Control method and device and vehicle

Abstract

The invention provides a control method and device and a vehicle. The control method and device can be applied to the field of intelligent driving. The method comprises the following steps: acquiring information of speed and acceleration of a car-following target in a preset duration; determining a first car-following algorithm from a plurality of car-following algorithms according to the speed and acceleration information of the car-following target within the preset duration, the plurality of car-following algorithms including linear quadratic control (LQR) and model predictive control (MPC) algorithms; and controlling the vehicle to run according to the first car following algorithm. The embodiment of the invention can be applied to an intelligent vehicle or an electric vehicle, the vehicle following efficiency of the vehicle can be improved, and the energy consumption of the vehicle during vehicle following can be reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent driving, and more particularly, to a control method, apparatus, and vehicle. Background Art

[0002] The control method of intelligent connected vehicles (ICV) is one of the key technologies for autonomous driving. In the driving environment, most working conditions are following conditions, and the current algorithms for dealing with following conditions are mainly adaptive cruise algorithms. However, existing algorithms mostly use fixed and simple models to process all scenarios, resulting in insufficient algorithm granularity, poor following efficiency, and high energy consumption in complex following scenarios. Summary of the Invention

[0003] This application provides a control method, apparatus, and vehicle, which helps to improve the following efficiency of the vehicle and also helps to reduce the energy consumption of the vehicle during following.

[0004] In a first aspect, a control method is provided. The method includes: obtaining information on the speed and acceleration of a following target within a preset time period; determining a first following algorithm from multiple following algorithms according to the information on the speed and acceleration of the following target within the preset time period, where the multiple following algorithms include linear quadratic regulator (LQR) and model predictive control (MPC) algorithms; and controlling the vehicle to travel according to the first following algorithm.

[0005] Based on the above technical solution, in different following conditions, the vehicle can use different following algorithms to follow the following target. In this way, it helps to solve the problems of insufficient algorithm granularity, poor following efficiency, and high energy consumption caused by using a single algorithm, helps to improve the following efficiency of the vehicle, and also helps to reduce the energy consumption of the vehicle during following.

[0006] In some possible implementation manners, the MPC algorithm can be understood as an algorithm for obtaining the acceleration control amount of the vehicle within a future period of time through an optimization iteration method.

[0007] In some possible implementation manners, the LQR algorithm can be understood as an algorithm for calculating the acceleration control amount of the vehicle at the next moment through a formula or an analytical solution.

[0008] In some possible implementation manners, controlling the vehicle to travel includes: controlling the vehicle to follow the following target.

[0009] In combination with the first aspect, in some implementations of the first aspect, a first car-following algorithm is determined from multiple car-following algorithms according to the speed and acceleration information of the car-following target within the preset duration, including: when the vehicle is in the first car-following condition, determining the first car-following algorithm as the LQR algorithm, where the first car-following condition indicates that the average speed of the car-following target within the preset duration is greater than or equal to the preset speed and the maximum value of the acceleration of the car-following target within the preset duration is less than the preset acceleration; or, when the vehicle is in the second car-following condition, determining the first car-following algorithm as the MPC algorithm, where the second car-following condition indicates that the average speed of the car-following target within the preset duration is greater than or equal to the preset speed and the maximum value of the acceleration of the car-following target within the preset duration is greater than or equal to the preset acceleration; or, when the vehicle is in the third car-following condition, determining the first car-following algorithm as the MPC algorithm, where the third car-following condition indicates that the average speed of the car-following target within the preset duration is less than the preset speed and the maximum value of the acceleration of the car-following target within the preset duration is less than the preset acceleration; or, when the vehicle is in the fourth car-following condition, determining the first car-following algorithm as the MPC algorithm, where the fourth car-following condition indicates that the average speed of the car-following target within the preset duration is less than the preset speed and the maximum value of the acceleration of the car-following target within the preset duration is greater than or equal to the preset acceleration.

[0010] The above first car-following condition can be understood as a high-speed stable condition, the second car-following condition can be understood as a high-speed fluctuating condition, the third car-following condition can be understood as a low-speed stable condition, and the fourth car-following condition can be understood as a low-speed fluctuating condition.

[0011] Based on the above technical solution, the LQR algorithm can be used when the vehicle is in the high-speed stable condition, and the MPC algorithm can be used when the vehicle is in a non-high-speed stable condition. It can be seen from the results of simulation tests and experimental tests that both the car-following effect of the vehicle on the car-following target and the energy-saving effect of the vehicle are improved.

[0012] In some possible implementations, the preset speed is 75 km / h.

[0013] In some possible implementations, the preset acceleration is 0.2 m / s 2 .

[0014] In combination with the first aspect, in some implementations of the first aspect, the state weight in the MPC algorithm corresponding to the second following driving condition is the first state weight and the acceleration fluctuation weight is the first acceleration fluctuation weight. The state weight in the MPC algorithm corresponding to the third following driving condition is the second state weight and the acceleration fluctuation weight is the second acceleration fluctuation weight. The state weight in the MPC algorithm corresponding to the fourth following driving condition is the third state weight and the acceleration fluctuation weight is the third acceleration fluctuation weight. Among them, the ratio of the first state weight to the first acceleration fluctuation weight is greater than the ratio of the second state weight to the second acceleration fluctuation weight, and the ratio of the second state weight to the second acceleration fluctuation weight is greater than the ratio of the third state weight to the third acceleration fluctuation weight.

[0015] Based on the above technical solutions, when the vehicle is in a high-speed fluctuation condition, a low-speed stable condition or a low-speed fluctuation condition, different state weights and acceleration fluctuation weights can be used during the process of controlling the vehicle using the MPC algorithm. It can be seen from the simulation test and experimental test results that by setting the ratio of the first state weight to the first acceleration fluctuation weight to be greater than the ratio of the second state weight to the second acceleration fluctuation weight, and the ratio of the second state weight to the second acceleration fluctuation weight to be greater than the ratio of the third state weight to the third acceleration fluctuation weight, the following driving effect and the energy-saving effect of the vehicle under different conditions can be improved.

[0016] In combination with the first aspect, in some implementations of the first aspect, the first state weight is 3 and the first acceleration fluctuation weight is 1; the second state weight is 4 and the second acceleration fluctuation weight is 2; the third state weight is 3 and the third acceleration fluctuation weight is 2.

