Vehicle speed determination method and apparatus, vehicle, and storage medium

Abstract

The application discloses a vehicle speed determination method and device, a vehicle and a storage medium. The method comprises the following steps: obtaining a first estimated vehicle speed and a second estimated vehicle speed corresponding to the vehicle, the first estimated vehicle speed being a current driving speed estimated based on a pre-constructed Kalman filter, and the second estimated vehicle speed being a current driving speed estimated based on a millimeter wave radar device; determining a first weight corresponding to the first estimated vehicle speed and a second weight corresponding to the second estimated vehicle speed based on error data corresponding to the first estimated vehicle speed; and performing weighted summation on the first estimated vehicle speed and the second estimated vehicle speed based on the first weight and the second weight to obtain a current vehicle speed corresponding to the vehicle. Thus, the error data capable of reflecting the accuracy of the first estimated vehicle speed based on the Kalman filter is used to determine the corresponding weights of the first estimated vehicle speed and the second estimated vehicle speed estimated based on the millimeter wave radar device, so that the current vehicle speed determined based on the obtained weights is more accurate.

Description

Technical Field

[0001] This application relates to the field of vehicle-assisted driving technology, and more specifically, to a method, apparatus, vehicle, and storage medium for determining vehicle speed. Background Technology

[0002] With the continuous development of vehicle-assisted driving technology, the demand for accurate estimation of the vehicle's current speed is also increasing. Typically, vehicles can obtain a speed estimate based on the Kalman filter algorithm. However, for systems with significant resource constraints and message delays, the large delay in the speed estimate makes it impossible to guarantee the real-time nature of the message, resulting in an inaccurate determination of the current speed. Summary of the Invention

[0003] In view of the above problems, this application proposes a method, device, vehicle and storage medium for determining vehicle speed, which can determine the current speed of the vehicle more accurately.

[0004] In a first aspect, embodiments of this application provide a method for determining vehicle speed. The method includes: obtaining a first estimated vehicle speed and a second estimated vehicle speed corresponding to the vehicle, wherein the first estimated vehicle speed is the current driving speed of the vehicle estimated based on a pre-constructed Kalman filter, and the second estimated vehicle speed is the current driving speed of the vehicle estimated based on a millimeter-wave radar device; determining a first weight corresponding to the first estimated vehicle speed and a second weight corresponding to the second estimated vehicle speed based on error data corresponding to the first estimated vehicle speed; and performing a weighted summation of the first estimated vehicle speed and the second estimated vehicle speed based on the first weight and the second weight to obtain the current vehicle speed corresponding to the vehicle.

[0005] Secondly, embodiments of this application provide a vehicle speed determination device, the device comprising: a vehicle speed estimation module, a weight determination module, and a vehicle speed determination module. The vehicle speed estimation module is used to obtain a first estimated vehicle speed and a second estimated vehicle speed corresponding to the vehicle, wherein the first estimated vehicle speed is the current driving speed of the vehicle estimated based on a pre-constructed Kalman filter, and the second estimated vehicle speed is the current driving speed of the vehicle estimated based on a millimeter-wave radar device; the weight determination module is used to determine a first weight corresponding to the first estimated vehicle speed and a second weight corresponding to the second estimated vehicle speed based on error data corresponding to the first estimated vehicle speed; the vehicle speed determination module is used to perform a weighted summation of the first estimated vehicle speed and the second estimated vehicle speed based on the first weight and the second weight to obtain the current vehicle speed corresponding to the vehicle.

[0006] Thirdly, embodiments of this application provide a vehicle, including: one or more processors; a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to perform the vehicle speed determination method provided in the first aspect above.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, which can be called by a processor to execute the vehicle speed determination method provided in the first aspect above.

[0008] The solution provided in this application obtains a first estimated vehicle speed and a second estimated vehicle speed. The first estimated vehicle speed is the current driving speed estimated based on a pre-built Kalman filter, and the second estimated vehicle speed is the current driving speed estimated based on a millimeter-wave radar device. Based on the error data corresponding to the first estimated vehicle speed, a first weight corresponding to the first estimated vehicle speed and a second weight corresponding to the second estimated vehicle speed are determined. Based on the first weight and the second weight, the first estimated vehicle speed and the second estimated vehicle speed are weighted and summed to obtain the current vehicle speed. Therefore, it is possible to determine corresponding weights for the first estimated vehicle speed and the second estimated vehicle speed estimated based on the millimeter-wave radar device based on error data that reflects the accuracy of the first estimated vehicle speed based on the Kalman filter, thereby making the current vehicle speed determined based on the obtained weights more accurate. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A flowchart illustrating a vehicle speed determination method provided in one embodiment of this application is shown.

[0011] Figure 2 A flowchart illustrating a vehicle speed determination method provided in another embodiment of this application is shown.

[0012] Figure 3 A schematic diagram of the target object detected by the vehicle in an embodiment of this application is shown.

[0013] Figure 4 A schematic diagram of the specific process of step S230 in another embodiment of this application is shown.

[0014] Figure 5A schematic diagram of the road edge line obtained by fitting the target object in an embodiment of this application is shown.

[0015] Figure 6 A schematic diagram of the process for determining a second estimated vehicle speed is shown in another embodiment of this application.

[0016] Figure 7 A flowchart of step S240 in another embodiment of this application is shown.

[0017] Figure 8 Another flowchart of step S240 in another embodiment of this application is shown.

[0018] Figure 9 This illustration shows another flowchart of step S240 in another embodiment of the present application.

[0019] Figure 10 A schematic diagram of the vehicle speed determination device provided in an embodiment of this application is shown.

