Vehicle stationary state detection method, system, device and storage medium
Through the vehicle static state detection method with multiple data threshold fitting, the accuracy problem of vehicle static state judgment in the environment of satellite signal loss is solved, and high accuracy and timely detection in different scenarios and vehicles is achieved.
Patent Information
- Application Number
- CN202411147917.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-08-21
AI Technical Summary
In the environment where satellite signal loss is locked, how to accurately determine the stationary state of a vehicle is an urgent problem to be solved, especially in urban tunnels and underground garages, microelectromechanical inertial measurement units (MEMS IMUs) are prone to error accumulation. Traditionally, Methods such as incompleteness constraints and zero-speed corrections require specific vehicle motion conditions to be used effectively.
The preset sensing device determines the heading angular velocity variance, heading angular velocity slope, rolling angular velocity variance, front-end and rear term difference extreme difference extreme difference extreme difference in the forward acceleration and heading angular velocity front-end term difference extreme difference through the preset sensing device, forming an initial threshold value set and updating it through real-time statistical data , and finally determine the vehicle's stationary state detection result. This method uses multiple threshold fitting to improve the timeliness and accuracy of detection.
Improves the accuracy of vehicle status judgment in the environment of satellite signal loss, reduces the error detection rate and missed detection rate, especially in strict static state detection, it is extremely low, and is suitable for reliable static state detection of different vehicles and scenarios. .
Smart Images

Figure CN118654670B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle inertial device stationary detection, and in particular to a vehicle stationary state detection method, system, device and storage medium. Background Art
[0002] With the development of technologies such as autonomous driving and vehicle networking, people's requirements for vehicle positioning are constantly increasing. Traditional integrated navigation technology combines the global satellite navigation system with the strapdown inertial navigation system to meet the requirements of high precision, high availability and high reliability in the above fields. However, due to the high price of high-level inertial measurement devices, high-precision integrated navigation systems can generally only be used in special fields such as mobile measurement, and are difficult to popularize in the civilian market.
[0003] Micro-electromechanical inertial measurement units (MEMS IMUs) can meet the needs of the general public due to their low cost. However, in scenarios where satellite navigation signals are denied, such as urban tunnels and underground garages, errors tend to accumulate quickly due to the loss of satellite navigation constraints. In such scenarios, methods such as non-holonomic constraints (NHC), zero speed correction (ZUPT), and zero angle correction (ZIHR) are often required to improve accuracy. These methods can only work under specific vehicle motion conditions. NHC requires that the vehicle has no side slip and jump, while ZUPT and ZIHR require that the vehicle is stationary.
[0004] Therefore, how to accurately determine the vehicle status when the satellite signal is lost has become a technical problem that needs to be solved urgently. Summary of the invention
[0005] In order to improve the accuracy of vehicle status judgment in an environment where satellite signals are lost, the present application provides a vehicle stationary state detection method, system, device and storage medium.
[0006] In the first aspect, the present application provides a vehicle stationary state detection method using the following technical solution:
[0007] A vehicle stationary state detection method, comprising:
[0008] Determine the first category of data, the second category of data, the third category of data, the fourth category of data, and the fifth category of data through a preset sensor device, and store all the acquired data as a target data set in a target data window;
[0009] After the start condition is met, determining an initial threshold set from the target data window;
[0010] Acquire real-time statistical data from a preset address and update the initial threshold set according to the data type to determine a final threshold set;
[0011] When receiving the status detection signal, real-time type 1 data, real-time type 2 data, real-time type 3 data, real-time type 4 data and real-time type 5 data of the target vehicle are obtained as a real-time data set;
[0012] A vehicle state detection result is determined according to the final threshold value set and the real-time data set.
[0013] Optionally, the one type of data is heading angular velocity variance;
[0014] The second type of data is the heading angular velocity slope;
[0015] The three types of data are roll angular velocity variance;
[0016] The four types of data are the extreme differences of the front and rear items of the forward acceleration;
[0017] The five types of data are the extreme differences between the front and rear items of the heading angular velocity.
[0018] Optionally, after the start condition is met, the step of determining an initial threshold set from the target data window includes:
[0019] When it is determined that the preset start condition is met, performing item-by-item elimination according to the data type in the target data window to obtain a first threshold value set;
[0020] In the first threshold set, data is updated according to a preset elimination method to determine an initial threshold set.
[0021] Optionally, the step of updating data in the first threshold set according to a preset elimination method to determine an initial threshold set includes:
[0022] Determine a mean and a root mean square error corresponding to each data type in the first threshold set;
[0023] The mean value plus three times the root mean square error is used as a preset elimination method;
[0024] Calculation is performed according to the preset elimination method to determine an initial threshold set.
