Pothole detection methods, driving control methods and vehicles

Abstract

This application discloses a pothole detection method, a vehicle control method, and a vehicle. The pothole detection method includes: during vehicle operation, acquiring the vehicle's vertical acceleration and attitude angle at a preset frequency; determining whether the vertical acceleration undergoes a sudden change, and if the duration of this change satisfies a first preset duration range, then determining that a vertical acceleration sudden change has occurred; determining whether the attitude angle undergoes a sudden change, and if the duration of this change satisfies a second preset duration range, then determining that an attitude angle sudden change has occurred; determining whether the vertical acceleration sudden change and the attitude angle sudden change occur simultaneously, and if they occur simultaneously, then determining that the vehicle has encountered a pothole, and uploading pothole information to a backend server, wherein the pothole information includes the geographical location of the pothole. The technical solution provided by this application can improve detection accuracy.

Description

Technical Field

[0001] This application belongs to the field of vehicle technology, and in particular relates to a pothole detection method, a driving control method, and a vehicle. Background Technology

[0002] Potholes are common road defects that pose a threat to driving safety, especially for autonomous vehicles. Due to the lack of real-time driver intervention, failure to detect and avoid potholes in advance may lead to vehicle instability and danger, affecting driving safety.

[0003] However, the accuracy of existing pothole detection technology needs to be improved to enhance driving safety. For example, existing pothole detection technology is affected by water accumulation and is not easy to detect. Therefore, this application proposes a pothole detection method that can improve detection accuracy. Summary of the Invention

[0004] The embodiments of this application provide a pothole detection method, a driving control method, and a vehicle, which can solve the problem of insufficient accuracy in pothole detection.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] According to one aspect of the embodiments of this application, a pothole detection method is provided, applied to a vehicle, the method comprising: During vehicle operation, the vertical acceleration and attitude angle of the vehicle are acquired according to a preset frequency. Determine whether the vertical acceleration has a sudden change, and whether the duration of the sudden change in vertical acceleration meets the first preset duration range. If so, determine that a sudden change in vertical acceleration has occurred. Determine whether the attitude angle has changed abruptly, and whether the duration of the change in attitude angle meets the second preset duration range. If so, determine that an attitude angle change has occurred. Determine whether the vertical acceleration change and the attitude angle change occur simultaneously. If they occur simultaneously, it is determined that the vehicle has encountered a pothole. Upload the pothole information to the backend server. The pothole information includes the geographical location of the pothole.

[0007] In some embodiments of this application, determining whether the vertical acceleration undergoes a sudden change includes: Obtain the acceleration difference between the current vertical acceleration and the previous vertical acceleration; Determine whether the acceleration difference exceeds a first real-time threshold. If it does, determine that the vertical acceleration has abruptly changed; if it does not, determine that the vertical acceleration has not abruptly changed. Before determining whether the acceleration difference exceeds the first real-time threshold, the method further includes: Based on the vehicle's current speed and a preset first proportional coefficient, a first dynamic adjustment value is obtained; The first real-time threshold is obtained based on the first dynamic adjustment value and the first basic threshold.

[0008] In some embodiments of this application, the attitude angle includes pitch angle and roll angle, and determining whether the attitude angle undergoes a sudden change includes: Obtain the pitch angle difference between the current pitch angle value and the previous pitch angle value; Obtain the difference between the current roll angle value and the previous roll angle value; If the pitch angle difference exceeds the second real-time threshold, or the roll angle difference exceeds the third real-time threshold, then it is determined that the attitude angle has abruptly changed. If the pitch angle difference does not exceed the second real-time threshold and the roll angle difference does not exceed the third real-time threshold, then it is determined that the attitude angle has not changed abruptly.

[0009] In some embodiments of this application, after obtaining the pitch angle difference between the current value and the previous value, the method further includes: The second dynamic adjustment value is obtained based on the vehicle's current speed and a preset second proportional coefficient; The second real-time threshold is obtained based on the second dynamic adjustment value and the second basic threshold. After obtaining the difference between the current roll angle value and the previous roll angle value, the method further includes: The third dynamic adjustment value is obtained based on the vehicle's current speed and the preset third proportional coefficient. The third real-time threshold is obtained based on the third dynamic adjustment value and the third basic threshold.

[0010] In some embodiments of this application, determining whether the vertical acceleration abrupt change and the attitude angle abrupt change occur simultaneously includes: Obtain the time difference between adjacent occurrences of the vertical acceleration abrupt change and the attitude angle abrupt change; If the time difference is less than or equal to the preset time difference, then it is determined that the vertical acceleration change and the attitude angle change occur synchronously. If the time difference is greater than the preset time difference, it is determined that the vertical acceleration change and the attitude angle change did not occur synchronously.

[0011] In some embodiments of this application, the method further includes: If the vertical acceleration change and the attitude angle change do not occur simultaneously, determine whether the current geographical location has a road hole mark on the cloud map. If so, upload the road hole-free information of the current geographical location to the backend server.

[0012] According to one aspect of the embodiments of this application, a pothole detection method is provided, applied to a backend server, the method comprising: Receive road pothole information uploaded by vehicles, wherein the road pothole information includes the geographical location of the road pothole; If the geographical location contained in the pothole information is not marked as a pothole in the cloud map, then starting from the first pothole information of the geographical location without a pothole mark, it is determined whether a first preset number of vehicles have uploaded pothole information of the same geographical location without a pothole mark. If a first preset number of vehicles upload pothole information at the same unmarked geographical location, then add a pothole marker to the corresponding geographical location on the cloud map.