[0020] Figure 11 A structural block diagram of a vehicle provided in an embodiment of this application is shown. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0022] In the field of autonomous driving, estimating the vehicle's current speed is a crucial driver assistance function. Commonly used speed estimation methods include direct integration, Kalman filtering, neural networks, and state observer methods. Direct integration uses integration to obtain estimates of the vehicle's driving state parameters. This method has low requirements for the vehicle model, includes fewer vehicle parameters, and has some robustness, but it is not suitable for long-term use because it integrates noise signals along with sensor measurement signals. Especially under poor road conditions, the signal-to-noise ratio of the measurement signals becomes very low over time, making it impossible to obtain reliable and accurate state estimates. The Kalman filtering algorithm is a predictor-corrector algorithm with numerical solutions. It combines the predictor equation with the vehicle dynamics model to calculate the state parameters and error covariance at the next moment, and combines the correction equation with the newly measured output variables of the vehicle system to finally obtain the state estimate at the current moment. This method is suitable for state estimation of weakly nonlinear systems, but its estimation performance is very unstable for some highly nonlinear extreme conditions, limiting its application in real vehicles. Neural network methods show good experimental results in the nonlinear region of vehicle operation, but these methods are highly dependent on experimental data, have slow model parameter convergence speed, poor robustness to operating conditions, and low practical application value in engineering. Nonlinear state observers for estimating longitudinal vehicle speed require constructing nonlinear vehicle and dynamic tire models, performing nonlinear iterative calculations, which are computationally intensive and difficult to guarantee in real-time performance.

[0023] In conclusion, any single speed estimation method will inevitably have shortcomings in various aspects and usually cannot accurately determine the vehicle's current speed. Even when combining multiple speed estimation methods, it is difficult to accurately determine the proportion of each estimated speed in the final determined current speed. If the proportion of each method is not accurately determined, then the current speed calculated from multiple different speed estimates may not necessarily be more accurate than that obtained using a single speed estimation method.

[0024] Therefore, this application provides a vehicle speed determination method, apparatus, vehicle, and storage medium. By analyzing the magnitude of the error data corresponding to the first estimated vehicle speed, the accuracy of the first estimated vehicle speed can be determined. Then, based on different levels of accuracy, a first weight corresponding to the first estimated vehicle speed is determined, and a second weight corresponding to the second estimated vehicle speed is determined based on the first weight, thereby making the current vehicle speed determined based on the first and second weights more accurate. The specific vehicle speed determination method will be described in detail in subsequent embodiments.

[0025] Please see Figure 1 , Figure 1 This paper illustrates a flowchart of a vehicle speed determination method according to an embodiment of this application. The following will focus on... Figure 1The process shown is explained in detail. The method for determining vehicle speed may specifically include the following steps:

[0026] Step S110: Obtain the first estimated vehicle speed and the second estimated vehicle speed corresponding to this vehicle. The first estimated vehicle speed is the current driving speed of this vehicle estimated based on a pre-built Kalman filter, and the second estimated vehicle speed is the current driving speed of this vehicle estimated based on a millimeter-wave radar device.

[0027] In this embodiment, the vehicle's current speed can be estimated in real time based on a pre-built Kalman filter during operation. Specifically, the vehicle can acquire current wheel speed signals through pre-installed wheel speed sensors and current acceleration signals through acceleration sensors. These wheel speed and acceleration signals are then input into the pre-built Kalman filter to obtain the corresponding first estimated speed. Additionally, the vehicle can detect the relative speed of obstacles in its current driving environment using pre-installed millimeter-wave radar equipment, and then estimate its current speed based on the relative speed of these obstacles, thus obtaining a second estimated speed. The obstacles detected by the millimeter-wave radar equipment can be other vehicles, pedestrians, road facilities such as streetlights, or even trees in the current driving environment.

[0028] Understandably, both the first estimated vehicle speed obtained through a Kalman filter and the second estimated vehicle speed obtained based on millimeter-wave radar can reflect the vehicle's current speed to some extent. However, the estimation performance of the Kalman filter is extremely unstable under certain highly nonlinear extreme conditions, limiting its application in real vehicles. In other words, the accuracy of the first estimated vehicle speed obtained through the Kalman filter may be insufficient. While the millimeter-wave radar estimates the vehicle's current speed based on the detected speed of obstacles relative to the vehicle, its second estimated speed, although more accurate, may not have an output value in some special cases. Therefore, this embodiment combines the first estimated vehicle speed obtained through the Kalman filter and the second estimated vehicle speed obtained through the millimeter-wave radar to comprehensively determine the vehicle's current speed. This overcomes the limitations of a single estimation method, resulting in a more accurate value.

[0029] Step S120: Based on the error data corresponding to the first estimated vehicle speed, determine the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed.

[0030] In this embodiment, during the process of determining the first estimated vehicle speed, the vehicle can also determine the error data corresponding to the first estimated vehicle speed based on the relevant parameters used in determining the first estimated vehicle speed. Then, based on the error data, a first weight corresponding to the first estimated vehicle speed and a second weight corresponding to the second estimated vehicle speed are determined. The error data corresponding to the first estimated vehicle speed can characterize the accuracy of the first estimated vehicle speed. Obviously, if the error data indicates a low accuracy of the first estimated vehicle speed, the first weight corresponding to the first estimated vehicle speed will be reduced accordingly, and the second weight corresponding to the second estimated vehicle speed will be increased accordingly. Therefore, the current vehicle speed determined based on the first and second weights will be closer to the more accurate second estimated vehicle speed, and significantly different from the less accurate first estimated vehicle speed.

[0031] Understandably, this vehicle can obtain an estimated current speed based on a pre-built Kalman filter at fixed intervals, where the time interval can be 50ms. Similarly, the second estimated speed obtained by this vehicle based on millimeter-wave radar equipment can also be a new data acquired at preset intervals, where the preset time interval can be 10ms.