[0025] Optionally, the step of acquiring real-time statistical data from a preset address and updating the initial threshold set according to the data type to determine the final threshold set includes:
[0026] Obtaining a set of identification data with a static identification from a preset address;
[0027] Obtaining a preset effective time interval, and determining final statistical data in the identification data set according to the effective time interval;
[0028] The initial threshold set is updated according to the final statistical data to determine a final threshold set.
[0029] Optionally, before the step of determining the vehicle state detection result according to the final threshold value set and the real-time data set, the method further includes:
[0030] Obtaining a final threshold value of the heading angular velocity variance from the final threshold value set and comparing it with the real-time heading angular velocity variance to obtain a first comparison result;
[0031] Obtaining a final threshold of the heading angular velocity slope from the final threshold set and comparing it with the real-time heading angular velocity slope to obtain a second comparison result;
[0032] Obtaining a final threshold of the roll angular velocity variance from the final threshold set and comparing it with the real-time roll angular velocity variance to obtain a third comparison result;
[0033] Obtaining a final threshold value of the range of the front and rear terms of the forward acceleration from the final threshold value set and comparing it with the range of the front and rear terms of the real-time forward acceleration to obtain a fourth comparison result;
[0034] The final threshold value of the range of the front and rear term differences of the heading angular velocity is obtained from the final threshold value set and compared with the range of the front and rear term differences of the real-time heading angular velocity to obtain a fifth comparison result.
[0035] Optionally, the step of determining the vehicle state detection result according to the final threshold value set and the real-time data set includes:
[0036] Determining whether the first comparison result and the third comparison result are both successful in the final threshold value set and the real-time data set;
[0037] If not, the current vehicle state is determined to be a moving state;
[0038] If yes, determining whether the second comparison result, the fourth comparison result, and the fifth comparison result are all successful;
[0039] If it is determined that the second comparison result, the fourth comparison result and the fifth comparison result are all successful at the same time, then it is determined that the current vehicle state is a strictly reliable stationary state;
[0040] If it is determined that the second comparison result, the fourth comparison result, and the fifth comparison result are not simultaneously successful, then it is determined that the current vehicle state is a fuzzy stationary state.
[0041] In a second aspect, the present application provides a vehicle stationary state detection system, the vehicle stationary state detection system comprising:
[0042] A target data set module is used to determine the first type of data, the second type of data, the third type of data, the fourth type of data and the fifth type of data through a preset sensor device, and store all the acquired data as a target data set in a target data window;
[0043] An initial threshold set module, used to determine an initial threshold set from the target data window after a start condition is met;
[0044] A final threshold set module, used to obtain real-time statistical data from a preset address and update the initial threshold set according to the data type to determine a final threshold set;
[0045] A real-time data collection module, for obtaining real-time first-category data, real-time second-category data, real-time third-category data, real-time fourth-category data and real-time fifth-category data of the target vehicle as a real-time data collection when receiving a status detection signal;
[0046] The vehicle status module is used to determine the vehicle status detection result according to the final threshold value set and the real-time data set.
[0047] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, wherein the processor executes the method described above when running computer instructions stored in the memory.
[0048] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, wherein the instructions are configured to execute the method described above when run.
[0049] In summary, the present application includes the following beneficial technical effects:
[0050] The present application determines the initial threshold value set by presetting the sensor device to determine the first type of data, the second type of data, the third type of data, the fourth type of data and the fifth type of data; after the start condition is met, the initial threshold value set is updated with the collected real-time statistical data and the final threshold value set is determined; the vehicle state of the target vehicle is detected and the detection result is obtained through the final threshold value set. By fitting and updating multiple thresholds for joint stationary detection, the timeliness and accuracy of the detection of the target vehicle state are improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 It is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application;
[0052] Figure 2 It is a flow chart of the first embodiment of the vehicle stationary state detection method of the present application;
[0053] Figure 3This is a flow chart of the first embodiment of the vehicle stationary state detection method of the present application, taking the satellite / inertial combined navigation data input as an example;
[0054] Figure 4 (a) shows the effect of the first elimination of the forward accelerometer front and rear term extreme difference cycle gross error elimination diagram; Figure 4 (b) shows the effect of the third elimination of the forward accelerometer front and rear term extreme difference cycle gross error elimination diagram; Figure 4 (c) shows the effect of the seventh elimination of the forward accelerometer front and rear term extreme difference cycle gross error elimination diagram; Figure 4 (d) shows the effect of the ninth elimination of the forward accelerometer front and rear term extreme difference cycle gross error elimination diagram;
[0055] Figure 5 This is a diagram showing the adaptive fitting effect of the heading angular velocity variance threshold value of the first embodiment of the vehicle stationary state detection method of the present application;
[0056] Figure 6 This is a loose threshold detection result diagram of the first embodiment of the vehicle stationary state detection method of the present application;
[0057] Figure 7 This is a strict threshold detection result diagram of the first embodiment of the vehicle stationary state detection method of the present application;
[0058] Figure 8 It is a structural block diagram of the first embodiment of the vehicle stationary state detection system of the present application. DETAILED DESCRIPTION
[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below through the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0060] Reference Figure 1 , Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.
