RULE-BASED ANALYSIS OF LANE CONTACT FOR AUTOMATED DRIVING

The system automates the identification of fault regions in autonomous vehicle steering systems by analyzing external and internal parameters, addressing the inefficiencies of manual data review in current methods.

DE102023129286A1Pending Publication Date: 2024-12-05GM GLOBAL TECHNOLOGY OPERATIONS LLC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
DE102023129286
Authority / Receiving Office
DE · DE
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-06-01
Filing Date
2023-10-25
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

Current methods for determining the cause of lane contact events in autonomous vehicles are time-consuming and subjective, requiring manual engineering review of data.

Method used

A system utilizing sensors and processors to detect and analyze external and internal parameters to identify error areas in the driving system, including vehicle detection, route planning, and vehicle control, to determine the cause of lane contact events.

Benefits of technology

Automates the identification of fault regions in the steering system, reducing the time and subjectivity in determining the cause of lane contact events, thereby improving guidance systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

A system for designing a driving system for a vehicle. The system comprises a first sensor, a second sensor, and a processor. The first sensor is configured to detect an external parameter indicating a lane marking during a period in which an automated driving program is running on the vehicle. The second sensor is configured to detect an internal parameter of the vehicle during the same period. The processor is configured to detect a lane-contact event occurring during this period, determine a fault in the driving system that led to the lane-contact event based on the internal and external parameters, identify a fault zone in the driving system where the fault occurs, and modify the structure of a driving system program with respect to the fault zone.
Need to check novelty before this filing date? Find Prior Art

Description

INTRODUCTION

[0001] The subject matter of the disclosure relates to the operation of an autonomous vehicle or a vehicle's cruise control system, and more particularly to a system and method for analyzing the occurrence of a lane departure event to identify a fault area of ​​a vehicle's steering system leading to the lane departure.

[0002] Both an autonomous vehicle and a vehicle operating in super-cruise mode can employ a guidance system to enable the vehicle to safely navigate a section of road. The guidance system keeps the vehicle within a lane designated by lane markings. A lane departure event occurs when the vehicle touches or overshoots a lane marking or deviates from its lane. For safety reasons, it is desirable to minimize or eliminate the occurrence of inadvertent lane departures. If a lane departure event occurs during automated vehicle operation, it is desirable to determine its cause so that the guidance system can be retrofitted or redesigned. Currently, determining the cause of a lane departure requires a team of engineers to manually review the data, which is time-consuming and subjective.Accordingly, it is desirable to provide a system that can determine the cause of a lane departure event to assist in the development and improvement of guidance systems. SUMMARY

[0003] In an exemplary embodiment, a method for operating a driving system for a vehicle is disclosed. An external parameter indicative of a lane marking is detected with a first sensor during a period in which an automated driving program is executed on the vehicle. An internal parameter of the vehicle is detected with the aid of a second sensor during the period. A lane departure event occurring during the period is detected. A fault occurring in the driving system that leads to the lane departure event is determined by a processor based on the internal parameter and the external parameter. The processor determines a fault region of the driving system in which the fault occurs. The design of a program of the driving system is modified with respect to the fault region.

[0004] In addition to one or more of the features described herein, each of the internal and external parameters comprises a time series of data acquired over a time interval. The error region is at least one of the following: vehicle detection region, path planning region, vehicle control region, and reporting region. An error in the vehicle detection region includes an error in detecting a lane marking. The method further includes determining an error in the path planning region when a lane engagement occurs by comparing a difference between a planned path of the vehicle and an actual path of the vehicle to a threshold. The method further includes determining a lane change problem due to at least one of late cancellation of a lane change, oversteering during a lane change, and overadaptation for the lane change.The method further includes determining the responsiveness of the driving system to the lane departure event.

