference states and N actual states of the current vehicle when the current vehicle is controlled by N accelerations;

[0010] Determine the acceleration of the current vehicle at N moments when the cost function outputs a minimum value under the constraints of the second constraint relationship model, and control the driver and the automatic driving system to accelerate the current vehicle based on the acceleration of the current vehicle at the current moment included in the accelerations at the N moments.

[0011] In a possible design, according to the acceleration of the current vehicle at the current moment included in the accelerations at the N moments, controlling the driver and the automatic driving system to accelerate the current vehicle includes:

[0012] Using the acceleration of the current vehicle at the current moment as the acceleration of the automatic driving system, and prompting the driver with the acceleration of the current vehicle at the current moment as the expected driver acceleration;

[0013] Acquire the acceleration input by the driver as the actual driver acceleration;

[0014] The actual driver acceleration and the automatic driving system acceleration are weighted to obtain the target acceleration, where the sum of the weight of the actual driver acceleration and the weight of the automatic driving system acceleration is 1;

[0015] The target acceleration is input into the braking system to accelerate the current vehicle.

[0016] In one possible design, the actual driver acceleration and the automatic driving system acceleration are weighted to obtain a target acceleration, including:

[0017] Obtaining the actual distance between the current vehicle and the vehicle in front at the current moment, and comparing the actual distance with the reference distance to obtain a comparison result;

[0018] determining a weight of the actual driver acceleration according to the comparison result and the reference distance, and determining a weight of the acceleration of the automated driving system according to the weight of the actual driver acceleration;

[0019] According to the weight of the actual driver acceleration and the weight of the automatic driving system acceleration, the actual driver acceleration and the automatic driving system acceleration are weighted and summed to obtain the target acceleration.

[0020] In one possible design, the weight of the actual driver acceleration is determined based on the comparison result and the reference distance, including:

[0021] If the comparison result is that the actual distance is greater than or equal to the reference distance, a weight of the actual driver acceleration is determined according to the difference between the actual distance and the reference distance, and the reference distance, wherein the weight of the actual driver acceleration is positively correlated to the difference and negatively correlated to the reference distance;

[0022] If the comparison result is that the actual distance is less than the reference distance, the weight of the actual driver acceleration is determined to be 0.

[0023] In a possible design, the second constraint relationship model further includes:

[0024] The N accelerations of the current vehicle are all within a preset acceleration range, the relative speeds between the current vehicle and the vehicle in front at N moments are all within a preset speed range, and the distances between the current vehicle and the vehicle in front at N moments are all within a preset distance range.

[0025] In one possible design, the kth state transition model is as follows:

[0026]

[0027] Among them, x k+1 is the actual state of the vehicle at time k+1, x k is the actual state of the vehicle at time k, u k is the acceleration of the vehicle at time k, a fk is the acceleration of the vehicle ahead at time k, I is the identity matrix, Δt is the time difference between two adjacent moments.

[0028] In one possible design, the reference distance is calculated as follows:

[0029]

[0030] Among them, d ref is the reference distance between the current vehicle and the vehicle ahead at the current moment, V rel is the relative speed between the current vehicle and the vehicle ahead at the current moment, T delay is the braking delay time of the current vehicle, f(μ) is the preset braking coefficient, V is the absolute speed of the current vehicle at the current moment, a max is the current maximum deceleration of the vehicle.

[0031] In a possible design, obtaining the first constraint relationship model of the current vehicle in the following state includes:

[0032] Constructing the kth state space equation of the current vehicle, the kth state space equation is used to describe the relationship between the differential result of the real state of the current vehicle at the k+1th time and the real state of the current vehicle at the kth time, the acceleration of the current vehicle at the kth time, and the acceleration of the front vehicle at the kth time;

[0033] The kth state space equation is discretized to obtain the kth state transfer model.

[0034] In a second aspect, the present application provides a vehicle control device in a following state, the device comprising:

[0035] An acquisition module is used to acquire a first constraint relationship model of the current vehicle in a following state, the first constraint relationship model including: N state transition models, N+1 reference state models, N+1 relative acceleration definition models, N+1 relative speed definition models, and N+1 distance definition models, where N is a positive integer greater than or equal to 0, and the kth state transition model is used to describe the relationship between the actual state of the current vehicle at the k+1th moment and the actual state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment, and k is greater than or equal to 0 and less than or an integer equal to N, the 0th moment is the current moment, the actual state includes: the actual distance between the current vehicle and the vehicle in front, the actual relative speed between the current vehicle and the vehicle in front, the mth reference state model is used to describe the relationship between the reference state of the current vehicle at the mth moment and the speed information of the current vehicle at the mth moment, m is an integer greater than or equal to 0 and less than or equal to N+1, the reference state includes the reference distance and the reference relative speed, the reference relative speed is 0, and the speed information includes: the relative speed between the current vehicle and the vehicle in front at the mth moment, and the absolute speed of the current vehicle at the mth moment;

[0036] A substitution module is used to obtain the actual state and speed information of the current vehicle at the current moment, and substitute it into the first constraint relationship model to obtain the second constraint relationship model;

[0037] A cost function module is used to obtain the cost function of the current vehicle at the current moment, where the cost function is used to indicate the difference and total acceleration between N reference states and N actual states of the current vehicle when the current vehicle is controlled by N accelerations;

[0038] The acceleration module is used to determine the acceleration of the current vehicle at N moments when the cost function outputs a minimum value under the constraints of the second constraint relationship model, and control the driver and the automatic driving system to accelerate the current vehicle according to the acceleration of the current vehicle at the current moment included in the accelerations at the N moments.

[0039] In one possible design, the acceleration module includes: an automatic driving system acceleration module, an actual driver acceleration module, a weighting module, and an input module;

[0040] An automatic driving system acceleration module, used to use the acceleration of the current vehicle at the current moment as the automatic driving system acceleration, and to prompt the driver with the acceleration of the current vehicle at the current moment as the expected driver acceleration;

[0041] An actual driver acceleration module, used for obtaining the acceleration input by the driver as the actual driver acceleration;

[0042] A weighting module, used for weighting the actual driver acceleration and the automatic driving system acceleration to obtain a target acceleration, where the sum of the weight of the actual driver acceleration and the weight of the automatic driving system acceleration is 1;

[0043] The input module is used to input the target acceleration into the braking system to accelerate the current vehicle.