[0061] like Figure 1As shown, the computer device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.
[0062] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.
[0063] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a vehicle stationary state detection program.
[0064] exist Figure 1 In the computer device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the present application can be set in the computer device, and the computer device calls the vehicle stationary state detection program stored in the memory 1005 through the processor 1001, and executes the vehicle stationary state detection method provided in the embodiment of the present application.
[0065] The present application provides a method for detecting a stationary state of a vehicle. Figure 2 , Figure 2 This is a flow chart of the first embodiment of the vehicle stationary state detection method of the present application.
[0066] In this embodiment, the vehicle stationary state detection method includes the following steps:
[0067] Step S10: Determine the first category of data, the second category of data, the third category of data, the fourth category of data and the fifth category of data through a preset sensor device, and store all acquired data as a target data set in a target data window.
[0068] It should be noted that the existing stationary detection method mainly constructs the stationary detection statistics by calculating the variance of the accelerometer and gyroscope data exported by the inertial measurement unit (IMU), and then performs stationary detection on the statistics according to the preset empirical threshold. There are two disadvantages of this method: on the one hand, the statistic setting is too single, and the screening of the stationary state is not strict enough, which easily leads to false omissions of stationary detection. In addition, if a single threshold is to obtain better detection results, a sufficiently long data window is required for calculating the variance, and a long window means high detection delay, which will cause false omissions when the vehicle state changes. On the other hand, when different vehicles are stationary, different IMU device noise, engine amplitude, and the tightness of the connection between the equipment and the vehicle will cause the variance of the IMU output to change, and the traditional stationary detection method relies on a fixed threshold determined by prior experience, and cannot perform reliable detection in different scenarios.
[0069] It can be understood that the preset sensing device in this embodiment refers to the accelerometer and the gyroscope, and the data collected by the accelerometer and the gyroscope are used to perform data calculation in this embodiment to determine the IMU's heading angular velocity variance, heading angular velocity slope, roll angular velocity variance, forward acceleration front and back term difference range, and heading angular velocity front and back term difference range at each moment. Therefore, in this embodiment, the first type of data is the heading angular velocity variance; the second type of data is the heading angular velocity slope; the third type of data is the roll angular velocity variance; the fourth type of data is the forward acceleration front and back term difference range; the fifth type of data is the heading angular velocity front and back term difference range.
[0070] It can be understood that all acquired data are stored as target data in the target data window and the corresponding data window is set according to the actual usage.
[0071] It is understandable that if Figure 3 A flow chart is shown, in this embodiment, through satellite / inertial combined navigation data input, mainly including four parts: satellite navigation stationary detection, IMU statistics selection, IMU adaptive threshold fitting and IMU stationary detection.
[0072] In the specific implementation, taking the IMU device with 100 Hz output as an example, the heading angular velocity variance, heading angular velocity slope, roll angular velocity variance, forward acceleration front and back term difference range, and heading angular velocity front and back term difference range of the IMU are calculated at each moment.
[0073] The above five statistics are calculated using 0.5s window data as the judgment condition for IMU static detection. The 0.5s window determines that the detection delay of this method is at most 0.5s. The specific meaning and calculation method of each statistic are as follows:
[0074] 1. Heading angular velocity variance ( S 1)
[0075] The heading angular velocity is output by the IMU's gyroscope and is recorded as , the data window size is , in this example ,in represents the mean angular velocity of heading; Represents the i-th heading angular velocity value, the heading angular velocity variance ( S 1) is calculated as follows:
[0076]
[0077] 2. Heading angular velocity slope ( S 2)
[0078] The heading angular velocity slope represents the ratio of the difference between the maximum and minimum values in the window to the window length. In order to eliminate the influence of outliers, the data in the front window is sorted from small to large, and the mean of the first 10% of the data is used to replace the minimum value, and the last 10% of the data is used to replace the maximum value. Then the heading angular velocity slope ( S 2) is calculated as follows:
[0079]
[0080] In the formula represents the calculation of the mean, Indicates the heading angular velocity sorted from small to large.
[0081] 3. Roll angular velocity variance ( S 3)
[0082] The rolling angular velocity is output by the IMU's gyroscope and is recorded as , and the heading angular velocity variance ( S 1) Calculation is consistent, the roll angular velocity variance ( S 3) is calculated as follows:
[0083]
[0084] 4. The difference between the front and rear terms of forward acceleration ( S 4)
[0085] The range of the difference between the front and rear terms of the forward acceleration indicates the maximum and minimum difference between the front and rear terms of the forward acceleration in the window. This statistic reflects the change in the IMU data after removing the constant zero bias in a window, and can very sensitively detect changes in the carrier's motion state. The forward acceleration is output by the IMU's accelerometer and is recorded as , the total forward acceleration in the window is recorded as , then the difference between the forward acceleration and the forward acceleration is extreme ( S 4) is calculated as follows:
[0086]
[0087] In the formula It represents the difference between the front and back terms of the forward acceleration in the window.