[0017] In combination with the first aspect, in some implementations of the first aspect, controlling the vehicle to travel according to the first following driving algorithm includes: determining a first acceleration control amount of the vehicle at a first moment according to the first following driving algorithm; controlling the vehicle to travel according to the first acceleration control amount; where the method further includes: when the following driving condition of the vehicle changes at a second moment, performing interpolation processing on the actual acceleration and the first acceleration control amount of the vehicle at the first moment during a transition duration, the second moment being the next moment of the first moment; controlling the vehicle to travel during the transition duration according to the result of the interpolation processing.

[0018] Based on the above technical solutions, by performing interpolation processing when the following driving condition of the vehicle changes, the jitter of the vehicle's acceleration during the transition time can be reduced, which helps to improve the user's driving and riding experience.

[0019] In combination with the first aspect, in certain implementations of the first aspect, obtaining information on the speed and acceleration of the following target within a preset duration includes: predicting information on the speed and acceleration of the following target within a future period according to the current speed and acceleration information of the following target.

[0020] In a second aspect, the present application provides a control device, which includes: an acquisition unit for acquiring information on the speed and acceleration of a following target within a preset duration; a determination unit for determining a first following algorithm from a plurality of following algorithms according to the information on the speed and acceleration of the following target within the preset duration, the plurality of following algorithms including a linear quadratic regulator (LQR) algorithm and a model predictive control (MPC) algorithm; and a control unit for controlling the vehicle to travel according to the first following algorithm.

[0021] In combination with the second aspect, in certain implementations of the second aspect, the determination unit is specifically configured to: when the vehicle is in a first following working condition, determine that the first following algorithm is the LQR algorithm, where the first following working condition indicates that the average speed of the following target within the preset duration is greater than or equal to a preset speed and the maximum value of the acceleration of the following target within the preset duration is less than a preset acceleration; or, when the vehicle is in a second following working condition, determine that the first following algorithm is the MPC algorithm, where the second following working condition indicates that the average speed of the following target within the preset duration is greater than or equal to the preset speed and the maximum value of the acceleration of the following target within the preset duration is greater than or equal to the preset acceleration; or, when the vehicle is in a third following working condition, determine that the first following algorithm is the MPC algorithm, where the third following working condition indicates that the average speed of the following target within the preset duration is less than or equal to the preset speed and the maximum value of the acceleration of the following target within the preset duration is less than the preset acceleration; or, when the vehicle is in a fourth following working condition, determine that the first following algorithm is the MPC algorithm, where the fourth following working condition indicates that the average speed of the following target within the preset duration is less than the preset speed and the maximum value of the acceleration of the following target within the preset duration is greater than or equal to the preset acceleration.

[0022] In combination with the second aspect, in certain implementations of the second aspect, the state weight in the MPC algorithm corresponding to the second car-following condition is the first state weight and the acceleration fluctuation weight is the first acceleration fluctuation weight, the state weight in the MPC algorithm corresponding to the third car-following condition is the second state weight and the acceleration fluctuation weight is the second acceleration fluctuation weight, and the state weight in the MPC algorithm corresponding to the fourth car-following condition is the third state weight and the acceleration fluctuation weight is the third acceleration fluctuation weight. Among them, the ratio of the first state weight to the first acceleration fluctuation weight is greater than the ratio of the second state weight to the second acceleration fluctuation weight, and the ratio of the second state weight to the second acceleration fluctuation weight is greater than the ratio of the third state weight to the third acceleration fluctuation weight.

[0023] In combination with the second aspect, in certain implementations of the second aspect, the first state weight is 3 and the first acceleration fluctuation weight is 1; the second state weight is 4 and the second acceleration fluctuation weight is 2; the third state weight is 3 and the third acceleration fluctuation weight is 2.

[0024] In combination with the second aspect, in certain implementations of the second aspect, the determining unit is further configured to determine a first acceleration control amount of the vehicle at a first moment according to the first car-following algorithm; the control unit is specifically configured to: control the vehicle to travel according to the first acceleration control amount; the control unit is further configured to: when the car-following condition of the vehicle changes at a second moment, perform interpolation processing on the actual acceleration of the vehicle at the first moment and the first acceleration control amount within a transition duration, where the second moment is the next moment of the first moment; and control the vehicle to travel within the transition duration according to the result of the interpolation processing.

[0025] In combination with the second aspect, in certain implementations of the second aspect, the obtaining unit is specifically configured to: predict the speed and acceleration information of the car-following target within a future period of time according to the current speed and acceleration information of the car-following target.

[0026] In a third aspect, the present application provides a control device, which includes a processor and a memory. The memory is used to store instructions, and the processor executes the instructions stored in the memory so that the device executes any possible method in the first aspect.

[0027] In a fourth aspect, the present application provides a vehicle, which includes any possible device in the second aspect or the third aspect.

[0028] In a fifth aspect, the present application provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, it causes the computer to execute any possible method in the first aspect above.

[0029] It should be noted that the above computer program code can be stored in whole or in part on the first storage medium. The first storage medium can be packaged together with the processor or separately packaged from the processor. The embodiments of the present application do not make specific limitations in this regard.

[0030] In a sixth aspect, the present application provides a computer-readable medium storing program code, which when run on a computer, causes the computer to execute any of the possible methods in the first aspect above.

[0031] In a seventh aspect, the present application provides a chip system including a processor for calling a computer program or computer instruction stored in a memory, so that the processor executes any of the possible methods in the first aspect above.

[0032] In combination with the seventh aspect, in a possible implementation, the processor is coupled to the memory through an interface.

[0033] In combination with the seventh aspect, in a possible implementation, the chip system further includes a memory storing a computer program or computer instruction.

[0034] In an eighth aspect, the present application provides a chip, and the chip system includes a circuit for executing any of the possible methods in the first aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic functional block diagram of a vehicle provided by an embodiment of the present application.

[0036] Figure 2 It is a schematic flowchart of a control method provided by an embodiment of the present application.

[0037] Figure 3 It is a schematic diagram of a test condition of a following vehicle provided by an embodiment of the present application.

[0038] Figure 4 It is a schematic diagram of an experimental scenario provided by an embodiment of the present application.

[0039] Figure 5 It is another schematic diagram of an experimental scenario provided by an embodiment of the present application.

[0040] Figure 6 It is a curve of various physical quantities over time during the following process of a vehicle following a following target provided by an embodiment of the present application.

[0041] Figure 7 It is a schematic flowchart of a control method provided by an embodiment of the present application.

