Vehicle driving method, device, computer equipment and readable storage medium

Abstract

The present application relates to the field of automatic driving technology, and in particular to a vehicle driving method, device, computer equipment and readable storage medium. The method includes: adjusting the driving state of the vehicle according to the target speed and target acceleration required for the vehicle to reach the target position, and obtaining the actual speed and actual acceleration of the vehicle; determining the acceleration pre-feedback value according to the target acceleration and the actual acceleration; determining the speed negative feedback value according to the actual speed and the target speed; optimizing the actual acceleration according to the acceleration pre-feedback value and the speed negative feedback value, so that when the actual speed reaches the target speed, the vehicle drives to the longitudinal planning position at the target speed.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle driving method, device, computer equipment and readable storage medium. Background Art

[0002] As one of the representatives of the new four modernizations of automobiles, the development momentum of technology is getting faster and faster. Among them, the autonomous driving technology of automobiles is the main battlefield of intelligent development. From the perspective of technology flow, autonomous driving technology can be divided into six major parts: perception, positioning, prediction, decision-making, planning and control. Among them, the planning layer plays a key role in connecting the upper and lower parts. Vehicles are divided into path planning and speed planning according to longitudinal and lateral movement. The purpose of speed planning is to plan a smooth speed sequence for the vehicle that meets the vehicle control requirements. It complements path planning and plays a key role in the lateral and longitudinal control of the back-end vehicle. The mutual support of the two technologies can greatly improve the intelligence level of the vehicle and accelerate the commercial landing process.

[0003] Most of the current speed planning and control methods cannot fully cover the more complex urban road environment. The current main urban speed planning and control method is generally longitudinal planning based on secondary planning, and then the acceleration command is directly given to the longitudinal control for torque and braking deceleration calculation.

[0004] However, the above method may cause the autonomous driving cruising speed to be unable to follow accurately in steady state and dynamic processes, so it is urgently needed to be improved. Summary of the invention

[0005] Based on this, it is necessary to provide a vehicle driving method, device, computer equipment and readable storage medium that can achieve precise vehicle speed following in response to the above technical problems.

[0006] In a first aspect, the present application provides a vehicle driving method, comprising:

[0007] According to the target speed and target acceleration required for the vehicle to reach the target position, the driving state of the vehicle is adjusted to obtain the actual speed and actual acceleration of the vehicle;

[0008] Determine the pre-acceleration feedback value according to the target acceleration and the actual acceleration;

[0009] Determine the speed negative feedback value according to the actual speed and the target speed;

[0010] According to the acceleration forward feedback value and the speed negative feedback value, the actual acceleration is optimized so that when the actual speed reaches the target speed, the vehicle travels to the longitudinal planning position at the target speed.

[0011] In one embodiment, determining the acceleration pre-feedback value according to the target acceleration and the actual acceleration includes:

[0012] The ratio between the target acceleration and the maximum acceleration corresponding to the vehicle is determined as the initial weight;

[0013] According to the acceleration difference between the actual acceleration and the target acceleration, the initial weight is adjusted to obtain the feedforward weight;

[0014] The product of the target acceleration and the feedforward weight is determined as the acceleration feedforward value.

[0015] In one embodiment, determining a speed negative feedback value according to the actual speed and the target speed includes:

[0016] determining a speed difference between an actual speed and a target speed;

[0017] Proportional and integral operations are performed on the speed difference to obtain the speed negative feedback value.

[0018] In one embodiment, performing proportional operation and integral operation on the speed difference to obtain a speed negative feedback value includes:

[0019] The difference between the set value and the feedforward weight is used as the negative feedback weight;

[0020] determining a first product between the speed difference and the negative feedback weight;

[0021] Proportional and integral operations are performed on the first product to obtain a speed negative feedback value.

[0022] In one embodiment, the initial weight is adjusted according to the acceleration difference between the actual acceleration and the target acceleration to obtain the feedforward weight, including:

[0023] Determine an adjustment coefficient according to the acceleration difference between the actual acceleration and the target acceleration; wherein the adjustment coefficient is positively correlated with the acceleration difference;

[0024] The second product between the adjustment coefficient and the initial weight is used as the feedforward weight.

[0025] In one embodiment, the actual acceleration is optimized according to the acceleration forward feedback value and the velocity negative feedback value, including:

[0026] The sum of the actual acceleration, the acceleration pre-feedback value, and the velocity negative feedback value is taken as the optimized acceleration;

[0027] The optimized acceleration is sent to a power system in the vehicle so that the power system adjusts the actual acceleration of the vehicle to the optimized acceleration.

[0028] In a second aspect, the present application further provides a vehicle driving device, comprising:

[0029] A planning module is used to adjust the driving state of the vehicle according to the target speed and target acceleration required for the vehicle to reach the target position, and obtain the actual speed and actual acceleration of the vehicle;

[0030] A forward feedback module is used to determine the acceleration forward feedback value according to the target acceleration and the actual acceleration;

[0031] A negative feedback module is used to determine a speed negative feedback value according to the actual speed and the target speed;

[0032] The driving adjustment module is used to optimize the actual acceleration according to the acceleration pre-feedback value and the speed negative feedback value, so that when the actual speed reaches the target speed, the vehicle drives to the longitudinal planning position through the target speed.

