Self-checking method of automatic driving control system and related equipment

Abstract

The invention provides an automatic driving control system self-checking method and related equipment, and the method comprises the steps: collecting the timestamps of a vehicle positioning signal, a planning track signal and a chassis signal in real time, and calculating the frequency of the vehicle positioning signal, the frequency of the planning track signal and the frequency of the chassis signal after obtaining the difference values between the timestamps and the current moment; if the signal exceeds the preset normal range or is not updated for a certain time, judging that the corresponding signal is invalid; a vehicle motion state signal is monitored in real time, and if the difference value between the current vehicle motion state signal and the planning signal exceeds a set threshold value, it is judged that the current vehicle motion state signal is invalid; as long as any one of the vehicle positioning signal, the planning track signal, the chassis signal and the current vehicle motion state signal fails, the type and time information of the failure signal is output; otherwise, the vehicle is automatically driven normally. Abnormity of the input signal can be found and responded in time, and the driving safety guarantee of the vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving control system self-checking method and related equipment. Background Art

[0002] With the rapid development of science and technology, autonomous driving technology has become a core issue in the automotive industry and intelligent transportation. Autonomous driving systems usually include three parts: perception layer, decision layer and execution layer. The perception layer collects information about the vehicle's surrounding environment through various sensors (such as lidar, millimeter-wave radar, cameras, etc.); the decision layer makes path planning and motion decisions based on the perception data, combined with the vehicle's current state and destination information; the execution layer is responsible for controlling the vehicle's steering, acceleration and braking to achieve specific driving actions. However, the complexity and high dependence of the autonomous driving system place extremely high demands on the reliability and stability of the system. Among them, the accuracy and real-time performance of the input signal are key factors affecting the control performance and safety of autonomous driving vehicles. Vehicle positioning signal, planned trajectory signal and ego vehicle status signal are several key input signals of the vehicle control system. The failure of the positioning signal may cause the vehicle to be unable to accurately determine its own position, thereby affecting path planning and motion control; the abnormality of the planned trajectory signal may make the vehicle unable to respond to environmental changes in a timely manner, causing deviation from the driving path; and the failure of the ego vehicle status signal may make the control system unable to accurately determine the vehicle's current state, resulting in the mis-issuance or failure of the control command. The failure of these input signals may cause the vehicle's lateral and longitudinal control to lose control, seriously threatening driving safety.

[0003] Currently, there are two methods in this field to solve the above problem and prevent the vehicle from losing control after the signal fails:

[0004] The first is to detect the fault status of each faulty device of the autonomous driving vehicle, generate the fault code value of each faulty device, and then integrate the fault code values ​​of each faulty device to obtain the integrated fault code value. Based on the integrated fault code value, the corresponding safety control strategy is obtained; based on the vehicle's surrounding environment information and the safety control strategy, the vehicle's lateral and longitudinal control signals are generated; based on the lateral and longitudinal control signals, the vehicle is driven to perform safety redundant control of the vehicle. The system involves the detection of multiple faulty devices, the integration of fault code values, and the acquisition of safety control strategies. However, this method will increase the complexity of the system, thereby increasing the cost of implementation and maintenance. Although the system can detect and respond to faults, in some cases, it may be necessary to respond to faults quickly in a short period of time. For some scenarios with high real-time requirements, the performance of the system may still need to be verified.

[0005] The second is to improve the perception capability of the perception layer of the autonomous driving system. Intelligent sensing equipment such as radar, camera, positioning navigation, etc. will be used on autonomous driving vehicles. By using high-precision sensing equipment such as lidar, millimeter-wave radar, camera, high-precision positioning navigation and other equipment, 360-degree full coverage and blind spot monitoring centered on the vehicle can be achieved, the coverage rate of the detection area can be improved, and the detection accuracy can be improved. According to the sensor signal, nearby vehicles, obstacles, pedestrians, etc. are monitored in real time, and corresponding countermeasures are taken for dangerous situations, such as deceleration, steering avoidance, etc. However, this method requires a variety of high-precision sensing equipment, such as lidar, millimeter-wave radar, camera, etc., which will increase the cost and complexity of the vehicle. In addition, although it can achieve full coverage and blind spot monitoring, it may place higher requirements on computing power and storage capacity when processing large amounts of data. Summary of the invention

[0006] The purpose of the present invention is to provide an automatic driving control system self-check method and related equipment to solve the above-mentioned problems, which can promptly detect and respond to abnormalities in input signals, comprehensively and accurately evaluate whether the input signals of the automatic driving control system have failed, and improve vehicle driving safety.

