Obstacle avoidance method and device for road surface anomaly

Abstract

This application discloses a method and apparatus for obstacle avoidance in the field of intelligent transportation and autonomous driving technology. The method includes: acquiring current sensor data of the target vehicle driving on the current road when the target vehicle is in a memory driving mode; determining whether a road abnormality event has occurred based on the current sensor data and preset road abnormality conditions; if so, determining the location information and size information of each abnormal area in the road abnormality event based on the current sensor data; and determining the abnormality level of each abnormal area and the vehicle avoidance strategy corresponding to each abnormality level based on the location information and size information, so that the target vehicle executes the vehicle avoidance strategy when it drives to the abnormal area again.

Description

Technical Field

[0001] This application relates to the fields of intelligent transportation and autonomous driving technology, and in particular to a method and device for avoiding road surface anomalies. Background Technology

[0002] Currently, with social development and technological progress, more and more vehicles are being equipped with autonomous driving technology. As autonomous driving technology develops, vehicles equipped with autonomous driving technology have made significant progress in perception, decision-making, and control. In particular, for users' frequently used fixed routes, autonomous driving technology usually controls the vehicle to enter a memory driving mode, which records the route's trajectory, speed, traffic signs, and dynamic events to achieve automated driving on specific routes.

[0003] However, in real-world road environments, autonomous driving technology still faces limitations in perception. Existing memory driving technologies mostly focus on path reproduction and environmental matching, lacking proactive learning and control of road comfort, such as minor potholes or other minor road surface anomalies. This can lead to situations where, when a vehicle passes through the same repeated road segment, if there is a road surface anomaly at a certain location, the system cannot avoid the road anomaly based on the road conditions recorded in the memory driving mode, thus affecting the user's driving and riding experience. Summary of the Invention

[0004] This application provides a method and apparatus for avoiding road anomalies. The embodiments provided by this application solve the technical problem in the prior art that the system cannot avoid road anomalies based on the road conditions recorded by the memory driving mode, thereby affecting the user's driving and riding experience. The embodiments provided by this application can automatically detect and avoid abnormal areas of the road, and generate vehicle avoidance strategies in the memory driving mode, thereby improving the user's driving and riding experience.

[0005] In a first aspect, this application provides a method for avoiding road surface anomalies, the method comprising: When the target vehicle is in memory driving mode, acquire the current sensor data of the target vehicle driving on the current road; Based on the current sensor data and preset road surface anomaly conditions, determine whether a road surface anomaly event has occurred; If so, then based on the current sensing data, determine the location and size information of each abnormal area in the road surface anomaly event; Based on the location information and the size information, the anomaly level of each anomaly area and the vehicle avoidance strategy corresponding to each anomaly level are determined, so that the target vehicle executes the vehicle avoidance strategy when it travels to the anomaly area again.

[0006] In one feasible implementation, the method further includes: The detected abnormal areas of the current road are stored in the abnormal area database; When the target vehicle travels to the location of the abnormal area again, it is determined whether the distance deviation between the repeated location of the repeated abnormal area detected again and the location of the corresponding abnormal area in the abnormal area database is within a preset distance deviation threshold. If so, the duplicate abnormal region and the corresponding abnormal region are merged into an updated abnormal region, and the updated abnormal region is stored in the abnormal region database to replace the abnormal region in the abnormal region database, thus completing the position update of the abnormal region.

[0007] In one feasible implementation, the method further includes: The detected abnormal areas of the current road are stored in the abnormal area database; When the target vehicle travels to the location of the abnormal area again, it is determined whether the distance deviation between the repeated location of the repeated abnormal area detected again and the location of the corresponding abnormal area in the abnormal area database is within a preset distance deviation threshold. If so, the duplicate abnormal region and the corresponding abnormal region are merged into an updated abnormal region, and the updated abnormal region is stored in the abnormal region database to replace the abnormal region in the abnormal region database, thus completing the position update of the abnormal region.

[0008] In one feasible implementation, the dynamic driving characteristic information of the target vehicle further includes the vehicle speed. Based on the current sensing data, the location information of each abnormal area in the road anomaly event is determined, including: For any of the abnormal areas, the longitudinal offset of the abnormal area on the current road is determined based on the trigger time of the road abnormality event of the target vehicle and the vehicle speed; For any of the aforementioned abnormal areas, the lateral offset of the abnormal area on the current road is determined based on the instantaneous wheel speed difference of the single wheel and the vertical vibration acceleration of the wheel. Based on the longitudinal offset and the lateral offset, the location information of each abnormal area of ​​the road surface anomaly event is determined.

[0009] In one feasible implementation, the dynamic driving characteristic information of the target vehicle further includes the vehicle speed, and based on the current sensing data, determining the size information of each abnormal region in the road anomaly event includes: For any of the aforementioned abnormal regions, the length of the abnormal region is determined based on the vehicle speed and the duration of the target vehicle's presence in the road surface anomaly event. For any of the aforementioned abnormal regions, the width of the abnormal region is determined based on the lateral coordinates of the left and right wheels of the target vehicle, wherein the lateral coordinates are used to characterize the coordinates of each wheel relative to the center of the vehicle. The depth of the abnormal region is determined based on the peak value of the vertical vibration acceleration or the integral data of the vertical vibration acceleration. For any of the aforementioned abnormal regions, the size information of each of the abnormal regions in the road surface anomaly event is determined based on the length, the width, and the depth.

[0010] In one feasible implementation, determining the lateral offset of the abnormal region on the current road based on the instantaneous wheel speed difference of the single wheel and the vertical vibration acceleration includes: Based on the overlap between the instantaneous wheel speed difference of the single wheel and the peak value of the vertical vibration acceleration, at least one candidate wheel that has deviated is identified. Based on the geometric parameters of the target vehicle, the lateral coordinates of each candidate wheel in the vehicle coordinate system are determined, wherein the geometric parameters are the lateral offset parameters of the wheel center relative to the center of the target vehicle. The lateral coordinates are transformed to the lane coordinate system to determine the lateral offset of the abnormal area on the current road.

[0011] In one feasible implementation, determining the anomaly level of each of the abnormal regions and the vehicle avoidance strategy corresponding to each anomaly level based on the location information and the size information includes: Based on the number of affected wheels, the peak value of the vertical vibration acceleration of the wheels, the location information, and the size information, the anomaly level of each anomaly region and the vehicle avoidance strategy corresponding to each anomaly region are determined, wherein the affected wheels are used to characterize the wheels that are trapped in the anomaly region.

[0012] In one feasible implementation, determining the anomaly level of each abnormal region and the corresponding vehicle avoidance strategy for each abnormal region based on the number of affected wheels, the peak value of the vertical vibration acceleration of the wheels, the position information, and the size information includes: When it is determined that the number of affected wheels is not greater than a first number threshold, or when it is determined that the peak value of the vertical vibration acceleration of the wheel is within a first preset wheel vibration amplitude range, or when it is determined that the size information is not greater than a first size threshold, or when it is determined that the distance between the position information and the edge of the lane line is not greater than a first distance threshold, the abnormality level of the abnormal area is determined to be a small abnormal area, and the vehicle avoidance strategy corresponding to the small abnormal area is determined to be an in-lane obstacle avoidance strategy. When it is determined that the number of affected wheels is greater than the first number threshold, or when it is determined that the peak value of the vertical vibration acceleration of the wheel is greater than the second preset wheel vibration amplitude threshold, or when it is determined that the size information is greater than the second size threshold, or when the distance between the position information and the edge of the lane line is greater than the first distance threshold, the abnormality level of the abnormal area is determined to be a large abnormal area, and the vehicle avoidance strategy corresponding to the large abnormal area is determined to be an early lane change strategy, wherein the second preset wheel vibration amplitude threshold is greater than the first preset wheel vibration amplitude range; and the second size threshold is greater than the first size threshold.

