Vehicle lateral abnormality detection method, device, equipment and medium

Abstract

Embodiments of the present disclosure relate to a vehicle lateral anomaly detection method, device, equipment and medium, wherein the method comprises: obtaining a real-time position, a reference trajectory and steering control information of a vehicle; determining a reference curvature of the vehicle at a current position according to the real-time position and the reference trajectory; determining a desired curvature of the vehicle according to the steering control information; and performing anomaly detection on the vehicle according to the reference curvature and the desired curvature. By using the above technical solution, the lateral anomaly detection of the vehicle is realized by comparing the reference curvature based on the reference trajectory projection point with the theoretical desired curvature corresponding to the vehicle steering control quantity, which can effectively detect the anomaly problem when tracking reference trajectories of different shapes. Since the reference curvature is relatively stable and the desired curvature is a theoretical calculation value, the defect of low accuracy caused by the existence of large noise and delay in feedback data is avoided, the accuracy of anomaly detection is improved, and the driving safety of the vehicle is improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle control technology, and in particular to a method, device, equipment and medium for detecting lateral anomalies in vehicles. Background Technology

[0002] Safety is a critical requirement in vehicle driving systems, especially autonomous driving systems. This includes aspects such as sensor safety, operating system security, control system security, and communication network security. During vehicle operation, it is necessary to assess real-time conditions to determine if an abnormal situation is occurring and to handle it according to the severity of the anomaly.

[0003] In controlling driving system safety, lateral tracking safety is paramount to ensuring normal vehicle operation. From a planning and control perspective, vehicles can typically automatically track the reference trajectory provided by the planning system or maintain a certain distance from it. However, when a vehicle encounters a sudden event, lateral anomaly detection is required in the control module. Currently, lateral anomaly detection typically uses lateral tracking deviation, steering wheel angle, or curvature as criteria for identifying lateral anomalies or safety malfunctions. However, methods based on lateral tracking deviation can lead to inaccurate detection results in specific road conditions or when thresholds are inaccurate. Methods based on steering wheel angle or curvature rely heavily on the accuracy of feedback signals, and the accuracy can be significantly reduced due to noise or delays in the feedback signals. Summary of the Invention

[0004] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a method, apparatus, equipment, and medium for detecting lateral anomalies in vehicles.

[0005] This disclosure provides a method for detecting lateral anomalies in vehicles, the method comprising:

[0006] Acquire the vehicle's real-time location, reference trajectory, and steering control information;

[0007] The reference curvature of the vehicle at its current position is determined based on the real-time position and the reference trajectory.

[0008] The desired curvature of the vehicle is determined based on the steering control information;

[0009] Anomaly detection is performed on the vehicle based on the reference curvature and the desired curvature.

[0010] This disclosure also provides a vehicle lateral anomaly detection device, the device comprising:

[0011] The information module is used to acquire the vehicle's real-time location, reference trajectory, and steering control information;

[0012] A reference module is used to determine the reference curvature of the vehicle at its current position based on the real-time position and the reference trajectory.

[0013] The desired module is used to determine the desired curvature of the vehicle based on the steering control information.

[0014] The detection module is used to perform anomaly detection on the vehicle based on the reference curvature and the desired curvature.

[0015] This disclosure also provides an electronic device, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the vehicle lateral anomaly detection method as provided in this disclosure.

[0016] This disclosure also provides a computer-readable storage medium storing a computer program for executing the vehicle lateral anomaly detection method provided in this disclosure.

[0017] Compared with the prior art, the technical solution provided in this disclosure has the following advantages: The vehicle lateral anomaly detection scheme provided in this disclosure acquires the vehicle's real-time position, reference trajectory, and steering control information; determines the reference curvature of the vehicle at its current position based on the real-time position and reference trajectory; determines the vehicle's desired curvature based on the steering control information; and performs anomaly detection on the vehicle based on the reference curvature and the desired curvature. By comparing the reference curvature of the reference trajectory projection point with the theoretical desired curvature corresponding to the vehicle's steering control quantity, lateral anomaly detection is achieved. This effectively detects anomalies when tracking reference trajectories of different shapes. Since the reference curvature is relatively stable and the desired curvature is a theoretically calculated value, it avoids the low accuracy caused by significant noise and delay in the feedback data, thus improving the accuracy of anomaly detection and consequently enhancing vehicle driving safety. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1A flowchart illustrating a vehicle lateral anomaly detection method provided in this embodiment of the disclosure;