[0005] In another exemplary embodiment, a driving system for a vehicle is disclosed. The driving system includes a first sensor, a second sensor, and a processor. The first sensor is configured to detect an external parameter indicative of a lane marking during a period in which an automated driving program is executed on the vehicle. The second sensor is configured to detect an internal parameter of the vehicle during the period. The processor is configured to detect a lane departure event occurring during the period, determine a fault occurring in the driving system and leading to the lane departure event based on the internal parameter and the external parameter, identify a fault region of the driving system in which the fault occurs, and modify the design of a program of the driving system with respect to the fault region.

[0006] In addition to one or more of the features described herein, each of the internal and external parameters includes a time series of data acquired over a time interval. The error range is at least one of the following: vehicle detection range, path planning range, vehicle control range, and reporting range. A vehicle detection range error includes a failure to detect a lane marking. The processor is further configured to determine an error in the path planning range when a lane incursion occurs by comparing a difference between a planned vehicle path and an actual vehicle path to a threshold.The processor is further configured to detect a lane change problem due to a late lane change cancellation and / or oversteer during a lane change and / or overadaptation for the lane change. The processor is further configured to determine the responsiveness of the driving system to the lane departure event.

[0007] In another exemplary embodiment, a system for designing a driving system for a vehicle is disclosed. The system includes a first sensor, a second sensor, and a processor. The first sensor is configured to detect an external parameter indicative of a lane marking during a period in which an automated driving program is being executed on the vehicle. The second sensor is configured to detect an internal parameter of the vehicle during the period. The processor is configured to detect a lane departure event occurring during the period, determine a fault occurring in the driving system and leading to the lane departure event based on the internal parameter and the external parameter, identify a fault region of the driving system in which the fault occurs, and modify the design of a program of the driving system with respect to the fault region.

[0008] In addition to one or more of the features described herein, the error region is at least one of the following: a vehicle detection region, a path planning region, a vehicle control region, and a reporting region. A vehicle detection region error includes a failure to detect a lane marking. The processor is further configured to determine an error in the path planning region when a lane incursion occurs by comparing a difference between a planned vehicle path and an actual vehicle path to a threshold. The processor is further configured to determine a lane change problem due to a late cancellation of a lane change, an oversteer during a lane change, and / or an overadaptation for the lane change.The processor is further configured to determine the responsiveness of the driving system to the lane departure event.

[0009] The above features and advantages, as well as other features and advantages of the disclosure, will be readily apparent from the following detailed description when taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Further features, advantages and details are listed only as examples in the following detailed description, which refers to the drawings in which: Fig. 1 shows a vehicle that can be operated in an autonomous mode or in a cruise control mode according to an exemplary embodiment; Fig. 2 is a schematic diagram showing a workflow for analyzing and improving a driving system with respect to lane marking detection and movement with respect to the lane markings; Fig. 3 is a schematic diagram showing various programs operating on the driving system to steer the vehicle along a trajectory, in an illustrative embodiment; Fig. Figure 4 shows a schematic diagram identifying error areas for the driving system programs; Fig. Figure 5 shows a variety of time series that can be analyzed in the remote processor to identify a fault area; Fig. 6 shows a flowchart of a method for identifying a reason for the occurrence of a lane touch in an illustrative embodiment; Fig. 7 shows a flowchart for identifying a lane marking detection problem in an illustrative embodiment; Fig. Figure 8 shows a flowchart of a method for identifying problems in route planning; Fig. 9 shows a flowchart of a method for detecting lane change problems; and Fig. Figure 10 shows a flowchart of a method for identifying problems on straight roads. DETAILED DESCRIPTION

[0011] The following description is merely exemplary in nature and is not intended to limit the disclosure, its application, or uses. It should be understood that throughout the drawings, corresponding reference numerals indicate like or corresponding parts and features.

[0012] According to an exemplary embodiment, Fig. 1 shows a vehicle 100 that can be operated in an autonomous mode or in a cruise control mode. The vehicle 100 has a driving system 102 that controls the movement of the vehicle over a section of road.

