A method for checking the transverse and longitudinal speed redundancy of an intelligent driving vehicle

Abstract

The application is suitable for the field of intelligent driving technology, and provides a method for checking the horizontal and longitudinal speed redundancy of an intelligent driving vehicle, comprising the following steps: obtaining the horizontal displacement, longitudinal displacement, horizontal speed and longitudinal speed; calculating the variance of 5 cycles through the horizontal and longitudinal displacement, and judging whether the variance is less than b1; calculating the average speed sum of 5 cycles through the horizontal and longitudinal displacement, and calculating the average value of 5 cycles through the horizontal speed and longitudinal speed; obtaining the average value and difference value; judging whether the difference value is less than b2*the horizontal and longitudinal speed; when the variance is less than b1 and the difference value is less than b2*the horizontal and longitudinal speed, determining that the horizontal and longitudinal speed state is Vx-fig1 and Vy-fig1; otherwise, determining that the horizontal and longitudinal speed state is Vx-fig2 and Vy-fig2. The application can find error data in time by checking the input horizontal and longitudinal speed information, and prevent the application layer software from executing error instructions.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, specifically to a method for verifying the lateral and longitudinal speed redundancy of intelligent driving vehicles. Background Technology

[0002] Intelligent driving essentially involves cognitive engineering of attention attraction and distraction, mainly comprising three stages: network navigation, autonomous driving, and human intervention. The prerequisites for intelligent driving are that the selected vehicle meets the dynamic requirements of driving, the onboard sensors can acquire relevant visual and auditory signals and information, and the corresponding servo system is controlled through cognitive computing. Intelligent driving and driverless driving are different concepts; intelligent driving is broader, referring to technologies that allow machines to assist humans in driving, and, in special circumstances, completely replace human driving. Currently, perception software measures or calibrates the longitudinal and lateral velocity parameters of target objects using sensors such as vision, high-precision maps, and LiDAR. After the application layer software obtains the basic data of the perception input, it filters and removes abrupt changes in data before performing relevant functional calculations. Existing technology almost entirely relies on the perception software to measure or calibrate the lateral and longitudinal velocity parameters of target objects using sensors such as cameras, high-precision maps, and LiDAR, simply performing filtering to eliminate obvious erroneous data. This can cause intelligent systems to place too much trust in the data from sensing sensors. If the sensors are tricked into providing a set of continuous, uniform but incorrect data, or if the sensors themselves experience a decrease in recognition accuracy, the application layer software will be unable to recognize the data and errors will occur immediately.

[0003] Therefore, a method for verifying the lateral and longitudinal speed redundancy of intelligent driving vehicles is needed to solve the above problems. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of this invention is to provide a method for cross-sectional and longitudinal speed redundancy verification of intelligent driving vehicles, so as to solve the problems existing in the background technology.

[0005] This invention is implemented as follows: a method for redundancy verification of lateral and longitudinal speeds in an intelligent driving vehicle, the method comprising the following steps:

[0006] Obtain the lateral displacement Dx, longitudinal displacement Dy, lateral velocity Vx, and longitudinal velocity Vy;

[0007] The variance of five periods is calculated using the lateral displacement Dx and the longitudinal displacement Dy, and it is determined whether the variance is less than the first parameter b1.

[0008] The average velocities Vy1 and Vx1 over five cycles are calculated using the lateral displacement Dx and the longitudinal displacement Dy.

[0009] The average values ​​Vy2 and Vx2 for five cycles are calculated using the lateral velocity Vx and the longitudinal velocity Vy.

[0010] Find the mean Vy3 of Vy1 and Vy2, and the mean Vx3 of Vx1 and Vx2;

[0011] Find the difference between Vy1 and Vy3, Vy4, and the difference between Vx1 and Vx3, Vx4;

[0012] Determine whether Vy4 is less than b2×Vy and whether Vx4 is less than b2×Vx, where b2 is the second parameter;

[0013] When the variance is less than the first parameter b1, Vy4 is less than b2×Vy, and Vx4 is less than b2×Vx, the lateral velocity state is determined to be Vx-fig1 and the longitudinal velocity state is determined to be Vy-fig1; otherwise, the lateral velocity state is determined to be Vx-fig2 and the longitudinal velocity state is determined to be Vy-fig2.