[0088] 5. The difference between the front and rear terms of heading angular velocity ( S 5)
[0089] The difference between the front and rear terms of the heading angular velocity and the front and rear terms of the forward acceleration ( S 4) Similarly, it represents the maximum and minimum difference between the front and back items of the heading angular velocity in the window. The overall heading angular velocity in the window is recorded as , then the extreme difference between the front and rear terms of the heading angular velocity ( S 5) is calculated as follows:
[0090]
[0091] In the formula Indicates the difference between the front and back items of the heading angular velocity within the window.
[0092] Step S20: After the start condition is met, an initial threshold set is determined from the target data window.
[0093] It should be noted that the start condition refers to that after the storage time of the target data window reaches the specified time, it is determined that the start condition is met. The storage time of the target data window is set by the system administrator according to the specific usage. In this embodiment, 20 seconds is used as an example for explanation.
[0094] It can be understood that the initial threshold set includes the threshold corresponding to each data type in step S10, specifically: the heading angular velocity variance initial threshold, the heading angular velocity slope initial threshold, the rolling angular velocity variance initial threshold, the forward acceleration front and back term difference range initial threshold, and the heading angular velocity front and back term difference range initial threshold.
[0095] In a specific implementation, after the start condition is met, the step of determining the initial threshold set from the target data window includes: when it is determined that the preset start condition is met, performing item-by-item differential elimination according to the data type in the target data window to obtain a first threshold set; and updating the data in the first threshold set according to a preset elimination method to determine the initial threshold set.
[0096] It should be noted that the step of updating data in the first threshold set according to a preset elimination method to determine the initial threshold set includes: determining the mean and root mean square error corresponding to each data type in the first threshold set; taking the mean plus three times the root mean square error as the preset elimination method; and calculating according to the preset elimination method to determine the initial threshold set.
[0097] It should be noted that after the start condition is met, the five different types of data in the data window are eliminated item by item to obtain a first threshold set, in which the "mean + 3 times the standard deviation" of each statistic is used as the initial threshold.
[0098] In the specific implementation, the IMU static detection statistical threshold is initialized using the five statistical data of the initial alignment stage of the integrated navigation when the satellite navigation signal is good and the vehicle is stationary. The initial alignment time of the integrated navigation is generally between 30s and 3min, and the IMU static detection adaptive threshold only needs 20s of data to fit, that is, there is enough time to obtain the IMU static detection adaptive initial threshold during the initialization of the integrated navigation system. The specific initialization method is as follows.
[0099] Get the five stored data in the target data window. When the number of each statistic reaches 2000 (100hz data 20s), start to initialize the fitting of the IMU static detection threshold. The threshold initialization algorithm is divided into two parts: gross error elimination and 3sigma fitting. Since the static indicated by the satellite navigation is not necessarily completely reliable, or the satellite navigation indicates static but the vehicle shakes due to situations such as people getting on and off the vehicle, some abnormal values will appear in the five statistics. These abnormal values need to be eliminated before fitting the IMU static detection threshold. In this algorithm, the gross error elimination method adopts the 3 sigma cycle elimination method. The implementation process is as follows: calculate the "mean + three times the root mean square error" of 2000 statistical data, use it as the threshold for gross error elimination, eliminate data greater than the threshold, and recalculate the "mean plus three times the root mean square error" for the eliminated data. Repeat the above steps to continue to eliminate gross errors, and repeat this process until all data are within the "mean + three times the root mean square error". The gross error elimination is successful. Otherwise, when the data volume after the cycle is eliminated is less than 60% of the initial data volume, the cycle is exited and the gross error elimination fails. Taking the forward accelerometer front and rear extremes as an example, the 3sigma cycle gross error elimination is used for the 2000 data window. The effects after the 1st, 3rd, 7th, and 9th eliminations are shown in Figure 4 (a); the effect after the 3rd elimination is shown in Figure 4 (b); the effect after the 7th elimination is shown in Figure 4 (c); and the effect after the 9th elimination is shown in Figure 4 (d). In the figure, " ” indicates the data removed each time. It can be seen that after the seventh removal, there are basically no abnormal values in the data within the window, and the 3 sigma cycle gross error removal method is effective.
[0100] It should be noted that if the statistical gross error elimination fails, the preset threshold will be used as the initial threshold corresponding to the five data items in the data window. And when the initialization fails, the 20s statistical data window is slid back 2s to obtain a new initialization data window, and the above initialization process is repeated until the initialization is successful, otherwise the preset threshold is always used.
[0101] Step S30: Acquire real-time statistical data from a preset address and update the initial threshold set according to the data type to determine a final threshold set.