[0044] In a possible design, the weighting module includes: a comparison module, a weight module and a summation module;

[0045] A comparison module is used to obtain the actual distance between the current vehicle and the vehicle in front at the current moment, and compare the actual distance with the reference distance to obtain a comparison result;

[0046] A weight module, used to determine a weight of the actual driver acceleration according to the comparison result and the reference distance, and determine a weight of the acceleration of the automatic driving system according to the weight of the actual driver acceleration;

[0047] The summing module is used to perform weighted summation of the actual driver acceleration and the automatic driving system acceleration according to the weight of the actual driver acceleration and the weight of the automatic driving system acceleration to obtain a target acceleration.

[0048] In one possible design, the weight module includes: a first determination module and a second determination module;

[0049] a first determination module, configured to determine a weight of the actual driver acceleration according to a difference between the actual distance and the reference distance and the reference distance if the comparison result is that the actual distance is greater than or equal to the reference distance, wherein the weight of the actual driver acceleration is positively correlated to the difference and negatively correlated to the reference distance;

[0050] The second determination module is configured to determine that the weight of the actual driver acceleration is 0 if the comparison result shows that the actual distance is less than the reference distance.

[0051] In a possible design, the second constraint relationship model further includes:

[0052] The N accelerations of the current vehicle are all within a preset acceleration range, the relative speeds between the current vehicle and the vehicle in front at N moments are all within a preset speed range, and the distances between the current vehicle and the vehicle in front at N moments are all within a preset distance range.

[0053] In one possible design, the kth state transition model is as follows:

[0054]

[0055] Among them, x k+1 is the actual state of the vehicle at time k+1, x k is the actual state of the vehicle at time k, u k is the acceleration of the vehicle at time k, a fk is the acceleration of the vehicle ahead at time k, I is the identity matrix, Δt is the time difference between two adjacent moments.

[0056] In one possible design, the reference distance is calculated as follows:

[0057]

[0058] Among them, d ref is the reference distance between the current vehicle and the vehicle ahead at the current moment, V rel is the relative speed between the current vehicle and the vehicle ahead at the current moment, T delay is the braking delay time of the current vehicle, f(μ) is the preset braking coefficient, V is the absolute speed of the current vehicle at the current moment, a max is the current maximum deceleration of the vehicle.

[0059] In one possible design, the acquisition module includes: a building block and a discrete module;

[0060] A construction module is used to construct a k-th state space equation of the current vehicle, where the k-th state space equation is used to describe the relationship between the differential result of the real state of the current vehicle at the k+1th moment and the real state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment;

[0061] The discretization module is used to discretize the kth state space equation to obtain the kth state transfer model.

[0062] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0063] Memory stores computer-executable instructions;

[0064] The processor executes the computer-executable instructions stored in the memory to implement a vehicle control method in a following state according to the first aspect of the invention.

[0065] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement a vehicle control method in a following state according to the invention content of the first aspect.

[0066] In a fifth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it is used to implement a vehicle control method in a following state according to the invention content of the first aspect.

[0067] The present application provides a vehicle control method, device, equipment, medium and product in a following state, the method comprising: obtaining a first constraint relationship model of the current vehicle in the following state, the first constraint relationship model comprising: N state transition models, N+1 reference state models, N+1 relative acceleration definition models, N+1 relative speed definition models, and N+1 distance definition models, N is a positive integer greater than or equal to 0, the kth state transition model is used to describe the relationship between the actual state of the current vehicle at the k+1th moment and the actual state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment, k is an integer greater than or equal to 0 and less than or equal to N, the 0th moment is the current moment, the actual state comprises: the actual distance between the current vehicle and the front vehicle, the actual relative speed between the current vehicle and the front vehicle, the mth reference state model is used to describe the reference state of the current vehicle at the mth moment The relationship between the state and the speed information of the current vehicle at the mth moment, m is an integer greater than or equal to 0 and less than or equal to N+1, the reference state includes a reference distance and a reference relative speed, the reference relative speed is 0, and the speed information includes: the relative speed between the current vehicle and the front vehicle at the mth moment, and the absolute speed of the current vehicle at the mth moment; the actual state and speed information of the current vehicle at the current moment are obtained, and are substituted into the first constraint relationship model to obtain the second constraint relationship model; the cost function of the current vehicle at the current moment is obtained, and the cost function is used to indicate the difference and total acceleration between the N reference states and the N actual states of the current vehicle when the current vehicle is controlled by N accelerations; determine the acceleration of the current vehicle at N moments when the cost function outputs a minimum value under the constraint of the second constraint relationship model, and control the driver and the automatic driving system to accelerate the current vehicle according to the acceleration of the current vehicle at the current moment included in the acceleration of the N moments.The following technical effects are achieved: by obtaining the first constraint relationship model of the current vehicle in the following state, and substituting the actual state and speed information of the current vehicle at the current moment into the first constraint relationship model, a second constraint relationship model is obtained, and then under the constraint of the second constraint relationship model, the N accelerations corresponding to the current vehicle from the current moment to the N-1th moment in the future are solved when the output value of the cost function is the minimum, and then the driver and the automatic driving system are controlled to accelerate the current vehicle according to the acceleration corresponding to the current moment, so as to achieve real-time adjustment of the acceleration of the current vehicle in the following process to cope with various complex and changeable traffic conditions, thereby further improving the safety and comfort of vehicle driving; the braking danger distance of the current vehicle is calculated in real time according to the algorithm model for calculating the braking danger distance, and the braking danger distance is defined as the reference distance, and then the state transfer model is constructed according to the dynamically changing reference distance to obtain the first constraint relationship model, so as to calculate the acceleration of the current vehicle at the current moment and multiple moments in the future according to the first constraint relationship model, so that the calculated value of the acceleration used to control the current vehicle is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0069] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0070] Figure 1 A flow chart of a vehicle control method in a following state provided in an embodiment of the present application Figure 1 ;

[0071] Figure 2 A flow chart of a vehicle control method in a following state provided in an embodiment of the present application Figure 2 ;

[0072] Figure 3 A schematic diagram of the structure of a vehicle control device in a following state provided in an embodiment of the present application;

[0073] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0074] Reference numerals:

[0075] 310-acquisition module; 320-substitution module; 330-cost function module; 340-acceleration module;

[0076] 410 - processor; 420 - memory; 430 - communication component; 440 - bus. DETAILED DESCRIPTION

[0077] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0078] In the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will appreciate that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more.