[0013] The driving system 102 may include a sensor system 104 for obtaining information about the environment of the vehicle 100 or the vehicle itself, a controller 106 for calculating possible actions for the autonomous vehicle based on the information obtained and for performing one or more of the possible actions, and an actuator system 108 that controls the navigation of the vehicle, such as a steering wheel actuator, a brake actuator, an acceleration actuator, etc., based on the action calculated by the controller 106.

[0014] The sensor system 104 may include external sensors (first sensors) such as cameras, lidar, radar, GPS, etc., which measure various external parameters of the environment, the road, the position of lane markings, etc. The sensor system 104 may also include internal sensors (second sensors) that measure internal parameters of the vehicle, such as an accelerometer, an angle measuring device, etc. The data obtained for a particular internal or external parameter may be collected as a time series. Example parameters include the road curvature, the distance between the vehicle and the lane and the right lanes or the left and right lane markings, the vehicle speed, the vehicle yaw rate, the vehicle lateral acceleration, the vehicle longitudinal acceleration, the vehicle location, the steering wheel angle (SWA), the steering torque, the LCOD status (Lane Change on Demand).Lane change on demand) and / or the LCC status (Lane Centering Control), etc.

[0015] The controller 106 may include processing circuitry, which may include an application-specific integrated circuit (ASIC), an electronic circuit, a processor (common, dedicated, or grouped), and memory executing one or more software or firmware programs, combinational logic circuitry, and / or other suitable components that provide the described functionality.The controller 106 may include a non-transitory computer-readable medium storing instructions that, when processed by one or more processors of the controller 106, implement a method for analyzing parameters received from the sensor system 104, determining the occurrence of a lane departure event, determining a root cause or fault zone for the lane departure event, and suggesting possible improvements to reduce the occurrence of a lane departure event in the future.

[0016] The vehicle 100 also includes a communication unit 110 that can communicate with a remote processor 120. In various embodiments, data can be transmitted from the vehicle 100 to the remote processor 120 for processing outside the vehicle. Data or software can also be transmitted from the remote processor 120 to the vehicle 100.

[0017] Fig. 2 shows a schematic diagram 200 illustrating a workflow for analyzing and improving a driver system 102 with respect to sensing lane markings and moving relative to the lane markings. The workflow includes calculations performed either onboard the vehicle 100 using a processor (e.g., in the controller 106) of the vehicle 100 or off-vehicle using the remote processor 120. A fleet of vehicles 202 is driven in various environments to obtain data in the form of a plurality of time-series data items. The plurality of time-series data items are sent to the remote processor 120, which analyzes the time-series data to determine when a lane departure occurs and the cause of the lane departure. In particular, the remote processor 120 determines an area where a fault leading to the lane departure occurs.A lane departure event can occur due to a fault in multiple areas. Examples of faults include, but are not limited to, lane awareness errors, path planning errors, steering errors, etc. When a lane departure event occurs, the remote processor 120 determines in which area the fault leading to the lane departure event occurred (a "fault area"). The result of the analysis is a recommendation for reviewing and / or improving the design of the fault area, which can be implemented and used in the vehicle fleet 202. If the analysis fails to identify a fault area, a new area (unknown class) can be created and used in subsequent analyses.

[0018] Fig. 3 shows a schematic diagram 300 depicting various programs operating on the driving system 102 to steer the vehicle along a trajectory, in one illustrative embodiment. The programs include a perception model 302, a path planning model 304, a vehicle tracking controller 306, a steering controller 308, and a vehicle position detection / estimation program 312. The perception model 302 determines the presence and position of lane markings from the data received from the detection system 104. The data may relate to weather conditions, road conditions, wind conditions, road gradient, etc. The path planning model 304 is an algorithm or model for planning a vehicle trajectory based on the position of the lane markings.The trajectory may include a straight-ahead journey, a curve, a lane change, a lane merge, a highway exit, a turn at an intersection, etc. The tracking controller 306 receives inputs indicating a deviation of the vehicle's travel path from a planned trajectory and determines actions that can be taken on the vehicle to make corrections so that the vehicle continues to move along the planned trajectory. The tracking controller 306 sends signals to the steering controller 308, which determines a steering torque or angle to be applied to a steering wheel of the vehicle 100 via the actuators 108.