[0021] Figure 2 A flowchart illustrating another vehicle lateral anomaly detection method provided in this embodiment of the present disclosure;

[0022] Figure 3 A flowchart illustrating another vehicle lateral anomaly detection method provided in this embodiment of the present disclosure;

[0023] Figure 4 This is a schematic diagram of the structure of a vehicle lateral anomaly detection device provided in an embodiment of the present disclosure;

[0024] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0025] In the following detailed description, numerous specific details of this disclosure are set forth by way of example in order to provide a thorough understanding of the relevant disclosure. However, it will be apparent to those skilled in the art that this disclosure may be practiced without these details. It should be understood that the terms “system,” “apparatus,” “unit,” and / or “module” used in this disclosure are a method of distinguishing different parts, elements, sections, or components at different levels in a sequential arrangement. However, these terms may be replaced by other expressions if they can achieve the same purpose.

[0026] It should be understood that when a device, unit, or module is referred to as being "on," "connected to," or "coupled to" another device, unit, or module, it may be directly connected to or coupled to, or communicate with, other devices, units, or modules, or there may be intermediate devices, units, or modules present, unless the context explicitly indicates otherwise. For example, the term "and / or" as used in this disclosure includes any one and all combinations of one or more of the associated listed items.

[0027] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure. As shown in this specification and claims, unless the context clearly indicates otherwise, words such as "a," "an," "an," and / or "the" do not specifically refer to the singular and may include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified features, integrals, steps, operations, elements, and / or components, and such expressions do not constitute an exclusive list, in which other features, integrals, steps, operations, elements, and / or components may also be included.

[0028] Referring to the following description and accompanying drawings, these and other features and characteristics, operating methods, functions of related structural elements, combinations of parts, and economics of manufacture of this disclosure can be better understood, wherein the description and drawings form part of the specification. However, it is clearly understood that the drawings are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this disclosure. It is understood that the drawings are not drawn to scale.

[0029] Various structural diagrams are used in this disclosure to illustrate various variations of embodiments according to this disclosure. It should be understood that the preceding or following structures are not intended to limit this disclosure. The scope of protection of this disclosure is defined by the claims.

[0030] During the operation of vehicle driving systems, especially autonomous driving systems, unforeseen problems such as uncontrolled steering mechanisms, tire blowouts, significant steering mechanism delays, and abnormal control program operation can occur. These issues can significantly impact the normal operation of the vehicle, especially at high speeds, potentially leading to traffic accidents. During vehicle operation, it is necessary to assess the real-time status to determine if an abnormal situation is occurring and to handle it according to the severity of the abnormality. Besides system failures caused by external factors, there is also the issue of ensuring the continued safe operation of the system by maintaining other modules based on established safety mechanisms when a single module fails due to unforeseen circumstances.

[0031] In controlling driving system safety, lateral tracking safety is paramount to ensuring normal vehicle operation. From a planning and control perspective, vehicles can typically automatically track the reference trajectory provided by the planning system or maintain a certain distance from it. However, when a vehicle encounters a sudden event, such as uncontrolled steering or a tire blowout, lateral anomaly detection is required in the control module. Currently, lateral anomaly detection typically uses lateral tracking deviation, steering wheel angle, or curvature as criteria for identifying lateral anomalies or safety malfunctions. However, methods based on lateral tracking deviation cannot keep the deviation within a small range for trajectories with various curvatures. Especially on high-curvature S-curves, roundabouts, and U-turns, the detection effectiveness drops significantly. Furthermore, setting the threshold is difficult; inaccurate threshold settings lead to inaccurate detection results, meaning inaccurate results exist on specific road sections or when the threshold is inaccurate. Methods based on steering wheel angle or curvature rely on the accuracy of the feedback signal, and the accuracy can be greatly reduced by noise or delays in the feedback signal. To address the aforementioned problems, this disclosure provides a method for detecting lateral anomalies in vehicles, which will be described below with reference to specific embodiments.

