Vehicle control method, device, equipment, medium and program product

Abstract

The invention discloses a vehicle control method, device and equipment, a medium and a program product. The vehicle control method comprises the following steps: acquiring a starting coordinate and a starting speed corresponding to a starting moment of a vehicle in a current time period; according to the distance between the starting coordinate and an end point coordinate in the current single-step planning path and the starting vehicle speed, determining a target vehicle speed corresponding to the vehicle in the current time period; monitoring the actual vehicle speed corresponding to the current time period of the vehicle; and according to the actual vehicle speed and the target vehicle speed, the target torque corresponding to the vehicle in the current time period is determined, and the target torque is sent to a corresponding downstream actuator to be executed. The corresponding relation between the opening degree of the accelerator pedal and the torque value does not need to be calibrated, the process of obtaining the target torque based on the starting coordinate, the starting vehicle speed, the end point coordinate and other information is achieved in one longitudinal control module in a centralized mode, the torque control real-time performance of automatic parking is improved, and comfortable automatic parking is achieved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a vehicle control method, device, equipment, medium and program product. Background Art

[0002] Automatic parking is a smart car technology that enables vehicles to automatically find and park in parking spaces without manual operation. This technology uses sensors on the vehicle (such as cameras and radars) to identify the surrounding environment, including parking spaces and obstacles, and plans the best parking path accordingly. During the parking process, the vehicle automatically controls the throttle, brakes and steering to achieve fully automated parking operations.

[0003] In the related art, automatic parking is achieved through deep learning. However, this method consumes a lot of computing resources and has opaque internal logic, which makes the effect of automatic parking uncontrollable. Therefore, how to ensure a more stable effect of automatic parking is an urgent problem to be solved. Summary of the invention

[0004] The embodiments of the present application provide a vehicle control method, device, equipment, medium and program product, which solves the technical problem of uncontrollable automatic parking effect in the prior art when automatic parking is achieved through deep learning, and achieves the technical effect of ensuring a more stable automatic parking effect.

[0005] In a first aspect, the present application provides a vehicle control method, the method comprising:

[0006] When the vehicle is in the current single-step planned path during the automatic parking process, obtaining the starting coordinates and starting speed of the vehicle corresponding to the starting time of the current time period;

[0007] Determining a target speed of the vehicle corresponding to the current time period according to the distance between the starting coordinate and the end point coordinate in the current single-step planned path and the starting speed;

[0008] Monitoring the actual speed of the vehicle during the current period;

[0009] Determine a target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed, and send the target torque to a corresponding downstream actuator for execution;

[0010] The end time corresponding to the current time period is used as the start time corresponding to the next time period, the next time period is updated to the current time period, and the step of obtaining the starting coordinates and the starting speed of the vehicle corresponding to the start time of the current time period is returned to the current single-step planned path when the vehicle is in the automatic parking process, until the vehicle reaches the end point coordinates of the current single-step planned path.

[0011] Furthermore, after the vehicle reaches the end point coordinates of the current single-step planned path, the method further includes:

[0012] The next single-step planned path of the vehicle during the automatic parking process is obtained, the next single-step planned path is updated to the current single-step planned path, and the step of returning to the current single-step planned path of the vehicle during the automatic parking process to obtain the starting coordinates and starting speed of the vehicle corresponding to the starting time of the current time period until the vehicle reaches the target parking space.

[0013] Further, determining the target speed of the vehicle corresponding to the current time period according to the distance between the starting coordinate and the end point coordinate in the current single-step planned path and the starting speed includes:

[0014] Determine the to-be-verified vehicle speed of the vehicle corresponding to the current time period according to the Euclidean distance between the starting coordinate and the ending coordinate, the starting vehicle speed, a preset gain coefficient, and a preset compensation value;

[0015] Determining whether the vehicle speed to be verified is less than or equal to a preset maximum speed limit of the vehicle;

[0016] When the vehicle speed to be verified is less than or equal to the preset maximum speed limit, determining the vehicle speed to be verified as the target vehicle speed corresponding to the vehicle in the current time period;

[0017] When the to-be-verified vehicle speed is greater than the preset maximum speed limit, the preset maximum speed limit is determined as the target vehicle speed corresponding to the vehicle in the current time period.

[0018] Further, the determining the to-be-verified vehicle speed of the vehicle corresponding to the current time period according to the Euclidean distance between the starting coordinate and the end point coordinate, the starting vehicle speed, a preset gain coefficient, and a preset compensation value includes:

[0019]

[0020] Among them, exp1 is the vehicle speed to be verified, x N ,y N is the end point coordinate, x i ,yi is the starting coordinate, gain and k are both gain coefficients, curspeed is the starting vehicle speed, and offset is the compensation value.

[0021] Furthermore, before determining whether the vehicle speed to be verified is less than or equal to a preset maximum speed limit of the vehicle, the method further includes:

[0022] Obtaining the weather conditions corresponding to the vehicle in the current time period, obtaining a first distance between the vehicle and the starting coordinates in the current single-step planned path, obtaining a second distance between the vehicle and an obstacle in the current driving direction of the vehicle, and obtaining a third distance between the vehicle and the end point coordinates;

[0023] The preset maximum speed limit of the vehicle corresponding to the current time period is determined according to the weather condition, the first distance, the second distance, and the third distance.

[0024] Further, determining the target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed includes:

[0025] determining, according to a speed deviation between the actual vehicle speed and the target vehicle speed, a to-be-verified torque corresponding to the vehicle in the current time period;

[0026] When the target vehicle speed is greater than a preset threshold speed and the speed deviation is greater than the preset threshold deviation, monitoring the duration of the first state in which the target vehicle speed is greater than the preset threshold speed and the speed deviation is greater than the preset threshold deviation;

[0027] When the duration of the first state is longer than a preset threshold duration, determining the sum of the to-be-verified torque and the preset calibrated torque as the target torque of the vehicle corresponding to the current time period;

[0028] When the target vehicle speed is less than or equal to a preset threshold speed, or the duration of the first state is less than or equal to the preset threshold duration, the torque to be verified is determined as the target torque corresponding to the vehicle in the current time period.