[0042] Figure 8 It is a schematic block diagram of a control device provided by an embodiment of the present application Detailed implementation manners

[0043] Next, the technical solutions in the embodiments of the present application will be described with reference to the accompanying drawings in the embodiments of the present application. Among them, in the description of the embodiments of the present application, unless otherwise specified, " / " means "or". For example, A / B may represent A or B; herein, "and / or" is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. These three situations. "At least one item" means one item or more than one item. For example, "at least one of A and B" is similar to "A and / or B", describing the association relationship of associated objects, indicating that there can be three relationships. For example, at least one of A and B may represent: A exists alone, A and B exist simultaneously, and B exists alone. These three situations.

[0044] In the embodiments of the present application, prefix words such as "first" and "second" are only used to distinguish different described objects, and have no limiting effect on the position, order, priority, quantity, content, etc. of the described objects. The use of ordinal numbers and other prefix words for distinguishing described objects in the embodiments of the present application does not constitute a limitation on the described objects. The statement of the described objects refers to the description in the context of the claims or embodiments, and should not constitute an unnecessary limitation because of the use of such prefix words. In addition, in the description of this embodiment, unless otherwise specified, the meaning of "a plurality" is two or more.

[0045] Figure 1 It is a schematic functional block diagram of a vehicle 100 provided by an embodiment of the present application. The vehicle 100 may include a sensing system 110, a computing platform 120, and a display device 130. Among them, the sensing system 110 may include one or more sensors for sensing information about the environment around the vehicle 100. For example, the sensing system 110 may include a positioning system, and the positioning system may be a global positioning system (GPS), or it may be a Beidou system or other positioning systems. For another example, the sensing system 110 may include an inertial measurement unit (IMU), an acceleration sensor, a lidar, a millimeter wave radar, an ultrasonic radar, and a camera device, etc. Exemplarily, the acceleration sensor may include a sensor for detecting the acceleration signal of the air suspension system, or it may also include a sensor for detecting the acceleration signal of the ESC.

[0046] Some or all functions of vehicle 100 can be controlled by computing platform 120. The computing platform 120 may include one or more processors, such as processors 121 to 12n (n is a positive integer). A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with the ability to read and execute instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a type of microprocessor), or a digital signal processor (DSP), etc.; in another implementation, the processor can achieve certain functions through the logical relationship of hardware circuits, and the logical relationship of the hardware circuits is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as a type of ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 120 may further include a memory for storing instructions, and some or all of the processors 121 to 12n can call the instructions in the memory to achieve corresponding functions.

[0047] The display device 130 in the cockpit is mainly divided into two categories. The first category is the vehicle display screen; the second category is the projection display screen, such as a head up display (HUD). The vehicle display screen is a physical display screen and an important part of the vehicle infotainment system. Multiple display screens can be set in the cockpit, such as a digital instrument display screen, a central control screen, a display screen in front of the passenger in the co-pilot seat (also called the front passenger), a display screen in front of the left rear passenger, and a display screen in front of the right rear passenger. Even the window can be used as a display screen for display. Head-up display, also known as a head-up display system. It is mainly used to display driving information such as speed and navigation on a display device in front of the driver (such as a windshield). To reduce the driver's line of sight transfer time, avoid pupil changes caused by the driver's line of sight transfer, and improve driving safety and comfort. HUD includes, for example, a combined head-up display (C-HUD) system, a windshield head-up display (W-HUD) system, and an augmented reality head-up display system (AR-HUD). It should be understood that other types of HUD systems may appear as technology evolves, and this application is not limited to this.

[0048] The above display device 130 is described by taking a vehicle-mounted display screen and a projection display screen as examples, and the embodiments of the present application are not limited thereto. For example, the display device 130 can also be a light display screen or a projection screen.

[0049] The current adaptive cruise algorithm is mainly based on three traditional control algorithms. The first is the proportion, integral, differential (PID) algorithm, which obtains the control quantity by weighted summation of the proportion, integral, and differential terms of the speed deviation. This type of method has the advantages of no redundant control quantity under stable conditions and low real-time computing burden, but it cannot effectively apply the dynamic model and performs poorly under conditions with large fluctuations; the second is the LQR algorithm, which can obtain the optimal control sequence of state linear feedback. This type of method has the advantages of being able to effectively apply the dynamic model, no redundant control quantity under stable conditions, and low computing burden, but due to the lack of rolling optimization link, it performs poorly under conditions with large fluctuations; the third is the MPC algorithm, which can predict the state of the control object through the dynamic model within a certain time domain, and obtain the optimal control sequence by minimizing the cost function. This method can effectively utilize the dynamic model and optimize multiple objectives simultaneously within the constraint range. Because it has a rolling optimization link, it performs better under conditions with large fluctuations, but it has a large computing burden and is prone to unnecessary control quantity under stable conditions. In summary, the existing control algorithms alone perform poorly in complex working conditions with both stability and fluctuations, and there is a lack of a control algorithm that can still achieve safety, efficiency, and energy saving in the face of complex working conditions.

[0050] The embodiments of the present application provide a multi-modal and switching algorithm design for complex following scenarios that takes into account both following performance and energy saving. It can adaptively switch algorithms under different working conditions according to the switching logic to achieve the goals of safety, efficiency and energy saving.

[0051] Figure 2 A schematic flow chart of a control method 200 provided in an embodiment of the present application is shown. The method 200 may be executed by the vehicle 100 described above. The method 200 includes:

[0052] S201 , the vehicle 100 obtains information of the following vehicle 200 .

[0053] When the vehicle 100 is traveling, the data collected by the sensor can be used to detect in real time the following vehicles within a preset range (e.g., 50 meters) ahead of the vehicle 100's traveling route. When the sensor of the vehicle 100 detects that there is a following vehicle 200 on the vehicle 100's traveling route, the process proceeds to S202; if no following vehicle is detected on the traveling route, the vehicle 100 can travel at a constant speed according to the speed limit of the road.

[0054] Optionally, if there are multiple vehicles within a preset distance (eg, 50 meters) ahead of the lane where the current vehicle 100 is located, the vehicle closest to the vehicle 100 is selected as the following vehicle 200 .

[0055] Optionally, before the vehicle 100 obtains information about the following vehicle 200, the method 200 further includes: determining that the user enables the adaptive cruise control function; in response to the user enabling the adaptive cruise control function, obtaining information about the following vehicle 200.

[0056] Exemplarily, the adaptive cruise control function may be an adaptive cruise control (ACC) function, a navigation cruise assist (NCA).

[0057] Input information such as the speed, acceleration of the host vehicle, and the speed, position, acceleration of the vehicle ahead into the calculation unit; if there is no vehicle in the 50-meter area ahead, drive at a constant speed according to the speed limit of the current road.