[0013] In some embodiments of this application, the method further includes: If no pothole information corresponding to the geographical location marked with a pothole is received in the cloud map within the first preset time period, then the pothole mark for the geographical location marked with a pothole is deleted from the cloud map; wherein, the pothole information is determined by the vehicle according to the method described above; Alternatively, if within a second preset time period, a second preset number of vehicles upload pothole-free information to the same geographical location marked with a pothole in the cloud map, and no pothole information is received from the same geographical location marked with a pothole, then the pothole mark for the same geographical location marked with a pothole is deleted from the cloud map; wherein, the pothole-free information is determined by the vehicle according to the method described above.

[0014] According to one aspect of the embodiments of this application, a vehicle control method is provided, applied to a vehicle, the method comprising: When the vehicle is in autonomous driving mode, information about potholes ahead of the vehicle is obtained from a cloud map with pothole markings, and when the vehicle travels to a preset distance from the geographical location of the pothole ahead, a pothole avoidance path is generated and executed.

[0015] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, wherein at least one piece of program code is stored therein, the at least one piece of program code being loaded and executed by a processor to implement the method described above.

[0016] According to one aspect of the embodiments of this application, a vehicle is provided, the vehicle including one or more processors and one or more memories, the one or more memories storing at least one piece of program code, the at least one piece of program code being loaded and executed by the one or more processors to implement the method as described above.

[0017] Based on the above solution, the technical solution provided in this application has at least the following advantages and advancements: This application acquires vertical acceleration and attitude angle in real time during vehicle operation. By determining whether the vertical acceleration undergoes abrupt changes and whether the duration of the change meets a first preset time range, and by determining whether the attitude angle undergoes abrupt changes and whether the duration of the change meets a second preset time range, the combined detection of abrupt changes in vertical acceleration and attitude angle can reduce misjudgments caused by road bumps and electromagnetic interference, significantly improving the accuracy of pothole detection and avoiding misjudgments and missed detections that are prone to occur with single-parameter judgment. Furthermore, the pothole information, including geographical location, is uploaded to the backend server, enabling real-time sharing and map marking of pothole information. This provides reliable road condition information for autonomous driving path planning, allowing autonomous vehicles to plan pothole avoidance paths in advance, effectively reducing the risks caused by potholes and improving the safety of autonomous driving.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 Schematic diagram of the pothole detection method provided in the embodiments of this application Figure 1 ; Figure 2 Schematic diagram of the pothole detection method provided in the embodiments of this application Figure 2 ; Figure 3 Schematic diagram of the pothole detection method provided in the embodiments of this application Figure 3 ; Figure 4 Schematic diagram of the pothole detection method provided in the embodiments of this application Figure 4 ; Figure 5 Schematic diagram of the pothole detection device provided in the embodiments of this application Figure 1 ; Figure 6Schematic diagram of the pothole detection device provided in the embodiments of this application Figure 2 ; Figure 7 This is a schematic diagram of the structure of a vehicle computer system provided in an embodiment of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0022] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0023] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0024] It should also be noted that the terms "first," "second," etc., used in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such uses of the terms can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described.

[0025] Road conditions such as potholes and water accumulation affect driving safety and are difficult to predict, especially for vehicles in autonomous driving mode. When sudden road conditions occur, the driver cannot intervene immediately, which may lead to vehicle instability and dangerous situations. This application provides a method for real-time detection of shared pothole information, which facilitates autonomous vehicles to plan routes in advance to avoid potholes and improve driving safety.

[0026] Figure 1 Schematic diagram of the pothole detection method provided in the embodiments of this application Figure 1 ,like Figure 1 As shown, applied to a vehicle, the method includes: S101. During vehicle operation, the vertical acceleration and attitude angle of the vehicle are obtained according to a preset frequency.

[0027] During vehicle operation, the vehicle's vertical acceleration and attitude angle are acquired in real time at a preset frequency. Vertical acceleration, the acceleration perpendicular to the road surface, is the core parameter for identifying pothole impacts. Potholes cause significant vertical bumps and impacts to the vehicle body, resulting in changes in vertical acceleration. The attitude angle reflects changes in vehicle tilt and can be used as an auxiliary parameter for pothole identification, combined with vertical acceleration to distinguish potholes from ordinary bumps. The preset frequency can be 100Hz. Simultaneously, the vehicle's positioning module can also collect geographical location (geographic coordinates) at a preset frequency, which can be 10Hz.

[0028] This embodiment selects vertical acceleration and attitude angle as real-time observation data to provide complete data support for subsequent pothole detection. The device for collecting data (vertical acceleration and attitude angle) can be an inertial measurement unit (IMU) on the vehicle. After the IMU collects the data, it transmits it to the vehicle's onboard processor, which is responsible for the subsequent data analysis process. The pothole detection process in this application can be performed under manual driving or autonomous driving conditions.

[0029] Optionally, the timing for starting data (vertical acceleration and attitude angle) collection can be after the vehicle starts and enters stable driving. For example, when the on-board processor detects that the vehicle has started and begun to enter stable driving, it initiates a command to control the inertial measurement unit to acquire the vehicle's vertical acceleration and attitude angle at a preset frequency. After the inertial measurement unit collects the data, it feeds the data back to the on-board processor in real time.

[0030] To ensure the accuracy of subsequent data processing, the data can be filtered before determining whether a sudden change has occurred.

[0031] S102. Determine whether the vertical acceleration has a sudden change, and whether the duration of the vertical acceleration change meets the first preset duration range. If so, determine that a vertical acceleration change has occurred.

[0032] Vertical acceleration is the core parameter for pothole detection, and its abrupt change is the primary characteristic of pothole existence.