[0029] Further, determining the target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed, and sending the target torque to the corresponding downstream actuator for execution, includes:

[0030] Determining the target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed;

[0031] Performing smoothing filtering on the target torque;

[0032] The target torque after smoothing and filtering is sent to the corresponding downstream actuator for execution.

[0033] Furthermore, when the vehicle is in the current single-step planned path during the automatic parking process, the method further includes:

[0034] Acquire a second distance between the vehicle and the nearest obstacle in the current driving direction of the vehicle and the obstacle type of the nearest obstacle;

[0035] A target deceleration and braking mode of the vehicle is determined according to the second distance and the obstacle type, and the target deceleration and braking mode is sent to a corresponding downstream actuator for execution.

[0036] Further, after sending the target torque or the target deceleration braking mode to the corresponding downstream actuator for execution, the method further includes:

[0037] receiving a notification instruction of failure of the legitimacy check of the target torque or the target deceleration braking mode feedback by the downstream actuator;

[0038] In response to the notification instruction, the deceleration braking mode of the vehicle is determined to be an emergency braking mode, and the emergency braking mode is sent to the corresponding downstream actuator for execution.

[0039] Furthermore, when the vehicle is in the current single-step planned path during the automatic parking process, the method further includes:

[0040] Abnormal data of the vehicle during the automatic parking process is screened and the abnormal data is uploaded to the cloud.

[0041] Furthermore, when the vehicle is in the current single-step planned path during the automatic parking process, the method further includes:

[0042] Monitoring the actual coordinates and actual torque of the vehicle;

[0043] In the case where the actual coordinates remain unchanged and the actual torque increases, if the duration of the second state in which the actual coordinates remain unchanged and the actual torque increases exceeds a preset duration, it is determined that the tire of the vehicle is in conflict with an obstacle;

[0044] The perception information of the tire's collision with the obstacle is fed back to the perception module, so that the perception module can combine the perception information to feed back the vehicle's environmental information to the path planning module, and the path planning module generates the next single-step planning path according to the environmental information.

[0045] In a second aspect, the present application provides a vehicle control device, the device comprising:

[0046] an acquisition unit, configured to acquire, when the vehicle is in a current single-step planned path during automatic parking, a starting coordinate and a starting speed of the vehicle corresponding to a starting time of a current time period;

[0047] A vehicle speed determination unit, configured to determine a target vehicle speed corresponding to the vehicle in the current time period according to a distance between the starting coordinate and the end point coordinate in the current single-step planned path and the starting vehicle speed;

[0048] A monitoring unit, used to monitor the actual speed of the vehicle corresponding to the current time period;

[0049] a torque determination unit, configured to determine a target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed, and send the target torque to a corresponding downstream actuator for execution;

[0050] The loop unit is used to use the end time corresponding to the current time period as the start time corresponding to the next time period, update the next time period to the current time period, and return to the step of obtaining the starting coordinates and starting speed of the vehicle corresponding to the start time of the current time period when the vehicle is in the current single-step planned path during automatic parking, until the vehicle reaches the end point coordinates of the current single-step planned path.

[0051] In a third aspect, the present application provides an electronic device, including:

[0052] processor;

[0053] a memory for storing instructions executable by the processor;

[0054] Wherein, the processor is configured to execute to implement a vehicle control method as provided in the first aspect.

[0055] In a fourth aspect, the present application provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute a vehicle control method as provided in the first aspect.

[0056] In a fifth aspect, the present application provides a computer program product, comprising computer instructions, wherein the computer instructions are executed by a processor to implement a vehicle control method as provided in the first aspect.

[0057] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0058] The embodiment of the present application abandons the calibration table lookup method and the deep learning method in the related art, but determines the target speed of the vehicle in the current period based on the information such as the starting coordinates, starting speed, and end point coordinates that can be directly collected, and realizes the torque control of the vehicle based on the difference between the target speed and the actual speed of the vehicle, thereby realizing the automatic parking process of the vehicle. The embodiment of the present application not only does not need to calibrate the corresponding relationship between the accelerator pedal opening and the torque value, but also concentrates the process of obtaining the target torque based on the starting coordinates, starting speed, end point coordinates and other information in a longitudinal control module, does not need to over-rely on downstream actuators, and does not involve the conversion process of the accelerator pedal opening to the torque value, thereby improving the real-time torque control of automatic parking and realizing comfortable automatic parking.

[0059] In addition, the embodiments of the present application are based on the information such as the starting coordinates, starting speed, and end point coordinates that can be directly collected, and there is no need to perform complex calculations involved in deep learning, thereby saving computing resources. Moreover, in the embodiments of the present application, the torque control of the vehicle is achieved based on the difference between the target speed and the actual speed of the vehicle. The internal logic is transparent, making the effect of automatic parking more controllable and improving the stability and safety of automatic parking. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0061] Figure 1 A schematic diagram of a vehicle control architecture flow chart provided in an embodiment of the present application;

[0062] Figure 2 A schematic diagram of a vehicle control method provided in an embodiment of the present application;

[0063] Figure 3 A schematic diagram of a single-step planning path provided in an embodiment of the present application;

[0064] Figure 4 A schematic diagram of the structure of a vehicle control device provided in an embodiment of the present application;

[0065] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] The embodiment of the present application provides a vehicle control method to solve the technical problem in the prior art of realizing automatic parking through deep learning, where the effect of automatic parking is uncontrollable.

[0067] The technical solution of the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0068] The embodiment of the present application abandons the calibration table lookup method and the deep learning method in the related art, but determines the target speed of the vehicle in the current period based on the information such as the starting coordinates, starting speed, and end point coordinates that can be directly collected, and realizes the torque control of the vehicle based on the difference between the target speed and the actual speed of the vehicle, thereby realizing the automatic parking process of the vehicle. The embodiment of the present application not only does not need to calibrate the corresponding relationship between the accelerator pedal opening and the torque value, but also concentrates the process of obtaining the target torque based on the starting coordinates, starting speed, end point coordinates and other information in a longitudinal control module, does not need to over-rely on downstream actuators, and does not involve the conversion process of the accelerator pedal opening to the torque value, thereby improving the real-time torque control of automatic parking and realizing comfortable automatic parking.