[0014] Determine whether the application layer function is activated. When the function is activated, output Vx-fig1 and Vy-fig1 or Vx-fig2 and Vy-fig2, where Vx-fig1 and Vy-fig1 are the current horizontal and vertical velocities, and Vx-fig2 and Vy-fig2 are the horizontal and vertical velocities of the previous cycle. When the function is not activated, cancel the output.

[0015] As a further aspect of the present invention: the lateral displacement Dx, longitudinal displacement Dy, lateral velocity Vx, and longitudinal velocity Vy are obtained from the vehicle's surrounding environment perception information, which is acquired through the perception layer software.

[0016] As a further aspect of the present invention: when obtaining the average velocities Vy1 and Vx1, the lateral displacement Dx and longitudinal displacement Dy of 5 cycles are determined, the duration of 5 cycles is retrieved, and the average velocities Vy1 and Vx1 are calculated.

[0017] As a further aspect of the present invention: when determining whether the variance is less than the first parameter b1, it is necessary to determine whether the lateral displacement variance over 5 periods and the longitudinal displacement variance over 5 periods are both less than the first parameter b1.

[0018] As a further aspect of the present invention: the lateral displacement variance = [(lateral displacement 1 - average lateral displacement)] 2 +(lateral displacement 2 - average lateral displacement) 2 +(lateral displacement 3 - average lateral displacement) 2 +(lateral displacement 4 - average lateral displacement) 2 +(lateral displacement 5 - average lateral displacement) 2 ]÷5.

[0019] As a further aspect of the present invention: the longitudinal displacement variance = [(longitudinal displacement 1 - average longitudinal displacement)] 2 +(Longitudinal displacement 2 - Average longitudinal displacement) 2 +(Longitudinal displacement 3 - Average longitudinal displacement) 2 +(Longitudinal displacement 4 - Average longitudinal displacement) 2 +(Longitudinal displacement 5 - Average longitudinal displacement) 2 ]÷5.

[0020] As a further aspect of the present invention: the average value Vx2 is equal to the sum of the lateral velocities Vx over 5 cycles divided by 5, and the average value Vy2 is equal to the sum of the longitudinal velocities Vy over 5 cycles divided by 5.

[0021] As a further aspect of the present invention: the mean value Vx3 = (Vx1 + Vx2) ÷ 2, and the mean value Vy3 = (Vy1 + Vy2) ÷ 2.

[0022] As a further aspect of the present invention: the difference Vx4 = |Vx1 - Vx3|, and the difference Vy4 = |Vy1 - Vy3|.

[0023] As a further aspect of the present invention, the output lateral velocity status and longitudinal velocity status are sent to the ADAS function module.

[0024] Compared with the prior art, the beneficial effects of the present invention are:

[0025] This invention verifies the input lateral and longitudinal velocity information. If no sudden changes or inconsistencies are found, the lateral and longitudinal velocity information is transmitted to the relevant control module. This allows for timely detection of erroneous data, preventing the application layer software from mistakenly executing incorrect instructions or actions. It also increases the stability of the application layer software, preventing false triggering of functions due to degraded or unstable sensor performance. By not completely trusting the input from the perception layer software, the application layer software largely avoids the instability of the perception layer software's recognition, which can lead to fluctuating data parameters and false triggering of functions. The invention verifies the authenticity of data at the data source, filtering out data that has fluctuated or been tampered with. Attached Figure Description

[0026] Figure 1 This is a flowchart of a method for redundancy verification of lateral and longitudinal speeds in an intelligent driving vehicle. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0028] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0029] like Figure 1 As shown in the figure, this embodiment of the invention provides a method for cross-sectional and longitudinal speed redundancy verification of an intelligent driving vehicle, the method comprising the following steps:

[0030] The first step is to obtain the lateral displacement Dx, longitudinal displacement Dy, lateral velocity Vx, and longitudinal velocity Vy;

[0031] The second step is to calculate the variance of 5 periods using the lateral displacement Dx and the longitudinal displacement Dy, and determine whether the variance is less than the first parameter b1.