[0033] If the sudden change in vertical acceleration lasts for too short a period, it may be caused by minor road impacts (such as road cracks) or noise from signal acquisition equipment (such as inertial measurement units), which are insufficient to indicate that the vehicle has encountered a pothole. Therefore, a reasonable lower limit can be set for the duration of the sudden change in vertical acceleration. It should be noted that minor road impacts or noise from signal acquisition equipment do not necessarily cause a sudden change in vertical acceleration.

[0034] If the duration of the abrupt change in vertical acceleration is too long, it may indicate the presence of continuous road surface influences (such as encountering gravel roads, speed bumps, or inclines / declines), exceeding the scope of pothole detection. Therefore, a reasonable upper limit can be set for the duration of the abrupt change in vertical acceleration. The lower and upper limits together constitute the first preset duration range; for example, the lower limit could be 50 ms and the upper limit 300 ms. Of course, if there is a need to detect road surface conditions beyond the upper limit, a further branch can be set to determine whether the duration of the abrupt change in vertical acceleration exceeds a third preset duration range. The third preset duration range may only have a lower limit, and this lower limit must be greater than the upper limit of the first preset duration range. If the duration of the abrupt change in vertical acceleration is greater than or equal to the lower limit of the first preset duration range and less than the upper limit, then it is determined to be within the first preset duration range.

[0035] When the duration of the abrupt change in vertical acceleration is exactly within the first preset duration, it is determined that the abrupt change in vertical acceleration corresponding to the pothole may indicate the presence of a pothole.

[0036] S103. Determine whether the attitude angle has changed abruptly, and whether the duration of the change in attitude angle meets the second preset duration range. If so, determine that an attitude angle change has occurred.

[0037] Attitude angle is a key auxiliary parameter for pothole detection, and its abrupt changes can serve as evidence of the existence of potholes.

[0038] If the duration of a sudden change in attitude angle is too short, it may be caused by minor road surface disturbances (such as minor road undulations) or noise from signal acquisition equipment (such as inertial measurement units). These factors are insufficient to indicate a substantial change in vehicle attitude caused by potholes. Therefore, a reasonable lower limit can be set for the duration of the sudden change in attitude angle. It should be noted that minor road surface disturbances or noise from signal acquisition equipment do not necessarily cause a sudden change in attitude angle.

[0039] If the duration of the sudden change in attitude angle is too long, it may be that the vehicle has entered a state of continuous attitude change (such as continuous turning, continuous slope driving, or vehicle load redistribution). These situations are beyond the scope of transient attitude changes caused by potholes and should not be misjudged as pothole characteristics. Therefore, a reasonable upper limit can be set for the duration of the sudden change in attitude angle.

[0040] The lower and upper limits together constitute the second preset duration range. For example, the lower limit can be set to 50ms and the upper limit can be set to 400ms; of course, the specific values ​​can be calibrated based on vehicle dynamics characteristics, sensor performance, and actual road test data.

[0041] When the duration of a sudden change in attitude angle falls exactly within the second preset duration range, a sudden change in attitude angle corresponding to a pothole is identified. This can be used as an auxiliary confirmation criterion for pothole detection and can be integrated with information on sudden changes in vertical acceleration to improve the accuracy and robustness of pothole identification. For example, if the duration of a sudden change in vertical acceleration is greater than or equal to the lower limit of the second preset duration range and less than the upper limit, it is determined to be within the second preset duration range. If there are multiple attitude angles, any one of them can fall within its corresponding second preset duration range. The upper and lower limits of the second preset duration range for different attitude angles can be the same or different.

[0042] S104. Determine whether the vertical acceleration change and the attitude angle change occur simultaneously. If they occur simultaneously, determine that the vehicle has encountered a pothole. Upload the pothole information to the backend server. The pothole information includes the geographical location of the pothole.

[0043] If a sudden change in vertical acceleration and a sudden change in attitude angle occur simultaneously within a short period of time, the presence of a pothole can be accurately determined. For example, if a sudden change in vertical acceleration is detected at the current moment, and a sudden change in attitude angle is detected within a preset time period after the detection of the sudden change in vertical acceleration, it can be determined that the vehicle has encountered a pothole.

[0044] For example, determining whether the vertical acceleration abrupt change and the attitude angle abrupt change occur simultaneously includes: Obtain the time difference between adjacent occurrences of the vertical acceleration abrupt change and the attitude angle abrupt change; If the time difference is less than or equal to the preset time difference, then it is determined that the vertical acceleration change and the attitude angle change occur synchronously. If the time difference is greater than the preset time difference, it is determined that the vertical acceleration change and the attitude angle change did not occur synchronously.

[0045] "Adjacent" refers to the fact that the detected vertical acceleration change and attitude angle change are adjacent or closest in timestamps. The time difference between the occurrence of the vertical acceleration change and attitude angle change is determined. The magnitude of the time difference can determine whether the vertical acceleration change and attitude angle change occur synchronously. If the time difference is less than or equal to the preset time difference, it means that the vertical acceleration change and attitude angle change occurred at close time and can be regarded as synchronous change. If the time difference is greater than the preset time difference, it means that the vertical acceleration change and attitude angle change occurred at far time and can be regarded as asynchronous change.

[0046] If a sudden change occurs, it can be determined that there is a pothole. The vehicle can upload the pothole information, including its geographical location, to the backend server. The backend server can then mark the pothole on the cloud map so that the vehicle in autonomous driving mode can refer to the cloud map to avoid it and ensure driving safety.

[0047] The absence of a synchronous sudden change could be due to encountering normal uphill or downhill situations, in which case pothole information does not need to be reported. Alternatively, when a vehicle passes through a location where a pothole is recorded on the cloud map, the same detection process described above for determining whether a synchronous vertical acceleration change and attitude angle change occurred can be used to verify whether the pothole still exists. For example, the method also includes: If the vertical acceleration change and the attitude angle change do not occur simultaneously, determine whether the current geographical location has a road hole mark on the cloud map. If so, upload the road hole-free information of the current geographical location to the backend server.