[0007] The present invention proposes a self-checking method for an automatic driving control system, comprising the following steps:

[0008] Collect the timestamps of vehicle positioning signals, planned trajectory signals and chassis signals in real time, and calculate the vehicle positioning signal frequency, planned trajectory signal frequency and chassis signal frequency by taking the difference between them and the current time.

[0009] If the vehicle positioning signal frequency, planned trajectory signal frequency, and chassis signal frequency exceed the preset normal range or are not updated for a certain period of time, the corresponding signal is deemed invalid;

[0010] Monitor the vehicle motion status signal in real time and compare the current vehicle motion status signal with the planned signal;

[0011] If the difference between the current vehicle motion state signal and the planned signal exceeds a set threshold, the current vehicle motion state signal is determined to be invalid;

[0012] As long as any of the vehicle positioning signal, planned trajectory signal, chassis signal, and current vehicle motion status signal fails, the type and time information of the failure signal will be output; otherwise, the vehicle will perform automatic driving normally.

[0013] In one embodiment, when any of the vehicle positioning signal, planned trajectory signal, chassis signal, and current vehicle motion state signal fails, the level of failure is determined based on the number of failed signals and the deviation from the normal range or threshold, and the vehicle speed is reduced according to the level of failure until the vehicle stops.

[0014] In one embodiment, when any of the vehicle positioning signal, planned trajectory signal, chassis signal, and current vehicle motion state signal fails, a takeover prompt is sent to the driver to exit the automatic driving state.

[0015] In one embodiment, the self-check method of the automatic driving control system further includes saving the collected and monitored signal data in the form of a log, wherein the monitored data includes the type, time, and frequency of the signal.

[0016] In one embodiment, the vehicle positioning signal frequency f localization The calculation formula is:

[0017] The vehicle planning trajectory signal frequency f planning The calculation formula is:

[0018] The vehicle chassis signal frequency f vehic The calculation formula is:

[0019] Where, ΔT localization is the time difference between the current moment and the current vehicle positioning signal, ΔT planning is the time difference between the current time and the current vehicle planning trajectory signal, ΔT vehicle is the time difference between the current moment and the current vehicle chassis signal, T current is the timestamp of the current moment; T localization The timestamp of the current vehicle positioning signal; T planning The timestamp of the current vehicle planning trajectory signal; T vehicle It is the timestamp of the current vehicle chassis signal.

[0020] In one embodiment, the vehicle motion state signal includes vehicle speed, acceleration, and steering angle.

[0021] In one embodiment, when determining whether the current vehicle motion state signal is invalid, the specific judgment is: if ΔS exceeds the invalid vehicle speed threshold ΔS threshold , Δa exceeds the failure acceleration threshold Δa threshold and / or Δθ exceeds the failure steering angle threshold Δθ threshold , then it is determined that the current vehicle motion state signal is invalid;

[0022] Among them, ΔS is the difference between the current planned speed and the current vehicle speed, Δa is the difference between the current planned acceleration and the current vehicle acceleration, and Δθ is the difference between the current planned steering angle and the current vehicle steering angle.

[0023] The present invention also proposes a computer device, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the self-check method of the automatic driving control system as described above.

[0024] The present invention also proposes a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the self-check method of the automatic driving control system as described above is implemented.

[0025] The present invention also proposes a computer program product, including a computer program, which, when executed by a processor, implements the self-check method of the automatic driving control system as described above.

[0026] Compared with the prior art, the self-checking method of the automatic driving control system of the present invention has the following beneficial effects:

[0027] 1) The present invention calculates the frequency of vehicle positioning, planned trajectory, and chassis signals in real time by recording the timestamp of each input signal, and compares it with the preset normal range. If the frequency is abnormal (such as too high, too low, or no update for a long time), the signal is determined to be invalid, and continuous monitoring of signal stability is achieved. Compared with traditional periodic inspections, it is more accurate and efficient, and can detect and respond to small changes in signals in a timely manner. At the same time, it does not require the addition of high-precision instruments, which can effectively control costs.

[0028] 2) The present invention not only monitors the vehicle positioning frequency, planned trajectory frequency and chassis signal frequency of the vehicle, but also monitors the vehicle's motion state, including vehicle speed, acceleration, steering angle, etc., forming a comprehensive coverage of the input signal of the automatic driving control system, so as to comprehensively evaluate and determine whether the input signal of the automatic driving control system fails.