[0102] It should be noted that the real-time statistical data obtained through the preset address is based on the premise of determining whether the detection state corresponding to the address is static.
[0103] Furthermore, in order to improve the accuracy of final threshold generation, the steps of obtaining real-time statistical data from a preset address and updating the initial threshold set according to the data type to determine the final threshold set include: obtaining an identification data set with a static identification from the preset address; obtaining a preset effective time interval, and determining the final statistical data in the identification data set according to the effective time interval; and updating the initial threshold set according to the final statistical data to determine the final threshold set.
[0104] In the specific implementation, due to the random walk error of the IMU device and the change of vehicle condition, the five statistics of IMU stationary detection may have certain differences over time. In order to obtain a more appropriate threshold, the threshold is also required to be updated in real time to improve the reliability of vehicle stationary state detection. Therefore, after the initialization of the five thresholds is completed, when the satellite navigation indicates the stationary moment, the IMU data is passed into the algorithm to update the threshold of vehicle stationary state detection. The threshold update algorithm is divided into two parts: gross error identification and threshold update. The gross error elimination method in the threshold update process is no longer a cyclic elimination of gross errors like initialization, but only needs to use the vehicle stationary state detection threshold calculated last time as the gross error elimination threshold, and the gross error identification is performed on the latest statistic passed to the algorithm. If the latest statistic passed is less than the gross error elimination threshold, the epoch data is updated to the 20s statistic sliding window, and the "mean + 3 times the root mean square error" of the data in the window is recalculated as the latest stationary detection threshold, otherwise the epoch data is eliminated and the vehicle stationary state detection threshold is not updated. Taking the heading angular velocity variance as an example, the threshold adaptive fitting effect based on the "mean + 3 times the root mean square error" method is as follows: Figure 5 The adaptive fitting effect diagram of the heading angular velocity variance threshold is shown in the figure. The initial preset threshold is 0.06. During the initial alignment of the integrated navigation, the heading angular velocity variance static detection threshold is quickly initialized and dropped to around 0.04. Then, at the static position indicated by the satellite navigation, the threshold is continuously updated in real time, and the threshold obtained by fitting can accurately separate the static state and the moving state.
[0105] Step S40: upon receiving the status detection signal, obtaining the real-time first-category data, the real-time second-category data, the real-time third-category data, the real-time fourth-category data and the real-time fifth-category data of the target vehicle as a real-time data set.
[0106] It can be understood that in this embodiment, the real-time type 1 data refers to the heading angular velocity variance; the real-time type 2 data refers to the rolling angular velocity variance; the real-time type 3 data refers to the heading angular velocity slope; the real-time type 4 data refers to the extreme difference between the front and rear terms of the forward acceleration; and the real-time type 5 data refers to the extreme difference between the front and rear terms of the heading angular velocity.
[0107] Step S50: Determine the vehicle status detection result according to the final threshold value set and the real-time data set.
[0108] Furthermore, in order to reasonably realize the determination of the vehicle state detection result, before the step of determining the vehicle state detection result according to the final threshold set and the real-time data set, it also includes: obtaining the final threshold of the heading angular velocity variance in the final threshold set and comparing it with the real-time heading angular velocity variance to obtain a first comparison result; obtaining the final threshold of the heading angular velocity slope in the final threshold set and comparing it with the real-time heading angular velocity slope to obtain a second comparison result; obtaining the final threshold of the roll angular velocity variance in the final threshold set and comparing it with the real-time roll angular velocity variance to obtain a third comparison result; obtaining the final threshold of the range of the forward acceleration front and back terms difference in the final threshold set and comparing it with the real-time forward acceleration front and back terms difference to obtain a fourth comparison result; obtaining the final threshold of the range of the heading angular velocity front and back terms difference in the final threshold set and comparing it with the real-time heading angular velocity front and back terms difference to obtain a fifth comparison result.
[0109] It should be noted that the step of determining the vehicle state detection result based on the final threshold set and the real-time data set includes: judging whether the first comparison result and the third comparison result are successful at the same time in the final threshold set and the real-time data set; if not, judging that the current vehicle state is a moving state; if so, judging whether the second comparison result, the fourth comparison result and the fifth comparison result are successful at the same time; if it is judged that the second comparison result, the fourth comparison result and the fifth comparison result are successful at the same time, then judging that the current vehicle state is a strictly reliable stationary state; if it is judged that the second comparison result, the fourth comparison result and the fifth comparison result are not successful at the same time, then judging that the current vehicle state is a fuzzy stationary state.