[0079] It should be noted that the "at..." in the embodiment of the present application can be the instant when a certain situation occurs, or can be a period of time after a certain situation occurs, and the embodiment of the present application does not specifically limit this. In addition, the vehicle control method in the following state provided in the embodiment of the present application is only used as an example, and the vehicle control method in the following state can also include more or less content.

[0080] The widespread use of autonomous driving technology can help reduce driver fatigue, reduce the incidence of traffic accidents, and thus improve road safety. However, in the face of complex traffic environments, existing autonomous driving systems still find it difficult to handle all possible situations completely independently, which requires that in some cases the driver must coordinate control with the autonomous driving system to jointly ensure driving safety.

[0081] Most of the current research and technology development focuses on the collaborative control method between the driver and the automatic driving system during the vehicle lane change process, while less attention is paid to the collaborative control method under vehicle following (i.e., car-following state). In other words, in the more common car-following driving state, that is, when the current vehicle follows the vehicle in front at a certain distance and speed, how to effectively achieve the collaborative control between the driver and the automatic driving system to deal with unforeseen situations such as sudden deceleration and emergency braking of the vehicle in front is still a key issue that needs to be solved urgently.

[0082] Based on this, the embodiment of the present application proposes a vehicle control method, device, equipment, medium and product in the following state, which can be used in the field of autonomous driving control technology, aiming to solve the above technical problems of the prior art, to fill this gap in the prior art, and to provide a solution for realizing efficient collaborative control of the driver and the autonomous driving system in the vehicle following state. The method optimizes the interaction mechanism between the driver and the autonomous driving system so that the two can work together more intelligently and efficiently, and adjusts the acceleration of the current vehicle in real time during the following process to cope with various complex and changeable traffic conditions, thereby further improving the safety and comfort of vehicle driving.

[0083] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0084] Figure 1 A flow chart of a vehicle control method in a following state provided in an embodiment of the present application Figure 1 .like Figure 1 As shown, the method includes:

[0085] S101. Obtain a first constraint relationship model of the current vehicle in a car-following state.

[0086] In the embodiment of the present application, the execution subject of a vehicle control method in a following state can be an electronic control unit (ECU) in the vehicle, which can be a controller specially designed for vehicle control in a following state, or a brake control unit (BCU) in the vehicle, and no specific limitation is made here. In addition, the acceleration in the embodiment of the present application refers to the braking acceleration during the vehicle braking process. In the embodiment of the present application, for the convenience of description, the magnitude of the acceleration value refers to the absolute value of the acceleration.

[0087] The first constraint relationship model includes: N state transfer models, N+1 reference state models, N+1 relative acceleration definition models, N+1 relative speed definition models, and N+1 distance definition models, where N is a positive integer greater than or equal to 0.

[0088] The kth state transition model is used to describe the relationship between the actual state of the current vehicle at the k+1th moment and the actual state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment, k is an integer greater than or equal to 0 and less than or equal to N, and the 0th moment is the current moment.

[0089] Specifically, the N state transition models include from the 0th moment (i.e., the current moment, k is 0) to the first moment (k is 1), the first moment to the second moment (k is 2), the second moment to the third moment (k is 3), and so on, until the N-1th moment (k is N-1) to the Nth moment (k is N), a total of N state transition models.

[0090] Furthermore, the k-th state transition model is as follows:

[0091]

[0092] Among them, x k+1 is the actual state of the vehicle at time k+1, x k is the actual state of the vehicle at time k, u k is the acceleration of the vehicle at time k, a fk is the acceleration of the vehicle ahead at time k, I is the identity matrix, Δt is the time difference between two adjacent moments, which is a preset value. That is, the actual state of the current vehicle at moment k+1 is calculated based on the actual state of the current vehicle at moment k, the acceleration at moment k, and the acceleration of the preceding vehicle at moment k.

[0093] The actual state includes: the actual distance between the current vehicle and the vehicle in front, and the actual relative speed between the current vehicle and the vehicle in front, which can be obtained through the sensor of the current vehicle.

[0094] The mth reference state model is used to describe the relationship between the reference state of the current vehicle at the mth moment and the speed information of the current vehicle at the mth moment, where m is an integer greater than or equal to 0 and less than or equal to N+1. The reference state includes a reference distance and a reference relative speed, and the reference relative speed is 0. Reference state x ref =[d ref , v ref ] T=[d ref ,0] T , where d ref is the reference distance, v ref is the reference relative speed, which is 0. A reference relative speed of 0 means that for the autonomous driving system, in order to maintain a stable following state, the desired speed of the current vehicle is the same as the speed of the vehicle in front. In other words, the reference state at any m-th moment is determined by the reference distance d. ref and 0. Reference distance d ref It is calculated based on two variables: the relative speed between the current vehicle and the vehicle in front at the mth moment, the speed of the current vehicle at the mth moment, and three fixed parameters: system delay time, braking factor and maximum deceleration of the current vehicle.