[0032] In some implementations, the vehicle can pre-set a basic weight for the first estimated speed and the second estimated speed. During the execution of the solution in this application, the basic weight is adjusted accordingly based on the magnitude of the error data corresponding to the first estimated speed, and the adjusted basic weight is used as the first weight and the second weight, respectively. For example, as a possible implementation, if the error data fluctuates within the range between the first value and the second value (the first value is less than the second value), the two original basic weights remain unchanged; if the error data is less than or equal to the first value, it indicates that the error data is small and the accuracy of the first estimated speed is high, so the basic weight corresponding to the first estimated speed is increased, and the basic weight corresponding to the second estimated speed is decreased accordingly; if the error data is greater than or equal to the second value, it indicates that the error data is large and the accuracy of the first estimated speed is low, so the basic weight corresponding to the first estimated speed is decreased, and the basic weight corresponding to the second estimated speed is increased accordingly. For example, as another possible implementation, if the error data is greater than the third value, it indicates that the accuracy of the first estimated speed is not high. In this case, the basic weight corresponding to the first estimated speed is reduced, and the basic weight corresponding to the second estimated speed is increased accordingly. If the error data is less than or equal to the third value, it indicates that the accuracy of the first estimated speed is high. In this case, the basic weights corresponding to the first estimated speed and the second estimated speed remain unchanged.

[0033] Step S130: Based on the first weight and the second weight, the first estimated vehicle speed and the second estimated vehicle speed are weighted and summed to obtain the current vehicle speed corresponding to this vehicle.

[0034] In this embodiment, after determining the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed, the vehicle can perform a weighted sum of the first and second estimated vehicle speeds to obtain the final determined current vehicle speed. Specifically, after adjusting the first weight based on the error data corresponding to the first estimated vehicle speed, the adjusted first weight can accurately represent the accuracy of the first estimated vehicle speed. Based on the first weight, the proportion of the first estimated vehicle speed in the final determined current vehicle speed can be adjusted. Obviously, if the first estimated vehicle speed is inaccurate based on the first weight, the proportion of the first estimated vehicle speed in the final determined current vehicle speed will inevitably decrease, while the proportion of the second estimated vehicle speed will increase. Conversely, if the first weight indicates that the first estimated vehicle speed is relatively accurate, the proportion of the first estimated vehicle speed in the final determined current vehicle speed will inevitably increase, and the corresponding proportion of the second estimated vehicle speed will decrease. Specifically, based on the first estimated vehicle speed V1 and its corresponding first weight Z1, and the second estimated vehicle speed V2 and its corresponding second weight Z2, the current vehicle speed V = Z1V1 + Z2V2 can be calculated.

[0035] In some implementations, while the second estimated vehicle speed obtained using millimeter-wave radar equipment is more accurate, a second estimated vehicle speed cannot be estimated for every sample. Specifically, if the vehicle fails to obtain a second estimated vehicle speed in a particular frame, the current vehicle speed can be directly determined to be the first estimated vehicle speed obtained based on the Kalman filter.

[0036] The vehicle speed determination method provided in this application obtains a first estimated vehicle speed and a second estimated vehicle speed corresponding to the vehicle. The first estimated vehicle speed is the current driving speed estimated based on a pre-constructed Kalman filter, and the second estimated vehicle speed is the current driving speed estimated based on a millimeter-wave radar device. Based on the error data corresponding to the first estimated vehicle speed, a first weight corresponding to the first estimated vehicle speed and a second weight corresponding to the second estimated vehicle speed are determined. Based on the first weight and the second weight, the first estimated vehicle speed and the second estimated vehicle speed are weighted and summed to obtain the current vehicle speed corresponding to the vehicle. Therefore, it is possible to determine corresponding weights for the first estimated vehicle speed and the second estimated vehicle speed estimated based on the millimeter-wave radar device based on error data that reflects the accuracy of the first estimated vehicle speed based on the Kalman filter, thereby making the current vehicle speed determined based on the obtained weights more accurate.

[0037] Please see Figure 2 , Figure 2 This paper illustrates a flowchart of a vehicle speed determination method provided in another embodiment of this application. The following will focus on... Figure 2The process shown is explained in detail. The method for determining vehicle speed may specifically include the following steps:

[0038] Step S210: Based on the pre-built Kalman filter and the wheel speed signal corresponding to the vehicle, determine the first estimated vehicle speed.

[0039] In this embodiment, the vehicle can collect wheel speed signals from its wheels using wheel speed meters and filter these signals. A Kalman filter is then constructed based on the Kalman filtering algorithm to estimate the vehicle speed. Specifically, considering that the vehicle primarily undergoes planar motion during operation, a Kalman filter can be designed based on a linear two-degree-of-freedom wheel model. The longitudinal speed of the vehicle is treated as a uniformly changing signal, and the average value of the filtered wheel speed signals is used as the observation. This yields the following state-space model:

[0040]

[0041] Where the subscripts i, i-1 (i = 1, 2, ..., n) represent sampling times, X represents the state vector at different times, A is the state transition matrix, W represents the process noise vector, Y is the wheel speed measurement value, H represents the measurement matrix, and V is the measurement noise. The state vector X... i =[v i a i ] T , where v i and a i Let i represent the longitudinal velocity and acceleration of the vehicle at time i, respectively; state transition matrix. Where Δt represents the sampling interval; the wheel speed measurement matrix H = [1,0]. Using the above state-space model and the vehicle's wheel speed signal, the first estimated vehicle speed can be obtained.

[0042] Step S220: Using millimeter-wave radar equipment, obtain the relative speed of each target object within the current lane where the vehicle is located.

[0043] In this embodiment, the vehicle can also utilize millimeter-wave radar equipment to obtain the relative speed of each target object within the current lane in the vehicle's corresponding vehicle coordinate system. It is understood that if the vehicle is moving forward at a target speed within the current lane, then, with the vehicle's corresponding vehicle coordinate system as a reference, all target objects within the current lane, whether other vehicles moving forward together in the current lane or stationary facilities such as seats or trash cans beside the lane, will have a relative speed to the vehicle. Furthermore, due to the limitations of the sensor itself—the longitudinal viewing angle of millimeter-wave radar is generally only about 15°—it cannot effectively distinguish between high-altitude gantries and traffic signs, low-lying, easily crossable cans and manhole covers, and normally moving dynamic vehicles and pedestrians. Therefore, the vehicle can obtain the relative speeds of multiple different target objects through millimeter-wave radar equipment.