[0019] The vehicle position detection / estimation program 312 tracks the position of the vehicle 100 in response to the steering signals applied to the vehicle. The vehicle position may be a lateral position of the vehicle within a lane or relative to a lane marking. The vehicle position is sent to a difference engine 314, which determines the travel path deviation based on the vehicle position and the planned trajectory. The travel path deviation may then be sent to the tracking controller 306 to form a feedback loop.

[0020] A lane departure event monitor 316 receives data from the driving system 102 programs and analyzes the data to determine when a lane departure event occurs. Further analysis can determine the cause of the lane departure, which can lead to improvements and redesigns.

[0021] Fig. 4 shows a schematic diagram 400 that identifies error areas for the programs of the driving system 102. The schematic diagram 400 includes a vehicle detection area 402, a path planning area 404, a vehicle control area 406, and a reporting area 408. The vehicle detection area 402 includes the perception model 302 and the vehicle position detection / estimation program 312. The path planning area 404 includes the path planning model 304. The vehicle control area 406 includes the tracking control program 306 and the steering control program 308. The reporting area includes a lane departure event monitor 316.

[0022] An error occurring in the vehicle detection area 402 may be due to lane marking issues, such as unclear lane markings, old and new lane markings, road color changes, the occurrence of a road split or road merge. An error may also occur due to global positioning system (GPS) satellite or map errors, poor perception due to weather, time of day, environment, etc., or the failure of a sensor.

[0023] An error in the path planning area 404 may be caused by a road split or junction, the occurrence of a construction site, the occurrence of other objects (e.g., vehicles, pedestrians) on the road that are nearby or hidden from view, etc. The error may also be due to the detection of ghost objects or the incorrect identification of an object's position.

[0024] A fault that occurs in the vehicle control area 406 can occur in the tracking controller 306 and / or the steering controller 308. The fault can be caused by control transition faults, weather-related control faults, or vehicle degradation faults. A control transition fault occurs at a transition point between human control and vehicle control. The control transition fault can be due to the operation of a Lane Change on Demand (LCOD) program or a manual lane change. Errors can be expected during sharp turns, zigzag paths, path changes, etc. Weather-related control errors can be errors caused by crosswinds, rain, snow, a slippery road, a bumpy road, a pothole, a road, a road grade, a bank angle, etc.Vehicle degradation faults may include faults due to tire pressure, wheel misalignment, suspension, uneven braking, uneven drive to the wheels, differential drive, steering sensor faults, actuator faults, etc.

[0025] An error occurring in the reporting area 408 is due to a malfunction of the lane departure event monitor 316. Such errors may be due to a data acquisition problem, a problem with the on-board memory, a problem with the electronic control unit, incorrect attribution of the lane departure to a vehicle control (rather than a manual control), and other false positives due to incorrect lane detection.

[0026] Fig. 5 shows a plurality of time series 500 that can be analyzed in the remote processor 120 to identify a fault area. For each time series, the time in seconds is indicated on the abscissa. A first time series 502 includes data related to when the vehicle 100 enters super cruise mode 509 and a lane departure 511 occurs. A second time series 504 includes data related to a steering and road curve. A third time series 506 includes data related to lane offset. A fourth time series 508 includes data related to the operation of the lane departure event monitor 316. In the first time series 502, a super trip curve 510 indicates that the super trip is activated at approximately t = 176.5 seconds, and a lane event curve 512 indicates that a lane contact occurs at approximately t = 178.3 seconds.In the second time series 504, a steering angle curve (SWA) 514 indicates that the steering wheel is briefly turned to the left at approximately t = 177.0 seconds. In the third time series 506, a distance-to-target-lane curve 516 indicates a rapid movement of the vehicle to the left at approximately t = 176.5 seconds. The occurrence of the lane-entry event 511 is also indicated.