[0048] If no simultaneous vertical acceleration change or attitude angle change occurs, determine whether the current geographical location has a pothole marker on the cloud map. If the current geographical location has a pothole marker on the cloud map, the pothole-free information of the current geographical location can be uploaded to the backend server so that the backend server can update the road conditions in real time. If the current geographical location does not have a pothole marker on the cloud map, there is no need to report information to the backend server.

[0049] The conditions for determining whether a vehicle is free of potholes are not limited to the absence of simultaneous vertical acceleration and attitude angle changes; they can also include the absence of vertical acceleration and / or attitude angle changes.

[0050] Figure 2 Schematic diagram of the pothole detection method provided in the embodiments of this application Figure 2 ,like Figure 2As shown, the method includes: S201. Obtain the acceleration difference between the current vertical acceleration and the previous vertical acceleration.

[0051] S202. Determine whether the acceleration difference exceeds a first real-time threshold. If it does, determine that the vertical acceleration has abruptly changed. If it does not, determine that the vertical acceleration has not abruptly changed.

[0052] Calculate the changes in vertical acceleration to determine if there is any abrupt change in vertical acceleration: Obtain the difference between the vertical acceleration at the current moment and the vertical acceleration at the previous moment. If the acceleration difference exceeds (is greater than or equal to) the first real-time threshold, it indicates that a sudden change has occurred in the vertical acceleration. If the acceleration difference does not exceed (is less than) the first real-time threshold, it indicates that no sudden change has occurred in the vertical acceleration. The data change is within the normal range and will not be identified as a sudden change in the vertical acceleration, thus avoiding misjudgment.

[0053] To more accurately identify abrupt changes in vertical acceleration, the first real-time threshold used to determine the acceleration difference is dynamically changed: For example, before determining whether the acceleration difference exceeds a first real-time threshold, the method further includes: Based on the vehicle's current speed and a preset first proportional coefficient, a first dynamic adjustment value is obtained; The first real-time threshold is obtained based on the first dynamic adjustment value and the first basic threshold.

[0054] Figure 3 Schematic diagram of the pothole detection method provided in the embodiments of this application Figure 3 ,like Figure 3 As shown, the attitude angles include pitch angle and roll angle, and the method includes: S301. Obtain the pitch angle difference between the current pitch angle value and the previous pitch angle value.

[0055] S302. Obtain the difference between the current roll angle value and the previous roll angle value.

[0056] S303. If the pitch angle difference exceeds the second real-time threshold, or the roll angle difference exceeds the third real-time threshold, then it is determined that the attitude angle has abruptly changed.

[0057] S304. If the pitch angle difference does not exceed the second real-time threshold and the roll angle difference does not exceed the third real-time threshold, then it is determined that the attitude angle has not changed abruptly.

[0058] In this embodiment, when calculating the changes in attitude angles and determining whether there is a sudden change in attitude angles, pitch angle and roll angle are used. That is, this application can determine whether a pothole has been encountered by checking whether there is a sudden change in vertical acceleration, or whether any type of attitude angle, such as pitch angle or roll angle, has a sudden change.

[0059] For each type of attitude angle (this embodiment uses two types, such as pitch and roll): the attitude angle difference between the current value and the previous value is obtained. If the difference of any type of attitude angle exceeds (is greater than or equal to) its corresponding real-time threshold, it indicates that a sudden change in the attitude angle has occurred. If neither type of attitude angle difference exceeds its corresponding real-time threshold, it indicates that neither attitude angle has experienced a sudden change. If neither type of attitude angle difference exceeds its corresponding real-time threshold, it indicates that the attitude angle change is within the normal range of data variation.

[0060] To more accurately identify attitude angle abrupt changes, the real-time thresholds (second and third real-time thresholds) used to determine attitude angle differences (pitch and roll differences) are dynamically changed: For example, after obtaining the pitch angle difference between the current value and the previous value, the method further includes: The second dynamic adjustment value is obtained based on the vehicle's current speed and a preset second proportional coefficient; The second real-time threshold is obtained based on the second dynamic adjustment value and the second basic threshold. After obtaining the difference between the current roll angle value and the previous roll angle value, the method further includes: The third dynamic adjustment value is obtained based on the vehicle's current speed and the preset third proportional coefficient. The third real-time threshold is obtained based on the third dynamic adjustment value and the third basic threshold.

[0061] Figure 4 Schematic diagram of the pothole detection method provided in the embodiments of this application Figure 4 ,like Figure 4 As shown, applied to a backend server, the method includes: S401. Receive road pothole information uploaded by the vehicle, wherein the road pothole information includes the geographical location of the road pothole.

[0062] S402. If the geographical location contained in the pothole information is not marked as a pothole in the cloud map, then starting from the first pothole information of the geographical location without a pothole mark, determine whether a first preset number of vehicles have uploaded pothole information of the same geographical location without a pothole mark.

[0063] S403. If a first preset number of vehicles upload pothole information at the same unmarked geographical location, then add a pothole marker to the corresponding geographical location on the cloud map.

[0064] The backend server can receive road pothole information uploaded by each vehicle in real time, and the road pothole information includes the geographical location of the road pothole. If the geographical location included in the road pothole information already has a corresponding road pothole mark in the same geographical location in the cloud map, the road pothole information can be temporarily stored, and the upload time corresponding to the road pothole information can be deleted. For example, road pothole information older than 7 days can be deleted every 7 days.