[0058] In one embodiment, if the vehicle 100 does not obtain information about the following vehicle 200, the vehicle 100 may drive at a constant speed according to the speed limit value of the road.

[0059] S202. The vehicle 100 obtains the speed information of the following vehicle 200 within a future period of time.

[0060] Exemplarily, the vehicle 100 obtains the speed characteristics of the following vehicle 200 within a future period of time, or the speed-time change curve.

[0061] Exemplarily, the vehicle 100 obtains the speed information of the following vehicle 200 within a future period of time, including: the vehicle 100 can determine the speed v of the following vehicle 200 at time T0 according to the data collected by the sensor p and acceleration a p . The vehicle 100 can input the speed v p and acceleration a p into the prediction model to obtain the position of the following vehicle 200 within the next 10 seconds and the speed-time change curve.

[0062] Exemplarily, the prediction model may be a long short-term memory (LSTM) network.

[0063] S203: The vehicle 100 determines the driving condition of the following vehicle 200 according to the speed information of the following vehicle 200 within a future period of time.

[0064] Exemplarily, the vehicle 100 may classify the driving condition according to the speed-time curve of the following vehicle 200 within the next 10 seconds. For example, it can be classified into the following four categories:

[0065] If the average driving speed of the following vehicle 200 in the next 10 seconds Greater than 75 km / h, and the acceleration a of the following vehicle 200 in the next 10 seconds p The absolute value maximum is greater than 0.2 m / s 2 , it is determined as operating condition category 1 - high-speed fluctuation condition.

[0066] If the average driving speed of the following vehicle 200 in the next 10 seconds is less than 75 km / h, and the acceleration a of the following vehicle 200 in the next 10 seconds p The absolute value maximum is greater than 0.2 m / s 2 , it is determined as operating condition category 2 - low-speed fluctuation condition.

[0067] If the average driving speed of the following vehicle 200 in the next 10 seconds is greater than 75 km / h, and the acceleration a of the following vehicle 200 in the next 10 seconds p The absolute value maximum is less than 0.2 m / s 2 , it is determined as operating condition category 3 - high-speed stable condition.

[0068] If the average driving speed of the following vehicle 200 in the next 10 seconds is less than 75 km / h, and the acceleration a of the following vehicle 200 in the next 10 seconds p The absolute value maximum is less than 0.2 m / s 2 , it is determined as operating condition category 4 - low-speed stable condition.

[0069] S204: Determine the following algorithm according to the operating condition of the following vehicle 200.

[0070] Optionally, if the classification result of S203 is the high-speed fluctuation condition, select the MPC algorithm for following.

[0071] Exemplarily, the MPC algorithm is as follows:

[0072] Each time the following algorithm is performed, predict the ideal acceleration of the vehicle 100 in the next 10 seconds, and take 0.5 seconds as the interval, so a total of 20 steps of the acceleration control amount of the host vehicle need to be predicted. Assume that the current host vehicle acceleration is u k , then the acceleration control matrix U(k) is:

[0073]

[0074] Based on the above formula, the acceleration change state matrix ΔU(k) can be obtained:

[0075]

[0076] At the same time, define the motion state of the current following condition as η(k):

[0077]

[0078] Among them, C t is a constant matrix, and x(k) is defined as follows:

[0079]

[0080] Among them, Δd(k) is the actual distance between the host vehicle and the leading vehicle, Δv(k) is the speed difference between the host vehicle and the leading vehicle, and a f (k) is the ideal acceleration of the host vehicle at the current moment, which is a fixed value.

[0081] Thus, the following sequence matrix Y(k) of the following 20-step following driving condition motion state can be obtained:

[0082]

[0083] Based on the above definitions, the optimal control quantity J can be obtained. Among them, the state weight Q and the acceleration fluctuation weight R are relative weights and are fixed values, and Y ref is the ideal following driving condition motion state and is also a fixed value.

[0084] J = (Y - Y ref ) T Q(Y - Y ref ) + ΔU T RΔU

[0085] Solve the following formula to find the control sequence U(k) of the host vehicle acceleration that minimizes J.

[0086] U(k) ideal = argmin u(k) J

[0087] Subsequently, obtain the first item in U(k) ideal , that is, u(k + 1) ideal as the ideal acceleration control quantity of the vehicle 100 in the next step.

[0088] There are two hyperparameters in the MPC algorithm that need to be adjusted according to the working conditions, namely the state weight Q and the acceleration fluctuation weight R in the optimal control quantity J.

[0089] Exemplarily, in the high-speed fluctuation working condition, Q and R can select parameter combination 1. For example, Q is taken as 3 and R is taken as 1.

[0090] Optionally, the ratio of Q to R under high-speed fluctuations is greater than the ratio of Q to R under low-speed steady conditions, and the ratio of Q to R under low-speed steady conditions is greater than the ratio of Q to R under low-speed fluctuations.

[0091] Exemplarily, if the classification result of S203 is low-speed fluctuation, the MPC algorithm is also used for car-following. At this time, parameter combination 2 is selected. For example, Q is taken as 3 and R is taken as 2.

[0092] Exemplarily, if the classification result of S203 is low-speed steady, the MPC algorithm is also used for car-following. At this time, parameter combination 3 is selected. For example, Q is taken as 4 and R is taken as 2.

[0093] The values corresponding to the state weight Q and the acceleration fluctuation weight R shown above are only illustrative, and the embodiments of the present application do not make specific limitations thereto.

[0094] Optionally, if the classification result of S203 is high-speed steady, vehicle 100 may use the LQR algorithm for car-following.

[0095] Exemplarily, the LQR algorithm is as follows:

[0096] Based on the historical positions and current speeds of vehicle 100 and the following vehicle 200, P(t) is determined, and P(t) includes the speed and position of vehicle 100 relative to the following vehicle 200.

[0097] The acceleration control amount at the next moment in the LQR algorithm is directly solved using a formula without prediction and optimal control. The calculation formula is as follows:

[0098] u = -Kx = -R -1 B T P(t) x

[0099]

[0100] Q = diag[q1, q2, q3]

[0101] R = r

[0102] Wherein, The expression of is the Ricatti formula, which is a form of differential equation. R, A, B, and Q are all constants or constant matrices. Based on this differential equation, the ideal state quantity P(t) can be solved. Finally, the acceleration control amount u of vehicle 100 at the next moment is obtained ideal .

[0103] The above LQR algorithm can also be understood as obtaining the acceleration control amount of vehicle 100 at the next moment by solving the analytical solution.

[0104] S205. Calculate the acceleration control amount u of vehicle 100 at the next moment according to the car-following algorithm ideal .