[0095] Furthermore, the calculation formula of the reference distance is as follows:

[0096]

[0097] Among them, d ref is the reference distance between the current vehicle and the vehicle ahead at the current moment, V rel is the relative speed between the current vehicle and the vehicle ahead at the current moment, T delay is the braking delay time of the current vehicle, which refers to the time required for the autonomous driving system to detect potential danger and start to perform braking operations. In the algorithm model (Seungwuk Moon model) for calculating the braking danger distance of the automatic emergency braking (AEB) system, this value can usually be set to 1.2 seconds, f(μ) is the preset braking coefficient (such as 0.2), V is the absolute speed of the current vehicle at the current moment, and a max The maximum deceleration of the current vehicle is the absolute value of the maximum braking acceleration that the current vehicle can achieve. In the Seungwuk Moon model, it can be set to 6m / S 2 . Reference distance d ref It can also be called the safety distance or braking danger distance between the current vehicle and the vehicle in front, which means the total distance traveled from the time the driver senses the danger and takes braking measures to the time the current vehicle stops completely at a specific speed.

[0098] Specifically, the reference distance between the current vehicle and the vehicle in front at the current moment can be calculated according to the existing Seungwuk Moon model. From the calculation formula of the reference distance, it can be seen that since the speeds of the current vehicle and the vehicle in front are constantly changing, the reference distance is also constantly changing dynamically.

[0099] The speed information includes: the relative speed between the current vehicle and the vehicle in front at the mth moment, and the absolute speed of the current vehicle at the mth moment.

[0100] Specifically, the calculation formula for the actual distance between the current vehicle and the vehicle in front is:

[0101] d=d f -d h

[0102] Where d is the actual distance between the current vehicle and the vehicle in front, d f is the longitudinal position of the vehicle ahead, d h is the longitudinal position of the current vehicle. That is, the mth distance definition model is used to define the actual distance between the current vehicle and the front vehicle at the mth moment as the difference between the longitudinal position of the front vehicle at the mth moment and the longitudinal position of the current vehicle.

[0103] The relative speed between the current vehicle and the vehicle in front at the current moment Among them, V f is the speed of the vehicle in front, and V is the absolute speed of the current vehicle at the current moment. That is, the mth relative speed definition model is used to define the relative speed between the current vehicle and the vehicle in front at the mth moment as the difference between the speed of the vehicle in front at the mth moment and the absolute speed of the current vehicle. The actual state of the current vehicle x = [d, V rel ] T .

[0104] The relative acceleration between the current vehicle and the vehicle ahead Among them, a f is the acceleration of the vehicle ahead, a h is the acceleration of the current vehicle at the current moment. That is, the mth relative acceleration definition model is used to define the relative acceleration between the current vehicle and the front vehicle at the mth moment as the difference between the acceleration of the front vehicle and the acceleration of the current vehicle at the mth moment.

[0105] S102: Obtain the actual state and speed information of the current vehicle at the current moment, and substitute them into the first constraint relationship model to obtain a second constraint relationship model.

[0106] Specifically, the ECU obtains the second constraint relationship model of the current vehicle at the current moment according to the actual state and speed information of the current vehicle at the current moment.

[0107] Furthermore, the second constraint relationship model also includes:

[0108] The N accelerations of the current vehicle are all within the preset acceleration range, the relative speed between the current vehicle and the vehicle in front at N moments is all within the preset speed range, and the distance between the current vehicle and the vehicle in front at N moments is all within the preset distance range.

[0109] x min ≤x k ≤x max

[0110] u min ≤u k ≤u max

[0111] Among them, x k is the actual state of the current vehicle at time k, including the actual distance between the current vehicle and the vehicle in front, and the actual relative speed between the current vehicle and the vehicle in front at time k. min The minimum value of the preset state, including the minimum value of the preset distance range between the current vehicle and the vehicle in front, and the minimum value of the preset speed range between the current vehicle and the vehicle in front. max It is the maximum value of the preset state, including the maximum value of the preset distance range between the current vehicle and the vehicle in front, and the maximum value of the preset speed range between the current vehicle and the vehicle in front. k is the acceleration of the vehicle at time k, u min is the minimum value of the preset acceleration range, u max It is the maximum value of the preset acceleration range.

[0112] S103: Obtain the cost function of the current vehicle at the current moment.

[0113] Specifically, the cost function is used to indicate the difference and total acceleration between N reference states and N actual states of the current vehicle when the current vehicle is controlled through N accelerations.

[0114] The cost function constructed according to Model Predictive Control (MPC) is:

[0115]

[0116] Among them, minJ is the output value of the cost function, is the reference state of the current vehicle at time k, Q = diag (Q d , Q v ), Q d is the error weight of the actual distance between the current vehicle and the vehicle in front, representing the penalty for the error in the actual distance; Q vis the error weight of the actual relative speed between the current vehicle and the vehicle in front, representing the penalty for the error of the actual relative speed. R is the weight of the acceleration of the current vehicle, representing the penalty for the input (acceleration). N is the actual state of the current vehicle at time N, is the reference state of the current vehicle at time N, and F is the terminal weight, which is used to control the error of the actual distance and the error of the actual relative speed at the final moment (time N).

[0117] In one possible implementation, F=Q.

[0118] S104. Determine the acceleration of the current vehicle at the N+1 moment when the cost function outputs the minimum value under the constraints of the second constraint relationship model, and control the driver and the automatic driving system to accelerate the current vehicle according to the acceleration of the current vehicle at the current moment included in the acceleration at the N+1 moment.

[0119] Specifically, we need to find the value from u0 to u corresponding to the current vehicle from the current moment to the N-1th moment in the future when the output value minJ of the cost function is the smallest. N-1 There are N accelerations in total. Then, the driver and the automatic driving system are controlled to accelerate the current vehicle according to the acceleration u0 corresponding to the current moment.