[0027] Fig. 6 shows a flowchart 600 of a method for identifying a reason for the occurrence of a lane contact in one illustrative embodiment. The method begins in box 602 where a lane contact report is received. In box 604, the lane contact report is compared with the left and right lane offsets to determine the integrity of the report. In box 606, a decision is made based on the results of the cross-check in box 604. If the report is not a correct report, the method proceeds to box 608. In box 608, an output indicating a report error is generated. The method then proceeds to box 636 where it ends.

[0028] If the report is correct according to field 606, the procedure continues with field 610. In field 610, a check is made to see if there was a problem in determining the lane marking(s). In field 612, a decision is made based on the results of the check in field 610. If there was a problem in detecting the lane marking, the procedure continues with field 614. In field 614, the procedure checks for related conditions and indicates lane detection problems. Details of the checks performed in field 614 are provided in Fig. 7. From field 614, the procedure continues with field 636, where the procedure ends.

[0029] If, according to field 612, there is no problem with the lane marking detection, the process continues with field 616. In field 616, a check is made to determine whether there are any problems with the route planning. In field 618, a decision is made based on the results of field 616. If there is a problem with the route planning, the process continues with field 620. In field 620, the route planning problem is identified and output. Details of the process performed in field 620 are described with reference to Fig. 8. From field 620, the procedure continues to field 636, where the procedure ends.

[0030] If, according to field 618, there is no problem with the path planning, the method continues to field 622. In field 622, a determination is made as to whether the fault occurred during a selected time frame shortly after the cruise control or speed controller was engaged. Such a fault may be related to the transition from human control of the vehicle to vehicle-based control of the vehicle. If the fault occurred within the selected time frame, the method continues to field 624. In field 624, the records are checked for conditions immediately prior to the cruise control being engaged, e.g., the vehicle's proximity to the lane markings during the transition, whether the vehicle was traveling on a road, etc. Such conditions are provided as output. The method then continues to field 636, where it ends.

[0031] If, according to field 622, the error occurred after the selected time frame, the procedure continues to field 626. In field 626, the records are checked to determine if the vehicle was traveling on a winding road. If the vehicle was traveling on a winding road at the time of lane contact, the procedure continues to field 628. In field 628, the records are checked for road entry or exit conditions or curve conditions, and the curve control problems are output. The procedure then continues to field 636, where it ends.

[0032] If, according to field 626, the vehicle was not on a winding road, the method continues to field 630. In field 630, the records are reviewed to determine if the vehicle responded to a lane change on demand (LCOD) command. If the vehicle responded to an LCOD, the method continues to field 632. In field 632, the records are reviewed for related LCOD conditions. The LCOD-related control problems are output. The method then continues to field 636, where it ends.

[0033] If, according to field 630, the vehicle has not responded to the LCOD, the process continues to field 634. In field 634, the records are reviewed for related response conditions. These possible related actions are output. The process then continues to field 636, where it ends.

[0034] Fig. Figure 7 shows a flowchart 700 for identifying a lane marking detection problem in one illustrative embodiment. The method begins in block 702. In block 704, variables for determining the lane marking prior to lane entry are entered and verified. These variables include, among others, Warning_Lane_Unsafe, Left_Lane_Quality_Indicator, Right_Lane_Quality_Indicator, Map_Quality, etc.

[0035] In field 706, a decision is made based on the variable Warning_Lane_Unsafe. If Warning_Lane_Unsafe is true (i.e., if the lane detection system indicates that it is unsure about detecting the lane marking), the method continues with field 712. Otherwise, the method continues with field 708. In field 708, a moving average of the lane qualities for the left and right lane markings is calculated using a sliding window and based on data from a camera and a map.