[0044] like Figure 3 As shown, if this vehicle is traveling to the right within the current lane, the millimeter-wave radar equipment can detect multiple target objects within the current lane. Figure 3 The black box in the diagram represents the target object moving to the right at a fixed speed. Each target object's speed relative to the vehicle can be considered to be moving to the left. The length of the arrow corresponding to each target object represents its speed relative to the vehicle; a longer arrow indicates a greater speed. Since most targets detected by the vehicle's millimeter-wave radar should be stationary objects along the lane edges on either side of the current lane, most targets on either side of the vehicle can have the same speed relative to it. Target objects id1 and id2 have lower speeds relative to the vehicle, suggesting they are more likely to be other vehicles moving to the right within the current lane.

[0045] Step S230: Based on the motion speed of each target object, determine the second estimated vehicle speed corresponding to this vehicle.

[0046] In this embodiment, after acquiring the relative speed of each target object within the current lane using millimeter-wave radar equipment, the vehicle can determine a second estimated speed based on the speed of each target object. Since most of the target objects detected by the millimeter-wave radar equipment are stationary in the world coordinate system, the vehicle can filter out these target objects through the following steps, and then determine the corresponding second estimated speed based on the speed of these target objects.

[0047] In some implementations, such as Figure 4 As shown, a vehicle can determine its second estimated speed by following these steps:

[0048] Step S231: Identify the left target object located on the left side of the vehicle and the right target object located on the right side of the vehicle.

[0049] In this embodiment, the vehicle can first divide all target objects detected by the millimeter-wave radar equipment into components. Using the vehicle's own coordinate system as a reference, target objects to the left of the vehicle are designated as left-side target objects, and target objects to the right of the vehicle are designated as right-side target objects. After dividing all target objects into left and right sides, the vehicle can fit the slopes of the left and right edges of the current lane based on the target objects on each side, where most have the same speed. In some implementations, the vehicle can filter all target objects on both sides according to preset conditions, designating those on the left side that meet the preset conditions as left-side target objects, and those on the right side that meet the preset conditions as right-side target objects. This facilitates subsequent fitting based on the filtered left and right target objects. The preset conditions are used to determine whether a target object is stationary in the world coordinate system; if the preset conditions are met, the target object is determined to be stationary in the world coordinate system.

[0050] In some implementations, the vehicle may first perform collision detection on all target objects within the current lane. Understandably, if the vehicle determines a potential collision risk between two target objects based on their relative speeds within the current lane, there is a high probability that the target object with the higher relative speed is actually a stationary object such as a manhole cover or speed limit sign in the world coordinate system. In this case, the vehicle may first use the speed of the target object with the higher relative speed as a reference speed, and based on the magnitude of the reference speed, filter all target objects that are likely stationary in the world coordinate system, classifying these target objects as left-side target objects located to the left of the vehicle and right-side target objects located to the right of the vehicle.

[0051] In some implementations, the vehicle can determine whether there are other dynamic target objects within a reference area, based on a pre-set collision duration t and the speed v of a target object. The reference area is defined by a longitudinal distance t*v behind the target object and a lateral distance of 1.5m to the left and right. If such objects exist, a collision risk is determined between them. The vehicle can then determine its reference speed based on the speeds of these two target objects, and further determine the left and right target objects based on these reference speeds.

[0052] In some implementations, after determining the reference speed v1 of the vehicle based on the collision detection, the vehicle can, based on the reference speed v1, designate the target objects on the left whose speed is within the range of v1±v' as the left target objects, and designate the target objects on the right whose speed is within the range of v1±v' as the right target objects.

[0053] Step S232: Based on the position of each left target object, fit the left target object to obtain the slope of the left edge line corresponding to the vehicle.

[0054] Step S233: Based on the position of each target object on the right, collect the target objects on the right to obtain the slope of the right edge line corresponding to the vehicle.

[0055] In this embodiment, after determining all left and right target objects in the target object using the above method, the vehicle can fit the left target object based on the position of each left target object to obtain the left edge line and slope of the current lane. Similarly, it can fit the right target object based on the position of each right target object to obtain the right edge line and slope of the current lane. This allows for determining the accuracy of the target object selection in the above steps based on the slopes of the left and right edges. Please refer to [link to relevant documentation]. Figure 5 The diagram shows the fitted left edge line y1 and right edge line y2. The curve formula for the left edge line is y1 = k1 × x1 + b1, where k1 is the slope of the left edge line. Similarly, the curve formula for the right edge line is y2 = k2 × x2 + b2, where k2 is the slope of the left edge line. In some implementations, the vehicle can fit the target object using clustering algorithms or the RANSAC algorithm.

[0056] Step S234: If the absolute value of the difference between the slope of the left edge line and the slope of the right edge line is less than the third preset value, then the second estimated vehicle speed is determined based on the movement speed of each left target object and the movement speed of each right target object.

[0057] In this embodiment, if the absolute value of the difference between the slope of the left edge line and the slope of the right edge line is less than a third preset value, it indicates that the calculation of the slopes of the left and right edges lines is accurate, meaning the determination of the target objects used to fit the left and right edges lines is also accurate. Therefore, the vehicle can determine its second estimated speed based on the movement speed of the target objects on these road edges. Ideally, the slopes of the left and right edges lines determined by the vehicle should be the same. However, considering the different road scenarios and the different installation positions of millimeter-wave radar equipment in mass-produced vehicles, a certain difference between the slopes of the left and right edges lines is permissible. Clearly, the smaller the third preset value, the more accurate the slope calculation, and the more accurate the determined second estimated speed.