[0013] In one feasible implementation, during the execution of the vehicle avoidance strategy to avoid the abnormal area, the method further includes: Based on the traffic environment and preset road rules of the target route, determine whether the abnormal area can be safely avoided; If the vehicle avoidance strategy conflicts with the traffic environment and / or the preset road rules, the vehicle avoidance strategy is abandoned and the corresponding safety operation is performed.

[0014] In a second aspect, this application provides an obstacle avoidance device for road surface anomalies, the obstacle avoidance device comprising: The acquisition module is used to acquire the current sensor data of the target vehicle driving on the current road when the target vehicle is in the memory driving mode; The first determining module is used to determine whether a road abnormality event has occurred based on the current sensing data and preset road abnormality conditions. The second determining module is used to determine the location and size information of each abnormal area in the road surface abnormality event based on the current sensing data if the condition is met. The third determining module is used to determine the anomaly level of each of the abnormal regions and the vehicle avoidance strategy corresponding to each anomaly level based on the location information and the size information, so that the target vehicle executes the vehicle avoidance strategy when it travels to the abnormal region again.

[0015] The obstacle avoidance method and apparatus for road anomalies provided in this application, compared with the prior art, obtains the current sensing data of the target vehicle driving on the current road when the target vehicle is in the memory driving mode. Unlike the traditional data acquisition method using conventional visual sensors or lidar sensors, the current sensing data of the current road is recorded by sensors and lane line information to record the full trajectory information of high-frequency travel routes. This high-frequency and specific full trajectory information can more accurately determine the road state of the current road than lidar sensor data. Then, based on the current sensing data and preset road anomaly conditions, it is determined whether a road anomaly event has occurred. If so, based on the current sensing data, the location and size information of each abnormal area in the road anomaly event are determined. This application can learn the location, size and influence range of abnormal areas through its own sensor data, and determine the anomaly level of each abnormal area and the corresponding vehicle avoidance strategy based on the location and size information. This allows the target vehicle to execute the vehicle avoidance strategy and automatically optimize the path when it drives to the abnormal area again, avoiding repeated passage through uneven abnormal road sections, thereby improving the user's driving and riding experience. Attached Figure Description

[0016] Figure 1 A flowchart illustrating an obstacle avoidance method for road surface anomalies provided in an embodiment of this application is shown. Figure 2 The flowchart of pothole updating in an obstacle avoidance method for road surface anomalies provided in an embodiment of this application is shown. Figure 3 This paper shows a structural block diagram of an obstacle avoidance device for abnormal road surfaces provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0017] Figure 3 and Figure 4 The correspondence between the figure labels and figure titles in the accompanying drawings is as follows: 300 Obstacle avoidance device for road surface anomalies; 310 Acquisition module; 320 First determination module; 330 Second determination module; 340 Third determination module; 350 Storage module; 360 Fourth determination module; 370 Update module; 400 Electronic device; 410 Processor; 420 Memory; 430 Bus. Detailed Implementation

[0018] To better understand the technical solutions provided in the embodiments of this specification, the technical solutions of the embodiments of this specification will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0019] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The term "two or more" includes two or more cases.

[0020] First, the applicable application scenarios of this application will be introduced. The embodiments provided in this application are applicable to the fields of intelligent transportation and autonomous driving technology, and in particular, they relate to an obstacle avoidance method and device for road surface anomalies.

[0021] Currently, in real-world road environments, autonomous driving technology still faces limitations in perception. Existing memory-based driving technologies mostly focus on path reproduction and environmental matching, lacking proactive learning and control of road comfort, such as minor potholes or other minor road surface anomalies. This can lead to situations where, when a vehicle passes through the same repeated road segment, if there is a road surface anomaly at a certain location, the system cannot avoid the road anomaly based on the road conditions recorded in the memory-based driving mode, thus affecting the user's driving and riding experience.

[0022] Based on this, the embodiments of this application provide a method and apparatus for avoiding road anomalies. The embodiments provided by this application solve the technical problem in the prior art that the system cannot avoid road anomalies according to the road conditions recorded by the memory driving mode, thereby affecting the user's driving experience and riding experience. The embodiments provided by this application can automatically detect and avoid abnormal areas of the road, and generate vehicle avoidance strategies in the memory driving mode, thereby improving the user's driving experience and riding experience.

[0023] The memory driving mode in this application can be specific but not limited to: Memory-based Navigation and Optimization for Autonomous driving (MNOA).

[0024] Figure 1 This is a flowchart illustrating an obstacle avoidance method for road surface anomalies provided in an embodiment of this application. Figure 1 As shown, the obstacle avoidance method for road surface anomalies includes the following steps: S101. When the target vehicle is in memory driving mode, acquire the current sensor data of the target vehicle driving on the current road.

[0025] In this step, in the embodiment provided in this application, when the target vehicle is in the memory driving mode, it is necessary to first obtain the current sensing data of the target vehicle driving on the current road. The sensing data includes at least one of the geographical trajectory information of the target route, the lane line boundary information of the target route, the attitude change information of the target vehicle, the dynamic driving characteristic information of the target vehicle, and the suspension displacement value of the target vehicle.

[0026] It should be noted that the detection sensor for collecting the attitude change information of the target vehicle in the embodiments provided in this application can be customized and used according to different application scenarios and usage conditions. The attitude change information of the target vehicle in the embodiments provided in this application can be specifically collected by an inertial measurement unit (IMU), and the sampling rate of the IMU is represented by f_IMU.

[0027] It is understood that the embodiments provided in this application are able to obtain the suspension displacement of the target vehicle on the premise that a suspension sensor is installed on the target vehicle and that the suspension sensor signal can be collected.

[0028] In this application, the device for collecting geographic trajectory information of the target route in the embodiments can be customized and used according to different application scenarios and usage conditions. The geographic trajectory information of the target route in the embodiments provided in this application can be specifically obtained through the Global Navigation Satellite System (GNSS) and the Inertial Navigation System (INS), and the geographic location of the target route with synchronized timestamps is specifically represented as: pose(t)={x,y,yaw,v}; X and y: used to represent the coordinates of the target vehicle on the planar map (such as metric coordinates after latitude and longitude projection); yaw: used to represent the heading angle of the target vehicle, which is the direction the front of the vehicle is facing (such as due north is 0°, increasing clockwise); v: used to represent the current speed of the target vehicle.

[0029] The attitude change information of the target vehicle in the embodiments provided in this application also includes the geometric parameters of the target vehicle, such as the front and rear wheelbase (the distance from the center of the front wheel to the center of the rear wheel) and the lateral position of the left and right wheels (the distance between the centers of the left and right wheels on the same axle).

[0030] The embodiments provided in this application achieve centimeter-level high-precision positioning of target vehicles by fusing GNSS technology with INS, and also know the vehicle's heading and speed.

[0031] In the above-mentioned embodiments, the dynamic driving characteristic information of the target vehicle may specifically include dynamic characteristics such as vehicle speed, acceleration, and steering angle.