[0120] The present embodiment provides a vehicle control method in a following state, the method comprising: obtaining a first constraint relationship model of the current vehicle in the following state, the first constraint relationship model comprising: N state transition models, N+1 reference state models, N+1 relative acceleration definition models, N+1 relative speed definition models, and N+1 distance definition models, N is a positive integer greater than or equal to 0, the kth state transition model is used to describe the relationship between the actual state of the current vehicle at the k+1th moment and the actual state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment, k is an integer greater than or equal to 0 and less than or equal to N, the 0th moment is the current moment, the actual state comprises: the actual distance between the current vehicle and the front vehicle, the actual relative speed between the current vehicle and the front vehicle, the mth reference state model is used to describe the relationship between the reference state of the current vehicle at the mth moment and the acceleration of the current vehicle at the mth moment. The method comprises the following steps: obtaining a first constraint relationship model and a second constraint relationship model, wherein m is an integer greater than or equal to 0 and less than or equal to N+1, wherein the reference state includes a reference distance and a reference relative speed, wherein the reference relative speed is 0, and wherein the speed information includes: the relative speed between the current vehicle and the vehicle in front at the mth moment, and the absolute speed of the current vehicle at the mth moment; obtaining the actual state and speed information of the current vehicle at the current moment, and substituting them into the first constraint relationship model to obtain the second constraint relationship model; obtaining the cost function of the current vehicle at the current moment, wherein the cost function is used to indicate the difference and total acceleration between N reference states and N actual states of the current vehicle when the current vehicle is controlled by N accelerations; determining the acceleration of the current vehicle at N moments when the cost function outputs a minimum value under the constraint of the second constraint relationship model, and controlling the driver and the automatic driving system to accelerate the current vehicle according to the acceleration of the current vehicle at the current moment included in the accelerations at the N moments.The following technical effects are achieved: by obtaining the first constraint relationship model of the current vehicle in the following state, and substituting the actual state and speed information of the current vehicle at the current moment into the first constraint relationship model, a second constraint relationship model is obtained, and then under the constraint of the second constraint relationship model, the N accelerations corresponding to the current vehicle from the current moment to the N-1th moment in the future are solved when the output value of the cost function is the minimum, and then the driver and the automatic driving system are controlled to accelerate the current vehicle according to the acceleration corresponding to the current moment, so as to achieve real-time adjustment of the acceleration of the current vehicle in the following process to cope with various complex and changeable traffic conditions, thereby further improving the safety and comfort of vehicle driving; the braking danger distance of the current vehicle is calculated in real time according to the algorithm model for calculating the braking danger distance, and the braking danger distance is defined as the reference distance, and then the state transfer model is constructed according to the dynamically changing reference distance to obtain the first constraint relationship model, so as to calculate the acceleration of the current vehicle at the current moment and multiple moments in the future according to the first constraint relationship model, so that the calculated value of the acceleration used to control the current vehicle is more accurate.

[0121] Figure 2 A flow chart of a vehicle control method in a following state provided in an embodiment of the present application Figure 2 In one possible example, Figure 2 As shown, in this embodiment Figure 1 Based on the embodiment, how the driver and the automatic driving system accelerate the current vehicle according to the current acceleration is described in detail. Figure 2 As shown, the method includes:

[0122] S201. Obtain a first constraint relationship model of the current vehicle in a car-following state.

[0123] S202: Obtain the actual state and speed information of the current vehicle at the current moment, and substitute them into the first constraint relationship model to obtain a second constraint relationship model.

[0124] S203: Obtain the cost function of the current vehicle at the current moment.

[0125] S204: Determine the acceleration of the current vehicle at N moments when the cost function outputs a minimum value under the constraints of the second constraint relationship model.

[0126] S201 - S204 are similar to S101 - S104 and will not be described in detail in this embodiment.

[0127] S205. Using the acceleration of the current vehicle at the current moment as the acceleration of the automatic driving system, and using the acceleration of the current vehicle at the current moment as the expected driver acceleration to prompt the driver.

[0128] In the embodiment of the present application, the driver and the automatic driving system are controlled to accelerate the current vehicle according to the acceleration of the current vehicle at the current moment included in the accelerations at N moments. This includes using the acceleration of the current vehicle at the current moment as the acceleration of the automatic driving system, and using the acceleration of the current vehicle at the current moment as the expected driver acceleration prompt to the driver. And different levels of brake takeover prompts can be output to the driver according to the numerical value of the expected driver acceleration. For example: when the expected driver acceleration is less than the first preset acceleration threshold (such as 0.315m / S 2 ), output a first-level takeover prompt (such as: please lightly step on the brake to take over); when the expected driver acceleration is greater than or equal to the first preset acceleration threshold and less than or equal to the second preset acceleration threshold (such as 1m / S 2 ), a second-level takeover prompt is output (such as: please brake to take over); when the expected driver acceleration is greater than the second preset acceleration threshold, a third-level takeover prompt is output (such as: please step on the brake deeply to take over).

[0129] Furthermore, the ECU can send a brake takeover prompt to a display device (such as the dashboard of the current vehicle), a lighting device or a vibration device, etc. The brake takeover prompt can be a text prompt, a voice prompt, or light flashing of different frequencies, a vibration prompt, etc.

[0130] S206: Acquire the acceleration input by the driver as the actual driver acceleration.

[0131] Specifically, when the driver receives a brake takeover prompt and inputs a braking acceleration to perform a braking operation on the current vehicle, the ECU can further obtain the acceleration input by the driver as the actual driver acceleration.

[0132] S207: Obtain the actual distance between the current vehicle and the vehicle in front at the current moment, and compare the actual distance with the reference distance to obtain a comparison result.

[0133] In the embodiment of the present application, the ECU can weight the actual driver acceleration and the automatic driving system acceleration to obtain the target acceleration, and the sum of the weight of the actual driver acceleration and the weight of the automatic driving system acceleration is 1. Specifically, in the process of the driver and the automatic driving system jointly controlling the current vehicle, it is necessary to ensure that the current vehicle can successfully avoid obstacles, and to avoid the automatic driving system from intervening in the vehicle control too early, thereby affecting the driver's normal driving operation. Therefore, it is necessary to minimize the interference of the automatic driving system on the driver's normal driving. Therefore, in this embodiment, the reference distance is used as a calculation parameter to determine the weight of the actual driver acceleration. Specifically, the ECU can first obtain the actual distance between the current vehicle and the vehicle in front at the current moment through the sensor, and then compare the actual distance with the reference distance, and obtain the comparison result.

[0134] S208: If the comparison result is that the actual distance is greater than or equal to the reference distance, determine the weight of the actual driver acceleration according to the difference between the actual distance and the reference distance, and the reference distance.