[0069] In addition, the embodiments of the present application are based on the information such as the starting coordinates, starting speed, and end point coordinates that can be directly collected, and there is no need to perform complex calculations involved in deep learning, thereby saving computing resources. Moreover, in the embodiments of the present application, the torque control of the vehicle is achieved based on the difference between the target speed and the actual speed of the vehicle. The internal logic is transparent, making the effect of automatic parking more controllable and improving the stability and safety of automatic parking.

[0070] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0071] First of all, the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0072] Automatic parking is a smart car technology that enables vehicles to automatically find and park in parking spaces without manual operation. This technology uses sensors on the vehicle (such as cameras and radars) to identify the surrounding environment, including parking spaces and obstacles, and plans the best parking path accordingly. During the parking process, the vehicle automatically controls the throttle, brakes and steering to achieve fully automated parking operations.

[0073] In the related art, automatic parking can be achieved by calibrating the table lookup method. Specifically, the related controller sends the accelerator pedal opening value to the downstream controller, and the downstream controller converts the accelerator pedal opening value into a torque value by looking up the table. The downstream controller sends the torque value to the downstream actuator for execution. However, this method is overly dependent on the downstream actuator, and the conversion process from the accelerator pedal opening to the torque value is relatively complex and has poor real-time performance, making it difficult to achieve comfortable automatic parking.

[0074] In addition, related technologies also implement automatic parking through deep learning. However, this method consumes a lot of computing resources and its internal logic is opaque, making the effect of automatic parking uncontrollable.

[0075] Therefore, how to ensure that the effect of automatic parking is more stable is a problem that needs to be solved urgently.

[0076] In order to solve the above problems, the embodiment of the present application provides a vehicle control method, which can be specifically executed by a related control module, such as a longitudinal control module. The controller architecture where the longitudinal control module is located includes a perception module, a path planning module, a longitudinal control module and an actuator. The architecture diagram is shown in FIG. Figure 1 . Among them, the perception module relies on the camera, radar and other equipment on the vehicle to monitor the environment in which the vehicle is located during the automatic parking process, and obtains the perception information in a comprehensive manner. The perception module sends the perception information to the path planning module. The path planning module calculates the single-step planning path for the vehicle's automatic parking based on the perception information and sends it to the longitudinal control module. The longitudinal control module determines the relevant control information for the vehicle's automatic parking based on the single-step planning path, such as the vehicle's driving speed, remaining driving distance, vehicle's expected torque, deceleration and braking mode, etc. The longitudinal control module sends the relevant control information to the corresponding actuator, and the actuator executes the target action of the relevant control information. The actuator may include controllers corresponding to devices such as steering wheels, accelerator pedals, and brake pedals.

[0077] Now combined Figure 1 The control architecture shown is used to illustrate a vehicle control method provided by an embodiment of the present application. Figure 2 A vehicle control method provided in an embodiment of the present application includes steps S21 to S25.

[0078] Step S21, when the vehicle is in the current single-step planned path during the automatic parking process, obtaining the starting coordinates and starting speed of the vehicle corresponding to the starting time of the current time period;

[0079] Step S22, determining a target speed of the vehicle corresponding to the current time period according to the distance between the starting coordinate and the end coordinate in the current single-step planned path and the starting speed;

[0080] Step S23, monitoring the actual speed of the vehicle corresponding to the current time period;

[0081] Step S24, determining a target torque of the vehicle corresponding to the current period according to the actual vehicle speed and the target vehicle speed, and sending the target torque to a corresponding downstream actuator for execution;

[0082] Step S25, taking the end time corresponding to the current time period as the start time corresponding to the next time period, updating the next time period to the current time period, and returning to execute the step of obtaining the starting coordinates and starting speed of the vehicle at the start time of the current time period when the vehicle is in the current single-step planned path during automatic parking, until the vehicle reaches the end coordinates of the current single-step planned path.

[0083] Regarding step S21, when the vehicle is in the current single-step planned path during the automatic parking process, the starting coordinates and the starting speed of the vehicle corresponding to the starting time of the current time period are obtained.

[0084] During the process of automatic parking of a vehicle, in order for the vehicle to enter the parking space and park the vehicle, the vehicle may need to continuously adjust and move back and forth, that is, the vehicle needs to move forward a distance and then backward a distance, then move forward a distance again, and then backward a distance again. This process can be called rubbing the storage. In this process, the embodiment of the present application refers to the moving path in the same direction as a single-step planning path. For example, the vehicle needs to move forward a distance A, backward a distance B, then move forward a distance C, and backward a distance D to enter the parking space to complete the parking action. The embodiment of the present application refers to the path in the process of moving forward a distance A as a single-step planning path. Similarly, the path in the process of moving backward a distance B is called a single-step planning path, the path in the process of moving forward a distance C is called a single-step planning path, and the path in the process of moving backward a distance D is called a single-step planning path.

[0085] As mentioned above, the path planning module calculates the single-step planning path for the vehicle's automatic parking based on the perception information and sends it to the longitudinal control module. It should be noted that the single-step planning path can be the walking path corresponding to any point on the vehicle, which point can be, for example, the center point of the rear axle of the vehicle.

[0086] After the longitudinal control module obtains the single-step planning path, step S21 is executed. In the embodiment of the present application, the single-step planning path being executed is defined as the current single-step planning path. The current single-step planning path includes the starting coordinates, the end coordinates, and the vehicle pre-driving path between the starting coordinates and the end coordinates. In the embodiment of the present application, the starting coordinates are marked as (x0, y0), and the end coordinates are marked as (x N ,y N ),like Figure 3As shown, this is a schematic diagram of a single-step planning path.

[0087] When the vehicle is in the current single-step planned path during automatic parking, the current single-step planned path is divided into multiple time periods according to a preset time length. For example, the time length corresponding to each second is divided into a time period. The embodiment of the present application will take 1 second as a time period as an example to illustrate the subsequent scheme.

[0088] Assume that the current time period of the vehicle is the i-th time period, which represents the time period corresponding to the i-th second in the current single-step planning path, i is an integer traversed from 0 to N, where N is a positive integer. From the position sensor and speed sensor deployed on the vehicle, obtain the starting coordinates and starting speed corresponding to the starting time of the current time period. Mark the starting coordinates as (x i ,y i ), and the starting speed is recorded as curspeed. The time period will change over time, and i will increase from 0 in sequence. The embodiment of the present application takes the i-th time period as an example to illustrate the subsequent scheme, and the i-th time period can be any time period in the current single-step planning path.