[0065] If the location containing the pothole information is not marked as a pothole in the same location on the cloud map, then starting from the first pothole information received in chronological order for that location without a pothole mark, it is determined whether a first preset number of vehicles have uploaded pothole information to the same location without a pothole mark. If so, a pothole mark is added to that location on the cloud map. For example, if the location containing the pothole information is X, and it is determined that there is no pothole mark at location X on the cloud map, then starting from the first pothole information received at location X in chronological order, it is determined whether K vehicles have uploaded pothole information at location X. If so, a pothole mark is added to location X on the cloud map.

[0066] The backend server can not only add pothole markers based on pothole information, but also delete pothole markers under preset conditions: For example, the method also includes: If no pothole information corresponding to the geographical location marked with a pothole is received in the cloud map within the first preset time period, then the pothole mark for the geographical location marked with a pothole is deleted from the cloud map; wherein, the pothole information is determined by the vehicle according to the method described above; Alternatively, if within a second preset time period, a second preset number of vehicles upload pothole-free information to the same geographical location marked with a pothole in the cloud map, and no pothole information is received from the same geographical location marked with a pothole, then the pothole mark for the same geographical location marked with a pothole is deleted from the cloud map; wherein, the pothole-free information is determined by the vehicle according to the method described above.

[0067] The first preset condition: A first preset time period is set in advance. Within each first preset time period, the location that already has a pothole mark is checked to see if pothole information has been received. If not, the pothole mark corresponding to the location with the pothole mark is deleted. For example, if the first preset time period is 3 days, and location A that already has a pothole mark has not received pothole information containing location A within the past 3 days, then the pothole mark for location A on the cloud map is deleted. If location B that already has a pothole mark has not received pothole information containing location B within the past 3 days, then the pothole mark for location B on the cloud map does not need to be deleted.

[0068] The second preset condition: A second preset time period is set in advance. Within each second preset time period, it is checked whether a second preset number of vehicles have uploaded pothole-free information from the same geographical location marked with a pothole in the cloud map, and whether no pothole information has been uploaded by any vehicle from the same geographical location marked with a pothole. If both conditions are met, the pothole mark for the same geographical location marked with a pothole is deleted from the cloud map. For example, if the second preset time period is 5 days, and in the past 5 days, geographical location C marked with a pothole has received pothole-free information from W vehicles that includes geographical location C, and no pothole information has been uploaded by any vehicle that includes geographical location C, then the pothole mark for geographical location C is deleted from the cloud map. If the above conditions are not met, i.e., no pothole-free information from W vehicles that includes geographical location C is received, or pothole information from vehicles that includes geographical location C is received, then the pothole mark for geographical location C is not deleted from the cloud map.

[0069] The preset values ​​for the first and second preset time periods can be related to road traffic volume. The backend server manages roads by region. For regions with high traffic volume, the preset time period can be set to a smaller value (which can speed up the calculation response). For regions with low traffic volume, the preset time period can be set to a larger value (which can improve the calculation accuracy).

[0070] The preset values ​​for the first and second preset quantities can also be related to road traffic volume. The backend server manages roads by region. For regions with high traffic volume, the preset quantity can be set to a smaller value (which can speed up the calculation response). For regions with low traffic volume, the preset quantity can be set to a larger value (which can improve the calculation accuracy).

[0071] This demonstrates that the backend server can not only add pothole markers to the cloud map in real time, but also delete pothole markers in real time, ensuring that the pothole markers on the cloud map are effective in real time and accurately recorded, so that vehicles in autonomous driving mode can refer to them.

[0072] This embodiment provides a driving control method applied to a vehicle. The method includes: when the vehicle is in an autonomous driving state, obtaining information about potholes ahead of the vehicle from a cloud map with pothole markings, and generating and executing a pothole avoidance path when the vehicle travels to a preset distance from the geographical location of the pothole ahead.

[0073] When the vehicle is in autonomous driving mode, it can obtain the geographical location of known potholes from the cloud map in real time, and automatically plan a route to avoid the pothole when the vehicle is at a preset distance from the geographical location of the pothole ahead, so as to ensure safe driving.

[0074] The following is a complete implementation example of the process for detecting and clearing potholes: 1. Real-time data acquisition: During vehicle operation, the IMU acquires vertical acceleration, pitch angle, and roll angle at a frequency of 100Hz, and the positioning module acquires geographic coordinates at a frequency of 10Hz. All data is continuously transmitted to the onboard processor.

[0075] 2. Pothole Detection and Judgment: The onboard processor performs filtering preprocessing on the collected data, calculates the abrupt changes in various parameters, and, combined with dynamic thresholds and abrupt change duration conditions, determines whether a pothole exists at the current location. Filtering preprocessing can remove interference using Kalman filtering to obtain smoothed parameter data.

[0076] 1) Vertical acceleration is the core parameter for pothole detection, and its abrupt change is the primary characteristic of pothole existence. The processing logic is as follows: Abrupt change judgment criteria: The on-board processor performs Kalman filtering preprocessing on the vertical acceleration data collected by the IMU (100Hz, i.e., one set of data is collected every 10ms) to remove interference from slight road bumps and sensor noise, and calculates the abrupt change value Δz (acceleration difference) between two adjacent sets of data; when the absolute value of Δz is greater than the vehicle speed adaptive dynamic threshold Zth (first real-time threshold), and the duration of the abrupt change is ≥50ms, it is judged as a vertical acceleration abrupt change.