[0032] Here, the current road in the embodiments provided in this application is a fixed route frequently traveled by the user when the target vehicle is in the memory driving mode, such as the route for the user to commute to and from get off work, pick up and drop off children, and go shopping.

[0033] The lane boundary information of the target route in the embodiments provided in this application can be specific but not limited to the lateral offset of the target vehicle center from the lane centerline, represented by lateral offset, lane_id.

[0034] S102. Based on the current sensor data and preset road surface anomaly conditions, determine whether a road surface anomaly event has occurred.

[0035] In this step, in the embodiments provided in this application, after acquiring the current sensor data of the target vehicle driving on the current road in real time, it is necessary to compare all types of current sensor data with the corresponding preset road surface anomaly conditions to determine whether the current sensor data can meet the preset road surface anomaly conditions, and if the current sensor data meets the preset road surface anomaly conditions, it is determined that a road surface anomaly event has occurred on the current road.

[0036] It should be noted that the abnormal road conditions in the embodiments provided in this application specifically refer to the event of determining whether the target vehicle has driven into an abnormal area.

[0037] It is understood that the abnormal areas in the embodiments provided in this application can be customized and used according to different road surfaces and application scenarios. The abnormal areas in the embodiments provided in this application can be specifically set as minor road surface abnormalities such as small potholes, uneven areas, or manhole cover settlement. This embodiment takes potholes as an example.

[0038] The current road is used to represent the road on which the target vehicle is currently traveling.

[0039] In the above-described embodiments, the present application first performs multi-channel signal filtering on the sensor data to determine the filtered standard sensor data. Then, the standard sensor data is interpolated to a unified time base to achieve synchronized timestamps. Finally, based on the standard sensor data and preset pothole triggering conditions, it is determined whether a pothole event has occurred on the target vehicle.

[0040] Specifically, the embodiments provided in this application will remove high-frequency noise, such as the current noise of electronic devices and the slight vibration of the sensor itself, which are not actual vehicle body bumps, by using IMU low-pass filtering; the embodiments provided in this application will remove the slow zero-point shift of the sensor caused by temperature and time by using IMU high-pass filtering.

[0041] Here, the embodiments provided in this application determine which wheel in the target vehicle is abnormal by measuring the wheel speed. Specifically, the method for determining which wheel is abnormal in this application involves: first, removing glitches and jumps from the wheel speed signal, and then calculating the relative ratio of the wheels. The specific formula is as follows: r_i(t)=ω_i(t) / mean(ω_all(t)); Where r_i(t) is used to characterize the relative ratio of the wheel speed of the i-th wheel at time t; ω_i(t) is used to characterize the absolute rotational speed of the i-th wheel at time t; mean(ω_all(t)) is used to characterize the average rotational speed of the four wheels at time t.

[0042] S103. If so, then based on the current sensor data, determine the location and size information of each abnormal area in the road surface abnormality event.

[0043] In this step, in the embodiments provided in this application, after determining that a road surface anomaly event has occurred on the current road, the embodiments provided in this application need to determine the location and size information of each abnormal area in the road surface anomaly event, i.e., each pothole, based on the current sensing data.

[0044] It should be noted that the position information and size information provided in the embodiments of this application can be selected and used according to different application scenarios and usage scenarios. The position information provided in the embodiments of this application includes longitudinal positioning and lateral positioning, and the size information includes length, width and depth.

[0045] S104. Based on location and size information, determine the anomaly level of each anomaly area and the corresponding vehicle avoidance strategy for each anomaly level, so that the target vehicle can execute the vehicle avoidance strategy when it travels to the anomaly area again.

[0046] In this step, in the embodiments provided in this application, after determining the location and size information of each abnormal area, i.e., the potholes, it is necessary to classify the potholes into abnormal levels according to their impact on the comfort or risk of the target vehicle, so as to generate vehicle avoidance strategies corresponding to different abnormal levels.

[0047] It should be noted that the embodiments provided in this application can specifically divide the abnormal area, that is, the abnormal level of the pothole, into large potholes and small potholes, and then determine the vehicle avoidance strategy corresponding to large potholes and the vehicle avoidance strategy corresponding to small potholes respectively.

[0048] It is understood that, in the embodiments provided in this application, the vehicle avoidance strategies corresponding to large potholes and small potholes can be customized and used according to different application scenarios and usage conditions. The vehicle avoidance strategy corresponding to large potholes in the embodiments provided in this application can be specifically set to change lanes in advance; and the vehicle avoidance strategy corresponding to small potholes in the embodiments provided in this application can be specifically set to make slight detours within the lane.

[0049] The obstacle avoidance method for road anomalies provided in this application, compared with the prior art, obtains the current sensor data of the target vehicle traveling on the current road when the target vehicle is in memory driving mode. This differs from the traditional data acquisition method using conventional visual sensors or lidar sensors. The current sensor data of the current road is recorded by sensors and lane line information to record the entire trajectory information of high-frequency travel routes. This high-frequency and specific entire trajectory information can more accurately determine the road condition of the current road compared with lidar sensor data. Then, based on the current sensor data and preset road anomaly conditions, it is determined whether a road anomaly event has occurred. If so, based on the current sensor data, the location and size information of each abnormal area in the road anomaly event are determined. This application can learn the location, size, and impact range of abnormal areas through its own sensor data, and determine the anomaly level of each abnormal area and the corresponding vehicle avoidance strategy based on the location and size information. This allows the target vehicle to execute the vehicle avoidance strategy and automatically optimize the path when it travels to an abnormal area again, avoiding repeated passage through uneven abnormal road sections, thereby improving the user's driving and riding experience.

[0050] For example, the current sensing data includes at least one of the target vehicle's attitude change information, the target vehicle's dynamic driving characteristic information, and the target vehicle's suspension displacement value. The target vehicle's attitude change information includes vertical vibration acceleration, and the target vehicle's dynamic driving characteristic information includes the wheel speed of each wheel. The preset abnormal road conditions include at least one of the following: vertical vibration acceleration is greater than or equal to a preset vertical acceleration threshold; the ratio of the instantaneous wheel speed difference of any wheel to the average wheel speed is greater than or equal to a preset wheel speed difference threshold, and the duration exceeds a preset duration, wherein the instantaneous wheel speed difference of a single wheel is determined by the difference between the wheel speeds of any two wheels; and the suspension displacement value is greater than or equal to a preset suspension displacement threshold.

[0051] It should be noted that, in the embodiments provided in this application, the vertical vibration acceleration is represented by a_z; the preset vertical acceleration threshold is represented by T_accel.

[0052] The instantaneous wheel speed difference of a single wheel is represented by |ω_i-ω_j| / mean(ω); the preset wheel speed difference threshold is represented by T_wheel, and in the embodiment provided in this application, T_wheel is set to 0.10, i.e. 10%.

[0053] Here, the vertical vibration acceleration being greater than or equal to a preset vertical acceleration threshold can be specifically expressed as the absolute value of the vertical vibration acceleration being greater than or equal to the preset vertical acceleration threshold, i.e., |a_z|>T_accel, and the preset duration t>T_dur_min. In the embodiments provided in this application, T_dur_min=0.03s; the preset duration is represented by T_dur_min; and the preset duration in the embodiments provided in this application can be customized and used according to different application scenarios and usage conditions.

[0054] In the above-mentioned embodiments, it is suggested that the initial value of the preset vertical acceleration threshold T_accel be set to 0.30g≈2.94m / s², and the preset vertical acceleration threshold can be customized and dynamically adjusted according to different application scenarios and usage conditions.