[0089] Regarding step S22, the target speed of the vehicle corresponding to the current time period is determined according to the distance between the starting coordinates and the end coordinates in the current single-step planned path and the starting vehicle speed.

[0090] Specifically, the method for determining the target vehicle speed corresponding to the current time period may include steps S221 to S224.

[0091] Step S221, determining the to-be-verified vehicle speed of the vehicle corresponding to the current time period according to the Euclidean distance between the starting coordinate and the ending coordinate, the starting vehicle speed, a preset gain coefficient, and a preset compensation value;

[0092] Step S222, determining whether the vehicle speed to be verified is less than or equal to a preset maximum speed limit of the vehicle;

[0093] Step S223, when the to-be-verified vehicle speed is less than or equal to the preset maximum speed limit, determining the to-be-verified vehicle speed as the target vehicle speed corresponding to the vehicle in the current time period;

[0094] Step S224, when the to-be-verified vehicle speed is greater than the preset maximum speed limit, the preset maximum speed limit is determined as the target vehicle speed corresponding to the vehicle in the current time period.

[0095] Regarding step S221, please refer to the following formula (1).

[0096]

[0097] Among them, exp1 is the vehicle speed to be verified, x N ,y N is the end point coordinate, x i ,y i is the starting coordinate, gain and k are both gain coefficients, curspeed is the starting vehicle speed, and offset is the compensation value. gain, k, and offset can be adjusted and calibrated according to the actual working conditions of the vehicle.

[0098] Regarding step S222, the method for determining the preset maximum speed limit includes steps S2221 and S2222.

[0099] Step S2221, obtaining the weather conditions corresponding to the vehicle in the current time period, obtaining the first distance between the vehicle and the starting coordinates in the current single-step planned path, obtaining the second distance between the vehicle and the obstacle in the current driving direction of the vehicle, and obtaining the third distance between the vehicle and the end point coordinates;

[0100] Step S2222: determining the preset maximum speed limit of the vehicle corresponding to the current time period according to the weather condition, the first distance, the second distance, and the third distance.

[0101] It should be noted that when determining the preset maximum speed limit, it is necessary to comprehensively consider the restrictions of the weather conditions, the first distance, the second distance and the third distance on the preset maximum speed limit, so as to obtain the preset maximum speed limit corresponding to the current time period.

[0102] The limitations of the preset maximum speed limit are now explained as follows from the aspects of the weather conditions, the first distance, the second distance and the third distance.

[0103] When the weather condition is rainy or snowy, the corresponding preset maximum speed limit is relatively low. When the weather condition is neither rainy nor snowy, the corresponding preset maximum speed limit is relatively high.

[0104] When the vehicle's current position (x i ,y i ) is closer to the first distance between the starting coordinates (x0, y0), the corresponding preset maximum speed limit is relatively lower, and when the first distance is farther, the corresponding preset maximum speed limit is relatively higher.

[0105] When the second distance between the obstacle and the vehicle in the current driving direction is closer, the corresponding preset maximum speed limit is relatively lower; when the second distance between the obstacle and the vehicle in the current driving direction is farther, the corresponding preset maximum speed limit is relatively higher.

[0106] When the vehicle's current position (x i ,y i ) and the end point coordinates (x N ,y N ), the closer the third distance between the two vehicles, the lower the corresponding preset maximum speed limit is; when the third distance is longer, the higher the corresponding preset maximum speed limit is.

[0107] The influence of the weather condition, the first distance, the second distance and the third distance on the preset maximum speed limit is comprehensively considered, so as to obtain the preset maximum speed limit finally corresponding to the current time period.

[0108] After obtaining the preset maximum speed limit corresponding to the current time period, compare the preset maximum speed limit with the vehicle speed to be verified. When the vehicle speed to be verified is less than or equal to the preset maximum speed limit, execute step S223; when the vehicle speed to be verified is greater than the preset maximum speed limit, execute step S224.

[0109] Regarding step S223, when the to-be-verified vehicle speed is less than or equal to the preset maximum speed limit, it means that the to-be-verified vehicle speed meets the maximum speed limit condition and can be used directly, and then the to-be-verified vehicle speed is determined as the target vehicle speed corresponding to the vehicle in the current time period.

[0110] Regarding step S224, when the to-be-verified vehicle speed is greater than the preset maximum speed limit, it means that the to-be-verified vehicle speed does not meet the maximum speed limit condition and cannot be used, and then the preset maximum speed limit is determined as the target vehicle speed corresponding to the vehicle in the current time period.

[0111] Regarding step S23, the actual speed of the vehicle corresponding to the current time period is monitored.

[0112] The actual speed of the vehicle in the current time period can be monitored according to a preset frequency. The actual speed may be different at different times in the current time period. When the vehicle is at the start of the current time period, the actual speed is the start speed. The preset frequency can be less than or equal to the duration of the current time period and can be set according to actual conditions. The embodiment of the present application does not limit this.

[0113] Step S23 may be executed synchronously during the execution of steps S21 and S22.

[0114] Regarding step S24, a target torque corresponding to the vehicle in the current period is determined according to the actual vehicle speed and the target vehicle speed, and the target torque is sent to a corresponding downstream actuator for execution.

[0115] The target speed is the speed that the vehicle ultimately wants to reach. When there is a difference between the actual speed and the target speed, it is necessary to control the actual speed change so that the actual speed continues to approach the target speed. In the best case, the actual speed can be adjusted to the target speed.

[0116] The method for determining the target torque includes steps S241 to S244.

[0117] Step S241, determining the to-be-verified torque of the vehicle corresponding to the current time period according to the speed deviation between the actual vehicle speed and the target vehicle speed;

[0118] Step S242, when the target vehicle speed is greater than a preset threshold speed and the speed deviation is greater than the preset threshold deviation, monitoring the duration of the first state in which the target vehicle speed is greater than the preset threshold speed and the speed deviation is greater than the preset threshold deviation;

[0119] Step S243, when the duration of the first state is greater than a preset threshold duration, determining the sum of the to-be-verified torque and the preset calibrated torque as the target torque of the vehicle corresponding to the current period;

[0120] Step S244, when the target vehicle speed is less than or equal to a preset threshold speed, or the duration of the first state is less than or equal to the preset threshold duration, the torque to be verified is determined as the target torque corresponding to the vehicle in the current time period.