[0077] Vehicle speed adaptive dynamic threshold Zth: At different vehicle speeds, the vertical acceleration abruptly changes significantly when a vehicle goes over a pothole (the higher the vehicle speed, the greater the impact on the vehicle body when going over a pothole, and the greater the abrupt change). Therefore, a fixed threshold is abandoned, and an adaptive threshold design is adopted. Specifically, the first real-time threshold is obtained using the following formula: Zth = k × v² + Z0 Where: k is the first proportionality coefficient, which, after extensive real-vehicle testing and calibration, ranges from 0.0015 to 0.0025 m / (s). 4The first proportional coefficient can be preset to any value within this range; v is the real-time vehicle speed (synchronously collected by the positioning module or onboard speed sensor); Z0 is the basic threshold, with a value ranging from 0.8 to 1.2 m / s², corresponding to the minimum sudden change amplitude at low speeds. This formula enables dynamic adjustment of the first real-time threshold at different vehicle speeds, ensuring that shallow potholes are not missed at low speeds (e.g., 10 km / h) and that no misjudgments are made due to bumps at high speeds (e.g., 120 km / h). s is for seconds, m is for meters, km is for kilometers, and h is for hours.

[0078] 2) Abrupt changes in pitch or roll angles are key auxiliary parameters for distinguishing between potholes and disturbances. These abrupt changes occur simultaneously with abrupt changes in vertical acceleration. The processing logic is as follows: Criteria for determining abrupt changes: Similarly, pitch and roll angle data are pre-processed with filtering, and the abrupt change values ​​Δa (pitch angle difference) and Δp (roll angle difference) of adjacent data sets are calculated. When the absolute value of Δa is greater than the attitude angle adaptive threshold Ath (second real-time threshold), or the absolute value of Δp is greater than the attitude angle adaptive threshold Pth (third real-time threshold), and the attitude angle abrupt change is synchronized with the vertical acceleration abrupt change in time (time difference ≤ 20ms, since the IMU acquisition frequency is 100Hz, parameter changes within 20ms can be considered synchronized), and the duration of the attitude angle abrupt change is ≥ 50ms, it is determined to be an attitude angle abrupt change.

[0079] Attitude angle adaptive threshold design: Similar to the vertical acceleration threshold logic, the attitude angle threshold is also related to vehicle speed, and the specific formula is as follows: Ath = m × v + A0 Pth = n × v + P0 Wherein, m is the second proportional coefficient, with a value ranging from 0.002 to 0.003 ° / (s•km); n is the third proportional coefficient, with a value ranging from 0.0025 to 0.0035 ° / (s•km); v is the real-time vehicle speed; A0 is the second basic threshold, with a value ranging from 0.3 to 0.5°; P0 is the third basic threshold, with a value ranging from 0.4 to 0.6°; and ° represents the angle. Through dynamic threshold adjustment, the system ensures accurate determination of sudden changes in attitude angle at different vehicle speeds, avoiding misjudgments caused by slight road inclination or steering.

[0080] 3) Dual mutation synergistic determination process Main parameter determination: Calculate the vertical acceleration mutation value Δz and compare it with the vehicle speed adaptive threshold Zth. If |Δz|>Zth and the duration is ≥50ms, it is determined to be a vertical acceleration mutation and enters the auxiliary parameter determination stage; if it does not meet the requirements, continue monitoring; |·| is the absolute value. Auxiliary parameter determination: Simultaneously calculate the pitch angle mutation value Δa and the roll angle mutation value Δp, and compare them with Ath and Pth respectively. If |Δa|>Ath or |Δp|>Pth, and the mutation is synchronized with the vertical acceleration mutation (time difference ≤20ms) and the duration is ≥50ms, it is determined to be an attitude angle mutation. Final determination: If both vertical acceleration change and attitude angle change (either pitch angle change or roll angle change) are satisfied, then a pothole is determined to exist at the current location; if only a single parameter change of vertical acceleration change or attitude angle change is satisfied, or if the change lasts for less than 50ms, it is determined to be interference (such as road bumps and electromagnetic interference), and the pothole marking process is not triggered.

[0081] It is evident that the determination of the above synchronization conditions can also be performed during attitude angle abrupt changes. Correspondingly, the pothole detection process can also be: During vehicle operation, the vertical acceleration and attitude angle of the vehicle are acquired according to a preset frequency. Determine whether the vertical acceleration has a sudden change, and whether the duration of the sudden change in vertical acceleration meets the first preset duration range. If so, determine that a sudden change in vertical acceleration has occurred. If a vertical acceleration change is determined, then determine whether the attitude angle changes within a preset time length (the preset time length is set similarly to the preset time difference, both of which can be set to 20ms) of the vertical acceleration change, and the duration of the attitude angle change satisfies the second preset time range. If the attitude angle changes abruptly within a preset time period, and the duration of the change in attitude angle meets the second preset time range, then it is determined that an attitude angle change has occurred, and it is determined that the vertical acceleration change and the attitude angle change occur simultaneously. If the vertical acceleration change and the attitude angle change occur simultaneously, it is determined that the vehicle has encountered a pothole. The pothole information is then uploaded to the backend server, whereby the pothole information includes the geographical location of the pothole.

[0082] At this point, the timing of synchronization differs from the above embodiments, but other processing methods, such as the mutation determination method and the mutation duration determination method, are the same as those in the above embodiments.

[0083] 3. Pothole Information Upload and Map Marking: If a pothole is detected, the vehicle processor packages the pothole information and uploads it to the backend via the 5G module; after the backend verifies the validity of the pothole through multiple vehicles, it updates the map in real time and stores it permanently (upload pothole information).

[0084] 4. Autonomous Driving Pothole Avoidance: During path planning, the autonomous vehicle calls upon background pothole map data to generate and execute a pothole avoidance path; during the journey, it receives real-time updates of pothole information from the background and dynamically adjusts the path. Warning Range: Can be set to 300m before the pothole, which can be set in combination with the vehicle's speed and the autonomous driving system's path planning response time to ensure that the autonomous vehicle has sufficient time to adjust the path.