[0058] In summary, please refer to Figure 6 The diagram illustrates the process for determining the second estimated vehicle speed in this embodiment. First, the vehicle can detect the relative speed of each target object to itself using millimeter-wave radar equipment, perform collision detection on the target objects, and then divide the target objects into regions, specifically identifying the left and right target objects. Next, the left target object is fitted to obtain its left edge line; the right target object is fitted to obtain its right edge line. Finally, a slope judgment is performed, determining whether the absolute value of the difference between the slopes of the left and right edge lines is less than a third preset value. If it is less, the second estimated vehicle speed is determined based on the speeds of the left and right target objects; if it is not less, the estimated speed fails. If the estimation fails, the vehicle can directly use the first estimated speed as its current speed.

[0059] Step S240: Based on the error data corresponding to the first estimated vehicle speed, determine the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed.

[0060] In some implementations, the error data may include the output interval duration, which is the duration between two consecutive first estimated vehicle speeds acquired by the vehicle. Thus, as... Figure 7 As shown, this vehicle can determine the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed based on the output interval duration corresponding to the first estimated vehicle speed through the following steps:

[0061] Step S241: If the output interval duration is greater than the first preset duration, then reduce the basic weight corresponding to the first estimated vehicle speed to obtain the first weight.

[0062] Step S242: If the output interval duration is less than or equal to the first preset duration, increase the basic weight corresponding to the first estimated vehicle speed to obtain the first weight.

[0063] In this embodiment, after determining the first estimated vehicle speed and the second estimated vehicle speed, the vehicle can further determine the error data corresponding to the first estimated vehicle speed to determine its accuracy. Specifically, the vehicle can collect wheel speed signals of each wheel at fixed intervals, and the Kalman filter will also output a first estimated vehicle speed at fixed intervals. The fixed interval can be 10ms or 50ms. Obviously, if the interval between two consecutive first estimated vehicle speeds is too long, exceeding a first preset time, this is likely due to a program freeze. In this case, the accuracy of the first estimated vehicle speed is reduced; therefore, the vehicle can reduce the base weight corresponding to the first estimated vehicle speed to obtain a first weight. Conversely, if the output interval is less than or equal to the first preset time, this output interval is the normal interval between two consecutive first estimated vehicle speeds, indicating that the accuracy of the first estimated vehicle speed is high. Therefore, the vehicle can appropriately increase the base weight corresponding to the first estimated vehicle speed to obtain a first weight. In some implementations, the first preset duration can be any value between 100ms and 150ms.

[0064] Specifically, if the output interval duration is greater than the first preset duration and less than the second preset duration, the base weight is reduced based on the output interval duration to obtain the first weight. The reduction of the base weight is positively correlated with the size of the output interval duration. The second preset duration is greater than the first preset duration. If the output interval duration is greater than or equal to the second preset duration, the first weight is determined to be zero.

[0065] Understandably, to limit the extreme values ​​of the first and second weights—that is, to restrict the magnitude of their change with error data—a reference range can be preset. For example, if the error value is greater than a first reference value but less than a second reference value, the magnitude of the decrease in the first weight and the increase in the second weight can be determined based on the error value. If the error value is greater than or equal to the second reference value, the first weight is directly set to zero or a preset smaller value, and the second weight is correspondingly set to 1 or a preset larger value. If the error value is less than or equal to the first reference value, both the first and second weights remain at their original base weights without change. Here, the first reference value is less than the second reference value.

[0066] Step S243: Based on the first weight, determine the second weight, and the sum of the first weight and the second weight is the first preset value.

[0067] In this embodiment of the application, the first weight and the second weight are used to characterize the proportion of the first estimated vehicle speed and the second estimated vehicle speed in the final determined current vehicle speed, respectively. Obviously, the sum of the first weight and the second weight is the first preset value, which can be 1.

[0068] In other embodiments, the error data may include the duration of a numerical pause, which is the duration during which the vehicle's most recent first estimated speed remained unchanged. Thus... Figure 8 As shown, this vehicle can determine the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed based on the numerical lag duration corresponding to the first estimated vehicle speed through the following steps:

[0069] Step S244: If the duration of the numerical lag is greater than the third preset duration, then reduce the base weight corresponding to the first estimated vehicle speed to obtain the first weight.

[0070] Step S245: If the duration of the numerical lag is less than or equal to the third preset duration, then increase the base weight corresponding to the first estimated vehicle speed to obtain the first weight.

[0071] In this embodiment, the vehicle acquires a first estimated speed at fixed intervals. However, during actual operation, the vehicle's speed does not remain constant for extended periods. Therefore, if the duration of the first estimated speed acquired by the vehicle remains unchanged within a third preset duration (i.e., the duration of the numerical delay exceeds the third preset duration), there is a high probability of a communication delay failure, resulting in the inability to receive the latest first estimated speed. In other words, the first estimated speed acquired by the vehicle is inaccurate. In this case, the base weight corresponding to the first estimated speed can be reduced to obtain a first weight. Conversely, if the duration of the numerical delay is less than or equal to the third preset duration, it indicates that the delay of the first estimated speed is within an acceptable range. The vehicle can increase the base weight corresponding to the first estimated speed to obtain a larger first weight, thereby increasing the weight of the first estimated speed in the current speed.

[0072] In some implementations, the error data may include not only the duration of the numerical lag but also the duration of the output interval. The vehicle can determine a first weight based on both the duration of the numerical lag and the duration of the output interval. For example, if the duration of the numerical lag is greater than a third preset duration and the duration of the output interval is greater than a first preset duration, the base weight corresponding to the first estimated vehicle speed is reduced to obtain the first weight. If the duration of the numerical lag is less than or equal to the third preset duration, or the duration of the output interval is less than or equal to the first preset duration, the base weight corresponding to the first estimated vehicle speed is increased to obtain the first weight. Alternatively, if the duration of the numerical lag is greater than the third preset duration, or the duration of the output interval is greater than the first preset duration, the base weight corresponding to the first estimated vehicle speed is reduced to obtain the first weight. If the duration of the numerical lag is less than or equal to the third preset duration, and the duration of the output interval is less than or equal to the first preset duration, the base weight corresponding to the first estimated vehicle speed is increased to obtain the first weight.