[0121] Regarding step S241 , based on the speed deviation between the actual vehicle speed and the target vehicle speed, the to-be-verified torque required by the vehicle in the current period to compensate for the speed deviation is determined.

[0122] Regarding step S242 and step S243, the preset threshold speed and the preset threshold duration are both calibrated values, which can be determined according to actual conditions. The role of the preset threshold speed and the preset threshold duration is to determine whether the torque to be verified needs torque compensation. When the target vehicle speed is greater than the preset threshold speed, it means that the target vehicle speed is relatively large. At this time, it is necessary to further determine whether the speed deviation is greater than the preset threshold deviation. If so, it means that the torque to be verified may need torque compensation. At this time, further monitor the duration of the first state in which the target vehicle speed is greater than the preset threshold speed and the speed deviation is greater than the preset threshold deviation. When the duration of the first state is greater than the preset threshold duration, it means that the error continues to be large, and the torque to be verified needs to be compensated. Specifically, the torque to be verified is added to the preset calibrated torque, and the sum of the two is used as the final target torque.

[0123] Regarding step S244, when the target vehicle speed is less than or equal to the preset threshold speed, or the duration of the first state is less than or equal to the preset threshold duration, it is considered that the torque to be verified does not need to be compensated, and the torque to be verified is directly determined as the target torque corresponding to the vehicle in the current time period.

[0124] After determining the target torque, before sending the target torque to the corresponding downstream actuator for execution, the target torque is first smoothed and filtered, and then the target torque after smoothing and filtering is sent to the corresponding downstream actuator for execution. This can make the torque change smoother and improve the comfort of the vehicle during automatic parking.

[0125] Regarding step S25, the end time corresponding to the current time period is used as the start time corresponding to the next time period, the next time period is updated to the current time period, and the process returns to the step of obtaining the starting coordinates and starting speed of the vehicle at the start time of the current time period when the vehicle is in the current single-step planned path during automatic parking, until the vehicle reaches the end coordinates of the current single-step planned path.

[0126] When the current period ends, the corresponding end time is the start time of the next period, and the next period is taken as the new current period, and steps S21 to S24 are performed in sequence until the vehicle reaches the end coordinates of the current single-step planning path. At this point, the vehicle has completed the parking action of the current single-step planning path.

[0127] After the vehicle reaches the end coordinates of the current single-step planning path, the next single-step planning path of the vehicle in the automatic parking process can be obtained, the next single-step planning path is updated to the current single-step planning path, and the step of returning to the current single-step planning path of the vehicle in the automatic parking process to obtain the starting coordinates and starting speed of the vehicle at the starting time of the current time period until the vehicle reaches the target parking space. At this point, the vehicle has completed the parking action of automatic parking.

[0128] In addition, in order to ensure the safety of the vehicle during automatic parking, the embodiment of the present application also provides the following technical solution, which is specifically implemented in the process of the current single-step planning path when the vehicle is in the process of automatic parking, specifically including step S31-step S32.

[0129] Step S31, obtaining a second distance between the vehicle and the nearest obstacle in the current driving direction of the vehicle and the obstacle type of the nearest obstacle;

[0130] Step S32: determining a target deceleration and braking mode of the vehicle according to the second distance and the obstacle type, and sending the target deceleration and braking mode to a corresponding downstream actuator for execution.

[0131] Based on camera and ultrasonic radar data, the nearest obstacle distance and obstacle type in the vehicle's current travel direction are identified, and different deceleration and braking modes are set based on the obstacle distance and type to ensure parking safety.

[0132] For example, the deceleration braking mode may include four modes, namely, no braking mode, slight braking mode, comfort braking mode and emergency braking mode, the braking efficiency increases successively, the braking effect increases successively, but at the same time, the braking experience of the user on the vehicle becomes worse successively. According to the second distance and the obstacle type, a target deceleration braking mode is selected from the above four braking modes, and the target deceleration braking mode is sent to the corresponding downstream actuator for execution.

[0133] After sending the target torque or the target deceleration braking mode to the corresponding downstream actuator for execution, the method further includes steps S41 and S42.

[0134] Step S41, receiving a notification instruction of a failure of the legality check of the target torque or the target deceleration braking mode feedback by the downstream actuator;

[0135] Step S42, in response to the notification instruction, determining that the deceleration braking mode of the vehicle is an emergency braking mode, and sending the emergency braking mode to the corresponding downstream actuator for execution.

[0136] After receiving the target torque or target deceleration braking mode, the downstream actuator will verify the relevant information of the target torque or target deceleration braking mode. If the verification fails, it will feedback the notification instruction of legality verification failure to the longitudinal control module. Based on the notification instruction, the longitudinal control module uses the emergency braking mode as the current target deceleration braking mode and sends it to the downstream actuator for execution, so as to achieve rapid braking of the vehicle, avoid greater damage or loss to the vehicle during the automatic parking process, and improve safety.

[0137] Among them, the verification method can adopt relevant technologies, such as CRC (Cyclic Redundancy Check), which is not limited in the embodiments of the present application.

[0138] When the longitudinal control module determines that the current braking mode is the emergency braking mode, an abnormal signal can be sent to the vehicle's central control display or a mobile terminal associated with the vehicle to remind the user to pay attention to the impact of emergency braking and improve the user experience.

[0139] When the vehicle is in the current single-step planned path during the automatic parking process, abnormal data of the vehicle during the automatic parking process can also be screened and uploaded to the cloud, and local data packets can be cleaned up regularly and quantitatively.

[0140] For example, in the software code of the automatic parking function, log printing is added to the key function entrance and exit, and key algorithm parameters are recorded. Abnormal data is filtered locally according to the established logic, such as abnormal data values, excessive CPU load, function failure, etc. The filtered problem logs can be uploaded to the cloud through the OTA (Over-the-Air Technology) channel to help companies summarize real vehicle problem data for continuous iterative optimization.

[0141] The abnormal data is uploaded to the cloud, so that the cloud can perform statistical analysis on the abnormal data during the automatic parking process, and provide a data basis for improving the automatic parking strategy. Regular and quantitative cleaning of local data packets can ensure sufficient local storage space, reduce the probability of insufficient local storage space, and improve user experience.