[0105] Exemplarily, after determining the following - following driving condition at a certain moment, the vehicle 100 can calculate the acceleration control amount u at the next moment according to the following - following algorithm corresponding to the following - following driving condition ideal 。

[0106] S206, determine whether the driving condition of the vehicle 100 has changed.

[0107] If the driving condition of the vehicle 100 has changed at the current moment (for example, from a high - speed fluctuating driving condition to a high - speed stable driving condition), go to step S207; otherwise, go to step S208, and make the actual acceleration control amount u c =u ideal 。

[0108] S207: If the following - following driving condition of the vehicle 100 has changed at the current moment, obtain the ego - vehicle acceleration u at the previous moment k and the ideal control amount u ideal , perform linear interpolation on the acceleration to obtain the acceleration control amount of the vehicle 100 during the transition duration.

[0109] Exemplarily, obtain the actual acceleration control amount u as shown in the following formula c , where T buffer is the transition duration, t0 is the start time of the transition switch, and t1 is the end time of the transition switch.

[0110]

[0111] T buffer =t1 - t0

[0112] Exemplarily, the transition duration can be a preset duration, such as 3 seconds.

[0113] S208: The vehicle 100 controls the driving of the vehicle 100 according to the acceleration control amount.

[0114] Input the obtained acceleration control amount into the lower - level hardware controller to complete the following - following control at the current moment. At this time, determine whether the driving destination has been reached. If so, end the algorithm; otherwise, return to S201 to start the next round of iterative control.

[0115] The embodiments of the present application have tested the proposed following - following algorithm and compared it with existing PID, pure MPC control, etc. The results show that it has advantages in both fuel consumption and following - following performance.

[0116] Exemplarily, Figure 3The figure shows a schematic diagram of the test conditions of the following vehicle 200 provided by the embodiments of the present application. A driving curve is set for the following vehicle 200 (or, the preceding vehicle), which is a complex curve mixed with four working conditions (including stage 1, stage 2, stage 3, and stage 4). Among them, stage 1 is low-speed fluctuation, stage 2 is high-speed stability, stage 3 is high-speed fluctuation, and stage 4 is low-speed stability.

[0117] Combined with the Carla, Carsim, and Simulink simulation platforms, a comparative experiment is conducted on the control method of the embodiments of the present application. Exemplarily, Figure 4 and Figure 5 The figure shows a schematic diagram of the experimental scenario provided by the embodiments of the present application.

[0118] Taking the vehicle 100 as a fuel vehicle as an example, two technical indicators are used as evaluation criteria, namely the comprehensive following error (TEI) and the driving fuel consumption (FCM). Among them, the comprehensive following error reflects the following effect in terms of distance and speed. The smaller the comprehensive following error, the better the vehicle 100 replicates the following vehicle 200. The driving fuel consumption reflects the fuel consumption of the vehicle 100 during the following process.

[0119] The above is described by taking the vehicle 100 as a fuel vehicle as an example, and the embodiments of the present application are not limited thereto. If the vehicle 100 is a hybrid vehicle or an electric vehicle, corresponding experimental results can also be obtained.

[0120] Exemplarily, the calculation formulas for the comprehensive following error and the driving fuel consumption are as follows:

[0121]

[0122]

[0123] Among them, T is the overall following time, Δv is the speed error between the host vehicle and the preceding vehicle at this moment, Δd is the error between the host vehicle and the ideal following distance, and Q eng is the energy consumption at each moment, which is calculated by the vehicle dynamics and fuel consumption models built in Carsim.

[0124] The test results are shown in Table 1.

[0125] Table 1

[0126]

[0127] As can be seen from the test results shown in Table 1, the embodiments of the present application have achieved improvements in following performance and fuel consumption. This is due to the selection of a following algorithm suitable for the current working conditions under various working conditions, which enhances the method granularity, and at the same time, the transition algorithm reduces the impact during method switching.

[0128] Figure 6 Shows the curves of various physical quantities over time during the following process of the following target by the vehicle 100 provided in the embodiment of the present application. Through the comparison of the distance between the vehicle 100 and the following target, the speed comparison between the vehicle 100 and the following target, and the acceleration comparison between the vehicle 100 and the following target, by using the control method of the embodiment of the present application, the vehicle 100 can basically maintain the following control synchronized with the following target.

[0129] Figure 7 Shows a schematic flowchart of the control method 700 provided in the embodiment of the present application. This method 700 can be executed by the above-mentioned vehicle 100, or this method 700 can be executed by the above-mentioned computing platform 120, or this method 700 can be executed by a system composed of the computing platform 120 and the perception system 110, or this method 700 can be executed by a system-on-a-chip (SoC) in the above-mentioned computing platform 120, or this method 700 can be executed by a processor, chip or circuit in the computing platform 120, or this method 700 can be executed by a cloud server. This method 700 includes:

[0130] S710, obtain information on the speed and acceleration of the following target within a preset time period.

[0131] Optionally, obtaining information on the speed and acceleration of the following target within a preset time period includes: obtaining information on the speed and acceleration of the following target within a future period of time.

[0132] Optionally, obtaining information on the speed and acceleration of the following target within a future period of time includes: predicting information on the speed and acceleration of the following target within a future period of time based on the current speed and acceleration information of the following target.

[0133] Exemplarily, the information on the speed and acceleration of the following target within a future period of time can be obtained by using model prediction. For example, the current speed and acceleration information of the following target can be input into a prediction model to obtain the information on the speed and acceleration of the following target within a future period of time.

[0134] Exemplarily, the prediction model can be an LSTM, a residual neural network (ResNet), a recurrent neural network (RNN), a multilayer perceptron (MLP), etc.

[0135] S720. According to the speed and acceleration information of the following vehicle target within the preset duration, determine a first following algorithm from multiple following algorithms, where the multiple following algorithms include an LQR algorithm and an MPC algorithm.

[0136] Optionally, the determining the first following algorithm from multiple following algorithms according to the speed and acceleration information of the following vehicle target within the preset duration includes: when the vehicle is in a first following working condition, determining the first following algorithm as the LQR algorithm, where the first following working condition indicates that the average speed of the following vehicle target within the preset duration is greater than or equal to a preset speed and the maximum value of the acceleration of the following vehicle target within the preset duration is less than a preset acceleration; or, when the vehicle is in a second following working condition, determining the first following algorithm as the MPC algorithm, where the second following working condition indicates that the average speed of the following vehicle target within the preset duration is greater than or equal to the preset speed and the maximum value of the acceleration of the following vehicle target within the preset duration is greater than or equal to the preset acceleration; or, when the vehicle is in a third following working condition, determining the first following algorithm as the MPC algorithm, where the third following working condition indicates that the average speed of the following vehicle target within the preset duration is less than or equal to the preset speed and the maximum value of the acceleration of the following vehicle target within the preset duration is less than the preset acceleration; or, when the vehicle is in a fourth following working condition, determining the first following algorithm as the MPC algorithm, where the fourth following working condition indicates that the average speed of the following vehicle target within the preset duration is less than the preset speed and the maximum value of the acceleration of the following vehicle target within the preset duration is greater than or equal to the preset acceleration.