[0029] 3) The present invention can also quickly take emergency measures to control the vehicle after detecting that the input signal fails, such as issuing an early warning, reducing the vehicle speed until it stops according to the level of failure, or issuing a takeover prompt to the driver, and ensuring that the driver notices the takeover request in a variety of ways, which helps to reduce potential risks caused by system failure, ensure vehicle safety, and solve most of the problems of vehicle lateral and longitudinal control out of control when the positioning module, planning module or the vehicle's own status fails. It effectively improves the response capability of the automatic driving control system when facing input signal failure, prevents the occurrence of vehicle loss of control, thereby improving the safety and reliability of vehicle driving, and achieving the purpose of improving vehicle driving safety.

[0030] 4) The present invention can record relevant data before and after the signal failure occurs, including the type, time, frequency and other information of the failure signal. These data are of great significance for subsequent analysis, troubleshooting and algorithm optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of a flow chart of a self-checking method for an automatic driving control system according to an embodiment of the present invention;

[0032] Figure 2 This is a screenshot of the software interface for abnormal vehicle positioning signal frequency according to an embodiment of the present invention;

[0033] Figure 3 This is a screenshot of the software interface of the vehicle planning trajectory signal frequency abnormality according to an embodiment of the present invention;

[0034] Figure 4 This is a screenshot of the software interface for abnormal vehicle chassis signal frequency according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present invention more understandable, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments of the specification. It should be noted that many specific details are set forth in the following description to facilitate a full understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0036] Secondly, "one embodiment" or "an embodiment" in this application refers to a specific feature, structure or characteristic that can be included in at least one implementation of the present invention. The "in one embodiment" and "an embodiment" that appear in different places in this specification do not all refer to the same embodiment, nor are they separate or selective embodiments that are mutually exclusive with other embodiments. The terms "including" and "comprising" indicate the presence of the claimed features, but do not exclude the presence of one or more other features. The term "and / or" used in this application includes any and all combinations of one or more of the relevant listed items.

[0037] The present invention proposes a self-checking method for an automatic driving control system, see Figure 1 , including the following steps:

[0038] Step S1, collect the timestamps of the vehicle positioning signal, the planned trajectory signal and the chassis signal in real time, and calculate the vehicle positioning signal frequency, the planned trajectory signal frequency and the chassis signal frequency by taking the difference between the timestamps and the current time.

[0039] Specifically, the vehicle positioning signal frequency f localization The calculation formula is: Vehicle planning trajectory signal frequency f planning The calculation formula is: Vehicle chassis signal frequency f vehicle The calculation formula is:

[0040] Where, ΔT localization is the time difference between the current moment and the current vehicle positioning signal, ΔT planning is the time difference between the current time and the current vehicle planning trajectory signal, ΔT vehicle is the time difference between the current moment and the current vehicle chassis signal, T current is the timestamp of the current moment; T localization The timestamp of the current vehicle positioning signal; T planning The timestamp of the current vehicle planning trajectory signal; T veh It is the timestamp of the current vehicle chassis signal.

[0041] Step S2: If the vehicle positioning signal frequency, the planned trajectory signal frequency, and the chassis signal frequency exceed the preset normal (ie, the frequency is too high or too low) or there is no update for more than a certain period of time, the signal is determined to be invalid.

[0042] Specifically, the vehicle positioning signal frequency, the planning trajectory signal frequency, and the chassis signal frequency are set to different normal ranges: f localization_min <f localization <f localization_max ;f planning_min <f planning <f planning_max ;f vehic_min <f vehicle <f vehic_max

[0043] Among them, f localization_min is the minimum value of the normal range of the vehicle positioning signal frequency, f localization_max The maximum value of the normal range of the vehicle positioning signal frequency. planning_min is the minimum value of the normal range of the planned trajectory signal frequency, f planning_max f is the maximum value of the normal range of the planned trajectory signal frequency; vehicle_min is the minimum value of the normal range of the chassis signal frequency set by the vehicle, f vehicle_max It is the maximum value of the normal range of the vehicle chassis signal frequency.

[0044] Step S3: monitor the vehicle motion state signal (vehicle speed, acceleration, steering angle, etc.) in real time, and compare the current vehicle motion state signal with the planning signal to comprehensively evaluate the input signal state of the automatic driving control system.

[0045] Step S4: If the difference between the current vehicle motion state signal and the planned signal exceeds a set threshold, the current vehicle motion state signal is determined to be invalid.

[0046] Specifically, let ΔS = |S planning -S vehicle |, Δa=|a planning -a vehicle |, Δθ=|θ planning -θ vehic |;

[0047] Among them, ΔS is the current planned speed S planning and the current vehicle speed S vehicle The difference between the two; Δa is the current planned acceleration a plannung and the current vehicle acceleration a vehicle The difference between Δθ and θ is the current planned steering angle θ. planning and the current vehicle steering angle θ vehicle The difference.