[0033] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0034] According to the target speed and target acceleration required for the vehicle to reach the target position, the driving state of the vehicle is adjusted to obtain the actual speed and actual acceleration of the vehicle;

[0035] Determine the pre-acceleration feedback value according to the target acceleration and the actual acceleration;

[0036] Determine the speed negative feedback value according to the actual speed and the target speed;

[0037] According to the acceleration forward feedback value and the speed negative feedback value, the actual acceleration is optimized so that when the actual speed reaches the target speed, the vehicle travels to the longitudinal planning position at the target speed.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0039] According to the target speed and target acceleration required for the vehicle to reach the target position, the driving state of the vehicle is adjusted to obtain the actual speed and actual acceleration of the vehicle;

[0040] Determine the pre-acceleration feedback value according to the target acceleration and the actual acceleration;

[0041] Determine the speed negative feedback value according to the actual speed and the target speed;

[0042] According to the acceleration forward feedback value and the speed negative feedback value, the actual acceleration is optimized so that when the actual speed reaches the target speed, the vehicle travels to the longitudinal planning position at the target speed.

[0043] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0044] According to the target speed and target acceleration required for the vehicle to reach the target position, the driving state of the vehicle is adjusted to obtain the actual speed and actual acceleration of the vehicle;

[0045] Determine the pre-acceleration feedback value according to the target acceleration and the actual acceleration;

[0046] Determine the speed negative feedback value according to the actual speed and the target speed;

[0047] According to the acceleration forward feedback value and the speed negative feedback value, the actual acceleration is optimized so that when the actual speed reaches the target speed, the vehicle travels to the longitudinal planning position at the target speed.

[0048] In the above-mentioned vehicle driving method, device, computer equipment and readable storage medium, the acceleration forward feedback value provides a predictive adjustment of future acceleration changes, which helps to reduce system delays and improve response speed. The speed negative feedback value is corrected according to the difference between the current speed and the target speed to ensure that the vehicle speed can stably approach the target speed; compared with the traditional technology that only relies on the target position of the vehicle to issue acceleration instructions, this application is a typical closed-loop control system, which continuously measures the actual acceleration, calculates the feedforward and negative feedback values, and adjusts and optimizes the acceleration accordingly, so that the vehicle can reach the desired driving state more stably and accurately. This control method combines the advantages of feedforward control and negative feedback control, and can improve the accuracy and stability of acceleration control in automatic driving or driving assistance systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 A schematic diagram of a process flow of a vehicle driving method in one embodiment;

[0051] Figure 2 A schematic flow chart of a step of determining a pre-acceleration feedback value in one embodiment;

[0052] Figure 3 A schematic flow chart of a step of determining a speed negative feedback value in one embodiment;

[0053] Figure 4 A schematic diagram of a process flow of a vehicle driving system in another embodiment;

[0054] Figure 5 is a structural block diagram of a vehicle traveling device in one embodiment;

[0055] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] Specifically, in the application scenario of autonomous driving in urban areas, the comprehensive external environment is relatively complex, and the vehicle needs to deal with variable traffic flow changes, path direction changes, road changes, etc. Among them, the following vehicle and the side vehicle cut-in response processing related to dynamic obstacles are mainly achieved through longitudinal planning control. The current main urban longitudinal planning method is based on dynamic planning and quadratic planning. The output signal is a fifth-order polynomial of position-time, which can express the longitudinal position command of the vehicle in the Frenet coordinate system in the next few seconds (usually 4 seconds), as shown in the following formula (1):

[0058] y=a0+a1*t+a2*t 2 +a3*t 3 +a4*t 4 +a5*t 5 (1)

[0059] Among them, a0~a5 are the 5th-order polynomial coefficients solved by quadratic programming;

[0060] t is time; y is the longitudinal position of the vehicle in the Frenet ego-vehicle coordinate system;

[0061] The speed command and acceleration command are obtained by differentiating them using the following equations (2) and (3):

[0062]

[0063]

[0064] In traditional technology, the acceleration command is directly controlled and sent to the longitudinal control model for torque control or directly to the chassis controller as acceleration and deceleration command. However, this method cannot accurately control the longitudinal speed following effect during self-driving, and cannot accurately achieve the desired cruising speed or the comfort of the dynamic process of speed change during dynamic following.

[0065] For example, when there is no vehicle ahead during cruising, the target cruising speed is set to 50 kph. When the actual speed of the vehicle is close to 50 kph, there must be a certain dynamic delay in the overall link and response. Therefore, when the longitudinal planning speed command has reached the target setting value of 50 kph according to the theoretical given, its secondary differential Accref acceleration command is already 0 m / s. 2 However, the actual speed of the vehicle has not reached the set speed of 50 kph. At this time, the vehicle is only accelerated according to the acceleration command of 0 m / s. 2 to execute, the steady-state speed error will be relatively large and the target speed cannot be reached.

[0066] In order to solve the above problems, in an exemplary embodiment, Figure 1 As shown, a vehicle driving method is provided, and the method is described by taking the method applied to a controller in a vehicle as an example, and the method includes:

[0067] Step 101, adjusting the driving state of the vehicle according to the target speed and target acceleration required for the vehicle to reach the target position, and obtaining the actual speed and actual acceleration of the vehicle.

[0068] In the case of an autonomous vehicle, the target location may be input by the user (e.g., setting a destination through a navigation system) or determined autonomously by the vehicle's autonomous driving system based on environmental perception and decision-making algorithms (e.g., in an autonomous taxi service, the target location may be the next passenger's pick-up point). The target speed is the speed the vehicle needs to reach, either to maintain a safe distance from the vehicle ahead or to achieve a predetermined driving speed. The target acceleration is the rate at which the vehicle needs to accelerate or decelerate in order to achieve the target speed.