[0142] In the case where the vehicle is in the current single-step planned path during automatic parking, the method further includes steps S51 to S53.

[0143] Step S51, monitoring the actual coordinates and actual torque of the vehicle;

[0144] Step S52, when the actual coordinates remain unchanged and the actual torque increases, if the duration of the second state in which the actual coordinates remain unchanged and the actual torque increases exceeds a preset duration, determining that the tire of the vehicle is in conflict with an obstacle;

[0145] Step S53, feeding back the perception information of the tire's collision with the obstacle to the perception module, so that the perception module can combine the perception information to feed back the environment information of the vehicle to the path planning module, and the path planning module generates the next single-step planning path according to the environment information.

[0146] Regarding step S51 , it is monitored whether the actual coordinates of the vehicle are changing, and whether the actual torque of the vehicle is increasing.

[0147] Regarding step S52, when the actual coordinates remain unchanged and the actual torque increases, the duration of the second state of the state is monitored, and it is determined whether the duration of the second state exceeds the preset duration. If so, it means that the torque of the vehicle is increasing while the position of the vehicle has not changed, which means that the tire of the vehicle is in conflict with an obstacle, and this obstacle is likely to be a wheel chock. At this time, the longitudinal control module feeds back the perception information of the tire conflicting with the obstacle to the perception module, and the perception module integrates the collected information of various sensors and the information of the tire conflicting with the obstacle sent by the longitudinal control module to obtain the perception information. The perception module sends the perception information to the path planning module for single-step path planning, and then the path planning module sends the single-step path planning path to the longitudinal control module to return to execute steps S21-S25 to perform automatic parking control on the vehicle.

[0148] It can be seen that the longitudinal control module of the embodiment of the present application can feedback the local subtle road conditions at the vehicle tires to the perception module, making up for the monitoring blind spots of monitoring equipment such as cameras and radars, and improving the comprehensiveness of the perception of the perception module, thereby improving the degree of fine control during the vehicle's automatic parking process and improving the stability of automatic parking.

[0149] In summary, in the embodiment of the present application, when the vehicle is on the current single-step planned path during automatic parking, the starting coordinates and the starting speed of the vehicle corresponding to the starting time of the current time period are obtained; the target speed of the vehicle corresponding to the current time period is determined according to the distance between the starting coordinates and the end point coordinates in the current single-step planned path and the starting speed; the actual speed of the vehicle corresponding to the current time period is monitored; the target torque of the vehicle corresponding to the current time period is determined according to the actual speed and the target speed, and the target torque is sent to the corresponding downstream actuator for execution; the end time corresponding to the current time period is used as the starting time corresponding to the next time period, the next time period is updated to the current time period, and the step of obtaining the starting coordinates and the starting speed of the vehicle corresponding to the starting time of the current time period when the vehicle is on the current single-step planned path during automatic parking is returned until the vehicle reaches the end point coordinates of the current single-step planned path.

[0150] It can be seen that the embodiment of the present application abandons the calibration table lookup method and the deep learning method in the related art, but determines the target speed of the vehicle in the current period based on the information such as the starting coordinates, starting speed, and end coordinates that can be directly collected, and realizes the torque control of the vehicle based on the difference between the target speed and the actual speed of the vehicle, thereby realizing the automatic parking process of the vehicle. The embodiment of the present application not only does not need to calibrate the corresponding relationship between the accelerator pedal opening and the torque value, but also concentrates the process of obtaining the target torque based on the starting coordinates, starting speed, end coordinates and other information in a longitudinal control module, does not need to rely too much on the downstream actuator, and does not involve the conversion process of the accelerator pedal opening to the torque value, thereby improving the real-time torque control of automatic parking and realizing comfortable automatic parking.

[0151] In addition, the embodiments of the present application are based on the information such as the starting coordinates, starting speed, and end point coordinates that can be directly collected, and there is no need to perform complex calculations involved in deep learning, thereby saving computing resources. Moreover, in the embodiments of the present application, the torque control of the vehicle is achieved based on the difference between the target speed and the actual speed of the vehicle. The internal logic is transparent, making the effect of automatic parking more controllable and improving the stability and safety of automatic parking.

[0152] Based on the same inventive concept, the present application embodiment provides the following Figure 4 A vehicle control device as shown, the device comprising:

[0153] An acquisition unit 41 is used to acquire the starting coordinates and starting speed of the vehicle corresponding to the starting time of the current time period when the vehicle is in the current single-step planned path during the automatic parking process;

[0154] A vehicle speed determination unit 42, configured to determine a target vehicle speed corresponding to the current time period according to the distance between the starting coordinate and the end point coordinate in the current single-step planned path and the starting vehicle speed;

[0155] A monitoring unit 43, used for monitoring the actual speed of the vehicle corresponding to the current time period;

[0156] A torque determination unit 44, configured to determine a target torque of the vehicle corresponding to the current period according to the actual vehicle speed and the target vehicle speed, and send the target torque to a corresponding downstream actuator for execution;

[0157] The loop unit 45 is used to use the end time corresponding to the current time period as the start time corresponding to the next time period, update the next time period to the current time period, and return to the step of obtaining the starting coordinates and starting speed of the vehicle corresponding to the start time of the current time period when the vehicle is in the current single-step planned path during automatic parking, until the vehicle reaches the end coordinates of the current single-step planned path.

[0158] Furthermore, the circulation unit 45 is used for:

[0159] After the vehicle reaches the end coordinates of the current single-step planned path, the next single-step planned path of the vehicle in the automatic parking process is obtained, the next single-step planned path is updated to the current single-step planned path, and the process returns to the step of obtaining the starting coordinates and starting speed of the vehicle corresponding to the starting time of the current time period when the vehicle is on the current single-step planned path during the automatic parking process, until the vehicle reaches the target parking space.

[0160] Furthermore, the vehicle speed determination unit 42 is used to:

[0161] Determine the to-be-verified vehicle speed of the vehicle corresponding to the current time period according to the Euclidean distance between the starting coordinate and the ending coordinate, the starting vehicle speed, a preset gain coefficient, and a preset compensation value;

[0162] Determining whether the vehicle speed to be verified is less than or equal to a preset maximum speed limit of the vehicle;

[0163] When the vehicle speed to be verified is less than or equal to the preset maximum speed limit, determining the vehicle speed to be verified as the target vehicle speed corresponding to the vehicle in the current time period;

[0164] When the to-be-verified vehicle speed is greater than the preset maximum speed limit, the preset maximum speed limit is determined as the target vehicle speed corresponding to the vehicle in the current time period.