[0048] If ΔS exceeds the failure speed threshold ΔS threshold , Δa exceeds the failure acceleration threshold Δa threshold and / or Δθ exceeds the failure steering angle threshold Δθ threshol , then it is determined that the current vehicle motion state signal is invalid;

[0049] Step S5: As long as any of the vehicle positioning signal, planned trajectory signal, chassis signal, and current vehicle motion state signal fails, that is, the positioning, planned trajectory, or chassis signal frequency is abnormal (such as too high, too low, or not updated for a long time) or the vehicle speed, acceleration, steering angle, and planned value differ from the threshold, the type and time information of the failure signal are output, and the failure level is determined according to the number of failure signals and the deviation from the normal range or threshold. The vehicle speed is reduced until it stops according to the failure level to ensure vehicle safety; or, a takeover prompt is issued to the driver through various means such as sound and light to exit the automatic driving state to ensure that the driver notices the takeover request and takes over the vehicle control in time; otherwise, that is, when there is no failure signal, the vehicle performs automatic driving normally.

[0050] The preset normal range and set threshold can be adjusted through multiple experiments to determine reasonable values. If the range or threshold is too large, the detection sensitivity will decrease, and if the range or threshold is too small, it will easily cause frequent errors.

[0051] After using the control system self-check method of the present invention to intervene in automatic driving, when the positioning module, planning module or the vehicle's own status fails, the control system can immediately issue a warning, and reduce the vehicle speed until it stops according to the level of failure to ensure vehicle safety; or issue a takeover prompt to the driver and ensure that the driver notices the takeover request through various means, which helps to reduce potential risks caused by system failure and avoid the dangerous phenomenon of the vehicle losing control of the lateral and longitudinal control.

[0052] In addition, the collected and monitored signal data will be saved in real time in the form of logs. The monitored data includes information such as signal type, time, frequency, etc., which will be used for subsequent analysis and troubleshooting. In particular, when any of the vehicle positioning signal, planned trajectory signal, chassis signal, and current vehicle motion status signal fails, the relevant data before and after the failure will be marked and recorded, such as Figure 2 , Figure 3 , Figure 4 As shown, in order to subsequently optimize the algorithm and improve system performance.

[0053] The present invention also proposes a computer device, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the self-check method of the automatic driving control system as described above.

[0054] The present invention also proposes a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the self-check method of the automatic driving control system as described above is implemented.

[0055] The present invention also proposes a computer program product, including a computer program, which, when executed by a processor, implements the self-check method of the automatic driving control system as described above.

[0056] It should be noted that Figure 2 , Figure 3 , Figure 4 Screenshots of the software prompt interface when the vehicle positioning signal frequency, the planning trajectory signal frequency and the chassis signal frequency are abnormal are shown. These figures are intended to show the implementation process and detection effect of the present invention in the actual software, rather than directly involving the technical solution of the present invention. These screenshots include color graphics and English expressions, which are the original presentation states of the software interface. These contents are not processed here to present the real state of the actual software. The contents presented are helpful for technicians in this field to more intuitively understand the implementation method of the software using the technical solution of the present invention. The color graphics and English expressions in the figure will not affect the understanding of the technical solution of the present invention itself.

[0057] The present invention has the following beneficial effects:

[0058] 1) The present invention calculates the frequency of vehicle positioning, planned trajectory, and chassis signals in real time by recording the timestamp of each input signal, and compares it with the preset normal range. If the frequency is abnormal (such as too high, too low, or no update for a long time), the signal is determined to be invalid, and continuous monitoring of signal stability is achieved. Compared with traditional periodic inspections, it is more accurate and efficient, and can detect and respond to small changes in signals in a timely manner. At the same time, it does not require the addition of high-precision instruments, which can effectively control costs.

[0059] 2) The present invention not only monitors the vehicle positioning frequency, planned trajectory frequency and chassis signal frequency of the vehicle, but also monitors the vehicle's motion state, including vehicle speed, acceleration, steering angle, etc., forming a comprehensive coverage of the input signal of the automatic driving control system, so as to comprehensively evaluate and determine whether the input signal of the automatic driving control system fails.