[0110] In the specific implementation, the five thresholds in the final threshold set of this embodiment respectively judge the five types of statistics in the real-time data set. When the two relatively stable statistics of the heading angular velocity variance and the rolling angular velocity variance meet the threshold conditions (loose threshold), it is judged as a loose static state, and there may be a certain amount of error at this time. When the five statistics of the heading angular velocity variance, the rolling angular velocity variance, the heading angular velocity slope, the front and back term difference range of the forward acceleration, and the front and back term difference range of the heading angular velocity all meet the threshold conditions (strict threshold), it is judged as a strictly reliable static state, and the false detection rate is extremely low at this time. The remaining scenarios that meet the loose threshold but do not meet the strict threshold are uniformly set to a fuzzy static state.
[0111] The above is the entire process of the vehicle-mounted high-sensitivity adaptive threshold stationary detection method based on MEMS IMU. Through the above steps, a reliable vehicle stationary state can be obtained. To verify the effectiveness of this method, the moment when the combined speed output by the fiber optic inertial group is less than 0.05m / s is used as the real stationary moment. The stationary moment detected by this method is compared with the real stationary moment, and the missed detection rate and false detection rate are used to characterize the accuracy of the detection. The calculation method is as follows:
[0112]
[0113] The experiment collects data from a MEMS-IMU / GNSS combined navigation sports car. After the vehicle is started, the antenna is unplugged to simulate satellite loss of lock. The vehicle stops at multiple traffic lights and uses this method for stationary detection. The missed detection rate and false detection rate are calculated. The detection results are shown in the figure. Figure 6 is the loose threshold detection result, Figure 7 The dashed line in the figure is the speed curve obtained by the Fiber Optic Inertial Group (FIGIM) solution, and the solid horizontal line is the speed boundary of 0.05m / s. In the experiment, the moment when the FIGIM speed is less than 0.05m / s is regarded as the real stationary moment of the vehicle. " indicates the false detection of stillness detection by this method (actual motion is detected as stillness). The " " indicates missed detection (actually stationary but not detected). The vertical line in the figure is the moment when the satellite antenna is pulled out. The stationary state before this moment is given by the satellite navigation, and during this period, the IMU stationary detection threshold is fitted using the stationary state indicated by the satellite navigation. The stationary state after this moment is given by the IMU stationary detection threshold detection obtained by fitting.
[0114] Figure 6 This is the relaxed stationary result obtained by using only two threshold detections. Taking the fiber speed less than 0.05m / s as the actual parking, the total parking time is 815.59s, the missed detection rate is 2.94%, and the false detection rate is 0.93%; Figure 7 For the strict static result obtained by combining five threshold detections, the total parking time is 818.59s, the missed detection rate is 9.59%, and the false detection rate is 0.16% when the fiber speed is less than 0.05m / s as the real parking. It can be seen that after the threshold items are increased, the false detection rate is sharply reduced, and the real speed at the time of false detection is also very small (within 0.2m / s), which will be very beneficial to the next step of zero-speed correction. When performing zero-speed correction, using static false detection (especially judging high speed as static) for zero-speed correction is likely to cause disorder in the data fusion filter. Therefore, the principle to be followed in static detection is to rather miss the detection for a short time without zero-speed correction, and not to force correction due to false detection to cause system abnormality.
[0115] In addition, it can be seen from the statistical results that the loose threshold of this method can give a stationary detection rate of more than 96%, and the strict threshold can give an extremely low false detection rate of less than 0.4%. The remaining approximately 1% to 3% of loose threshold false detections can be uniformly classified into the fuzzy stationary state, and an indication is given when zero-speed correction is used.
[0116] This embodiment determines the initial threshold value set by presetting the sensor device to determine the first type of data, the second type of data, the third type of data, the fourth type of data and the fifth type of data; after the start condition is met, the initial threshold value set is updated with the collected real-time statistical data and the final threshold value set is determined; the vehicle state of the target vehicle is detected by the final threshold value set and the detection result is obtained. By fitting and updating multiple thresholds for joint stationary detection, the timeliness and accuracy of the target vehicle state detection are improved.
[0117] In addition, an embodiment of the present application further proposes a computer-readable storage medium, on which a program for detecting a vehicle stationary state is stored. When the program for detecting a vehicle stationary state is executed by a processor, the steps of the method for detecting a vehicle stationary state as described above are implemented.
[0118] Reference Figure 8 , Figure 8 This is a structural block diagram of the first embodiment of the vehicle stationary state detection system of the present application.
[0119] like Figure 8 As shown, the vehicle stationary state detection system proposed in the embodiment of the present application includes:
[0120] The target data set module 10 is used to determine the first type of data, the second type of data, the third type of data, the fourth type of data and the fifth type of data through a preset sensor device, and store all the acquired data as a target data set in a target data window;
[0121] An initial threshold set module 20, for determining an initial threshold set from a target data window after a start condition is met;
[0122] The final threshold set module 30 is used to obtain real-time statistical data from a preset address and update the initial threshold set according to the data type to determine the final threshold set;
[0123] The real-time data collection module 40 is used to obtain the real-time first-category data, the real-time second-category data, the real-time third-category data, the real-time fourth-category data and the real-time fifth-category data of the target vehicle as the real-time data collection when receiving the status detection signal;
[0124] The vehicle state module 50 is used to determine the vehicle state detection result according to the final threshold value set and the real-time data set.