[0165] Furthermore, the vehicle speed determination unit 42 is used to execute:

[0166]

[0167] Among them, exp1 is the vehicle speed to be verified, x N ,y N is the end point coordinate, x i ,y i is the starting coordinate, gain and k are both gain coefficients, curspeed is the starting vehicle speed, and offset is the compensation value.

[0168] Furthermore, the vehicle speed determination unit 42 is used to:

[0169] Before determining whether the to-be-verified vehicle speed is less than or equal to the preset maximum speed limit of the vehicle, obtaining the weather condition of the vehicle corresponding to the current time period, obtaining the first distance between the vehicle and the start coordinates in the current single-step planned path, obtaining the second distance between the obstacle in the current driving direction of the vehicle and the vehicle, and obtaining the third distance between the vehicle and the end coordinates;

[0170] The preset maximum speed limit of the vehicle corresponding to the current time period is determined according to the weather condition, the first distance, the second distance, and the third distance.

[0171] Further, the torque determination unit 44 is used to:

[0172] determining, according to a speed deviation between the actual vehicle speed and the target vehicle speed, a to-be-verified torque corresponding to the vehicle in the current time period;

[0173] When the target vehicle speed is greater than a preset threshold speed and the speed deviation is greater than the preset threshold deviation, monitoring the duration of the first state in which the target vehicle speed is greater than the preset threshold speed and the speed deviation is greater than the preset threshold deviation;

[0174] When the duration of the first state is longer than a preset threshold duration, determining the sum of the to-be-verified torque and the preset calibrated torque as the target torque of the vehicle corresponding to the current time period;

[0175] When the target vehicle speed is less than or equal to a preset threshold speed, or the duration of the first state is less than or equal to the preset threshold duration, the torque to be verified is determined as the target torque corresponding to the vehicle in the current time period.

[0176] Further, the torque determination unit 44 is used to:

[0177] Determining the target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed;

[0178] Performing smoothing filtering on the target torque;

[0179] The target torque after smoothing and filtering is sent to the corresponding downstream actuator for execution.

[0180] Further, the braking mode determination unit is used to:

[0181] When the vehicle is in the current single-step planned path during automatic parking, obtaining a second distance between the vehicle and the nearest obstacle in the current driving direction of the vehicle and an obstacle type of the nearest obstacle;

[0182] A target deceleration and braking mode of the vehicle is determined according to the second distance and the obstacle type, and the target deceleration and braking mode is sent to a corresponding downstream actuator for execution.

[0183] Further, the braking mode determination unit is used to:

[0184] After sending the target torque or the target deceleration and braking mode to a corresponding downstream actuator for execution, receiving a notification instruction of a failure of a legality check of feedback from the downstream actuator on the target torque or the target deceleration and braking mode;

[0185] In response to the notification instruction, the deceleration braking mode of the vehicle is determined to be an emergency braking mode, and the emergency braking mode is sent to the corresponding downstream actuator for execution.

[0186] Furthermore, the data screening unit is used to:

[0187] When the vehicle is in the current single-step planned path during the automatic parking process, abnormal data of the vehicle during the automatic parking process is screened and the abnormal data is uploaded to the cloud.

[0188] Furthermore, the obstacle feedback unit is used to:

[0189] When the vehicle is in the current single-step planned path during automatic parking, monitoring the actual coordinates and the actual torque of the vehicle;

[0190] In the case where the actual coordinates remain unchanged and the actual torque increases, if the duration of the second state in which the actual coordinates remain unchanged and the actual torque increases exceeds a preset duration, it is determined that the tire of the vehicle is in conflict with an obstacle;

[0191] The perception information of the tire's collision with the obstacle is fed back to the perception module, so that the perception module can combine the perception information to feed back the vehicle's environmental information to the path planning module, and the path planning module generates the next single-step planning path according to the environmental information.

[0192] Based on the same inventive concept, the present application embodiment provides the following Figure 5 An electronic device as shown includes:

[0193] Processor 51;

[0194] A memory for storing instructions executable by the processor 51;

[0195] The processor 51 is configured to execute to implement a vehicle control method as provided above.

[0196] Based on the same inventive concept, an embodiment of the present application provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by the processor 51 of the electronic device, the electronic device can execute a vehicle control method as provided above.

[0197] Based on the same inventive concept, an embodiment of the present application provides a computer program product, including computer instructions, which are executed by the processor 51 to implement a vehicle control method as provided above.

[0198] Since the electronic device introduced in this embodiment is an electronic device used to implement the information processing method in the embodiment of the present application, based on the information processing method introduced in the embodiment of the present application, a person skilled in the art can understand the specific implementation of the electronic device of the present embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as a person skilled in the art implements the electronic device used by the information processing method in the embodiment of the present application, it belongs to the scope of protection of this application.

[0199] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0200] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0201] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0202] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0203] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0204] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A vehicle control method, characterized in that: The method comprises: When the vehicle is in the current single-step planned path during the automatic parking process, obtaining the starting coordinates and starting speed of the vehicle corresponding to the starting time of the current time period; Determining a target speed of the vehicle corresponding to the current time period according to the distance between the starting coordinate and the end point coordinate in the current single-step planned path and the starting speed; Monitoring the actual speed of the vehicle during the current period; Determine a target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed, and send the target torque to a corresponding downstream actuator for execution; The end time corresponding to the current time period is used as the start time corresponding to the next time period, the next time period is updated to the current time period, and the step of obtaining the starting coordinates and the starting speed of the vehicle corresponding to the start time of the current time period is returned to the current single-step planned path when the vehicle is in the automatic parking process, until the vehicle reaches the end point coordinates of the current single-step planned path.

2. The method according to claim 1, characterized in that After the vehicle reaches the end point coordinates of the current single-step planned path, the method further includes: The next single-step planned path of the vehicle during the automatic parking process is obtained, the next single-step planned path is updated to the current single-step planned path, and the step of returning to the current single-step planned path of the vehicle during the automatic parking process to obtain the starting coordinates and starting speed of the vehicle corresponding to the starting time of the current time period until the vehicle reaches the target parking space.