[0032] The third step is to calculate the average velocities Vy1 and Vx1 over the five cycles using the lateral displacement Dx and the longitudinal displacement Dy.

[0033] The fourth step is to calculate the average values ​​Vy2 and Vx2 of the five cycles using the lateral velocity Vx and the longitudinal velocity Vy.

[0034] Fifth step, calculate the mean Vy3 of Vy1 and Vy2, and the mean Vx3 of Vx1 and Vx2;

[0035] Step 6: Calculate the difference between Vy1 and Vy3, Vy4, and the difference between Vx1 and Vx3, Vx4.

[0036] Step 7: Determine whether Vy4 is less than b2×Vy and whether Vx4 is less than b2×Vx, where b2 is the second parameter;

[0037] Step 8: When the variance is less than the first parameter b1, Vy4 is less than b2×Vy and Vx4 is less than b2×Vx, determine the lateral velocity state as Vx-fig1 and the longitudinal velocity state as Vy-fig1; otherwise, determine the lateral velocity state as Vx-fig2 and the longitudinal velocity state as Vy-fig2.

[0038] Step 9: Determine whether the application layer function is activated. When the function is activated, output Vx-fig1 and Vy-fig1 or Vx-fig2 and Vy-fig2. Vx-fig1 and Vy-fig1 are the current horizontal and vertical velocities, and Vx-fig2 and Vy-fig2 are the horizontal and vertical velocities of the previous cycle. When the function is not activated, cancel the output.

[0039] It should be noted that current perception software measures or calibrates the longitudinal and lateral velocity parameters of a target object using sensors such as vision, high-precision maps, and LiDAR. After the application layer software acquires the basic data input from the perception software, it filters and removes abrupt changes before performing relevant functional calculations. Existing technology almost entirely relies on the lateral and longitudinal velocity parameters of the target object measured or calibrated by the perception software using sensors such as cameras, high-precision maps, and LiDAR, simply performing filtering to eliminate obvious erroneous data. This can lead to the intelligent system over-relying on the data from the perception sensors. If the sensors are tricked into providing a set of continuous, uniform, but erroneous data, or if the sensor's recognition accuracy decreases due to its own limitations, the application layer software will be unable to recognize the data, resulting in an immediate error. The purpose of this invention is to verify the lateral and longitudinal velocity information input by the perception software in the application layer software. Only when no abrupt changes or unreasonable conditions are found should the lateral and longitudinal velocity information be transmitted to the relevant control module. Thus, if the perception layer software is tampered with or the sensors are maliciously deceived, resulting in erroneous parameters output by the perception layer software, the application layer software can detect the error promptly through data verification, and can reasonably avoid or process the data, or alert the driver to take over the vehicle in time. To prevent application layer software from accidentally executing incorrect instructions or actions; to increase the stability of application layer software and prevent the occurrence of false triggering of functions when sensor performance degrades or becomes unstable.

[0040] In this embodiment of the invention, after the perception layer software outputs parameters and before the application layer software receives and processes them, a redundant verification step is added to verify the horizontal and vertical velocity parameters to ensure that the parameters are accurate, without any step changes, and have not been tampered with.