[0125] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present application. In specific applications, technicians in this field can make settings as needed, and the present application does not impose any limitation on this.
[0126] This embodiment determines the initial threshold value set by presetting the sensor device to determine the first type of data, the second type of data, the third type of data, the fourth type of data and the fifth type of data; after the start condition is met, the initial threshold value set is updated with the collected real-time statistical data and the final threshold value set is determined; the vehicle state of the target vehicle is detected by the final threshold value set and the detection result is obtained. By fitting and updating multiple thresholds for joint stationary detection, the timeliness and accuracy of the target vehicle state detection are improved.
[0127] In one embodiment, the target data set module 10 also includes a first type of data, which is the variance of the heading angular velocity; a second type of data, which is the slope of the heading angular velocity; a third type of data, which is the variance of the rolling angular velocity; a fourth type of data, which is the range of the difference between the front and rear terms of the forward acceleration; and a fifth type of data, which is the range of the difference between the front and rear terms of the heading angular velocity.
[0128] In one embodiment, the target data set module 10 is also used to perform item-by-item elimination according to the data type in the target data window to obtain a first threshold set when it is determined that the preset start condition is met; and update the data in the first threshold set according to the preset elimination method to determine the initial threshold set.
[0129] In one embodiment, the target data set module 10 is further used to determine the mean and root mean square error corresponding to each data type in the first threshold set; the mean plus three times the root mean square error is used as a preset elimination method; and calculation is performed according to the preset elimination method to determine the initial threshold set.
[0130] In one embodiment, the final threshold set module 30 is also used to obtain an identification data set with a static identification from a preset address; obtain a preset effective time interval, and determine the final statistical data in the identification data set according to the effective time interval; and update the initial threshold set according to the final statistical data to determine the final threshold set.
[0131] In one embodiment, the vehicle status module 50 is also used to obtain a final threshold value of the heading angular velocity variance in the final threshold value set and compare it with the real-time heading angular velocity variance to obtain a first comparison result; obtain a final threshold value of the heading angular velocity slope in the final threshold value set and compare it with the real-time heading angular velocity slope to obtain a second comparison result; obtain a final threshold value of the roll angular velocity variance in the final threshold value set and compare it with the real-time roll angular velocity variance to obtain a third comparison result; obtain a final threshold value of the range of the forward acceleration front and back terms difference in the final threshold value set and compare it with the real-time forward acceleration front and back terms difference to obtain a fourth comparison result; obtain a final threshold value of the range of the heading angular velocity front and back terms difference in the final threshold value set and compare it with the real-time heading angular velocity front and back terms difference to obtain a fifth comparison result.
[0132] In one embodiment, the vehicle state module 50 is also used to determine whether the first comparison result and the third comparison result are successful at the same time in the final threshold set and the real-time data set; if not, the current vehicle state is determined to be a moving state; if so, it is determined whether the second comparison result, the fourth comparison result and the fifth comparison result are successful at the same time; if it is determined that the second comparison result, the fourth comparison result and the fifth comparison result are successful at the same time, the current vehicle state is determined to be a strictly reliable stationary state; if it is determined that the second comparison result, the fourth comparison result and the fifth comparison result are not successful at the same time, the current vehicle state is determined to be a fuzzy stationary state.
[0133] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present application. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.
[0134] In addition, for technical details not described in detail in this embodiment, please refer to the method for detecting the vehicle stationary state provided in any embodiment of the present application, and will not be repeated here.
[0135] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0136] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0137] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application.
[0138] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A vehicle stationary state detection method, characterized in that: include: Determine the first category of data, the second category of data, the third category of data, the fourth category of data, and the fifth category of data through a preset sensor device, and store all the acquired data as a target data set in a target data window; After the start condition is met, determining an initial threshold set from the target data window; Acquire real-time statistical data from a preset address and update the initial threshold set according to the data type to determine a final threshold set; When receiving the status detection signal, real-time type 1 data, real-time type 2 data, real-time type 3 data, real-time type 4 data and real-time type 5 data of the target vehicle are obtained as a real-time data set; Determine a vehicle state detection result according to the final threshold value set and the real-time data set; Wherein, the one type of data is heading angular velocity variance; The second type of data is the heading angular velocity slope; The three types of data are roll angular velocity variance; The four types of data are the extreme differences of the front and rear items of the forward acceleration; The five types of data are the extreme differences of the front and rear items of the heading angular velocity; Wherein, after the start condition is met, the step of determining the initial threshold set from the target data window comprises: When it is determined that the preset start condition is met, performing item-by-item elimination according to the data type in the target data window to obtain a first threshold value set; updating data in the first threshold value set according to a preset elimination method to determine an initial threshold value set; The step of updating data in the first threshold set according to a preset elimination method to determine the initial threshold set includes: Determine a mean and a root mean square error corresponding to each data type in the first threshold set; The mean value plus three times the root mean square error is used as a preset elimination method; Perform calculation according to the preset elimination method to determine an initial threshold set; The step of acquiring real-time statistical data from a preset address and updating the initial threshold set according to the data type to determine the final threshold set includes: Obtaining a set of identification data with a static identification from a preset address; Obtaining a preset effective time interval, and determining final statistical data in the identification data set according to the effective time interval; updating the initial threshold set according to the final statistical data to determine a final threshold set; The start condition refers to that after the storage time of the target data window reaches a specified time, it is determined that the start condition is met.