[0036] In field 710, a decision is made based on the lane quality. If the lane quality is low or poor, the process continues to field 712. In field 712, the records are checked for related conditions, e.g., a lane merge or split, road construction, a curved road, a lane change, etc. In field 714, the lane detection problem is output with the corresponding conditions. The process then continues to field 718, where it ends. If, according to field 710, the lane quality is good, the process continues to field 716. In field 716, an output is generated indicating that there is no lane marking problem.

[0037] Fig. 8 shows a flowchart 800 of a method for identifying problems in path planning. The method begins in block 802. In block 804, the values ​​of the path planning variables, and thus the values ​​determined within a selected time period prior to the lane entry event, are checked. These path planning variables include, among others, the variable Distance_to_Target_Path(t). In an exemplary embodiment, the time period spans from three seconds before lane entry to one second before lane entry. A negative value of Distance_to_Target_Path > 0 means the vehicle is traveling to the left; a positive value means the vehicle is traveling to the right.

[0038] In field 806, a minimum value for the distance to the target route during the selected time and a maximum value for the distance to the target route during the selected period are determined.

[0039] In field 808, a path planning error condition is checked. The condition is, for example, whether the minimum value is within 40 centimeters of the left lane and a touch of the left lane is received, or the maximum value is within 40 centimeters of the right lane marking and a touch of the right lane is received, and that the road is not curved and a lane change is not specified. If this is the case, the process continues with field 810. In field 810, the problem with the path planning is output. The process continues in field 814, where it ends.

[0040] If the condition is not met according to field 808, the process continues with field 812. Field 812 generates an output indicating that there is no problem with the route planning. From field 812, the process continues to field 814, where the process ends.

[0041] Fig. Figure 9 shows a flowchart 900 of a method for detecting lane change problems. The method begins in field 902. In field 904, the values ​​of the lane change variables determined within a selected time period prior to the lane contact event are entered. These lane change variables include, among others, a lane change status and a lane offset.

[0042] In field 906, the records are reviewed to determine if a lane change was aborted before the lane contact event occurred. If the lane change was aborted before the lane contact, the process continues to field 908. Field 908 generates an output indicating that a delayed or late lane change abort occurred. The process continues to field 920, where it ends.

[0043] If, according to field 906, the lane change was not aborted or was aborted after a lane contact event, the method continues to field 910. In field 910, the records are checked to determine if another lane marking is contacted, e.g., a next lane marking of the next lane. If the next lane marking is contacted, the method continues to field 912. In field 912, output is generated to indicate a lane change override. The method continues to field 920, where it ends.

[0044] If, according to field 910, the nearest lane marking is not contacted, the method continues to field 914. In field 914, the records are reviewed to determine if the nearest lane was contacted again after the lane contact event. If the nearest lane is contacted again, the method continues to field 916. In field 916, an output is generated indicating that an excessive lane change adjustment was made. The method then continues to field 920, where it ends.

[0045] If, according to field 914, the nearest lane is not engaged after the initial lane engagement event, the method proceeds to field 918. In field 918, an output is generated indicating that there are no lane change issues. From field 918, the method proceeds to field 920, where the method ends.

[0046] Fig.10 shows a flowchart 1000 of a method for identifying problems on straight roads. The method begins in block 1002. In block 1004, the values ​​of the steering variables that occur within a time window prior to the lane departure event are entered. Such values ​​of steering variables may include, but are not limited to, a steering angle, a lane offset, etc. In one illustrative embodiment, the time window may range from approximately 2 seconds prior to the lane departure event to approximately 1 second prior to the lane departure event.

[0047] In field 1006, an average value of the steering angle A within the time window is calculated. In field 1008, the average steering angle is compared to a threshold value for the steering angle. If the absolute value of the average steering angle is less than or equal to the threshold value, the method proceeds to field 1010. In field 1010, an output is generated indicating that the steering did not respond to the lane departure event. From field 1010, the method continues to field 1018, where the method ends.

[0048] If, according to field 1008, the magnitude value of the average steering angle is greater than the threshold, the process proceeds to field 1012. In field 1012, the records are reviewed to determine whether the steering angle steered the vehicle toward the lane that was contacted. If the steering was toward the contacted lane, the process proceeds to field 1014. Otherwise, the process continues with field 1016.