[0069] For example, the urban autonomous driving scenario is complex and the optimization algorithm takes a long time to operate. The operation cycle of longitudinal planning is generally 100ms, while the cycle of longitudinal control is generally 20ms. Longitudinal planning cycle (100ms): This is the time interval for the autonomous driving system to perform path planning and decision updates. Due to the complexity of the urban environment, the system needs to analyze the current environment within this time period to calculate the optimal driving path and speed and acceleration instructions for the next period of time. Longitudinal control cycle (20ms): This is the time interval for the vehicle's execution system (such as throttle, brake, etc.) to receive instructions and respond. This time period is shorter to ensure that the vehicle can respond quickly and accurately to the instructions of the planning system.

[0070] Since the update cycle of longitudinal planning is longer than that of longitudinal control, a timing synchronization module is required to ensure the coordination between the two. The function of this module is to extract the corresponding value from the latest longitudinal planning 5th-order polynomial instruction according to the actual time accumulation in each longitudinal control cycle. In this way, even if the update cycle of longitudinal planning is longer, the longitudinal controller can obtain the latest speed and acceleration instructions synchronized with time in each control cycle.

[0071] Specifically, the vehicle's current actual speed and acceleration are obtained through the vehicle's sensor system (such as speed sensor, acceleration sensor, etc.). Based on the calculated adjustment amount, the controller will send instructions to the vehicle's engine, brake and steering systems, etc. These instructions will adjust the vehicle's throttle opening, brake force or steering angle, etc., to change the vehicle's speed and acceleration.

[0072] If the actual speed and acceleration are still different from the target value, the controller will further adjust the command until it reaches or approaches the target value. After a series of adjustments, the actual speed and acceleration of the vehicle will gradually approach the target speed and acceleration. Once the target state is reached or approached, the controller will maintain the current driving command to maintain the vehicle's speed and acceleration.

[0073] Step 102: Determine the acceleration pre-feedback value according to the target acceleration and the actual acceleration.

[0074] In the controller, feedforward is a predictive control strategy that adjusts the control input based on the prediction of the future system state to reduce system delay and improve response speed. Acceleration feedforward specifically refers to the advance adjustment of the control input according to the expected acceleration change so that the system can reach the expected acceleration more quickly. The target acceleration is the acceleration value that the system hopes to achieve, which is usually calculated based on factors such as path planning, speed control and safety distance. The actual acceleration is the actual acceleration value of the current vehicle obtained by the vehicle's acceleration sensor or other measuring equipment. The calculation of the acceleration feedforward value is usually based on the difference between the target acceleration and the actual acceleration. This difference reflects the deviation between the current vehicle acceleration and the expected acceleration. The controller needs to adjust the control input based on this deviation to make the vehicle acceleration approach the target value as soon as possible.

[0075] The acceleration feedback value can be a proportional coefficient multiplied by this deviation, or calculated by a more complex control algorithm (such as proportional-integral-derivative control in a PID controller). Once the acceleration feedback value is calculated, the controller combines it with other control inputs (such as position feedback, velocity feedback, etc.) to generate the final control command. These commands adjust the vehicle's throttle, brake and other actuators to achieve precise control of the vehicle's acceleration.

[0076] Step 103, determining a speed negative feedback value according to the actual speed and the target speed.

[0077] Among them, negative feedback is a common method in the controller, which generates a control signal to correct the difference by comparing the difference between the actual output of the system and the expected output. In speed control, when the actual speed is higher than the target speed, negative feedback will reduce the control signal to reduce the speed; when the actual speed is lower than the target speed, negative feedback will increase the control signal to increase the speed. The actual speed is the current vehicle speed measured by the vehicle's speed sensor. The target speed is the speed that the vehicle is expected to reach and maintain. It may be set by the user or determined by the path planning and decision-making algorithm of the autonomous driving system. The controller calculates the difference between the actual speed and the target speed, which indicates the direction and magnitude of the vehicle speed adjustment.

[0078] Specifically, based on the speed difference, the controller will calculate the speed negative feedback value through a control algorithm (such as proportional control, proportional-integral-derivative (PID) control, etc.). This negative feedback value is an adjustment used to correct the difference between the actual speed and the target speed. The calculated speed negative feedback value will be added to the controller and combined with other control signals (such as forward feedback value, position feedback value, etc.) to generate the final control instructions. These instructions will adjust the vehicle's drive and braking systems to bring the vehicle speed closer to the target speed.

[0079] Step 104 , optimizing the actual acceleration according to the acceleration forward feedback value and the speed negative feedback value, so that when the actual speed reaches the target speed, the vehicle travels to the longitudinal planning position at the target speed.

[0080] Specifically, the controller combines the acceleration forward feedback value and the speed negative feedback value to calculate an optimized acceleration command through a specific control algorithm (such as a PID controller or other advanced control strategies). This optimization process aims to find an acceleration value that can quickly respond to changes in the target acceleration (thanks to the forward feedback) and effectively adjust the actual speed to the target speed (thanks to the negative feedback). The optimized acceleration command is sent to the vehicle's power system to control the vehicle's acceleration by adjusting the throttle and brakes. As the acceleration is adjusted, the vehicle's actual speed will gradually approach and stabilize at the target speed. At the same time, the controller monitors the vehicle's position to ensure that while reaching the target speed, the vehicle can accurately drive to the predetermined position according to the longitudinal plan.