2. The vehicle stationary state detection method according to claim 1, characterized in that: Before the step of determining the vehicle state detection result according to the final threshold value set and the real-time data set, the method further includes: Obtaining a final threshold value of the heading angular velocity variance from the final threshold value set and comparing it with the real-time heading angular velocity variance to obtain a first comparison result; Obtaining a final threshold of the heading angular velocity slope from the final threshold set and comparing it with the real-time heading angular velocity slope to obtain a second comparison result; Obtaining a final threshold of the roll angular velocity variance from the final threshold set and comparing it with the real-time roll angular velocity variance to obtain a third comparison result; Obtaining a final threshold value of the range of the front and rear terms of the forward acceleration from the final threshold value set and comparing it with the range of the front and rear terms of the real-time forward acceleration to obtain a fourth comparison result; The final threshold value of the range of the front and rear term differences of the heading angular velocity is obtained from the final threshold value set and compared with the range of the front and rear term differences of the real-time heading angular velocity to obtain a fifth comparison result.
3. The vehicle stationary state detection method according to claim 2, characterized in that: The step of determining the vehicle state detection result according to the final threshold value set and the real-time data set comprises: Determining whether the first comparison result and the third comparison result are both successful in the final threshold value set and the real-time data set; If not, the current vehicle state is determined to be a moving state; If yes, determining whether the second comparison result, the fourth comparison result, and the fifth comparison result are all successful; If it is determined that the second comparison result, the fourth comparison result and the fifth comparison result are all successful at the same time, then it is determined that the current vehicle state is a strictly reliable stationary state; If it is determined that the second comparison result, the fourth comparison result, and the fifth comparison result are not simultaneously successful, then it is determined that the current vehicle state is a fuzzy stationary state.
4. A vehicle stationary state detection system, characterized in that: The vehicle stationary state detection system comprises: A target data set module is used to determine the first type of data, the second type of data, the third type of data, the fourth type of data and the fifth type of data through a preset sensor device, and store all the acquired data as a target data set in a target data window; An initial threshold set module, used to determine an initial threshold set from the target data window after a start condition is met; A final threshold set module, used to obtain real-time statistical data from a preset address and update the initial threshold set according to the data type to determine a final threshold set; A real-time data collection module, for obtaining real-time first-category data, real-time second-category data, real-time third-category data, real-time fourth-category data and real-time fifth-category data of the target vehicle as a real-time data collection when receiving a status detection signal; A vehicle status module, configured to determine a vehicle status detection result according to the final threshold value set and the real-time data set; Wherein, the one type of data is heading angular velocity variance; The second type of data is the heading angular velocity slope; The three types of data are roll angular velocity variance; The four types of data are the extreme differences of the front and rear items of the forward acceleration; The five types of data are the extreme differences of the front and rear items of the heading angular velocity; The start condition refers to that after the storage time of the target data window reaches the specified time, it is determined that the start condition is met; The initial threshold set module is further configured to, when it is determined that the preset start condition is met, perform item-by-item elimination according to the data type in the target data window to obtain a first threshold set; updating data in the first threshold value set according to a preset elimination method to determine an initial threshold value set; The initial threshold set module is further used to determine the mean and root mean square error corresponding to each data type in the first threshold set; The mean value plus three times the root mean square error is used as a preset elimination method; Perform calculation according to the preset elimination method to determine an initial threshold set; Wherein, the final threshold set module is further used to obtain a set of identification data with a static identification from a preset address; Obtaining a preset effective time interval, and determining final statistical data in the identification data set according to the effective time interval; The initial threshold set is updated according to the final statistical data to determine a final threshold set.
5. A computer device, characterized in that: The device comprises: a memory and a processor, wherein the processor executes the method according to any one of claims 1 to 3 when running computer instructions stored in the memory.
6. A computer-readable storage medium, characterized in that: The method comprises instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 3.
Citation Information
Patent Citations
Driving behavior detection method and device, electronic equipment and storage medium thereof
CN113635907A
Zero-speed state detection method and device and electronic equipment
CN114019182A