[0137] The above first following working condition can be understood as a high-speed stable working condition, the second following working condition can be understood as a high-speed fluctuating working condition, the third following working condition can be understood as a low-speed stable working condition, and the fourth following working condition can be understood as a low-speed fluctuating working condition.

[0138] Exemplarily, the preset speed can be 75 km / h.

[0139] Exemplarily, the preset acceleration can be 0.2 m / s 2 。

[0140] Exemplarily, Table 2 shows a mapping relationship that can be saved between the following working condition and the following algorithm in vehicle 100.

[0141] Table 2

[0142] Following driving condition Following driving algorithm High-speed stable condition LQR algorithm Non-high-speed stable condition MPC algorithm

[0143] The above non-high-speed steady conditions may include high-speed fluctuation conditions, low-speed steady conditions, and low-speed fluctuation conditions.

[0144] Optionally, the state weight in the MPC algorithm corresponding to the second following condition is the first state weight and the acceleration fluctuation weight is the first acceleration fluctuation weight. The state weight in the MPC algorithm corresponding to the third following condition is the second state weight and the acceleration fluctuation weight is the second acceleration fluctuation weight. The state weight in the MPC algorithm corresponding to the fourth following condition is the third state weight and the acceleration fluctuation weight is the third acceleration fluctuation weight. Wherein, the ratio of the first state weight to the first acceleration fluctuation weight is greater than the ratio of the second state weight to the second acceleration fluctuation weight, and the ratio of the second state weight to the second acceleration fluctuation weight is greater than the ratio of the third state weight to the third acceleration fluctuation weight.

[0145] Exemplarily, Table 3 shows the mapping relationship between the state weight and the acceleration fluctuation weight in the MPC algorithm used under high-speed fluctuation conditions, low-speed steady conditions, and low-speed fluctuation conditions.

[0146] Table 3

[0147] Following driving condition State weight Acceleration fluctuation weight High-speed fluctuation condition <![CDATA[Q1]]> <![CDATA[R1]]> Low-speed stable condition <![CDATA[Q2]]> <![CDATA[R2]]> Low-speed fluctuation condition <![CDATA[Q3]]> <![CDATA[R3]]>

[0148] Optionally, Q1 / R1 > Q2 / R2 > Q3 / R3.

[0149] Exemplarily, the first state weight is 3 and the first acceleration fluctuation weight is 1; the second state weight is 4 and the second acceleration fluctuation weight is 2; the third state weight is 3 and the third acceleration fluctuation weight is 2.

[0150] The above shows through Table 3 that the state weight and the acceleration fluctuation weight in the MPC algorithm used under high-speed fluctuation conditions, low-speed steady conditions, and low-speed fluctuation conditions may be different. The embodiments of the present application are not limited thereto. For example, the state weight and the acceleration fluctuation weight in the MPC algorithm used under non-high-speed steady conditions may also be fixed values. For example, in the MPC algorithm used under high-speed fluctuation conditions, low-speed steady conditions, and low-speed fluctuation conditions, the state weight may be 4 and the acceleration fluctuation weight may be 2.

[0151] S730, control the vehicle to travel according to the first following algorithm.

[0152] Optionally, controlling the vehicle according to the first car-following algorithm includes: determining a first acceleration control amount of the vehicle at a first moment according to the first car-following algorithm; controlling the vehicle to travel according to the first acceleration control amount; wherein, the method further includes: when the car-following condition of the vehicle changes at a second moment, performing interpolation processing on the actual acceleration and the first acceleration control amount of the vehicle at the first moment during a transition duration, the second moment being the next moment of the first moment; and controlling the vehicle to travel during the transition duration according to the result of the interpolation processing.

[0153] Exemplarily, the result of the interpolation processing can be the expression of the above acceleration control amount u c When the car-following condition of the vehicle changes, interpolation processing can reduce the jitter of the vehicle's acceleration during the transition time, thereby helping to improve the user's driving and riding experience.

[0154] Figure 8 FIG. shows a schematic block diagram of a control device 800 provided in an embodiment of the present application. The device 800 includes: an acquisition unit 810, configured to acquire information on the speed and acceleration of a car-following target within a preset duration; a determination unit 820, configured to determine a first car-following algorithm from a plurality of car-following algorithms according to the information on the speed and acceleration of the car-following target within the preset duration, the plurality of car-following algorithms including a linear quadratic regulator (LQR) algorithm and a model predictive control (MPC) algorithm; and a control unit 830, configured to control the vehicle to travel according to the first car-following algorithm.

[0155] Optionally, the determination unit 820 is specifically configured to: when the vehicle is in a first car-following condition, determine the first car-following algorithm as the LQR algorithm, where the first car-following condition indicates that the average speed of the car-following target within the preset duration is greater than or equal to a preset speed and the maximum value of the acceleration of the car-following target within the preset duration is less than a preset acceleration; or, when the vehicle is in a second car-following condition, determine the first car-following algorithm as the MPC algorithm, where the second car-following condition indicates that the average speed of the car-following target within the preset duration is greater than or equal to the preset speed and the maximum value of the acceleration of the car-following target within the preset duration is greater than or equal to the preset acceleration; or, when the vehicle is in a third car-following condition, determine the first car-following algorithm as the MPC algorithm, where the third car-following condition indicates that the average speed of the car-following target within the preset duration is less than or equal to the preset speed and the maximum value of the acceleration of the car-following target within the preset duration is less than the preset acceleration; or, when the vehicle is in a fourth car-following condition, determine the first car-following algorithm as the MPC algorithm, where the fourth car-following condition indicates that the average speed of the car-following target within the preset duration is less than the preset speed and the maximum value of the acceleration of the car-following target within the preset duration is greater than or equal to the preset acceleration.