[0081] In the above-mentioned vehicle driving method, the acceleration forward feedback value provides a predictive adjustment of future acceleration changes, which helps to reduce system delays and improve response speed. The speed negative feedback value is corrected according to the difference between the current speed and the target speed to ensure that the vehicle speed can stably approach the target speed; compared with the traditional technology that only relies on the target position of the vehicle to issue acceleration instructions, this application is a typical closed-loop controller, which continuously measures the actual acceleration, calculates the feedforward and negative feedback values, and adjusts and optimizes the acceleration accordingly, so that the vehicle can reach the desired driving state more stably and accurately. This control method combines the advantages of feedforward control and negative feedback control, and can improve the accuracy and stability of acceleration control in autonomous driving or driving assistance systems.

[0082] In an exemplary embodiment, the driving state of the vehicle is adjusted according to the target speed and target acceleration required for the vehicle to reach the target position to obtain the actual speed and actual acceleration of the vehicle, including: sending the target speed and target acceleration required for the vehicle to reach the target position to the power system in the vehicle so that the power system adjusts the driving state of the vehicle; after the driving state is adjusted, the actual speed and actual acceleration of the vehicle are obtained.

[0083] Specifically, the power system can adjust the power output of the engine or motor according to the driver's needs or the driving conditions of the vehicle. For example, when rapid acceleration is required, the power system can increase the power output, and when stable driving or deceleration is required, the power output can be reduced. Furthermore, the speed sensor can measure the actual driving speed, and the acceleration sensor can measure the acceleration of the vehicle.

[0084] In an exemplary embodiment, Figure 2 As shown, according to the target acceleration and the actual acceleration, the acceleration pre-feedback value is determined, including:

[0085] Step 201, determining the ratio between the target acceleration and the maximum acceleration corresponding to the vehicle as the initial weight.

[0086] Among them, the target speed is the acceleration value that the controller wants the vehicle to achieve. It may be calculated based on factors such as path planning, speed control, and safe distance, and is a key parameter in autonomous driving or driver assistance systems. Maximum acceleration corresponding to the vehicle: This refers to the maximum acceleration that the vehicle can produce under current conditions. This value may be affected by many factors such as vehicle power performance, road conditions, load, and friction coefficient between tires and roads. Usually, this maximum acceleration value is determined during vehicle design, or estimated in real time by sensors and controllers during actual operation. Ratio calculation: The target acceleration is divided by the maximum acceleration corresponding to the vehicle, and the result is this ratio. This ratio reflects the ratio of the target acceleration to the maximum acceleration capability of the vehicle, and can be regarded as a standardized acceleration requirement. Determined as the initial weight: This ratio is used as the initial weight, which means that in subsequent acceleration control calculations, it will be used as a basic parameter to adjust or calculate the acceleration pre-feedback value. This initial weight helps ensure that the acceleration command does not exceed the actual capability of the vehicle, and also provides a benchmark for subsequent dynamic adjustments.

[0087] For example, if the target acceleration is 2m / s 2 , and the maximum acceleration of the vehicle is 4m / s 2 , then the initial weight is 0.5 (i.e. 2 / 4). This weight indicates that the target acceleration is half of the vehicle's maximum acceleration capability. By determining this initial weight, the controller can more accurately adjust the acceleration according to the actual situation of the vehicle, avoiding exceeding the physical limitations of the vehicle while ensuring smooth and safe driving.

[0088] Step 202: Adjust the initial weight according to the acceleration difference between the actual acceleration and the target acceleration to obtain a feedforward weight.

[0089] First, the controller needs to calculate the difference between the actual acceleration and the target acceleration. This difference reflects the degree of deviation between the current vehicle acceleration and the desired acceleration. If the actual acceleration is less than the target acceleration, the difference will be positive; if the actual acceleration is greater than the target acceleration, the difference will be negative.

[0090] Next, the initial weight determined in step 201 is adjusted according to the calculated acceleration difference. The purpose of the adjustment is to make the feedforward control more precise so as to respond faster to the change of the target acceleration. The adjustment method may include simple proportional adjustment, integral adjustment or use of more complex control algorithms.

[0091] After the above adjustment, the weight value obtained is the feedforward weight. This feedforward weight will be used to calculate the acceleration forward feedback value to guide the acceleration control of the vehicle. By introducing feedforward control, the controller can predict and adjust the acceleration in advance to reduce delay and improve response speed.

[0092] Specifically, the initial weight is adjusted according to the acceleration difference between the actual acceleration and the target acceleration to obtain the feedforward weight, including: determining an adjustment coefficient according to the acceleration difference between the actual acceleration and the target acceleration; and taking the second product between the adjustment coefficient and the initial weight as the feedforward weight.

[0093] Among them, the adjustment coefficient is positively correlated with the acceleration difference.

[0094] First, the acceleration difference between the actual acceleration and the target acceleration needs to be calculated. This difference represents the gap between the current vehicle acceleration state and the target state. Next, an adjustment coefficient is determined based on this acceleration difference. This adjustment coefficient is positively correlated with the acceleration difference, which means that the larger the acceleration difference, the larger the adjustment coefficient. The specific mathematical form of the positive correlation can be determined according to the specific needs and design of the controller, which may be linear or nonlinear. The adjustment coefficient is determined to reflect the degree of influence of the gap between the actual acceleration and the target acceleration on the weight adjustment. When the actual acceleration is far from the target acceleration, a greater adjustment force is required to make the actual acceleration approach the target value.