[0085] 5. Reporting of No Abnormal Traffic Data: When other vehicles pass through the pothole area, if no change in vertical acceleration or attitude angle is detected, the on-board processor automatically generates a report of no abnormal traffic (no pothole information) and uploads it to the backend; the backend records this data in the traffic statistics log of the corresponding pothole.

[0086] 6. Dynamic removal of pothole markers: The background continuously collects traffic data. When R vehicles have uploaded no abnormal traffic reports for a consecutive period, and no vehicle reports a pothole during the period, the pothole marker in the map is automatically removed, completing the closed loop.

[0087] R for vehicles: The default value is R=5, which is set according to the average daily traffic flow on urban roads. For road sections with high traffic flow, R can be reduced (e.g., R=3) to speed up the labeling and updating efficiency. For road sections with low traffic flow, R can be increased (e.g., R=8) to avoid false deletion due to insufficient sample size.

[0088] During the experimental testing, this application was based on real-vehicle test data of 10 different vehicle types (sedans, SUVs, MPVs) with road potholes of varying depths (5-50mm) to ensure coverage of most real-world road pothole scenarios. This also eliminated interference from normal road conditions such as minor bumps and road seams. During the testing process, a good proportional coefficient and basic threshold were established for calculating real-time thresholds. The preset number of vehicles can also be of different types.

[0089] In summary, the composite judgment logic of vertical acceleration change and attitude angle change (either pitch angle change or roll angle change) in this application, combined with the vehicle speed adaptive dynamic threshold design, not only avoids the misjudgment caused by road bumps and electromagnetic interference that are easily affected by single parameter detection, but also eliminates instantaneous false acquisition by verifying the duration of the change, which significantly improves the accuracy of pothole identification and can stably identify potholes of different depths and locations.

[0090] Breaking away from the limitations of traditional fixed-time pothole markings, this design adopts a default long-term retention approach to ensure the continuous reliability of autonomous driving path planning. At the same time, it uses dynamic clearing conditions (such as multiple vehicles reporting no pothole information) to clear currently invalid pothole markings, achieving automated and intelligent updates of pothole markings. This avoids the impact of residual markings after pothole repair on path planning and also prevents erroneous clearing due to insufficient sample size, ensuring the real-time performance and accuracy of map data.

[0091] A full-link vehicle-cloud collaborative architecture is constructed, encompassing vehicle-mounted detection, backend verification, map updates, and pothole avoidance planning. Real-time uploading and sharing of pothole information is achieved through 5G low-latency communication. A customized data interaction interface is designed for autonomous driving scenarios, providing auxiliary data such as lane distribution and avoidance path suggestions while pushing pothole coordinates. This directly provides constraint support for autonomous driving path planning and fills the technical gap in connecting pothole detection with autonomous driving decision-making.

[0092] This application can improve the safety of autonomous driving and avoid losses caused by safety accidents. It can also reduce traffic congestion and disorderly lane changes caused by potholes by enabling autonomous driving to accurately avoid potholes and slow down ordinary vehicles in advance, thereby improving road traffic efficiency.

[0093] The following describes an apparatus embodiment of this application, which can be used to perform the methods described in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the methods described in the above embodiments of this application.

[0094] Figure 5 Schematic diagram of the pothole detection device provided in the embodiments of this application Figure 1 Applied to vehicles, the device 500 may include: a data acquisition module 501, a first determination module 502, a second determination module 503, and a processing module 504; The data acquisition module 501 is used to acquire the vertical acceleration and attitude angle of the vehicle according to a preset frequency during the vehicle's operation.

[0095] The first determination module 502 is used to determine whether the vertical acceleration has a sudden change, and the duration of the vertical acceleration change meets the first preset duration range. If so, it is determined that a vertical acceleration change has occurred.

[0096] The second determination module 503 is used to determine whether the attitude angle has changed abruptly, and whether the duration of the change in attitude angle meets the second preset duration range. If so, it is determined that an attitude angle change has occurred.

[0097] The processing module 504 is used to determine whether the vertical acceleration change and the attitude angle change occur simultaneously. If they occur simultaneously, it is determined that the vehicle has encountered a pothole, and the pothole information is uploaded to the background server. The pothole information includes the geographical location of the pothole.

[0098] Figure 6 Schematic diagram of the pothole detection device provided in the embodiments of this application Figure 2 Applied to a backend server, the device 600 may include: a data receiving module 601, a marking module 602, and a deletion module 603; The data receiving module 601 is used to receive road pothole information uploaded by vehicles, wherein the road pothole information includes the geographical location of the road pothole.

[0099] The marking module 602 is used to determine whether a first preset number of vehicles have uploaded pothole information from the same unmarked geographical location if the geographical location contained in the pothole information has no pothole mark in the cloud map.

[0100] The deletion module 603 is used to add a pothole marker to the corresponding geographical location on the cloud map if it receives a first preset number of pothole information uploaded by vehicles in the same geographical location without pothole markers.

[0101] It should be noted that for any content not described in detail in this embodiment of the device, please refer to the method described above.

[0102] Figure 7 This is a schematic diagram of the structure of a vehicle computer system provided in an embodiment of this application. It should be noted that... Figure 7 The vehicle computer system 700 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0103] like Figure 7 As shown, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 702 or programs loaded from storage portion 708 into Random Access Memory (RAM) 703, such as performing the methods described in the above embodiments. The RAM 703 also stores various programs and data required for system operation. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An Input / Output (I / O) interface 705 is also connected to the bus 704.