[0055] In the embodiments provided in this application, not all target vehicles are equipped with suspension displacement sensors. Therefore, if a target vehicle is equipped with the aforementioned suspension displacement sensor, the abnormal road conditions include the determination of vertical vibration acceleration, that is, it is necessary to determine whether the vertical vibration acceleration is greater than or equal to a preset vertical acceleration threshold, that is, to determine |δ_suspension|>T_sus. If the target vehicle is not equipped with a suspension displacement sensor, the abnormal road conditions do not include the determination of vertical vibration acceleration.

[0056] The embodiments provided in this application can also reduce false alarms by using acoustic sensors, vibration sensors, or acceleration spectrum characteristics.

[0057] For example, the embodiments provided in this application can also trigger an alarm when the wheels of the target vehicle enter an abnormal area of ​​the current road, and set the trigger time for the wheels entering the abnormal area to t0.

[0058] However, the ideal driving process of the target vehicle described above may actually occur within the first 0.05 seconds of driving. Therefore, it is necessary to trace back a bit to see the initial state of the target vehicle when it actually "enters the pothole". Moreover, after the target vehicle's wheels have passed through the abnormal area, the vibration will continue for a while, such as the body still shaking or the wheels still vibrating. Therefore, it is necessary to extend the time by 0.3 seconds to obtain the complete vibration waveform from when the wheel first touches the pothole to when it completely leaves the pothole. This will facilitate the subsequent accurate estimation of the length and severity of the pothole.

[0059] Here, in the embodiment provided in this application, the trigger time window of the abnormal region is defined as: [t0-Δt_pre,t0+Δt_post]. Assuming that Δt_pre=0.05s and Δt_post=0.3s are specifically set, this represents the target vehicle's wheels collecting signals forward or backward from the trigger time to obtain the complete event.

[0060] In this application, the spatial location (i.e., latitude and longitude coordinates) and degree of influence (i.e., vibration amplitude and duration) of potholes are estimated by the difference in vehicle posture and wheel speed under preset abnormal road conditions, thereby determining whether the target vehicle has passed through the abnormal area or pothole.

[0061] For example, the dynamic driving characteristic information of the target vehicle also includes the vehicle speed. Based on the current sensor data, the location information of each abnormal area in the road anomaly event is determined, including: For any abnormal area, the longitudinal offset of the abnormal area on the current road is determined based on the trigger time and speed of the target vehicle when the road abnormal event occurs; for any abnormal area, the lateral offset of the abnormal area on the current road is determined based on the instantaneous wheel speed difference of a single wheel and the vertical vibration acceleration; based on each longitudinal offset and each lateral offset, the location information of each abnormal area of ​​the road abnormal event is determined.

[0062] In the embodiments provided in this application, after determining at least one abnormal area on the current road, the embodiments provided in this application require, for any one of the above-mentioned abnormal areas, to determine the location information of each abnormal area in the road abnormal event based on the current sensing data and the vehicle speed of the target vehicle in the current sensing data. Specifically, it is necessary to determine the longitudinal and lateral offsets of each of the above-mentioned abnormal areas on the current road.

[0063] It should be noted that the lateral offset of the abnormal area in the embodiments provided in this application is determined by identifying which wheels have run over or hit the abnormal area.

[0064] Based on the instantaneous wheel speed difference and vertical vibration acceleration of a single wheel, the lateral offset of the abnormal area on the current road is determined, including: identifying at least one candidate wheel that has shifted based on the overlap of the peak values ​​of the instantaneous wheel speed difference and vertical vibration acceleration of a single wheel; determining the lateral coordinates of each candidate wheel in the vehicle coordinate system based on the geometric parameters of the target vehicle, wherein the geometric parameters are the lateral offset parameters of the wheel center relative to the center of the target vehicle; and transforming the lateral coordinates to the lane coordinate system to determine the lateral offset of the abnormal area on the current road.

[0065] It is understood that the embodiments provided in this application need to use the lateral coordinates of the target vehicle's wheels relative to the vehicle center to determine the lateral offset of the abnormal area on the current road, that is, to map the "affected wheel set" to the lateral coverage of the abnormal area.

[0066] In the embodiments provided in this application, if both the left and right wheels of the target vehicle are affected at the same time, it indicates that the potholes on the current road cross the middle of the lane, or that the wheel track is wide; if only one wheel of the target vehicle is affected, it indicates that the potholes on the current road are close to the edge of the lane.

[0067] In the embodiments provided in this application, the longitudinal offset of the pothole on the road is calculated using the trigger time t_impact of the road surface anomaly event of the target vehicle and the vehicle speed v. The specific formula for the longitudinal offset is as follows: s_pit=s_ego(t_impact)-v(t_impact)*t_latency_compensation; Among them, s_pit is used to characterize the longitudinal offset formula; t_latency_compensation is used to characterize the compensation value, that is, the sensor and processing delay is generally calibrated to 0.02–0.1s.

[0068] Here, the detected pothole locations are corrected to their actual locations.

[0069] In this application, the instantaneous wheel speed difference and vertical vibration acceleration of a single wheel are used to determine which wheel has hit the pothole. Based on the fixed position of the wheel on the target vehicle, the lateral range of the pothole under the vehicle is determined. Combined with the vehicle's position in the lane, the precise lateral position of the pothole in the lane is calculated. This allows the target vehicle to accurately avoid the pothole when it passes by next time.

[0070] For example, the dynamic driving characteristic information of the target vehicle also includes the vehicle speed, and based on the current sensor data, the size information of each abnormal region in the road anomaly event is determined, including: For any abnormal region, the length of the abnormal region is determined based on the vehicle speed and the duration of the target vehicle in the road abnormality event; for any abnormal region, the width of the abnormal region is determined based on the lateral coordinates of the left and right wheels of the target vehicle, where the lateral coordinates are used to characterize the coordinates of each wheel relative to the center of the vehicle; the depth of the abnormal region is determined based on the peak value or integral data of the vertical vibration acceleration; for any abnormal region, the size information of each abnormal region in the road abnormality event is determined based on the length, width, and depth.

[0071] In the embodiments provided in this application, after determining the location information of the abnormal region, it is also necessary to determine the size information of the abnormal region, that is, to determine the size information of the abnormal region by determining the length, width and depth of the abnormal region.

[0072] It should be noted that in the embodiments provided in this application, the direction in which the length of the abnormal area is determined is the direction in which the target vehicle travels along the current road.

[0073] It is understood that the formula for determining the length of the abnormal region in the embodiments provided in this application is specifically: length_est=v_mean*duration_impact; Among them, length_est is used to represent the length of the abnormal region; v_mean is used to represent the vehicle speed; duration_impact is used to represent the duration of the target vehicle in the abnormal road event, that is, the cumulative time of the IMU exceeding the threshold, which is the sum of the time when "abnormal wheel vibration" is actually detected. For example, "the wheel bumped once when it first entered the pothole, then smoothed out in the middle, and then bumped again when it came out of the pothole", then only the time of these two bumps is added together.

[0074] Here, the formula for determining the width of the abnormal region in the embodiments provided in this application is as follows: width_est=max(lateral_coords)-min(lateral_coords)+margin; Among them, width_est is used to represent the width of the abnormal region; lateral_coords is used to represent the lateral coordinates of the affected wheel relative to the center of the vehicle; margin is used to represent the margin, which is used to avoid the point where the wheel runs over not being equal to the boundary of the pit, because the wheel itself has a width.