[0073] Step S246: Based on the first weight, determine the second weight, and the sum of the first weight and the second weight is the first preset value.

[0074] In the embodiments of this application, step S246 can refer to other steps of the embodiments, and will not be described in detail here.

[0075] In some other embodiments, the error data may include a speed difference, which is the absolute value of the difference between a first estimated vehicle speed and a second estimated vehicle speed. Thus, as... Figure 9 As shown, this vehicle can determine the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed based on the error data corresponding to the first estimated vehicle speed through the following steps:

[0076] Step S247: If the speed difference is greater than the second preset value, then reduce the basic weight corresponding to the first estimated vehicle speed to obtain the first weight.

[0077] Step S248: If the speed difference is less than or equal to the second preset value, increase the basic weight corresponding to the first estimated vehicle speed to obtain the first weight.

[0078] In this embodiment, both the first estimated vehicle speed and the second estimated vehicle speed obtained by the vehicle can represent the current vehicle speed. Therefore, if the estimated vehicle speed is accurate, the difference between the first estimated vehicle speed and the second estimated vehicle speed should be small. Conversely, if the absolute value of the difference between the first estimated vehicle speed and the second estimated vehicle speed is greater than a second preset value, it indicates that the two estimated vehicle speeds obtained by the vehicle differ significantly. In this case, the vehicle defaults to using the second estimated vehicle speed estimated by the millimeter-wave radar equipment, which is more accurate. Therefore, the vehicle can reduce the base weight corresponding to the first estimated vehicle speed to obtain the first weight, and increase the base weight corresponding to the second estimated vehicle speed to obtain the second weight. Specifically, if the first estimated vehicle speed v1 and the second estimated vehicle speed v2 satisfy abs(v2-v1)>cost*abs(v1), the base weight corresponding to the first estimated vehicle speed can be reduced to obtain the first weight. Here, cost is the error coefficient between the first estimated vehicle speed v1 and the second estimated vehicle speed v2, which can be selected as 10%.

[0079] In some implementations, the error data may include not only the speed difference but also the output interval duration, which is the time interval between two consecutive first estimated vehicle speeds obtained by the vehicle. The vehicle can determine the first weight based on a combination of the speed difference and the output interval duration. For example, if the speed difference is greater than a second preset value and the output interval duration is greater than a first preset duration, the base weight corresponding to the first estimated vehicle speed is reduced to obtain the first weight; if the speed difference is less than or equal to the second preset value, or the output interval duration is less than or equal to the first preset duration, the base weight corresponding to the first estimated vehicle speed is increased to obtain the first weight. Similarly, if the speed difference is greater than the second preset value, or the output interval duration is greater than the first preset duration, the base weight corresponding to the first estimated vehicle speed is reduced to obtain the first weight; if the speed difference is less than or equal to the second preset value, and the output interval duration is less than or equal to the first preset duration, the base weight corresponding to the first estimated vehicle speed is increased to obtain the first weight.

[0080] In other implementations, the error data may include not only the speed difference but also the duration of the numerical lag, which is the duration during which the vehicle's most recent estimated speed remains unchanged. The vehicle can determine a first weight based on a combination of the speed difference and the numerical lag duration. For example, if the speed difference is greater than a second preset value and the numerical lag duration is greater than a third preset duration, the base weight corresponding to the first estimated speed is reduced to obtain the first weight; if the speed difference is less than or equal to the second preset value, or the numerical lag duration is less than or equal to the third preset duration, the base weight corresponding to the first estimated speed is increased to obtain the first weight. Similarly, if the speed difference is greater than the second preset value, or the numerical lag duration is greater than the third preset duration, the base weight corresponding to the first estimated speed is reduced to obtain the first weight; if the speed difference is less than or equal to the second preset value, and the numerical lag duration is less than or equal to the third preset duration, the base weight corresponding to the first estimated speed is increased to obtain the first weight.

[0081] Step S249: Based on the first weight, determine the second weight, and the sum of the first weight and the second weight is the first preset value.

[0082] In the embodiments of this application, step S249 can refer to other steps of the embodiments, and will not be described in detail here.

[0083] Step S250: Based on the error data corresponding to the first estimated vehicle speed, determine the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed.

[0084] In this embodiment, step S250 can be explained with reference to the explanations of other embodiments, and will not be repeated here.

[0085] The vehicle speed determination method provided in this application embodiment determines a first estimated vehicle speed based on a pre-constructed Kalman filter and the wheel speed signal corresponding to the vehicle; it then uses millimeter-wave radar equipment to acquire the relative speed of each target object within the current lane where the vehicle is located; based on the speed of each target object, it determines a second estimated vehicle speed; based on the error data corresponding to the first estimated vehicle speed, it determines a first weight and a second weight corresponding to the second estimated vehicle speed; and so on. Thus, the accuracy of the first estimated vehicle speed is judged by the error data, and different first weights are determined according to different levels of accuracy. Finally, based on the first and second weights, the final obtained current vehicle speed is made more accurate.