[0095] Once the adjustment factor is determined, the next step is to multiply it with the initial weight, and the result is the feedforward weight. This second product reflects the dynamic adjustment of the initial weight after considering the difference between the actual acceleration and the target acceleration. The calculation of the feedforward weight is a key step in the feedforward control strategy, which enables the controller to flexibly adjust the acceleration command according to the actual driving situation to achieve a faster and more accurate response.

[0096] Step 203: The product of the target acceleration and the feedforward weight is determined as the acceleration feedforward value.

[0097] The feedforward weight is calculated in the previous step by comprehensively considering factors such as the target acceleration, actual acceleration, and vehicle performance. The feedforward weight reflects how much the controller should adjust the acceleration command in order to achieve the target acceleration under the current driving conditions. The controller multiplies the target acceleration by the feedforward weight. This product represents the acceleration value that the controller believes should be applied after considering the current vehicle state and driving goals, that is, the acceleration forward feedback value.

[0098] That is: acceleration feedback value = target acceleration × feedforward weight.

[0099] In this embodiment, the acceleration feedback value calculated in the above manner not only takes into account the driving target (target acceleration), but also takes into account the current state of the vehicle (reflected by the feedforward weight), thereby making the acceleration control more precise and dynamic. This control strategy helps to improve the response speed and control accuracy of the automatic driving or driving assistance system, and ensure the safety and comfort of driving.

[0100] In an exemplary embodiment, determining the speed negative feedback value according to the actual speed and the target speed includes: determining the speed difference between the actual speed and the target speed; and performing proportional and integral operations on the speed difference to obtain the speed negative feedback value.

[0101] First, the controller needs to obtain the actual speed of the vehicle and the set target speed. The actual speed can be measured by the speed sensor or other related equipment on the vehicle, while the target speed is the desired speed set based on factors such as driving intention, path planning or traffic conditions. Next, the controller calculates the difference between the actual speed and the target speed. This difference reflects the degree of deviation between the current vehicle speed and the desired speed and is the basis for subsequent negative feedback calculations. After obtaining the speed difference, the controller will perform proportional and integral operations on the difference.

[0102] Proportional operation refers to multiplying the speed difference by a proportional coefficient to obtain an adjustment amount proportional to the difference. Proportional operation can quickly respond to changes in the speed difference and make the actual speed quickly approach the target speed. The size of the proportional coefficient determines the controller's sensitivity to the speed difference and the adjustment strength.

[0103] Integral operation is the process of accumulating and summing the speed difference. Through integral operation, the controller can take into account the cumulative effect of speed difference over a period of time, thereby eliminating steady-state errors and making the actual speed reach the target speed more stably. Integral operation is often used in conjunction with proportional operation to improve the stability and accuracy of the controller.

[0104] The negative feedback value of speed is obtained by adding the results of proportional operation and integral operation. This negative feedback value will be used to adjust the acceleration or power output of the vehicle so that the actual speed reaches and stabilizes at the target speed as quickly as possible.

[0105] Specifically, Figure 3 As shown, the speed difference is subjected to proportional and integral operations to obtain the speed negative feedback value, including:

[0106] Step 301: The difference between the set value and the feedforward weight is used as the negative feedback weight.

[0107] The value is set to 1. The purpose of this step is to balance the effects of feedforward control and negative feedback control. The feedforward weight has been calculated in the previous step based on the target acceleration and actual acceleration, which reflects the system's prediction of future acceleration requirements. The negative feedback weight is dynamically adjusted based on this feedforward weight to ensure the stability and responsiveness of the system.

[0108] Step 302, determining a first product between the speed difference and the negative feedback weight.

[0109] Calculate the first product between the speed difference and the negative feedback weight. The speed difference is the difference between the actual speed and the target speed, which reflects the degree of deviation between the current speed and the expected speed. Multiplying this difference with the negative feedback weight can get an adjustment amount, which will be used for subsequent negative feedback control.

[0110] Step 303, performing proportional operation and integral operation on the first product to obtain a speed negative feedback value.

[0111] Specifically, the proportional operation and the integral operation are implemented by a proportional-integral PI regulator.

[0112] It can be understood that the proportional operation refers to multiplying the deviation (here, the first product of the speed difference and the negative feedback weight) by a proportional coefficient (K_p). The proportional coefficient determines the system's sensitivity to the deviation and its ability to respond quickly. The output of the proportional operation is proportional to the deviation, so when a deviation occurs, the proportional operation will immediately produce a corresponding control action to reduce the deviation.

[0113] The integral operation is to integrate the deviation over time and then multiply it by an integral coefficient (K_i). The purpose of the integral operation is to eliminate the steady-state error. Even if the deviation is very small, the integral term will accumulate over time, thereby pushing the system output gradually closer to the set value. The integral coefficient determines the strength of the integral action.

[0114] The output of the PI regulator is the sum of proportional and integral operations, that is, [\text{PI output}=K_p\times\text{deviation}+K_i\times\int\text{deviation},dt]

[0115] Among them, "deviation" is the first product of the speed difference and the negative feedback weight. This PI output is the so-called "speed negative feedback value", which will be used to adjust the system (such as the vehicle's speed controller) to make the actual speed approach the target speed.

[0116] Furthermore, the actual acceleration is optimized according to the pre-feedback value of acceleration and the negative feedback value of speed, including: taking the sum of the actual acceleration, the pre-feedback value of acceleration and the negative feedback value of speed as the optimized acceleration; and sending the optimized acceleration to the power system in the vehicle so that the power system adjusts the actual acceleration of the vehicle to the optimized acceleration.