[0104] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0105] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit (CPU) 701, it performs various functions defined in the system of this application.

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0107] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0108] In another aspect, this application also provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A vehicle's processor reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the vehicle to perform the methods described above.

[0109] In another aspect, this application also provides a computer-readable medium, which may be included in the vehicle described in the above embodiments; or it may exist independently and not installed in the vehicle. The computer-readable medium carries one or more programs that, when executed by the vehicle, cause the vehicle to implement the methods described in the above embodiments.

[0110] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0111] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0112] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for detecting potholes, characterized in that, Applied to vehicles, the method includes: During vehicle operation, the vertical acceleration and attitude angle of the vehicle are acquired according to a preset frequency. Determine whether the vertical acceleration has a sudden change, and whether the duration of the sudden change in vertical acceleration meets the first preset duration range. If so, determine that a sudden change in vertical acceleration has occurred. Determine whether the attitude angle has changed abruptly, and whether the duration of the change in attitude angle meets the second preset duration range. If so, determine that an attitude angle change has occurred. Determine whether the vertical acceleration change and the attitude angle change occur simultaneously. If they occur simultaneously, it is determined that the vehicle has encountered a pothole. Upload the pothole information to the backend server. The pothole information includes the geographical location of the pothole.

2. The method according to claim 1, characterized in that, Determining whether the vertical acceleration undergoes a sudden change includes: Obtain the acceleration difference between the current vertical acceleration and the previous vertical acceleration; Determine whether the acceleration difference exceeds a first real-time threshold. If it does, determine that the vertical acceleration has abruptly changed; if it does not, determine that the vertical acceleration has not abruptly changed. Before determining whether the acceleration difference exceeds the first real-time threshold, the method further includes: Based on the vehicle's current speed and a preset first proportional coefficient, a first dynamic adjustment value is obtained; The first real-time threshold is obtained based on the first dynamic adjustment value and the first basic threshold.

3. The method according to claim 1, characterized in that, The attitude angles include pitch angle and roll angle, and determining whether the attitude angles undergo a sudden change includes: Obtain the pitch angle difference between the current pitch angle value and the previous pitch angle value; Obtain the difference between the current roll angle value and the previous roll angle value; If the pitch angle difference exceeds the second real-time threshold, or the roll angle difference exceeds the third real-time threshold, then it is determined that the attitude angle has abruptly changed. If the pitch angle difference does not exceed the second real-time threshold and the roll angle difference does not exceed the third real-time threshold, then it is determined that the attitude angle has not changed abruptly.

4. The method according to claim 3, characterized in that, After obtaining the pitch angle difference between the current value and the previous value, the method further includes: The second dynamic adjustment value is obtained based on the vehicle's current speed and a preset second proportional coefficient; The second real-time threshold is obtained based on the second dynamic adjustment value and the second basic threshold. After obtaining the difference between the current roll angle value and the previous roll angle value, the method further includes: The third dynamic adjustment value is obtained based on the vehicle's current speed and the preset third proportional coefficient. The third real-time threshold is obtained based on the third dynamic adjustment value and the third basic threshold.

5. The method according to any one of claims 1-4, characterized in that, Determining whether the vertical acceleration abrupt change and the attitude angle abrupt change occur simultaneously includes: Obtain the time difference between adjacent occurrences of the vertical acceleration abrupt change and the attitude angle abrupt change; If the time difference is less than or equal to the preset time difference, then it is determined that the vertical acceleration change and the attitude angle change occur synchronously. If the time difference is greater than the preset time difference, it is determined that the vertical acceleration change and the attitude angle change did not occur synchronously.

6. The method according to claim 5, characterized in that, The method further includes: If the vertical acceleration change and the attitude angle change do not occur simultaneously, determine whether the current geographical location has a road hole mark on the cloud map. If so, upload the road hole-free information of the current geographical location to the backend server.

7. A method for detecting potholes, characterized in that, Applied to a backend server, the method includes: Receive road pothole information uploaded by vehicles, wherein the road pothole information includes the geographical location of the road pothole; If the geographical location contained in the pothole information is not marked as a pothole in the cloud map, then starting from the first pothole information of the geographical location without a pothole mark, it is determined whether a first preset number of vehicles have uploaded pothole information of the same geographical location without a pothole mark. If a first preset number of vehicles upload pothole information at the same unmarked geographical location, then add a pothole marker to the corresponding geographical location on the cloud map.

8. The method according to claim 7, characterized in that, The method further includes: If no pothole information corresponding to the geographical location marked with a pothole is received in the cloud map within the first preset time period, then the pothole mark of the geographical location marked with a pothole is deleted from the cloud map; wherein, the pothole information is determined by the vehicle according to any one of claims 1-5. Alternatively, if within a second preset time period, a second preset number of vehicles upload pothole-free information to the same geographical location marked with a pothole in the cloud map, and no pothole information is received from the vehicle at the same geographical location marked with a pothole, then the pothole mark for the same geographical location marked with a pothole is deleted from the cloud map; wherein the pothole-free information is determined by the vehicle according to the method described in claim 6.

9. A driving control method, characterized in that, Applied to vehicles, the method includes: When the vehicle is in autonomous driving mode, information about potholes ahead of the vehicle is obtained from a cloud map with pothole markings, and when the vehicle travels to a preset distance from the geographical location of the pothole ahead, a pothole avoidance path is generated and executed.

10. A vehicle, characterized in that, The vehicle includes one or more processors and one or more memories, the one or more memories storing at least one piece of program code, the at least one piece of program code being loaded and executed by the one or more processors to implement the method as claimed in any one of claims 1 to 6, or to implement the method as claimed in claim 9.

Images