[0075] When only a single wheel pressure is triggered, an empirical value is used to determine the pothole width. In this case, it is conservatively estimated that the pothole is at least the contact width of one wheel (0.3-0.6 meters), and it is marked as "low confidence". This means that "the target vehicle is not sure how wide the pothole is and needs to check again next time it passes by".

[0076] Here, in the embodiments provided in this application, the depth of the abnormal region is specifically determined by the peak value of the vertical vibration acceleration peak_z_acc, the integral data of the vertical vibration acceleration ∫|a_z|dt, or the vibration energy integral_z_energy.

[0077] In the above, vibration energy is used to characterize the energy of adding up the vibration intensity at each instant during the entire turbulence process.

[0078] In this application, the length, width, and depth of the abnormal area are determined to more accurately determine the size information of the abnormal area, thereby providing a more accurate basis for the subsequent road abnormality avoidance of the target vehicle.

[0079] For example, based on location and size information, the anomaly level of each abnormal region and the corresponding vehicle avoidance strategy for each anomaly level are determined, including: Based on the number of affected wheels, the peak value of the vertical vibration acceleration of the wheels, location information, and size information, the anomaly level of each anomaly region and the corresponding vehicle avoidance strategy for each anomaly region are determined. Among them, the affected wheels are used to characterize the wheels that are trapped in the anomaly region.

[0080] In the above-described embodiments, when the number of affected wheels is not greater than a first quantity threshold, or when the peak value of the vertical vibration acceleration of the wheels is within a first preset wheel vibration amplitude range, or when the size information is not greater than a first size threshold, or when the distance between the position information and the edge of the lane line is not greater than a first distance threshold, the abnormality level of the abnormal area is determined to be a small abnormal area, and the vehicle avoidance strategy corresponding to the small abnormal area is determined to be an in-lane obstacle avoidance strategy; when the number of affected wheels is greater than the first quantity threshold, or when the peak value of the vertical vibration acceleration of the wheels is determined to be a second preset wheel vibration amplitude threshold, or when the size information is greater than the second size threshold, or when the distance between the position information and the edge of the lane line is greater than the first distance threshold, the abnormality level of the abnormal area is determined to be a large abnormal area, and the vehicle avoidance strategy corresponding to the large abnormal area is determined to be an early lane change strategy, wherein the second preset wheel vibration amplitude threshold is greater than the first preset wheel vibration amplitude range; and the second size threshold is greater than the first size threshold.

[0081] It should be noted that, in the embodiments provided in this application, when it is determined that the number of affected wheels, wheel_impact_count, is not greater than the first quantity threshold 1, that is, when it is determined that only one wheel has hit the pothole, or when the width of the pothole is less than 0.5 meters, it indicates that the pothole is not large, that is, the pothole does not span the entire lane, and may be a manhole cover depression or a small crack. At this time, the abnormal area, that is, the abnormal level of the pothole, is determined to be a small abnormal area.

[0082] The embodiments provided in this application determine that when the peak value of the vertical vibration acceleration of the wheel is within the first preset wheel vibration amplitude range, i.e., peak_z_acc∈[T_accel_min,T_accel_medium), the abnormality level of the abnormal region is determined to be a small abnormal region.

[0083] That is, when it is determined that the target vehicle hits a pothole, the intensity of the up-and-down vibration of the target vehicle is between 0.3g and 0.6g, indicating that the abnormal level is a small abnormal area. Among them, the setting of the first preset wheel vibration amplitude range in the embodiments provided by the present application can be customarily selected and used according to different application scenarios and usage conditions. The first preset wheel vibration amplitude range in the embodiments provided by the present application can be specifically set to [0.3g - 0.6g].

[0084] In the above, when it is determined that the peak value of the vertical vibration acceleration of the wheel reaches the second preset wheel vibration amplitude threshold, that is, peak_z_acc≥1g, or z_energy is too high, or wheel_impact_count is affected on both sides, it is determined that the abnormal level of the abnormal area is a large abnormal area, and the vehicle avoidance strategy corresponding to the large abnormal area is determined.

[0085] In the embodiments provided by the present application, when it is determined that the edge distance between the position information and the lane line is not greater than the first distance threshold, that is, |lat_offset| < lane_width / 2 - margin, that is to say, it is determined that the distance between the abnormal area and the lane boundary is less than margin, that is, the pothole is close to the edge of the lane line. At this time, it is determined that the abnormal level of the abnormal area is a small abnormal area.

[0086] It can be understood that in the embodiments provided by the present application, if it is determined that the abnormal level of the abnormal area is a small abnormal area, at this time, the vehicle needs to execute an in-lane obstacle avoidance strategy to avoid obstacles in the above small abnormal area, and record the center position and its length and width range of the pothole. If the in-lane micro-avoidance is not feasible, an in-lane micro-obstacle avoidance combined with a deceleration passing strategy is generated. Here, since the pothole represented by the abnormal area is not large and is on the side, only need to deviate slightly in the current lane, for example, deviate 0.3 - 0.5 meters to the other side, and it can be easily bypassed; if the pothole is still detected after the micro-obstacle avoidance, the size parameter of the pothole area is automatically widened, and the pothole size in the database is updated.

[0087] Here, the deceleration passing strategy specifically includes: determining a safe passing speed according to the depth of the pothole, passing through the pothole at the safe passing speed, and generating a smooth acceleration trajectory to restore the original speed after the vehicle passes through the pothole.

[0088] Among them, in the embodiments provided by the present application, if it is determined that the abnormal level of the abnormal area is a large abnormal area, at this time, the vehicle avoidance strategy corresponding to the large abnormal area is an early lane change strategy, and a warning is given at a far end, and an "early lane change flag bit" is output. If the lane change is not feasible, a deceleration passing strategy is generated and manual intervention is prompted. If it is observed at a low speed (for example, in a parking section), it is recommended to report it as an obstacle and notify the cloud.

[0089] Here, when a target vehicle encounters the aforementioned large abnormal area in the same lane, it will perform a lane change operation in advance to bypass the lane containing the pothole. The specific steps for performing a lane change operation in advance are as follows: when the distance to the pothole is greater than the preset lane change distance, a lane change request is initiated; the safety gap behind and in front of the target lane is checked; if the safety gap meets the preset conditions and the current road section allows lane changing, then the lane change operation is performed.

[0090] In this application, different obstacle avoidance strategies are implemented by identifying abnormal regions of different abnormality levels. When generating the obstacle avoidance strategy, the cost of at least one of the following is calculated: comfort cost, safety cost, time cost, and energy cost. The obstacle avoidance strategy with the lowest overall cost is selected as the obstacle avoidance strategy to be implemented by the target vehicle, thereby improving the efficiency, accuracy, and cost-effectiveness of the obstacle avoidance of the target vehicle.

[0091] For example, in the process of executing a vehicle avoidance strategy to avoid an abnormal area, the method further includes: determining whether it is safe to avoid the abnormal area based on the traffic environment of the target route and preset road rules; if the vehicle avoidance strategy conflicts with the traffic environment and / or preset road rules, then the vehicle avoidance strategy is abandoned and the corresponding safety operation is performed.

[0092] In the embodiments provided in this application, the limitations on the traffic environment of the target route include: determining the minimum safe distance G_min_rear that the following vehicle needs to maintain and the minimum safe distance G_min_front that the preceding vehicle needs to maintain. Specifically, when changing lanes, a following distance of 1.5 seconds is allowed behind and a following distance of 1.0 second is allowed in front. This ensures sufficient safety margin regardless of vehicle speed.