[0117] Specifically, the actual acceleration, the acceleration feedback value before and the speed negative feedback value are added together to obtain a sum value. This sum value comprehensively considers the current acceleration state (actual acceleration), the future acceleration demand (acceleration feedback value before) and the acceleration adjustment required to eliminate the speed deviation (speed negative feedback value). This process can be expressed as: optimized acceleration = actual acceleration + acceleration feedback value before + speed negative feedback. This optimized acceleration is an acceleration target value that combines multiple factors, aiming to make the vehicle reach the desired speed and acceleration state more smoothly and accurately.

[0118] Next, the system will send the optimized acceleration to the power system in the vehicle so that the power system can adjust the actual acceleration of the vehicle to the optimized acceleration. This adjustment process may involve changing the vehicle's throttle opening, braking force, or other power control parameters to ensure that the vehicle can accelerate or decelerate according to the optimized acceleration. This adjustment process needs to be performed accurately and quickly to ensure that the vehicle can respond quickly to changes in the optimized acceleration. At the same time, the system also needs to consider the dynamic characteristics and driving safety of the vehicle to avoid excessive acceleration or sudden braking.

[0119] In an exemplary embodiment, Figure 4 As shown, the present application provides a vehicle driving system, including a vehicle controller, which includes: a longitudinal planning acceleration instruction PlanningAccRef module, a whole vehicle information-actual acceleration module of the vehicle, a longitudinal planning speed instruction VelRef module, a whole vehicle information-actual speed module of the vehicle, an acceleration feedforward module, a feedback feedforward dynamic parameter calculation module, a PI regulator and a final acceleration instruction module.

[0120] Calculate the speed command array Vref: calculate the first-order derivative of the quintic position polynomial of the longitudinal planning to obtain the speed polynomial. Use the speed polynomial to calculate the speed value every 20 milliseconds in the next 4 seconds to form a speed command array Vref. Calculate the second-order derivative of the quintic position polynomial of the longitudinal planning to obtain the acceleration polynomial. Use the acceleration polynomial to calculate the acceleration value every 20 milliseconds in the next 4 seconds to form an acceleration command array Accref. When the new longitudinal planning command data is sent to the longitudinal controller, the timing starts. At the end of each longitudinal control cycle (20 milliseconds), the speed and acceleration command values ​​of the corresponding time are taken from Vref and Accref according to the accumulated time. When the longitudinal controller receives the next new longitudinal planning command, the accumulated time is reset to 0, and the values ​​are taken from Vref and Accref again according to the control cycle.

[0121] Then, step (1): adjust the weight input according to the longitudinal planning acceleration command: the acceleration command PlanningAccRef calculated by the longitudinal planning. Weight calculation: When PlanningAccRef is large, it means that a faster acceleration response is required. Therefore, the feedforward weight KAccforward is set to |PlanningAccRef / ACCmax| (ACCmax is the maximum possible acceleration), so that the influence of the feedforward control will be increased so that the desired acceleration can be achieved faster. At the same time, the weight of the closed-loop feedback control Kcloseloop is set to 1-KAccforward to ensure that the sum of the weights is 1. Result: When rapid acceleration or deceleration is required, feedforward control dominates; when the acceleration command is small, the influence of the closed-loop feedback control is relatively large.

[0122] Step (2): Adjust weights based on acceleration error

[0123] Input: Error between actual acceleration and desired acceleration.

[0124] Weight adjustment: When the acceleration error is large, increase the weight of the feedforward control KAccforward_accerr, and reduce the weight of the closed-loop feedback control Kcloseloop_accerr. The weights of the two are also complementary, that is, their sum should be kept at 1. Result: When the acceleration error is large, the system tends to rely more on feedforward control to quickly correct the error; when the error is small, the closed-loop feedback control plays a greater role to maintain the stability of the system.

[0125] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0126] Based on the same inventive concept, the embodiment of the present application also provides a vehicle driving device for implementing the vehicle driving method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle driving device embodiments provided below can refer to the limitations on the vehicle driving method above, and will not be repeated here.

[0127] In an exemplary embodiment, Figure 5 As shown, a vehicle driving device is provided, comprising:

[0128] The planning module 11 is used to adjust the driving state of the vehicle according to the target speed and target acceleration required for the vehicle to reach the target position, and obtain the actual speed and actual acceleration of the vehicle;

[0129] A forward feedback module 12 is used to determine an acceleration forward feedback value according to the target acceleration and the actual acceleration;

[0130] The negative feedback module 13 is used to determine the speed negative feedback value according to the actual speed and the target speed;

[0131] The driving adjustment module 14 is used to optimize the actual acceleration according to the acceleration forward feedback value and the speed negative feedback value, so that when the actual speed reaches the target speed, the vehicle drives to the longitudinal planning position at the target speed.

[0132] In one embodiment, the forward feedback module 12 is further used for:

[0133] The ratio between the target acceleration and the maximum acceleration corresponding to the vehicle is determined as the initial weight;

[0134] According to the acceleration difference between the actual acceleration and the target acceleration, the initial weight is adjusted to obtain the feedforward weight;

[0135] The product of the target acceleration and the feedforward weight is determined as the acceleration feedforward value.

[0136] In one embodiment, the forward feedback module 12 includes:

[0137] A difference determination submodule is used to determine the speed difference between the actual speed and the target speed;

[0138] The proportional operation submodule is used to perform proportional operation and integral operation on the speed difference to obtain the speed negative feedback value.

[0139] In one embodiment, the ratio operation submodule is further used for:

[0140] The difference between the set value and the feedforward weight is used as the negative feedback weight;

[0141] determining a first product between the speed difference and the negative feedback weight;

[0142] Proportional and integral operations are performed on the first product to obtain a speed negative feedback value.