[0041] In this embodiment of the invention, the lateral displacement Dx, longitudinal displacement Dy, lateral velocity Vx, and longitudinal velocity Vy are obtained from the vehicle's surrounding environment perception information, which is acquired through the perception layer software. When obtaining the average velocities Vy1 and Vx1, the lateral displacement Dx and longitudinal displacement Dy for five cycles are first determined, then the duration of the five cycles is retrieved, and finally the average velocities Vy1 and Vx1 are calculated. When determining whether the variance is less than the first parameter b1, it is necessary to determine whether the variance of the lateral displacement for five cycles and the variance of the longitudinal displacement for five cycles are simultaneously less than the first parameter b1. The lateral displacement variance = [(lateral displacement 1 - average lateral displacement)]. 2 +(lateral displacement 2 - average lateral displacement) 2 +(lateral displacement 3 - average lateral displacement) 2 +(lateral displacement 4 - average lateral displacement) 2 +(lateral displacement 5 - average lateral displacement) 2]÷5, where lateral displacement 1 is the lateral displacement of the first cycle, lateral displacement 2 is the lateral displacement of the second cycle, and so on. The longitudinal displacement variance = [(longitudinal displacement 1 - average longitudinal displacement)] 2 +(Longitudinal displacement 2 - Average longitudinal displacement) 2 +(Longitudinal displacement 3 - Average longitudinal displacement) 2 +(Longitudinal displacement 4 - Average longitudinal displacement) 2 +(Longitudinal displacement 5 - Average longitudinal displacement) 2 The longitudinal displacement 1 is the longitudinal displacement of the first cycle, the longitudinal displacement 2 is the longitudinal displacement of the second cycle, and so on. The average value Vx2 is equal to the sum of the lateral velocities Vx of the 5 cycles divided by 5, and the average value Vy2 is equal to the sum of the longitudinal velocities Vy of the 5 cycles divided by 5. The mean value Vx3 = (Vx1 + Vx2) ÷ 2, and the mean value Vy3 = (Vy1 + Vy2) ÷ 2. The difference Vx4 = |Vx1 - Vx3|, and the difference Vy4 = |Vy1 - Vy3|. When the variance is less than the first parameter b1, Vy4 is less than b2×Vy, and Vx4 is less than b2×Vx, the lateral velocity state is determined to be Vx-fig1 and the longitudinal velocity state is determined to be Vy-fig1; otherwise, the lateral velocity state is determined to be Vx-fig2 and the longitudinal velocity state is determined to be Vy-fig2. Vx-fig1 and Vy-fig1 are the current lateral and longitudinal velocities, and Vx-fig2 and Vy-fig2 are the lateral and longitudinal velocities of the previous cycle. When the application layer function is activated, the velocity status data is output. The output lateral and longitudinal velocity states are sent to the ADAS function module. The first parameter b1 and the second parameter b2 are pre-set values ​​according to actual needs.

[0042] In this embodiment of the invention, the application layer software verifies the perception layer software to prevent deviations in the perceived input data caused by tampering with the perception layer software, malicious deception of the sensor, or degraded sensor performance, which could lead to the application layer software erroneously executing incorrect instructions or actions. This largely avoids the instability of the perception layer software, resulting in fluctuating data parameters and mis-triggering of functions, such as AEB triggering due to complex surrounding environments. The application layer software does not completely trust the input from the perception layer software, verifying the authenticity of the data from the data source (perception software input), filtering out data that has fluctuated or been tampered with, increasing the stability of the application layer software, and avoiding mis-triggering of functions when sensor performance degrades or becomes unstable.