[0093] For example: G_min_rear=max(v_ego*t_buffer_rear,min_rear_distance), t_buffer_rear≈1.5s; G_min_front=max(v_ego*t_buffer_front,min_front_distance), t_buffer_front≈1.0s; In the embodiments provided in this application, after determining that the abnormality level of the abnormal area is a small abnormal area, the target vehicle needs to be deflected to avoid the small abnormal area, and the maximum deflection is controlled within 0.6 meters and the lateral acceleration is controlled within 0.3g.

[0094] It should be noted that the preset road rules in the embodiments provided in this application include: prohibiting lane changes on solid line sections, intersections, and near exits; ensuring a safe distance between vehicles behind and in front of the target lane when changing lanes; and ensuring that obstacle avoidance operations do not interfere with normal traffic flow.

[0095] It is understood that the embodiments provided in this application do not allow lane changes when there are motorcycles, bicycles, or pedestrians in the adjacent lane.

[0096] In the embodiments provided in this application, while ensuring that the lane meets comfort constraints, a limited offset is required to avoid the pit bounding box. The specific method is as follows: Project the potholes onto the current lane coordinate system and calculate the minimum safe offset d_req, such that the distance between the driving trajectory and the center of the pothole is greater than or equal to safety_clearance.

[0097] Here, safety_clearance=0.25m.

[0098] lateraloffset=current_offset+sign*min(d_req,d_max_allowed), and generate the lateral(t) curve using cubic splines or quintic polynomials. The time T_manuever is determined by the current velocity v (e.g., T=clamp(0.8s-2.5s,basedonv)).

[0099] In this application, the early lane change strategy needs to be triggered when distance_to_pit ≥ D_min_change and the lane change safety condition is met. D_min_change = safe_change_distance = v * t_margin + maneuver_distance. For example, if t_margin = 2.0s, and v = 20m / s (72km / h), then D_min_change ≈ 40m.

[0100] The obstacle avoidance strategy within the lane needs to satisfy the following conditions: maximum lateral displacement d_lat≤d_max, and |a_lat|≤A_lat_max (suggested lower limit 0.3g≈2.94m / s²), |jerk|≤J_max (e.g. 2.0m / s³).

[0101] Wherein, d_max=0.6m, that is, the total trajectory should meet the vehicle trajectory tracker and passenger comfort specifications.

[0102] When there are multiple potholes in the target lane or potholes and obstacles coexist, the obstacle avoidance priority is: priority: obstacle / pedestrian / vehicle > severe pit > moderate pit > minor pit. If the pothole ahead conflicts with the lane change target (e.g., there are potholes or obstacles in the target lane), try to slow down.

[0103] For example, in the embodiments provided in this application, when the target vehicle fails to change lanes or is blocked, such as when there are always cars next to it, or the car behind does not give way, or the conditions for changing lanes are not met, resulting in the lane change request being rejected (lane change failure), the target vehicle will not wait idly, nor will it forcibly change lanes. It will automatically downgrade to the alternative solution: try to avoid the lane within the current lane (micro-offset), while slowing down to minimize the impact.

[0104] In the above scenario, the target vehicle will gradually decelerate using a smooth curve, with the deceleration increasing and decreasing slowly, without any jerking throughout the process.

[0105] After passing the aforementioned potholes, the target vehicle will smoothly accelerate back to its original speed.

[0106] For example, the method further includes the following steps: The detected abnormal areas of the current road are stored in the abnormal area database. When the target vehicle travels to the location of the abnormal area again, it is determined whether the distance deviation between the repeated location of the repeated abnormal area and the location of the corresponding abnormal area in the abnormal area database is within the preset distance deviation threshold. If so, the repeated abnormal area and the corresponding abnormal area are merged into an updated abnormal area, and the updated abnormal area is stored in the abnormal area database to replace the abnormal area in the abnormal area database, thus completing the location update of the abnormal area.

[0107] In the embodiments provided in this application, when the target vehicle travels to the abnormal area again, the target vehicle will dynamically update the abnormal area database according to the detection results. When it is determined that the pothole has disappeared (vibration is not detected), its confidence weight is reduced; if the pothole repeatedly exists, its weight is increased and it is locked as a long-term avoidance point.

[0108] It should be noted that the embodiments provided in this application will optimize the parameters and confidence level in the pothole record based on the results of multiple updates. When the confidence level is lower than a certain minimum value C_min (such as 0.2), the pothole will be moved from the "active database" to the "historical archive" and will no longer be actively avoided.

[0109] It is understood that in the embodiments provided in this application, when the location of a newly observed pothole meets a preset distance threshold with that of an existing pothole in the database, the two are merged (e.g., by using spatial clustering). During merging, the length of the pothole is updated to a weighted average, the width and peak vertical acceleration are taken as the larger value, the occurrence count is incremented by one, and the confidence level is increased by a preset increment. If the occurrence count reaches a preset threshold, the pothole level is increased.

[0110] In the above process, the potholes in the pothole database are periodically spatially clustered, and potholes that are less than the preset clustering distance and are located in the same lane are merged into one pothole record.

[0111] The pothole level can be customized and used according to different application scenarios and usage conditions.

[0112] Here, the pothole record also includes the pothole detection confidence, which is dynamically updated based on signal strength and multiple observations.

[0113] In this application, personalized comfort map lane lines are gradually formed through multiple driving lessons, achieving long-term self-optimization.

[0114] For example, the method further includes: if the pothole is not detected after multiple consecutive passes of the location information, its confidence level is reduced by a preset attenuation factor; when the confidence level is lower than a preset confidence threshold, the pothole is moved to the historical database and is no longer used as an active obstacle avoidance target.

[0115] In this application, the abnormal area database can be dynamically updated and can adapt to changes in the conditions of different roads.

[0116] If a pedestrian appears during the lane change adjustment process, the vehicle's target obstacle avoidance priority is determined based on the preset target avoidance priority, and it is also determined whether there are similar potholes on the road to be changed.

[0117] The following example illustrates a method for updating abnormal areas, i.e., pits. Please refer to [link / reference]. Figure 2 , Figure 2 The diagram shows a flowchart of pothole updating in an obstacle avoidance method for road surface anomalies provided in an embodiment of this application.

[0118] like Figure 2 As shown, the system first receives pothole detection events (i.e., abnormal road conditions). Then, based on the received pothole detection events, it reads the location and lane information of the potholes and generates pothole coordinates. Next, it determines whether there is already a matching pothole in the abnormal area database. If so, it merges and updates the records, writes the updated records to the database, and synchronously caches them in the cloud. If not, it adds a new pothole entry, writes the updated records to the database, and synchronously caches them in the cloud.

[0119] Figure 3 A structural block diagram of an obstacle avoidance device for road surface anomalies provided in an embodiment of this application is shown. Figure 3 As shown, the obstacle avoidance device 300 for road surface anomalies includes: The acquisition module is used to acquire the current sensor data of the target vehicle driving on the current road when the target vehicle is in the memory driving mode.

[0120] The first determination module is used to determine whether a road abnormality event has occurred based on the current sensor data and preset road abnormality conditions.

[0121] The second determining module is used to determine the location and size information of each abnormal area in the road abnormality event based on the current sensing data if the condition is met.