[0049] In box 1014, an output is generated indicating that the steering incorrectly responded to the lane departure. In box 1016, an output is generated indicating that the steering was too late or too little to respond to the lane departure event. From box 1014 or box 1016, the method continues to box 1018, where the method ends.

[0050] The terms "a" and "an" do not imply a limitation of quantity, but denote the presence of at least one of the mentioned items. The term "or" means "and / or" unless the context clearly indicates otherwise. Whenever "an aspect" is mentioned throughout the description, this means that a particular element (e.g. a feature, structure, step or property) described in connection with the aspect is included in at least one of the aspects described therein and may or may not be present in other aspects. It is understood that the described elements in the various aspects may be combined in any suitable way.

[0051] When an element such as a layer, film, sheet, region, or substrate is described as lying "on" another element, it may lie directly on top of the other element, or there may be intervening elements. In contrast, when an element is described as lying "directly on" another element, there are no intervening elements.

[0052] Unless otherwise indicated herein, all examination standards are the most recent standard in effect on the filing date of this application or, if priority is claimed, on the filing date of the earliest priority application in which the examination standard appears.

[0053] Unless otherwise defined, technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0054] While the above disclosure has been described with reference to exemplary embodiments, those skilled in the art will understand that various changes may be made and equivalents may be substituted for elements thereof without departing from the scope of the disclosure. Furthermore, many modifications may be made to adapt a particular situation or material to the teachings of the disclosure without departing from the essential scope of the disclosure. Therefore, the present disclosure is not intended to be limited to the particular embodiments disclosed, but is intended to include all embodiments falling within its scope.

Claims

[1] A method for operating a driving system for a vehicle, comprising: Detecting an external parameter indicative of a lane marking using a first sensor during a period in which an automated driving program is executed on the vehicle; Recording an internal parameter of the vehicle using a second sensor during the period; Detecting a lane departure event that occurs during the period; Determining, in a processor, a fault occurring in the driving system resulting in the lane departure event based on the internal parameter and the external parameter; Identifying, in the processor, a fault area of ​​the driving system in which the fault occurs; and Changing the structure of a driving system program with respect to the error area. [2] The method of claim 1, wherein each of the internal parameter and the external parameter includes a time series of data obtained over a time interval. [3] The method of claim 1, wherein the error region is at least one of: (i) a vehicle detection region; (ii) a route planning region; (iii) a vehicle control region; and (iv) a reporting region. [4] The method of claim 3, wherein an error in the vehicle detection area comprises an error in detecting a lane marking. [5] The method of claim 3, further comprising determining an error in the route planning area when a lane touch occurs by comparing a difference between a planned route of the vehicle and an actual route of the vehicle with a threshold value. [6] Driving system for a vehicle, comprising: a first sensor configured to detect an external parameter indicative of a lane marking during a period in which an automated driving program is being executed on the vehicle; a second sensor configured to detect an internal parameter of the vehicle during the period; a processor configured to: Detecting a lane departure event that occurs during the period; Determining a fault occurring in the driving system resulting in the lane departure event based on the internal parameter and the external parameter; Identifying a fault area of ​​the driving system in which the fault occurs; and Changing the structure of a driving system program with respect to the error area. [7] The driving system of claim 6, wherein each of the internal parameter and the external parameter includes a time series of data obtained over a time interval. [8] The driving system according to claim 6, wherein the error area is at least one of: (i) a vehicle detection area; (ii) a route planning area; (iii) a vehicle control area; and (iv) a reporting area. [9] The driving system of claim 8, wherein an error in the vehicle detection area includes an error in detecting a lane marking. [10] The driving system of claim 8, wherein the processor is further configured to determine an error in the travel path planning area when a lane touch occurs by comparing a difference between a planned travel path of the vehicle and an actual travel path of the vehicle with a threshold value.