[0143] In one embodiment, the forward feedback module 12 is further used for:

[0144] Determine an adjustment coefficient according to the acceleration difference between the actual acceleration and the target acceleration; wherein the adjustment coefficient is positively correlated with the acceleration difference;

[0145] The second product between the adjustment coefficient and the initial weight is used as the feedforward weight.

[0146] In one embodiment, the driving adjustment module 14 is further configured to:

[0147] The sum of the actual acceleration, the acceleration pre-feedback value and the velocity negative feedback value is taken as the optimized acceleration;

[0148] The optimized acceleration is sent to a power system in the vehicle so that the power system adjusts the actual acceleration of the vehicle to the optimized acceleration.

[0149] In one embodiment, the planning module 11 is further configured to:

[0150] Sending a target speed and a target acceleration required for the vehicle to reach a target position to a power system in the vehicle so that the power system can adjust the driving state of the vehicle;

[0151] After the driving state is adjusted, the actual speed and actual acceleration of the vehicle are obtained. Each module in the above vehicle driving device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0152] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data on the vehicle driving method. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a vehicle driving method is implemented.

[0153] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0154] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0155] According to the target speed and target acceleration required for the vehicle to reach the target position, the driving state of the vehicle is adjusted to obtain the actual speed and actual acceleration of the vehicle;

[0156] Determine the pre-acceleration feedback value according to the target acceleration and the actual acceleration;

[0157] Determine the speed negative feedback value according to the actual speed and the target speed;

[0158] According to the acceleration forward feedback value and the speed negative feedback value, the actual acceleration is optimized so that when the actual speed reaches the target speed, the vehicle travels to the longitudinal planning position at the target speed.

[0159] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the ratio between the target acceleration and the maximum acceleration corresponding to the vehicle is determined as the initial weight; the initial weight is adjusted according to the acceleration difference between the actual acceleration and the target acceleration to obtain the feedforward weight; the product between the target acceleration and the feedforward weight is determined as the acceleration forward feedback value.

[0160] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining the speed difference between the actual speed and the target speed; performing proportional operation and integral operation on the speed difference to obtain a speed negative feedback value.

[0161] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the difference between the set value and the feedforward weight is used as the negative feedback weight; the first product between the speed difference and the negative feedback weight is determined; and the first product is proportionally and integrally operated to obtain a speed negative feedback value.

[0162] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining an adjustment coefficient based on the acceleration difference between the actual acceleration and the target acceleration; wherein the adjustment coefficient is positively correlated with the acceleration difference; and using the second product between the adjustment coefficient and the initial weight as the feedforward weight.

[0163] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the sum of the actual acceleration, the acceleration pre-feedback value and the speed negative feedback value is used as the optimized acceleration; the optimized acceleration is sent to the power system in the vehicle so that the power system adjusts the actual acceleration of the vehicle to the optimized acceleration.

[0164] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the target speed and target acceleration required for the vehicle to reach the target position are sent to the power system in the vehicle so that the power system adjusts the driving state of the vehicle; after the driving state is adjusted, the actual speed and actual acceleration of the vehicle are obtained.

[0165] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0166] According to the target speed and target acceleration required for the vehicle to reach the target position, the driving state of the vehicle is adjusted to obtain the actual speed and actual acceleration of the vehicle;

[0167] Determine the pre-acceleration feedback value according to the target acceleration and the actual acceleration;

[0168] Determine the speed negative feedback value according to the actual speed and the target speed;

[0169] According to the acceleration forward feedback value and the speed negative feedback value, the actual acceleration is optimized so that when the actual speed reaches the target speed, the vehicle travels to the longitudinal planning position at the target speed.

[0170] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the ratio between the target acceleration and the maximum acceleration corresponding to the vehicle is determined as the initial weight; the initial weight is adjusted according to the acceleration difference between the actual acceleration and the target acceleration to obtain the feedforward weight; the product between the target acceleration and the feedforward weight is determined as the acceleration forward feedback value.

[0171] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the speed difference between the actual speed and the target speed; performing proportional operation and integral operation on the speed difference to obtain a speed negative feedback value.

[0172] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the difference between the set value and the feedforward weight is used as the negative feedback weight; the first product between the speed difference and the negative feedback weight is determined; and the first product is proportionally and integrally operated to obtain a speed negative feedback value.

[0173] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining an adjustment coefficient based on the acceleration difference between the actual acceleration and the target acceleration; wherein the adjustment coefficient is positively correlated with the acceleration difference; and using the second product between the adjustment coefficient and the initial weight as the feedforward weight.

[0174] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the sum of the actual acceleration, the acceleration pre-feedback value and the speed negative feedback value is used as the optimized acceleration; the optimized acceleration is sent to the power system in the vehicle so that the power system adjusts the actual acceleration of the vehicle to the optimized acceleration.

[0175] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the target speed and target acceleration required for the vehicle to reach the target position are sent to the power system in the vehicle so that the power system adjusts the driving state of the vehicle; after the driving state is adjusted, the actual speed and actual acceleration of the vehicle are obtained.

[0176] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0177] According to the target speed and target acceleration required for the vehicle to reach the target position, the driving state of the vehicle is adjusted to obtain the actual speed and actual acceleration of the vehicle;

[0178] Determine the pre-acceleration feedback value according to the target acceleration and the actual acceleration;

[0179] Determine the speed negative feedback value according to the actual speed and the target speed;

[0180] According to the acceleration forward feedback value and the speed negative feedback value, the actual acceleration is optimized so that when the actual speed reaches the target speed, the vehicle travels to the longitudinal planning position at the target speed.