3. The method according to claim 1, characterized in that The determining, according to the distance between the starting coordinate and the end point coordinate in the current single-step planned path and the starting speed, a target speed of the vehicle corresponding to the current time period includes: Determine the to-be-verified vehicle speed of the vehicle corresponding to the current time period according to the Euclidean distance between the starting coordinate and the ending coordinate, the starting vehicle speed, a preset gain coefficient, and a preset compensation value; Determining whether the vehicle speed to be verified is less than or equal to a preset maximum speed limit of the vehicle; When the vehicle speed to be verified is less than or equal to the preset maximum speed limit, determining the vehicle speed to be verified as the target vehicle speed corresponding to the vehicle in the current time period; When the to-be-verified vehicle speed is greater than the preset maximum speed limit, the preset maximum speed limit is determined as the target vehicle speed corresponding to the vehicle in the current time period.

4. The method according to claim 3, characterized in that The determining, according to the Euclidean distance between the starting coordinate and the ending coordinate, the starting vehicle speed, a preset gain coefficient, and a preset compensation value, of the vehicle speed to be verified corresponding to the current time period includes: Among them, exp1 is the vehicle speed to be verified, x N ,y N is the end point coordinate, x i ,y i is the starting coordinate, gain and k are both gain coefficients, curspeed is the starting vehicle speed, and offset is the compensation value.

5. The method according to claim 3, characterized in that Before determining whether the to-be-verified vehicle speed is less than or equal to a preset maximum speed limit of the vehicle, the method further includes: Obtaining the weather conditions corresponding to the vehicle in the current time period, obtaining a first distance between the vehicle and the starting coordinates in the current single-step planned path, obtaining a second distance between the vehicle and an obstacle in the current driving direction of the vehicle, and obtaining a third distance between the vehicle and the end point coordinates; The preset maximum speed limit of the vehicle corresponding to the current time period is determined according to the weather condition, the first distance, the second distance, and the third distance.

6. The method according to claim 1, characterized in that The determining the target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed includes: determining, according to a speed deviation between the actual vehicle speed and the target vehicle speed, a to-be-verified torque corresponding to the vehicle in the current time period; When the target vehicle speed is greater than a preset threshold speed and the speed deviation is greater than the preset threshold deviation, monitoring the duration of the first state in which the target vehicle speed is greater than the preset threshold speed and the speed deviation is greater than the preset threshold deviation; When the duration of the first state is longer than a preset threshold duration, determining the sum of the to-be-verified torque and the preset calibrated torque as the target torque of the vehicle corresponding to the current time period; When the target vehicle speed is less than or equal to a preset threshold speed, or the duration of the first state is less than or equal to the preset threshold duration, the torque to be verified is determined as the target torque corresponding to the vehicle in the current time period.

7. The method according to claim 1, characterized in that The determining the target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed, and sending the target torque to the corresponding downstream actuator for execution, includes: Determining the target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed; Performing smoothing filtering on the target torque; The target torque after smoothing and filtering is sent to the corresponding downstream actuator for execution.

8. The method according to claim 1, characterized in that In the case where the vehicle is in the current single-step planned path during the automatic parking process, the method further includes: Acquire a second distance between the vehicle and the nearest obstacle in the current driving direction of the vehicle and the obstacle type of the nearest obstacle; A target deceleration and braking mode of the vehicle is determined according to the second distance and the obstacle type, and the target deceleration and braking mode is sent to a corresponding downstream actuator for execution.

9. The method according to any one of claims 1, 7 and 8, characterized in that: After sending the target torque or the target deceleration braking mode to the corresponding downstream actuator for execution, the method further includes: receiving a notification instruction of failure of the legitimacy check of the target torque or the target deceleration braking mode feedback by the downstream actuator; In response to the notification instruction, the deceleration braking mode of the vehicle is determined to be an emergency braking mode, and the emergency braking mode is sent to the corresponding downstream actuator for execution.

10. The method according to claim 1, characterized in that In the case where the vehicle is in the current single-step planned path during the automatic parking process, the method further includes: Abnormal data of the vehicle during the automatic parking process is screened and the abnormal data is uploaded to the cloud.

11. The method according to claim 1, characterized in that In the case where the vehicle is in the current single-step planned path during the automatic parking process, the method further includes: Monitoring the actual coordinates and actual torque of the vehicle; In the case where the actual coordinates remain unchanged and the actual torque increases, if the duration of the second state in which the actual coordinates remain unchanged and the actual torque increases exceeds a preset duration, it is determined that the tire of the vehicle is in conflict with an obstacle; The perception information of the tire's collision with the obstacle is fed back to the perception module, so that the perception module can combine the perception information to feed back the vehicle's environmental information to the path planning module, and the path planning module generates the next single-step planning path according to the environmental information.

12. A vehicle control device, characterized in that: The device comprises: an acquisition unit, configured to acquire, when the vehicle is in a current single-step planned path during automatic parking, a starting coordinate and a starting speed of the vehicle corresponding to a starting time of a current time period; A vehicle speed determination unit, configured to determine a target vehicle speed corresponding to the vehicle in the current time period according to a distance between the starting coordinate and the end point coordinate in the current single-step planned path and the starting vehicle speed; A monitoring unit, used to monitor the actual speed of the vehicle corresponding to the current time period; a torque determination unit, configured to determine a target torque of the vehicle corresponding to the current time period according to the actual vehicle speed and the target vehicle speed, and send the target torque to a corresponding downstream actuator for execution; The loop unit is used to use the end time corresponding to the current time period as the start time corresponding to the next time period, update the next time period to the current time period, and return to the step of obtaining the starting coordinates and starting speed of the vehicle corresponding to the start time of the current time period when the vehicle is in the current single-step planned path during automatic parking, until the vehicle reaches the end point coordinates of the current single-step planned path.

13. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute to implement a vehicle control method as claimed in any one of claims 1 to 11.

14. A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement a vehicle control method as claimed in any one of claims 1 to 11.

15. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are executed by a processor to implement a vehicle control method according to any one of claims 1 to 11.

Images