[0135] In the embodiment of the present application, the ECU can determine the weight of the actual driver acceleration based on the comparison result and the reference distance. Specifically, if the comparison result is that the actual distance is greater than or equal to the reference distance, the weight of the actual driver acceleration is determined based on the difference between the actual distance and the reference distance, and the reference distance. The weight of the actual driver acceleration is positively correlated to the difference and negatively correlated to the reference distance. Specifically, when the actual distance is greater than or equal to the reference distance, the calculation formula for determining the weight of the actual driver acceleration is:

[0136]

[0137] Where λ is the weight of the actual driver acceleration, d is the actual distance between the current vehicle and the vehicle in front, and d ref is the reference distance between the current vehicle and the vehicle in front at the current moment.

[0138] From the calculation formula of the weight of the actual driver's acceleration, it can be seen that when the actual distance is greater than or equal to the reference distance, as the distance between the current vehicle and the vehicle in front gradually decreases, the weight of the actual driver's acceleration also gradually decreases. Since the sum of the weight of the actual driver's acceleration and the weight of the automatic driving system acceleration is 1, the weight of the automatic driving system acceleration is gradually increasing to ensure the safety of the current vehicle and avoid collision between the current vehicle and the vehicle in front.

[0139] S209: If the comparison result is that the actual distance is smaller than the reference distance, determine that the weight of the actual driver acceleration is 0.

[0140] Specifically, when the actual distance is less than the reference distance, the current vehicle will be completely controlled by the autonomous driving system to brake in time to avoid a collision between the current vehicle and the vehicle in front.

[0141] S210. Determine the weight of the acceleration of the automatic driving system according to the weight of the actual driver acceleration.

[0142] In this embodiment, the sum of the weight of the actual driver acceleration and the weight of the automatic driving system acceleration is 1. After determining the weight of the actual driver acceleration at the current moment, the weight of the automatic driving system acceleration can be determined to be 1-λ.

[0143] S211. According to the weight of the actual driver acceleration and the weight of the automatic driving system acceleration, a weighted sum is performed on the actual driver acceleration and the automatic driving system acceleration to obtain a target acceleration.

[0144] In this embodiment, the calculation formula of the target acceleration is:

[0145] a=λa D +(1-λ)a A

[0146] Among them, a is the target acceleration for accelerating the current vehicle, a D is the actual driver acceleration, a A The acceleration of the autonomous driving system, here a A =u0.

[0147] S212: Input the target acceleration into the braking system to accelerate the current vehicle.

[0148] In this embodiment, after calculating the target acceleration, the ECU can perform braking control on the current vehicle according to the target acceleration.

[0149] Furthermore, obtaining the first constraint relationship model of the current vehicle in the following state also includes: constructing the kth state space equation of the current vehicle, the kth state space equation is used to describe the relationship between the differential result of the real state of the current vehicle at the k+1th moment and the real state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment.

[0150] Specifically, the kth state space equation is:

[0151]

[0152] Then, the kth state space equation is discretized to obtain the kth state transition model. Here, the forward Euler method can be used to Discretize it and get

[0153] A vehicle control method in a following state provided in an embodiment of the present application can promptly prompt the driver to control the vehicle by sending a brake takeover prompt to a display device (such as the dashboard of the current vehicle), a lighting device or a vibration device and other vehicle equipment; a reference distance is used as a calculation parameter for determining the weight of the actual driver's acceleration, thereby achieving a smooth switching of the control rights of the current vehicle between the driver and the automatic driving system, and improving the driving safety and comfort of the current vehicle; when the actual distance is greater than or equal to the reference distance, as the distance between the current vehicle and the vehicle in front gradually decreases, the weight of the actual driver's acceleration also gradually decreases, and when the actual distance is less than the reference distance, the current vehicle is completely controlled by the automatic driving system to achieve timely emergency braking and avoid a collision between the current vehicle and the vehicle in front.

[0154] The embodiment of the present invention can divide the electronic device or the main control device into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0155] Figure 3 This is a schematic diagram of the structure of a vehicle control device in a following state provided by an embodiment of the present application. Figure 3 As shown, the vehicle control device in the following state includes: an acquisition module 310, a substitution module 320, a cost function module 330 and an acceleration module 340;

[0156] The acquisition module 310 is used to acquire the first constraint relationship model of the current vehicle in the following state, the first constraint relationship model includes: N state transition models, N+1 reference state models, N+1 relative acceleration definition models, N+1 relative speed definition models, and N+1 distance definition models, N is a positive integer greater than or equal to 0, and the kth state transition model is used to describe the relationship between the actual state of the current vehicle at the k+1th moment and the actual state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment, k is greater than or equal to 0, and An integer less than or equal to N, the 0th moment is the current moment, the actual state includes: the actual distance between the current vehicle and the vehicle in front, the actual relative speed between the current vehicle and the vehicle in front, the mth reference state model is used to describe the relationship between the reference state of the current vehicle at the mth moment and the speed information of the current vehicle at the mth moment, m is an integer greater than or equal to 0 and less than or equal to N+1, the reference state includes the reference distance and the reference relative speed, the reference relative speed is 0, and the speed information includes: the relative speed between the current vehicle and the vehicle in front at the mth moment, and the absolute speed of the current vehicle at the mth moment;

[0157] The substitution module 320 is used to obtain the actual state and speed information of the current vehicle at the current moment, and substitute them into the first constraint relationship model to obtain the second constraint relationship model;

[0158] A cost function module 330 is used to obtain a cost function of the current vehicle at a current moment, where the cost function is used to indicate the difference between N reference states and N actual states of the current vehicle and the total acceleration when the current vehicle is controlled by N accelerations;

[0159] The acceleration module 340 is used to determine the acceleration of the current vehicle at N moments when the cost function outputs a minimum value under the constraints of the second constraint relationship model, and control the driver and the automatic driving system to accelerate the current vehicle according to the acceleration of the current vehicle at the current moment included in the accelerations at the N moments.