[0181] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the ratio between the target acceleration and the maximum acceleration corresponding to the vehicle is determined as the initial weight; the initial weight is adjusted according to the acceleration difference between the actual acceleration and the target acceleration to obtain the feedforward weight; the product between the target acceleration and the feedforward weight is determined as the acceleration forward feedback value.

[0182] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the speed difference between the actual speed and the target speed; performing proportional operation and integral operation on the speed difference to obtain a speed negative feedback value.

[0183] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the difference between the set value and the feedforward weight is used as the negative feedback weight; the first product between the speed difference and the negative feedback weight is determined; and the first product is proportionally and integrally operated to obtain a speed negative feedback value.

[0184] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining an adjustment coefficient based on the acceleration difference between the actual acceleration and the target acceleration; wherein the adjustment coefficient is positively correlated with the acceleration difference; and using the second product between the adjustment coefficient and the initial weight as the feedforward weight.

[0185] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the sum of the actual acceleration, the acceleration pre-feedback value and the speed negative feedback value is used as the optimized acceleration; the optimized acceleration is sent to the power system in the vehicle so that the power system adjusts the actual acceleration of the vehicle to the optimized acceleration.

[0186] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the target speed and target acceleration required for the vehicle to reach the target position are sent to the power system in the vehicle so that the power system adjusts the driving state of the vehicle; after the driving state is adjusted, the actual speed and actual acceleration of the vehicle are obtained.

[0187] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0188] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0189] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0190] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle driving method, characterized in that: The method comprises: According to the target speed and target acceleration required for the vehicle to reach the target position, the driving state of the vehicle is adjusted to obtain the actual speed and actual acceleration of the vehicle; Determine the ratio between the target acceleration and the maximum acceleration corresponding to the vehicle as an initial weight; According to the acceleration difference between the actual acceleration and the target acceleration, the initial weight is adjusted to obtain a feedforward weight; Determine the product of the target acceleration and the feedforward weight as the acceleration feedforward value; determining a speed difference between the actual speed and the target speed; Performing proportional and integral operations on the speed difference to obtain a speed negative feedback value; The sum of the actual acceleration, the acceleration pre-feedback value and the velocity negative feedback value is used as the optimized acceleration; The optimized acceleration is sent to the power system in the vehicle so that the power system adjusts the actual acceleration of the vehicle to the optimized acceleration, so that when the actual speed reaches the target speed, the vehicle travels to the longitudinal planning position at the target speed.

2. The method according to claim 1, characterized in that The performing proportional operation and integral operation on the speed difference to obtain a speed negative feedback value includes: The difference between the set value and the feedforward weight is used as the negative feedback weight; determining a first product between the speed difference and the negative feedback weight; Proportional operation and integral operation are performed on the first product to obtain a speed negative feedback value.

3. The method according to claim 1, characterized in that The adjusting the initial weight according to the acceleration difference between the actual acceleration and the target acceleration to obtain the feedforward weight includes: Determining an adjustment coefficient according to an acceleration difference between the actual acceleration and the target acceleration; wherein the adjustment coefficient is positively correlated with the acceleration difference; A second product of the adjustment coefficient and the initial weight is used as a feedforward weight.

4. The method according to claim 1, characterized in that The step of adjusting the driving state of the vehicle according to the target speed and target acceleration required for the vehicle to reach the target position to obtain the actual speed and actual acceleration of the vehicle includes: Sending a target speed and a target acceleration required for the vehicle to reach a target position to a power system in the vehicle so that the power system adjusts the driving state of the vehicle; After the driving state is adjusted, the actual speed and actual acceleration of the vehicle are obtained.

5. The method according to claim 2, characterized in that: The set value is 1.

6. The method according to claim 2, characterized in that The performing proportional operation and integral operation on the first product to obtain a speed negative feedback value includes: A proportional-integral PI regulator is used to perform proportional and integral operations on the first product to obtain a speed negative feedback value.

7. The method according to claim 1, characterized in that The adjusting the initial weight according to the acceleration difference between the actual acceleration and the target acceleration to obtain the feedforward weight includes: Subtracting the actual acceleration from the target acceleration to obtain an acceleration difference; The initial weight is adjusted according to the acceleration difference between the actual acceleration and the target acceleration to obtain a feedforward weight.

8. A vehicle travel device, characterized in that: The device comprises: A planning module, used to adjust the driving state of the vehicle according to the target speed and target acceleration required for the vehicle to reach the target position, so as to obtain the actual speed and actual acceleration of the vehicle; A feedforward module is used to determine the ratio between the target acceleration and the maximum acceleration corresponding to the vehicle as an initial weight; adjust the initial weight according to the acceleration difference between the actual acceleration and the target acceleration to obtain a feedforward weight; and determine the product between the target acceleration and the feedforward weight as an acceleration feedforward value; A negative feedback module is used to determine the speed difference between the actual speed and the target speed; perform proportional operation and integral operation on the speed difference to obtain a speed negative feedback value; The driving adjustment module is used to use the sum of the actual acceleration, the acceleration pre-feedback value and the speed negative feedback value as the optimized acceleration; and send the optimized acceleration to the power system in the vehicle so that the power system adjusts the actual acceleration of the vehicle to the optimized acceleration, so that when the actual speed reaches the target speed, the vehicle drives to the longitudinal planning position at the target speed.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images