[0122] The third determination module is used to determine the anomaly level of each anomaly area and the corresponding vehicle avoidance strategy based on location and size information, so that the target vehicle can execute the vehicle avoidance strategy when it travels to the anomaly area again.

[0123] The storage module is used to store the detected abnormal areas of the current road into the abnormal area database.

[0124] The fourth determination module is used to determine whether the distance deviation between the repeated location of the re-detected abnormal area and the location of the corresponding abnormal area in the abnormal area database is within a preset distance deviation threshold when the target vehicle travels to the location of the abnormal area again.

[0125] The update module is used to merge the duplicate abnormal region with the corresponding abnormal region into an updated abnormal region if the condition is met, and store the updated abnormal region in the abnormal region database to replace the abnormal region in the database, thus completing the position update of the abnormal region.

[0126] For example, the current sensing data includes at least one of the target vehicle's attitude change information, the target vehicle's dynamic driving characteristic information, and the target vehicle's suspension displacement value. The target vehicle's attitude change information includes vertical vibration acceleration, and the target vehicle's dynamic driving characteristic information includes the wheel speed of each wheel. Preset abnormal road conditions include at least one of the following: The vertical vibration acceleration is greater than or equal to the preset vertical acceleration threshold.

[0127] The ratio of the instantaneous wheel speed difference of any single wheel to the average wheel speed is greater than or equal to a preset wheel speed difference threshold, and the duration exceeds a preset duration. The instantaneous wheel speed difference of a single wheel is determined by the difference between the wheel speeds of any two wheels.

[0128] The suspension displacement value is greater than or equal to the preset suspension displacement threshold.

[0129] For example, the dynamic driving characteristic information of the target vehicle also includes the vehicle speed. The first determining module is specifically used for: For any abnormal area, the longitudinal offset of the abnormal area on the current road is determined based on the trigger time and speed of the target vehicle when the road abnormality event occurs.

[0130] For any abnormal area, the lateral offset of the abnormal area on the current road is determined based on the instantaneous wheel speed difference of a single wheel and the vertical vibration acceleration.

[0131] Based on each longitudinal offset and each lateral offset, the location information of each abnormal area of ​​the road surface anomaly event is determined.

[0132] For example, the dynamic driving characteristic information of the target vehicle also includes the vehicle speed. The second determining module is specifically used for: For any abnormal region, the length of the abnormal region is determined based on the vehicle speed and the duration of the target vehicle's abnormal event on the road surface. For any abnormal region, the width of the abnormal region is determined based on the lateral coordinates of the left and right wheels of the target vehicle. The lateral coordinates are used to represent the coordinates of each wheel relative to the center of the vehicle.

[0133] The depth of the abnormal region is determined based on the peak value or integral data of vertical vibration acceleration.

[0134] For any abnormal region, the size information of each abnormal region in the road surface anomaly event is determined based on its length, width, and depth.

[0135] For example, determining the lateral offset of an abnormal area on the current road based on the instantaneous wheel speed difference of a single wheel and the vertical vibration acceleration includes: Based on the overlap between the instantaneous wheel speed difference of a single wheel and the peak value of the vertical vibration acceleration, at least one candidate wheel that has deviated is identified.

[0136] Based on the geometric parameters of the target vehicle, the lateral coordinates of each candidate wheel in the vehicle coordinate system are determined, where the geometric parameters are the lateral offset parameters of the wheel center relative to the center of the target vehicle.

[0137] Transform the lateral coordinates to the lane coordinate system to determine the lateral offset of the abnormal area on the current road.

[0138] For example, the third determining module is specifically used for: Based on the number of affected wheels, the peak value of the vertical vibration acceleration of the wheels, location information, and size information, the anomaly level of each anomaly region and the corresponding vehicle avoidance strategy for each anomaly region are determined. Among them, the affected wheels are used to characterize the wheels that are trapped in the anomaly region.

[0139] For example, based on the number of affected wheels, the peak value of the wheel's vertical vibration acceleration, location information, and size information, the anomaly level of each anomaly region and the corresponding vehicle avoidance strategy for each anomaly region are determined, including: When it is determined that the number of affected wheels is not greater than a first quantity threshold, or when it is determined that the peak value of the vertical vibration acceleration of the wheel is within the first preset wheel vibration amplitude range, or when it is determined that the size information is not greater than a first size threshold, or when it is determined that the distance between the position information and the edge of the lane line is not greater than a first distance threshold, the abnormality level of the abnormal area is determined to be a small abnormal area, and the vehicle avoidance strategy corresponding to the small abnormal area is determined to be an in-lane obstacle avoidance strategy.

[0140] When the number of affected wheels is determined to be greater than a first quantity threshold, or when the peak value of the vertical vibration acceleration of the wheels is determined to be a second preset wheel vibration amplitude threshold, or when the size information is determined to be greater than a second size threshold, or when the distance between the position information and the edge of the lane line is greater than a first distance threshold, the abnormality level of the abnormal area is determined to be a large abnormal area, and the vehicle avoidance strategy corresponding to the large abnormal area is determined to be an early lane change strategy. The second preset wheel vibration amplitude threshold is greater than the first preset wheel vibration amplitude range; the second size threshold is greater than the first size threshold.

[0141] For example, during the execution of a vehicle avoidance strategy to avoid abnormal areas, the obstacle avoidance device for road abnormalities also includes: Based on the traffic environment and pre-defined road rules of the target route, determine whether it is safe to avoid abnormal areas.

[0142] If the vehicle avoidance strategy conflicts with the traffic environment and / or preset road rules, the vehicle avoidance strategy will be abandoned and the corresponding safety operation will be performed.

[0143] Compared with the prior art, the obstacle avoidance device for road anomalies provided in this application obtains the current sensor data of the target vehicle traveling on the current road when the target vehicle is in memory driving mode. This differs from the traditional data acquisition method that uses conventional visual sensors or lidar sensors. The current sensor data of the current road is recorded by sensors and lane line information to record the entire trajectory information of high-frequency travel routes. This high-frequency and specific entire trajectory information can more accurately determine the road condition of the current road than lidar sensor data. Then, based on the current sensor data and preset road anomaly conditions, it is determined whether a road anomaly event has occurred. If so, based on the current sensor data, the location and size information of each abnormal area in the road anomaly event are determined. This application can learn the location, size, and impact range of abnormal areas through its own sensor data, and determine the anomaly level of each abnormal area and the corresponding vehicle avoidance strategy based on the location and size information. This allows the target vehicle to execute the vehicle avoidance strategy and automatically optimize the path when it travels to an abnormal area again, avoiding repeated passage through uneven abnormal road sections, thereby improving the user's driving and riding experience.

[0144] Please see Figure 4 , Figure 4 This application provides a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.

[0145] Memory 420 stores machine-readable instructions executable by processor 410. When electronic device 400 is running, processor 410 and memory 420 communicate via bus 430. When the machine-readable instructions are executed by processor 410, they can perform the operations described above. Figures 1 to 2 The steps of the obstacle avoidance method for road surface anomalies in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0146] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figures 1 to 2 The steps of the obstacle avoidance method for road surface anomalies in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0147] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0148] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0149] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0150] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0151] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0152] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0153] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to execute a process for determining a fault identification model.

[0154] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0155] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0156] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0157] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0158] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0159] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0160] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0161] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this specification.

[0162] Obviously, those skilled in the art can make various modifications and variations to this specification without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims and their equivalents, this specification is also intended to include such modifications and variations.