[0156] Optionally, the state weight in the MPC algorithm corresponding to the second car-following condition is the first state weight and the acceleration fluctuation weight is the first acceleration fluctuation weight. The state weight in the MPC algorithm corresponding to the third car-following condition is the second state weight and the acceleration fluctuation weight is the second acceleration fluctuation weight. The state weight in the MPC algorithm corresponding to the fourth car-following condition is the third state weight and the acceleration fluctuation weight is the third acceleration fluctuation weight. Among them, the ratio of the first state weight to the first acceleration fluctuation weight is greater than the ratio of the second state weight to the second acceleration fluctuation weight, and the ratio of the second state weight to the second acceleration fluctuation weight is greater than the ratio of the third state weight to the third acceleration fluctuation weight.

[0157] Optionally, the first state weight is 3 and the first acceleration fluctuation weight is 1; the second state weight is 4 and the second acceleration fluctuation weight is 2; the third state weight is 3 and the third acceleration fluctuation weight is 2.

[0158] Optionally, the determining unit 820 is further configured to determine a first acceleration control amount of the vehicle at a first moment according to the first car-following algorithm. The control unit 830 is specifically configured to: control the vehicle to travel according to the first acceleration control amount. The control unit 830 is further configured to: when the car-following condition of the vehicle changes at a second moment, perform interpolation processing on the actual acceleration and the first acceleration control amount of the vehicle within a transition duration. The second moment is the next moment of the first moment; and control the vehicle to travel within the transition duration according to the result of the interpolation processing.

[0159] Optionally, the obtaining unit 810 is specifically configured to: predict the speed and acceleration information of the car-following target within a future period of time according to the current speed and acceleration information of the car-following target.

[0160] For example, the obtaining unit 810 may be Figure 1 the computing platform in or the processing circuit, processor or controller in the computing platform. Taking the obtaining unit 810 as the processor 121 in the computing platform as an example, the processor 121 may obtain the speed and acceleration information of the car-following target within a future period of time (for example, 10 s).

[0161] For another example, the determining unit 820 may be Figure 1 the computing platform in or the processing circuit, processor or controller in the computing platform. Taking the determining unit 820 as the processor 122 in the computing platform as an example, the processor 122 may determine the car-following condition according to the speed and acceleration information of the car-following target within a future period of time (for example, 10 s) obtained by the processor 121, and determine the first car-following algorithm according to the mapping relationship between the car-following condition and the car-following algorithm.

[0162] For another example, the control unit 830 may be Figure 1 the computing platform in [reference document] or the processing circuit, processor, or controller in the computing platform. Taking the processor 123 in the computing platform as the control unit 830 as an example, the processor 123 may control the vehicle to follow the following target according to the first car-following algorithm determined by the processor 122.

[0163] The functions implemented by the above acquisition unit 810, the determination unit 820, and the noise reduction unit 830 may be implemented by different processors, or may be implemented by the same processor, or some functions may be implemented by the same processor. The embodiments of the present application do not limit this.

[0164] It should be understood that the division of each unit in the above device is only a division of logical functions. In actual implementation, it may be fully or partially integrated into a physical entity, or physically separated. In addition, the units in the device may be implemented in the form of a processor calling software; for example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or the functions of each unit of the device. The processor is, for example, a general-purpose processor, such as a CPU or a microprocessor, and the memory is a memory inside or outside the device. Or, the units in the device may be implemented in the form of hardware circuits, and the functions of some or all units may be implemented by designing the hardware circuits. The hardware circuits may be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are implemented by designing the logical relationship between the components in the circuit; for another example, in another implementation, the hardware circuit may be implemented by a PLD. Taking an FPGA as an example, it may include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured through a configuration file to implement the functions of some or all of the above units. All units of the above device may be all implemented in the form of a processor calling software, or all implemented in the form of hardware circuits, or some implemented in the form of a processor calling software, and the remaining part implemented in the form of hardware circuits.

[0165] In the embodiments of the present application, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and running capabilities, such as a CPU, microprocessor, GPU, or DSP, etc.; in another implementation, the processor can achieve certain functions through the logical relationship of hardware circuits, and the logical relationship of the hardware circuits is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as a type of ASIC, such as an NPU, TPU, DPU, etc.

[0166] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0167] In addition, each unit in the above device can be fully or partially integrated together, or can be independently implemented. In one implementation, these units are integrated together and implemented in the form of an SoC. The SoC can include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The types of the at least one processor can be different, such as including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0168] The embodiments of the present application also provide a device, which includes a processing unit and a storage unit, where the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit so that the device executes the method or steps executed in the above embodiments.

[0169] Optionally, if the device is located in a vehicle, the above processing unit can be Figure 1 the processors 121 - 12n shown.

[0170] The embodiments of the present application also provide a control system, which can include a computing platform and a perception system, and the computing platform can include the above control device.

[0171] The embodiments of the present application also provide a vehicle, which can include the above control device or control system.

[0172] The embodiments of the present application also provide a computer program product, which includes computer program code. When the computer program code runs on a computer, the computer is caused to execute the control method in the above embodiments.

[0173] The embodiments of the present application also provide a computer-readable medium, which stores program code. When the computer program code runs on a computer, the computer is caused to execute the control method in the above embodiments.

[0174] The embodiments of the present application also provide a chip, which includes a circuit for executing the control method in the above embodiments.

[0175] In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor or the instructions in software form. The method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware processor, or executed and completed by the combination of the hardware and software modules in the processor. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0176] It should be understood that in the embodiments of the present application, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.

[0177] It should also be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0178] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by the combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professionals 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 present application.

[0179] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0180] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0181] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0183] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present application, or the part that contributes to the prior art, or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0184] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A control method, characterized in that, Including: Obtain information on the speed and acceleration of the following vehicle target within a preset time period; Determine a first following algorithm from multiple following algorithms according to the information on the speed and acceleration of the following vehicle target within the preset time period, where the multiple following algorithms include a linear quadratic regulator (LQR) algorithm and a model predictive control (MPC) algorithm; Control the vehicle to travel according to the first following algorithm.

2. The method according to claim 1, wherein The determining of the first following algorithm from multiple following algorithms according to the information on the speed and acceleration of the following vehicle target within the preset time period includes: When the vehicle is in a first following condition, determine the first following algorithm as the LQR algorithm, where the first following condition indicates that the average speed of the following vehicle target within the preset time period is greater than or equal to a preset speed and the maximum value of the acceleration of the following vehicle target within the preset time period is less than a preset acceleration; or, When the vehicle is in a second following condition, determine the first following algorithm as the MPC algorithm, where the second following condition indicates that the average speed of the following vehicle target within the preset time period is greater than or equal to the preset speed and the maximum value of the acceleration of the following vehicle target within the preset time period is greater than or equal to the preset acceleration; or, When the vehicle is in a third following condition, determine the first following algorithm as the MPC algorithm, where the third following condition indicates that the average speed of the following vehicle target within the preset time period is less than or equal to the preset speed and the maximum value of the acceleration of the following vehicle target within the preset time period is less than the preset acceleration; or, When the vehicle is in a fourth following condition, determine the first following algorithm as the MPC algorithm, where the fourth following condition indicates that the average speed of the following vehicle target within the preset time period is less than the preset speed and the maximum value of the acceleration of the following vehicle target within the preset time period is greater than or equal to the preset acceleration.