[0160] In one possible design, the acceleration module 340 includes: an automatic driving system acceleration module, an actual driver acceleration module, a weighting module, and an input module;

[0161] An automatic driving system acceleration module, used to use the acceleration of the current vehicle at the current moment as the automatic driving system acceleration, and to prompt the driver with the acceleration of the current vehicle at the current moment as the expected driver acceleration;

[0162] An actual driver acceleration module, used for obtaining the acceleration input by the driver as the actual driver acceleration;

[0163] A weighting module, used for weighting the actual driver acceleration and the automatic driving system acceleration to obtain a target acceleration, where the sum of the weight of the actual driver acceleration and the weight of the automatic driving system acceleration is 1;

[0164] The input module is used to input the target acceleration into the braking system to accelerate the current vehicle.

[0165] In a possible design, the weighting module includes: a comparison module, a weight module and a summation module;

[0166] A comparison module is used to obtain the actual distance between the current vehicle and the vehicle in front at the current moment, and compare the actual distance with the reference distance to obtain a comparison result;

[0167] A weight module, used to determine a weight of the actual driver acceleration according to the comparison result and the reference distance, and determine a weight of the acceleration of the automatic driving system according to the weight of the actual driver acceleration;

[0168] The summing module is used to perform weighted summation of the actual driver acceleration and the automatic driving system acceleration according to the weight of the actual driver acceleration and the weight of the automatic driving system acceleration to obtain a target acceleration.

[0169] In one possible design, the weight module includes: a first determination module and a second determination module;

[0170] a first determination module, configured to determine a weight of the actual driver acceleration according to a difference between the actual distance and the reference distance and the reference distance if the comparison result is that the actual distance is greater than or equal to the reference distance, wherein the weight of the actual driver acceleration is positively correlated to the difference and negatively correlated to the reference distance;

[0171] The second determination module is configured to determine that the weight of the actual driver acceleration is 0 if the comparison result shows that the actual distance is less than the reference distance.

[0172] In a possible design, the second constraint relationship model further includes:

[0173] The N accelerations of the current vehicle are all within a preset acceleration range, the relative speeds between the current vehicle and the vehicle in front at N moments are all within a preset speed range, and the distances between the current vehicle and the vehicle in front at N moments are all within a preset distance range.

[0174] In one possible design, the kth state transition model is as follows:

[0175]

[0176] Among them, x k+1 is the actual state of the vehicle at time k+1, xk is the actual state of the vehicle at time k, u k is the acceleration of the vehicle at time k, a fk is the acceleration of the vehicle ahead at time k, I is the identity matrix, Δt is the time difference between two adjacent moments.

[0177] In one possible design, the reference distance is calculated as follows:

[0178]

[0179] Among them, d ref is the reference distance between the current vehicle and the vehicle ahead at the current moment, V rel is the relative speed between the current vehicle and the vehicle ahead at the current moment, T delay is the braking delay time of the current vehicle, f(μ) is the preset braking coefficient, V is the absolute speed of the current vehicle at the current moment, a max is the current maximum deceleration of the vehicle.

[0180] In one possible design, the acquisition module 310 includes: a construction module and a discrete module;

[0181] A construction module is used to construct a k-th state space equation of the current vehicle, where the k-th state space equation is used to describe the relationship between the differential result of the real state of the current vehicle at the k+1th moment and the real state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment;

[0182] The discretization module is used to discretize the kth state space equation to obtain the kth state transfer model.

[0183] The present embodiment provides a vehicle control device in a car-following state, which can execute a vehicle control method in a car-following state of the above-mentioned embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0184] In the specific implementation of the aforementioned vehicle control device in a following state, each module can be implemented as a processor, and the processor can execute computer execution instructions stored in the memory, so that the processor executes the aforementioned vehicle control method in a following state.

[0185] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4As shown, the electronic device includes: at least one processor 410 and a memory 420. The electronic device also includes a communication component 430. The processor 410, the memory 420 and the communication component 430 are connected via a bus 440.

[0186] In the specific implementation process, at least one processor 410 executes the computer execution instructions stored in the memory 420, so that at least one processor 410 executes a vehicle control method in a following state as executed by the electronic device side above.

[0187] The specific implementation process of the processor 410 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0188] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0189] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0190] 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. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0191] The above-mentioned functions implemented by the electronic device and the main control device introduce the scheme provided by the embodiment of the present invention. It can be understood that in order to implement the above-mentioned functions, the electronic device or the main control device includes a hardware structure and / or software module corresponding to the execution of each function. In combination with the units and algorithm steps of each example described in the embodiment disclosed in the embodiment of the present invention, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present invention.

[0192] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, it is used to implement the vehicle control method in the following state as described above.

[0193] The above-mentioned readable storage medium 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 memory, 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.

[0194] 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 a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in an electronic device or a main control device.

[0195] The present application also provides a computer program product, which includes a computer program. The computer program is stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium. At least one processor executes the computer program so that the electronic device executes the solution provided in any of the above embodiments.

[0196] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by hardware related to program instructions. The above program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above method embodiments are executed; and the above storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0197] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle control method in a following state, characterized in that: include: Obtain a first constraint relationship model of the current vehicle in a following state, the first constraint relationship model comprising: N state transition models, N+1 reference state models, N+1 relative acceleration definition models, N+1 relative speed definition models, and N+1 distance definition models, N is a positive integer greater than or equal to 0, the kth state transition model is used to describe the relationship between the actual state of the current vehicle at the k+1th moment and the actual state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the front vehicle at the kth moment, the k is an integer greater than or equal to 0 and less than or equal to N, the 0th moment The mth moment is the current moment, the actual state includes: the actual distance between the current vehicle and the vehicle in front, the actual relative speed between the current vehicle and the vehicle in front, the mth reference state model is used to describe the relationship between the reference state of the current vehicle at the mth moment and the speed information of the current vehicle at the mth moment, m is an integer greater than or equal to 0 and less than or equal to N+1, the reference state includes a reference distance and a reference relative speed, the reference relative speed is 0, and the speed information includes: the relative speed between the current vehicle and the vehicle in front at the mth moment, and the absolute speed of the current vehicle at the mth moment; Obtaining the actual state and speed information of the current vehicle at the current moment, and substituting them into the first constraint relationship model to obtain a second constraint relationship model; Acquire a cost function of the current vehicle at a current moment, the cost function being used to indicate the difference and total acceleration between the N reference states and the N actual states of the current vehicle when the current vehicle is controlled by the N accelerations; Determine the acceleration of the current vehicle at N moments when the cost function outputs a minimum value under the constraints of the second constraint relationship model, and control the driver and the automatic driving system to accelerate the current vehicle based on the acceleration of the current vehicle at a current moment included in the accelerations at the N moments.