Claims

1. A method for obstacle avoidance in the event of road surface anomalies, characterized in that, The obstacle avoidance methods for road surface anomalies include: When the target vehicle is in memory driving mode, acquire the current sensor data of the target vehicle driving on the current road; Based on the current sensor data and preset road surface anomaly conditions, determine whether a road surface anomaly event has occurred; If so, then based on the current sensing data, determine the location and size information of each abnormal area in the road surface anomaly event; Based on the location information and the size information, the anomaly level of each anomaly area and the vehicle avoidance strategy corresponding to each anomaly level are determined, so that the target vehicle executes the vehicle avoidance strategy when it travels to the anomaly area again.

2. The obstacle avoidance method for road surface anomalies according to claim 1, characterized in that, The method further includes: The detected abnormal areas of the current road are stored in the abnormal area database; When the target vehicle travels to the location of the abnormal area again, it is determined whether the distance deviation between the repeated location of the repeated abnormal area detected again and the location of the corresponding abnormal area in the abnormal area database is within a preset distance deviation threshold. If so, the duplicate abnormal region and the corresponding abnormal region are merged into an updated abnormal region, and the updated abnormal region is stored in the abnormal region database to replace the abnormal region in the abnormal region database, thus completing the position update of the abnormal region.

3. The obstacle avoidance method for road surface anomalies according to claim 1, characterized in that, The current sensing data includes at least one of the target vehicle's attitude change information, the target vehicle's dynamic driving characteristic information, and the target vehicle's suspension displacement value. The target vehicle's attitude change information includes vertical vibration acceleration, and the target vehicle's dynamic driving characteristic information includes the wheel speed of each wheel. The preset abnormal road surface conditions include at least one of the following: The vertical vibration acceleration is greater than or equal to a preset vertical acceleration threshold. The ratio of the instantaneous wheel speed difference of any one of the wheels to the average wheel speed is greater than or equal to a preset wheel speed difference threshold, and the duration exceeds a preset duration. The instantaneous wheel speed difference of a single wheel is determined by the difference between the wheel speeds of any two of the wheels. The suspension displacement value is greater than or equal to a preset suspension displacement threshold.

4. The obstacle avoidance method for road surface anomalies according to claim 3, characterized in that, The dynamic driving characteristic information of the target vehicle also includes the vehicle speed. Based on the current sensor data, the location information of each abnormal area in the road anomaly event is determined, including: For any of the abnormal areas, the longitudinal offset of the abnormal area on the current road is determined based on the trigger time of the road abnormality event of the target vehicle and the vehicle speed; For any of the aforementioned abnormal areas, the lateral offset of the abnormal area on the current road is determined based on the instantaneous wheel speed difference of the single wheel and the vertical vibration acceleration of the wheel. Based on the longitudinal offset and the lateral offset, the location information of each abnormal area of ​​the road surface anomaly event is determined.

5. The obstacle avoidance method for road surface anomalies according to claim 3, characterized in that, The dynamic driving characteristic information of the target vehicle also includes the vehicle speed. Based on the current sensing data, the size information of each abnormal region in the road anomaly event is determined, including: For any of the aforementioned abnormal regions, the length of the abnormal region is determined based on the vehicle speed and the duration of the target vehicle's presence in the road surface anomaly event. For any of the aforementioned abnormal regions, the width of the abnormal region is determined based on the lateral coordinates of the left and right wheels of the target vehicle, wherein the lateral coordinates are used to characterize the coordinates of each wheel relative to the center of the vehicle. The depth of the abnormal region is determined based on the peak value of the vertical vibration acceleration or the integral data of the vertical vibration acceleration. For any of the aforementioned abnormal regions, the size information of each of the abnormal regions in the road surface anomaly event is determined based on the length, the width, and the depth.

6. The obstacle avoidance method for road surface anomalies according to claim 4, characterized in that, The determination of the lateral offset of the abnormal region on the current road based on the instantaneous wheel speed difference of the single wheel and the vertical vibration acceleration includes: Based on the overlap between the instantaneous wheel speed difference of the single wheel and the peak value of the vertical vibration acceleration, at least one candidate wheel that has deviated is identified. Based on the geometric parameters of the target vehicle, the lateral coordinates of each candidate wheel in the vehicle coordinate system are determined, wherein the geometric parameters are the lateral offset parameters of the wheel center relative to the center of the target vehicle. The lateral coordinates are transformed to the lane coordinate system to determine the lateral offset of the abnormal area on the current road.

7. The obstacle avoidance method for road surface anomalies according to claim 3, characterized in that, The step of determining the anomaly level of each of the abnormal regions and the corresponding vehicle avoidance strategy based on the location information and the size information includes: Based on the number of affected wheels, the peak value of the vertical vibration acceleration of the wheels, the location information, and the size information, the anomaly level of each anomaly region and the vehicle avoidance strategy corresponding to each anomaly region are determined, wherein the affected wheels are used to characterize the wheels that are trapped in the anomaly region.

8. The obstacle avoidance method for road surface anomalies according to claim 7, characterized in that, The process of determining the anomaly level of each abnormal region and the corresponding vehicle avoidance strategy for each abnormal region based on the number of affected wheels, the peak value of the vertical vibration acceleration of the wheels, the location information, and the size information includes: When it is determined that the number of affected wheels is not greater than a first number threshold, or when it is determined that the peak value of the vertical vibration acceleration of the wheel is within a first preset wheel vibration amplitude range, or when it is determined that the size information is not greater than a first size threshold, or when it is determined that the distance between the position information and the edge of the lane line is not greater than a first distance threshold, the abnormality level of the abnormal area is determined to be a small abnormal area, and the vehicle avoidance strategy corresponding to the small abnormal area is determined to be an in-lane obstacle avoidance strategy. When it is determined that the number of affected wheels is greater than the first number threshold, or when it is determined that the peak value of the vertical vibration acceleration of the wheel is greater than the second preset wheel vibration amplitude threshold, or when it is determined that the size information is greater than the second size threshold, or when the distance between the position information and the edge of the lane line is greater than the first distance threshold, the abnormality level of the abnormal area is determined to be a large abnormal area, and the vehicle avoidance strategy corresponding to the large abnormal area is determined to be an early lane change strategy, wherein the second preset wheel vibration amplitude threshold is greater than the first preset wheel vibration amplitude range; and the second size threshold is greater than the first size threshold.

9. The obstacle avoidance method for road surface anomalies according to claim 1, characterized in that, During the execution of the vehicle avoidance strategy to avoid the abnormal area, the method further includes: Based on the traffic environment and preset road rules of the target route, determine whether the abnormal area can be safely avoided; If the vehicle avoidance strategy conflicts with the traffic environment and / or the preset road rules, the vehicle avoidance strategy is abandoned and the corresponding safety operation is performed.

10. An obstacle avoidance device for abnormal road surfaces, characterized in that, The obstacle avoidance device for road surface anomalies includes: The acquisition module is used to acquire the current sensor data of the target vehicle driving on the current road when the target vehicle is in the memory driving mode; The first determining module is used to determine whether a road abnormality event has occurred based on the current sensing data and preset road abnormality conditions. The second determining module is used to determine the location and size information of each abnormal area in the road surface abnormality event based on the current sensing data if the condition is met. The third determining module is used to determine the anomaly level of each of the abnormal regions and the vehicle avoidance strategy corresponding to each anomaly level based on the location information and the size information, so that the target vehicle executes the vehicle avoidance strategy when it travels to the abnormal region again.

Images