3. The method according to claim 2, wherein The state weight in the MPC algorithm corresponding to the second following condition is a first state weight and the acceleration fluctuation weight is a first acceleration fluctuation weight, the state weight in the MPC algorithm corresponding to the third following condition is a second state weight and the acceleration fluctuation weight is a second acceleration fluctuation weight, and the state weight in the MPC algorithm corresponding to the fourth following condition is a third state weight and the acceleration fluctuation weight is a third acceleration fluctuation weight, where The ratio of the first state weight to the first acceleration fluctuation weight is greater than the ratio of the second state weight to the second acceleration fluctuation weight, and the ratio of the second state weight to the second acceleration fluctuation weight is greater than the ratio of the third state weight to the third acceleration fluctuation weight.

4. The method according to claim 3, wherein The first state weight is 3 and the first acceleration fluctuation weight is 1; The second state weight is 4 and the second acceleration fluctuation weight is 2; The third state weight is 3 and the third acceleration fluctuation weight is 2.

5. The method according to any one of claims 2 to 4, characterized in that, The controlling of the vehicle to travel according to the first following algorithm includes: Determine a first acceleration control amount of the vehicle at a first moment according to the first following algorithm; Control the driving of the vehicle according to the first acceleration control amount; Wherein, the method further includes: When the following driving condition of the vehicle changes at a second moment, perform interpolation processing on the actual acceleration of the vehicle at the first moment and the first acceleration control amount within a transition duration, and the second moment is the next moment of the first moment; Control the driving of the vehicle within the transition duration according to the result of the interpolation processing.

6. The method according to any one of claims 1 to 5, characterized in that, The obtaining the information of the speed and acceleration of the following target within a preset duration includes: Predict the information of the speed and acceleration of the following target within a future period according to the information of the current speed and acceleration of the following target.

7. A control device, characterized in that, Includes: An obtaining unit, configured to obtain the information of the speed and acceleration of the following target within a preset duration; A determining unit, configured to determine a first following algorithm from multiple following algorithms according to the information of the speed and acceleration of the following target within the preset duration, and the multiple following algorithms include a linear quadratic regulator (LQR) algorithm and a model predictive control (MPC) algorithm; A control unit, configured to control the driving of the vehicle according to the first following algorithm.

8. The device according to claim 7, characterized in that, The determining unit is specifically configured to: When the vehicle is in a first following driving condition, determine that the first following algorithm is the LQR algorithm, and the first following driving condition indicates that the average speed of the following target within the preset duration is greater than or equal to a preset speed and the maximum value of the acceleration of the following target within the preset duration is less than a preset acceleration; Or, When the vehicle is in a second following driving condition, determine that the first following algorithm is the MPC algorithm, and the second following driving condition indicates that the average speed of the following target within the preset duration is greater than or equal to the preset speed and the maximum value of the acceleration of the following target within the preset duration is greater than or equal to the preset acceleration; Or, When the vehicle is in a third following driving condition, determine that the first following algorithm is the MPC algorithm, and the third following driving condition indicates that the average speed of the following target within the preset duration is less than or equal to the preset speed and the maximum value of the acceleration of the following target within the preset duration is less than the preset acceleration; Or, When the vehicle is in a fourth following driving condition, determine that the first following algorithm is the MPC algorithm, and the fourth following driving condition indicates that the average speed of the following target within the preset duration is less than the preset speed and the maximum value of the acceleration of the following target within the preset duration is greater than or equal to the preset acceleration.

9. The device according to claim 8, characterized in that, The state weight in the MPC algorithm corresponding to the second following driving condition is a first state weight and the acceleration fluctuation weight is a first acceleration fluctuation weight, the state weight in the MPC algorithm corresponding to the third following driving condition is a second state weight and the acceleration fluctuation weight is a second acceleration fluctuation weight, and the state weight in the MPC algorithm corresponding to the fourth following driving condition is a third state weight and the acceleration fluctuation weight is a third acceleration fluctuation weight, wherein, The ratio of the first state weight to the first acceleration fluctuation weight is greater than the ratio of the second state weight to the second acceleration fluctuation weight, and the ratio of the second state weight to the second acceleration fluctuation weight is greater than the ratio of the third state weight to the third acceleration fluctuation weight.

10. The apparatus according to claim 9, wherein the first state weight is 3 and the first acceleration fluctuation weight is 1; the second state weight is 4 and the second acceleration fluctuation weight is 2; the third state weight is 3 and the third acceleration fluctuation weight is 2.

11. The apparatus according to any one of claims 8 to 10, wherein the determining unit is further configured to determine a first acceleration control amount of the vehicle at a first moment according to the first car-following algorithm; the control unit is specifically configured to: control the vehicle to travel according to the first acceleration control amount; the control unit is further configured to: when the car-following condition of the vehicle changes at a second moment, perform interpolation processing on the actual acceleration of the vehicle at the first moment and the first acceleration control amount within a transition duration, where the second moment is the next moment of the first moment; control the vehicle to travel within the transition duration according to the result of the interpolation processing.

12. The device according to any one of claims 7 to 11, characterized in that, The obtaining unit is specifically configured to: predict the speed and acceleration information of the car-following target within a future period according to the current speed and acceleration information of the car-following target.

13. A control device, characterized in that, including: a memory for storing a computer program; a processor for executing the computer program stored in the memory, so that the apparatus executes the method according to any one of claims 1 to 6.

14. A vehicle, characterized in that, including the apparatus according to any one of claims 7 to 13.

15. A computer-readable storage medium, characterized in that, Instructions are stored thereon, and when the instructions are executed by a processor, the processor is caused to implement the method according to any one of claims 1 to 6.

16. A computer program product, characterized in that, The computer program product includes computer program code, and when the computer program code runs on a computer, the computer is caused to implement the method according to any one of claims 1 to 6.

17. A chip, characterized in that, The chip includes a circuit, and the circuit is used to execute the method according to any one of claims 1 to 6.

Images