[0086] Please see Figure 10The diagram illustrates a structural block diagram of a vehicle speed determination device 200 provided in an embodiment of this application. The vehicle speed determination device 200 includes a vehicle speed estimation module 210, a weight determination module 220, and a vehicle speed determination module 230. The vehicle speed estimation module 210 is used to obtain a first estimated vehicle speed and a second estimated vehicle speed corresponding to the vehicle. The first estimated vehicle speed is the current driving speed of the vehicle estimated based on a pre-built Kalman filter, and the second estimated vehicle speed is the current driving speed of the vehicle estimated based on a millimeter-wave radar device. The weight determination module 220 is used to determine a first weight corresponding to the first estimated vehicle speed and a second weight corresponding to the second estimated vehicle speed based on the error data corresponding to the first estimated vehicle speed. The vehicle speed determination module 230 is used to perform a weighted summation of the first estimated vehicle speed and the second estimated vehicle speed based on the first weight and the second weight to obtain the current vehicle speed corresponding to the vehicle.

[0087] In one possible implementation, the error data includes the output interval duration, which is the duration between two consecutive first estimated vehicle speeds obtained by the vehicle. The weight determination module 220 includes a first reduction unit, a first increase unit, and a first determination unit. The first reduction unit is used to reduce the base weight corresponding to the first estimated vehicle speed to obtain a first weight if the output interval duration is greater than a first preset duration. The first increase unit is used to increase the base weight corresponding to the first estimated vehicle speed to obtain a first weight if the output interval duration is less than or equal to the first preset duration. The first determination unit is used to determine a second weight based on the first weight, and the sum of the first weight and the second weight is a first preset value.

[0088] In one possible implementation, the first reduction unit is further configured to reduce the base weight based on the output interval duration if the output interval duration is greater than the first preset duration and less than the second preset duration, to obtain the first weight, wherein the reduction magnitude of the base weight is positively correlated with the size of the output interval duration, and the second preset duration is greater than the first preset duration; if the output interval duration is greater than or equal to the second preset duration, the first weight is determined to be zero.

[0089] In one possible implementation, the error data includes the numerical lag duration, which is the duration during which the vehicle's most recent estimated speed remains unchanged. The weight determination module 220 includes a second reduction unit, a second increase unit, and a second determination unit. The second reduction unit reduces the base weight corresponding to the first estimated speed to obtain a first weight if the numerical lag duration is greater than a third preset duration. The second increase unit increases the base weight corresponding to the first estimated speed to obtain the first weight if the numerical lag duration is less than or equal to the third preset duration. The second determination unit determines a second weight based on the first weight, and the sum of the first weight and the second weight is a first preset value.

[0090] In one possible implementation, the error data includes a speed difference, which is the absolute value of the difference between the first estimated vehicle speed and the second estimated vehicle speed. The weight determination module 220 includes a third reduction unit, a third increase unit, and a third determination unit. The third reduction unit is used to reduce the base weight corresponding to the first estimated vehicle speed to obtain a first weight if the speed difference is greater than a second preset value. The third increase unit is used to increase the base weight corresponding to the first estimated vehicle speed to obtain the first weight if the speed difference is less than or equal to the second preset value. The third determination unit is used to determine a second weight based on the first weight, and the sum of the first weight and the second weight is the first preset value.

[0091] In one possible implementation, the vehicle speed estimation module 210 includes a first vehicle speed determination unit, a target speed acquisition unit, and a second vehicle speed determination unit. The first vehicle speed determination unit determines a first estimated vehicle speed based on a pre-built Kalman filter and the vehicle's corresponding wheel speed signal. The target speed acquisition unit uses millimeter-wave radar equipment to acquire the relative speed of each target object within the current lane where the vehicle is located. The second vehicle speed determination unit determines a second estimated vehicle speed based on the relative speed of each target object.

[0092] In one possible implementation, the second vehicle speed determination unit is further configured to determine the left target object located to the left of the vehicle and the right target object located to the right of the vehicle; based on the position of each left target object, the left target object is fitted to obtain the slope of the left edge line corresponding to the vehicle; based on the position of each right target object, the right target objects are aggregated to obtain the slope of the right edge line corresponding to the vehicle; if the absolute value of the difference between the slope of the left edge line and the slope of the right edge line is less than a third preset value, then based on the movement speed corresponding to each left target object and the movement speed corresponding to each right target object, the second estimated vehicle speed corresponding to the vehicle is determined.

[0093] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0094] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0095] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0096] In summary, the solution provided in this application obtains a first estimated vehicle speed and a second estimated vehicle speed. The first estimated vehicle speed is the current driving speed estimated based on a pre-built Kalman filter, and the second estimated vehicle speed is the current driving speed estimated based on a millimeter-wave radar device. Based on the error data corresponding to the first estimated vehicle speed, a first weight corresponding to the first estimated vehicle speed and a second weight corresponding to the second estimated vehicle speed are determined. Based on the first weight and the second weight, the first estimated vehicle speed and the second estimated vehicle speed are weighted and summed to obtain the current vehicle speed. Therefore, it is possible to determine corresponding weights for the first estimated vehicle speed and the second estimated vehicle speed estimated based on the millimeter-wave radar device based on error data that reflects the accuracy of the first estimated vehicle speed based on the Kalman filter, thereby making the current vehicle speed determined based on the obtained weights more accurate.

[0097] Please see Figure 11 The diagram illustrates a structural block diagram of a vehicle 400 provided in an embodiment of this application. The vehicle 400 in this application may include one or more of the following components: a processor 410, a memory 420, and one or more application programs. The one or more application programs may be stored in the memory 420 and configured to be executed by one or more processors 410. The one or more programs are configured to perform the methods described in the foregoing method embodiments.

[0098] Processor 410 may include one or more processing cores. Processor 410 connects to various parts of the computer device using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 420, and by calling data stored in memory 420. Optionally, processor 410 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 410 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 410 and may be implemented separately using a communication chip.

[0099] The memory 420 may include random access memory (RAM) or read-only memory (ROM). The memory 420 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 420 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described below. The data storage area may also store data created during the use of the computer device (such as phone books, audio and video data, chat log data, etc.).

[0100] This application provides a structural block diagram of a computer-readable storage medium. The computer-readable medium stores program code that can be called by a processor to execute the methods described in the above method embodiments.