[0060] 3) The present invention can also quickly take emergency measures to control the vehicle after detecting that the input signal fails, such as issuing an early warning, reducing the vehicle speed until it stops according to the level of failure, or issuing a takeover prompt to the driver, and ensuring that the driver notices the takeover request in a variety of ways, which helps to reduce potential risks caused by system failure, ensure vehicle safety, and solve most of the problems of vehicle lateral and longitudinal control out of control when the positioning module, planning module or the vehicle's own status fails. It effectively improves the response capability of the automatic driving control system when facing input signal failure, prevents the occurrence of vehicle loss of control, thereby improving the safety and reliability of vehicle driving, and achieving the purpose of improving vehicle driving safety.

[0061] 4) The present invention can record relevant data before and after the signal failure occurs, including the type, time, frequency and other information of the failure signal. These data are of great significance for subsequent analysis, troubleshooting and algorithm optimization.

[0062] Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., parameter values, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in this application. For example, the order or sequence of any process or method steps may be changed or reordered according to alternative embodiments. Therefore, all such modifications are intended to be included within the scope of the present invention. In the claims, any "means plus function" clause is intended to cover the structures described herein that perform the functions, and is not only structurally equivalent but also equivalent structures. Without departing from the spirit and substance of the present invention, those skilled in the art may make various corresponding modifications and changes according to the present invention, but these corresponding modifications and changes should all fall within the scope of protection of the present invention.

Claims

1. A self-checking method for an automatic driving control system, characterized in that: The steps include: Collect the timestamps of vehicle positioning signals, planned trajectory signals and chassis signals in real time, and calculate the vehicle positioning signal frequency, planned trajectory signal frequency and chassis signal frequency by taking the difference between them and the current time. If the vehicle positioning signal frequency, planned trajectory signal frequency, and chassis signal frequency exceed the preset normal range or are not updated for a certain period of time, the corresponding signal is deemed invalid; Monitor the vehicle motion status signal in real time and compare the current vehicle motion status signal with the planned signal; If the difference between the current vehicle motion state signal and the planned signal exceeds a set threshold, the current vehicle motion state signal is determined to be invalid; As long as any of the vehicle positioning signal, planned trajectory signal, chassis signal, and current vehicle motion state signal fails, the type and time information of the failure signal will be output; Otherwise, the vehicle operates autonomously normally.

2. The self-checking method of the automatic driving control system according to claim 1, characterized in that: When any of the vehicle positioning signal, planned trajectory signal, chassis signal, and current vehicle motion status signal fails, the level of failure is determined based on the number of failed signals and the deviation from the normal range or threshold, and the vehicle speed is reduced until it stops according to the level of failure.

3. The self-checking method of the automatic driving control system according to claim 1, characterized in that: When any of the vehicle positioning signal, planned trajectory signal, chassis signal, and current vehicle motion status signal fails, a takeover prompt is issued to the driver to exit the automatic driving state.

4. The self-checking method of the automatic driving control system according to claim 1, characterized in that: It also includes saving the collected and monitored signal data in the form of a log, wherein the monitored data includes the type, time, and frequency of the signal.

5. The self-checking method of the automatic driving control system according to claim 1, characterized in that: The vehicle positioning signal frequency f localization The calculation formula is: The vehicle planning trajectory signal frequency f planning The calculation formula is: The vehicle chassis signal frequency f vehicle The calculation formula is: Where, ΔT localization is the time difference between the current moment and the current vehicle positioning signal, ΔT planning is the time difference between the current time and the current vehicle planning trajectory signal, ΔT vehicle is the time difference between the current moment and the current vehicle chassis signal, T current is the timestamp of the current moment; T localization The timestamp of the current vehicle positioning signal; T planning The timestamp of the current vehicle planning trajectory signal; T vehicle It is the timestamp of the current vehicle chassis signal.

6. The self-checking method of the automatic driving control system according to claim 1, characterized in that: The vehicle motion state signal includes vehicle speed, acceleration, and steering angle.

7. The self-checking method of the automatic driving control system according to claim 6, characterized in that: When determining whether the current vehicle motion state signal is invalid, the specific judgment is: if ΔS exceeds the invalid vehicle speed threshold ΔS threshol , Δa exceeds the failure acceleration threshold Δa threshol and / or Δθ exceeds the failure steering angle threshold Δθ threshol , then it is determined that the current vehicle motion state signal is invalid; Among them, ΔS is the difference between the current planned speed and the current vehicle speed, Δa is the difference between the current planned acceleration and the current vehicle acceleration, and Δθ is the difference between the current planned steering angle and the current vehicle steering angle.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the self-test method of the automatic driving control system according to any one of claims 1 to 7.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the self-check method of the automatic driving control system as described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by the processor, the self-check method of the automatic driving control system as described in any one of claims 1 to 7 is implemented.

Images