[0043] The above description only details the preferred embodiments of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0044] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0045] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0046] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the disclosure in the specification and embodiments. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A method for redundancy verification of lateral and longitudinal speeds in an intelligent driving vehicle, characterized in that, The method includes the following steps: Obtain the lateral displacement Dx, longitudinal displacement Dy, lateral velocity Vx, and longitudinal velocity Vy; The variance of five periods is calculated using the lateral displacement Dx and the longitudinal displacement Dy, and it is determined whether the variance is less than the first parameter b1. The average velocities Vy1 and Vx1 over five cycles are calculated using the lateral displacement Dx and the longitudinal displacement Dy. The average values ​​Vy2 and Vx2 for five cycles are calculated using the lateral velocity Vx and the longitudinal velocity Vy. Find the mean Vy3 of Vy1 and Vy2, and the mean Vx3 of Vx1 and Vx2; Find the difference between Vy1 and Vy3, Vy4, and the difference between Vx1 and Vx3, Vx4; Determine whether Vy4 is less than b2×Vy and whether Vx4 is less than b2×Vx, where b2 is the second parameter; When the variance is less than the first parameter b1, Vy4 is less than b2×Vy, and Vx4 is less than b2×Vx, the lateral velocity state is determined to be Vx-fig1 and the longitudinal velocity state is determined to be Vy-fig1; otherwise, the lateral velocity state is determined to be Vx-fig2 and the longitudinal velocity state is determined to be Vy-fig2. Determine whether the application layer function is activated. When the function is activated, output Vx-fig1 and Vy-fig1 or Vx-fig2 and Vy-fig2, where Vx-fig1 and Vy-fig1 are the current horizontal and vertical velocities, and Vx-fig2 and Vy-fig2 are the horizontal and vertical velocities of the previous cycle. When the function is not activated, cancel the output.

2. The method for redundancy verification of lateral and longitudinal speeds of intelligent driving vehicles according to claim 1, characterized in that, The lateral displacement Dx, longitudinal displacement Dy, lateral velocity Vx, and longitudinal velocity Vy are obtained from the vehicle's surrounding environment perception information, which is acquired through the perception layer software.

3. The method for redundancy verification of lateral and longitudinal speeds of intelligent driving vehicles according to claim 1, characterized in that, When obtaining the average velocities Vy1 and Vx1, the lateral displacement Dx and longitudinal displacement Dy of 5 cycles are determined, the duration of 5 cycles is retrieved, and the average velocities Vy1 and Vx1 are calculated.

4. The method for redundancy verification of lateral and longitudinal speeds of intelligent driving vehicles according to claim 1, characterized in that, When determining whether the variance is less than the first parameter b1, it is necessary to determine whether the variance of the lateral displacement over 5 periods and the variance of the longitudinal displacement over 5 periods are both less than the first parameter b1.

5. The method for redundancy verification of lateral and longitudinal speeds of intelligent driving vehicles according to claim 4, characterized in that, The variance of the lateral displacement = [(lateral displacement 1 - average lateral displacement)] 2 +(lateral displacement 2 - average lateral displacement) 2 +(lateral displacement 3 - average lateral displacement) 2 +(lateral displacement 4 - average lateral displacement) 2 +(lateral displacement 5 - average lateral displacement) 2 ]÷5.

6. The method for redundancy verification of lateral and longitudinal speeds of intelligent driving vehicles according to claim 4, characterized in that, The longitudinal displacement variance = [(Longitudinal displacement 1 - Average longitudinal displacement)] 2 +(Longitudinal displacement 2 - Average longitudinal displacement) 2 +(Longitudinal displacement 3 - Average longitudinal displacement) 2 +(Longitudinal displacement 4 - Average longitudinal displacement) 2 +(Longitudinal displacement 5 - Average longitudinal displacement) 2 ]÷5.

7. The method for redundancy verification of lateral and longitudinal speeds of intelligent driving vehicles according to claim 1, characterized in that, The average value Vx2 is equal to the sum of the lateral velocities Vx over 5 cycles divided by 5, and the average value Vy2 is equal to the sum of the longitudinal velocities Vy over 5 cycles divided by 5.

8. The method of cross and longitudinal vehicle speed redundancy checking for intelligent vehicles of claim 1, wherein, The mean value Vx3 = (Vx1 + Vx2) ÷ 2, and the mean value Vy3 = (Vy1 + Vy2) ÷ 2.

9. The method of cross and longitudinal vehicle speed redundancy checking for intelligent vehicles of claim 1, wherein, The difference Vx4 = |Vx1 - Vx3|, and the difference Vy4 = |Vy1 - Vy3|.

10. The method for redundancy verification of lateral and longitudinal speeds of an intelligent driving vehicle according to claim 1, characterized in that, The output lateral and longitudinal velocity statuses are sent to the ADAS function module.

Images