[0101] Computer-readable storage media can be electronic storage devices such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, computer-readable storage media includes non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program code that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code can be compressed, for example, in a suitable form.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for determining vehicle speed, characterized in that, The method includes: Obtain the first estimated vehicle speed and the second estimated vehicle speed corresponding to this vehicle. The first estimated vehicle speed is the current driving speed of the vehicle estimated based on a pre-built Kalman filter, and the second estimated vehicle speed is the current driving speed of the vehicle estimated based on a millimeter-wave radar device. Based on the error data corresponding to the first estimated vehicle speed, a first weight corresponding to the first estimated vehicle speed and a second weight corresponding to the second estimated vehicle speed are determined. Based on the first weight and the second weight, the first estimated vehicle speed and the second estimated vehicle speed are weighted and summed to obtain the current vehicle speed corresponding to the vehicle. The error data includes the output interval duration, which is the duration between two consecutive estimated vehicle speeds obtained by the vehicle. The step of determining the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed based on the error data corresponding to the first estimated vehicle speed includes: If the output interval duration is greater than the first preset duration, then the base weight corresponding to the first estimated vehicle speed is reduced to obtain the first weight; If the output interval duration is less than or equal to the first preset duration, then increase the base weight corresponding to the first estimated vehicle speed to obtain the first weight; Based on the first weight, the second weight is determined, and the sum of the first weight and the second weight is a first preset value.

2. The method according to claim 1, characterized in that, If the output interval duration is greater than a first preset duration, then the base weight corresponding to the first estimated vehicle speed is reduced to obtain the first weight, including: If the output interval duration is greater than the first preset duration and less than the second preset duration, then the base weight is reduced based on the output interval duration to obtain the first weight. The reduction of the base weight is positively correlated with the magnitude of the output interval duration, and the second preset duration is greater than the first preset duration. If the output interval duration is greater than or equal to the second preset duration, then the first weight is determined to be zero.

3. The method according to claim 1, characterized in that, The error data includes the duration of numerical lag, which is the duration during which the most recent estimated vehicle speed of the vehicle remains unchanged. The step of determining the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed based on the error data corresponding to the first estimated vehicle speed includes: If the duration of the numerical lag exceeds the third preset duration, the base weight corresponding to the first estimated vehicle speed is reduced to obtain the first weight. If the duration of the numerical lag is less than or equal to the third preset duration, then the base weight corresponding to the first estimated vehicle speed is increased to obtain the first weight. Based on the first weight, the second weight is determined, and the sum of the first weight and the second weight is a first preset value.

4. The method according to claim 1, characterized in that, The error data includes a speed difference, which is the absolute value of the difference between the first estimated vehicle speed and the second estimated vehicle speed. The step of determining the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed based on the error data corresponding to the first estimated vehicle speed includes: If the speed difference is greater than the second preset value, then the base weight corresponding to the first estimated vehicle speed is reduced to obtain the first weight; If the speed difference is less than or equal to the second preset value, then the base weight corresponding to the first estimated vehicle speed is increased to obtain the first weight; Based on the first weight, the second weight is determined, and the sum of the first weight and the second weight is a first preset value.

5. The method according to any one of claims 1-4, characterized in that, The process of obtaining the first estimated speed and the second estimated speed of the vehicle includes: Based on the pre-constructed Kalman filter and the wheel speed signal corresponding to the vehicle, the first estimated vehicle speed is determined. Using millimeter-wave radar equipment, the relative speed of each target object within the current lane where the vehicle is located is obtained; Based on the motion speed corresponding to each of the target objects, the second estimated vehicle speed corresponding to the vehicle is determined.

6. The method according to claim 5, characterized in that, The step of determining the second estimated vehicle speed based on the motion speed corresponding to each of the target objects includes: Identify the left target object located on the left side of the vehicle and the right target object located on the right side of the vehicle; Based on the position of each left-side target object, the left-side target object is fitted to obtain the slope of the left edge line corresponding to the vehicle. Based on the position of each of the right-side target objects, the right-side target objects are fitted to obtain the slope of the right-side edge line corresponding to the vehicle. If the absolute value of the difference between the slope of the left edge line and the slope of the right edge line is less than a third preset value, then the second estimated vehicle speed corresponding to the vehicle is determined based on the movement speed corresponding to each left target object and the movement speed corresponding to each right target object.

7. A vehicle speed determining device, characterized in that, The device includes: The vehicle speed estimation module is used to obtain the first estimated vehicle speed and the second estimated vehicle speed corresponding to the vehicle. The first estimated vehicle speed is the current driving speed of the vehicle estimated based on a pre-built Kalman filter, and the second estimated vehicle speed is the current driving speed of the vehicle estimated based on a millimeter-wave radar device. The weight determination module is used to determine the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed based on the error data corresponding to the first estimated vehicle speed. The vehicle speed determination module is used to perform a weighted summation of the first estimated vehicle speed and the second estimated vehicle speed based on the first weight and the second weight to obtain the current vehicle speed corresponding to the vehicle. The error data includes the output interval duration, which is the duration between two consecutive estimated vehicle speeds obtained by the vehicle. The step of determining the first weight corresponding to the first estimated vehicle speed and the second weight corresponding to the second estimated vehicle speed based on the error data corresponding to the first estimated vehicle speed includes: If the output interval duration is greater than the first preset duration, then the base weight corresponding to the first estimated vehicle speed is reduced to obtain the first weight; If the output interval duration is less than or equal to the first preset duration, then increase the base weight corresponding to the first estimated vehicle speed to obtain the first weight; Based on the first weight, the second weight is determined, and the sum of the first weight and the second weight is a first preset value.

8. A vehicle, characterized in that, The vehicles include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code that can be invoked by a processor to execute the method as described in any one of claims 1-6.

Images