2. The method according to claim 1, characterized in that The controlling the driver and the automatic driving system to accelerate the current vehicle according to the acceleration of the current vehicle at the current moment included in the accelerations at the N moments includes: Using the acceleration of the current vehicle at the current moment as the acceleration of the automatic driving system, and prompting the driver with the acceleration of the current vehicle at the current moment as the expected driver acceleration; acquiring the acceleration input by the driver as the actual driver acceleration; Weighting the actual driver acceleration and the automatic driving system acceleration to obtain a target acceleration, wherein the sum of the weight of the actual driver acceleration and the weight of the automatic driving system acceleration is 1; The target acceleration is input into a braking system to accelerate the current vehicle.

3. The method according to claim 2, characterized in that The step of weighting the actual driver acceleration and the automatic driving system acceleration to obtain a target acceleration includes: Acquire the actual distance between the current vehicle and the vehicle in front at the current moment, and compare the actual distance with the reference distance to obtain a comparison result; determining a weight of the actual driver acceleration according to the comparison result and the reference distance, and determining a weight of the automatic driving system acceleration according to the weight of the actual driver acceleration; According to the weight of the actual driver acceleration and the weight of the automatic driving system acceleration, a weighted sum is performed on the actual driver acceleration and the automatic driving system acceleration to obtain the target acceleration.

4. The method according to claim 3, characterized in that The step of determining the weight of the actual driver acceleration according to the comparison result and the reference distance comprises: If the comparison result is that the actual distance is greater than or equal to the reference distance, determining the weight of the actual driver acceleration according to the difference between the actual distance and the reference distance and the reference distance, wherein the weight of the actual driver acceleration is positively correlated to the difference and negatively correlated to the reference distance; If the comparison result is that the actual distance is smaller than the reference distance, the weight of the actual driver acceleration is determined to be 0.

5. The method according to claim 4, characterized in that The second constraint relationship model also includes: The N accelerations of the current vehicle are all within a preset acceleration range, the relative speed between the current vehicle and the vehicle in front at N+1 moments is all within a preset speed range, and the distance between the current vehicle and the vehicle in front at N+1 moments is all within a preset distance range.

6. The method according to any one of claims 1 to 5, characterized in that The kth state transition model is as follows: Among them, the x k+1 is the actual state of the vehicle at time k+1, x k is the actual state of the vehicle at time k, u k is the acceleration of the vehicle at time k, a fk is the acceleration of the front vehicle at time k, I is the identity matrix, Δt is the time difference between two adjacent moments.

7. The method according to any one of claims 1 to 5, characterized in that The calculation formula of the reference distance is as follows: Among them, d ref is the reference distance between the current vehicle and the vehicle ahead at the current moment, V rel is the relative speed between the current vehicle and the vehicle ahead at the current moment, T delay is the braking delay time of the current vehicle, f(μ) is the preset braking coefficient, V is the absolute speed of the current vehicle at the current moment, a max is the maximum deceleration of the current vehicle.

8. The method according to any one of claims 1 to 5, characterized in that The obtaining of the first constraint relationship model of the current vehicle in the following state includes: Constructing a kth state space equation of the current vehicle, wherein the kth state space equation is used to describe the relationship between the differential result of the real state of the current vehicle at the k+1th time and the real state of the current vehicle at the kth time, the acceleration of the current vehicle at the kth time, and the acceleration of the front vehicle at the kth time; The kth state space equation is discretized to obtain the kth state transfer model.

9. A vehicle control device in a following state, characterized in that: include: an acquisition module, for acquiring a first constraint relationship model of the current vehicle in a following state, the first constraint relationship model comprising: N state transition models, N+1 reference state models, N+1 relative acceleration definition models, N+1 relative speed definition models, and N+1 distance definition models, where N is a positive integer greater than or equal to 0, and the kth state transition model is used to describe the relationship between the actual state of the current vehicle at the k+1th moment and the actual state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the leading vehicle at the kth moment, where k is an integer greater than or equal to 0 and less than or equal to N, and the kth state transition model is used to describe the relationship between the actual state of the current vehicle at the k+1th moment and the actual state of the current vehicle at the kth moment, the acceleration of the current vehicle at the kth moment, and the acceleration of the leading vehicle at the kth moment. The 0th moment is the current moment, the actual state includes: the actual distance between the current vehicle and the vehicle in front, the actual relative speed between the current vehicle and the vehicle in front, the mth reference state model is used to describe the relationship between the reference state of the current vehicle at the mth moment and the speed information of the current vehicle at the mth moment, m is an integer greater than or equal to 0 and less than or equal to N+1, the reference state includes a reference distance and a reference relative speed, the reference relative speed is 0, and the speed information includes: the relative speed between the current vehicle and the vehicle in front at the mth moment, and the absolute speed of the current vehicle at the mth moment; A substitution module, used for obtaining the actual state and speed information of the current vehicle at the current moment, and substituting the information into the first constraint relationship model to obtain a second constraint relationship model; a cost function module, used to obtain a cost function of the current vehicle at a current moment, the cost function being used to indicate the difference and total acceleration between the N reference states and the N actual states of the current vehicle when the current vehicle is controlled by the N accelerations; An acceleration module is used to determine the acceleration of the current vehicle at N moments when the cost function outputs a minimum value under the constraints of the second constraint relationship model, and control the driver and the automatic driving system to accelerate the current vehicle according to the acceleration of the current vehicle at a current moment included in the accelerations at the N moments.

10. 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 vehicle control method in the following state as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the vehicle control method in the following state as described in any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the vehicle control method in the following state as claimed in any one of claims 1 to 8 is implemented.

Images