[0032] Figure 1This is a flowchart illustrating a vehicle lateral anomaly detection method provided in an embodiment of this disclosure. The method can be executed by a vehicle lateral anomaly detection device, which can be implemented using software and / or hardware, and is generally integrated into an electronic device. Figure 1 As shown, the method includes:

[0033] Step 101: Obtain the vehicle's real-time location, reference trajectory, and steering control information.

[0034] The vehicles described in this disclosure can be of various types, such as autonomous vehicles. The real-time position of the vehicle can be its specific location at different times during its operation. The reference trajectory can be a pre-planned driving trajectory by the vehicle's control module, which the vehicle follows. Steering control information can be information issued by the control module to control the vehicle's steering based on its real-time driving status during operation. This information can be calculated by the control module using a vehicle control algorithm. In this disclosure, the steering control information may include the steering wheel angle or front wheel angle issued by the control module.

[0035] In this embodiment of the disclosure, the vehicle lateral anomaly detection device can obtain the real-time position of the vehicle through sensors pre-installed in the vehicle, and obtain the reference trajectory pre-stored by the control module and the currently issued steering control information.

[0036] Step 102: Determine the reference curvature of the vehicle at its current location based on the real-time location and the reference trajectory.

[0037] Among them, the reference curvature can be the curvature determined based on the reference trajectory. Curvature can be the rate of rotation of the tangent direction with respect to the arc length at a certain point on the curve, indicating the degree to which the curve deviates from a straight line. Mathematically, it characterizes the degree of curvature of the curve at a certain point. The greater the curvature, the greater the degree of curvature of the curve.

[0038] In this embodiment of the disclosure, determining the reference curvature of the vehicle at its current position based on the real-time location and the reference trajectory may include: determining the reference curvature of the vehicle at its current position using a preset curvature algorithm based on the real-time location and the reference trajectory, wherein the preset curvature algorithm includes the three-point method or the model tracking method.

[0039] In some embodiments, when the preset curvature algorithm is the three-point method, the preset curvature algorithm is used to determine the reference curvature of the vehicle at the current position based on the real-time position and the reference trajectory, including: determining the projection point of the real-time position in the reference trajectory, the previous reference point, and the next reference point; determining the Euclidean distance between each pair of points based on the coordinates of the projection point, the previous reference point, and the next reference point; and determining the reference curvature of the vehicle at the current position based on the Euclidean distance between each pair of points.

[0040] Here, both the projection point and the reference point are points on the reference trajectory. Assume the vehicle's real-time position is projected onto the reference trajectory at coordinates (x2, y2). There is at least one reference point before and after the projection point, with coordinates (x1, y1) for the former and (x3, y3) for the latter. The Euclidean distance between any two of these three points can be expressed as:

[0041]

[0042]

[0043]

[0044] The reference curvature can then be expressed as Where ρ curv Indicates the reference curvature.

[0045] Step 103: Determine the desired curvature of the vehicle based on the steering control information.

[0046] The desired curvature can be a curvature determined based on steering control information.

[0047] In this embodiment of the disclosure, determining the desired curvature of the vehicle based on steering control information may include: inputting the steering control information and the vehicle's wheelbase into the vehicle steering kinematics model to obtain the desired curvature of the vehicle.

[0048] The vehicle steering kinematics module can be represented as Where ρ ctrl The desired curvature is represented by L, the wheelbase of the vehicle is represented by δ, and the steering control information is represented by either the steering wheel angle or the front wheel angle.

[0049] Step 104: Perform anomaly detection on the vehicle based on the reference curvature and the desired curvature.

[0050] In this embodiment of the disclosure, anomaly detection of a vehicle based on a reference curvature and a desired curvature may include: determining the curvature difference between the reference curvature and the desired curvature; and determining that the vehicle has an anomaly when the curvature difference is greater than or equal to a first threshold.

[0051] The first threshold can be the maximum value of the curvature difference mentioned above when the vehicle is driving normally, and can be set according to the actual situation. After determining the reference curvature and the desired curvature, the vehicle lateral anomaly detection device can determine the curvature difference between the two curvatures and compare the curvature difference with the first threshold. If the curvature threshold exceeds the first threshold, it is determined that the current vehicle has a driving abnormality.

[0052] This solution provides a method that compares the reference curvature corresponding to the reference trajectory with the expected curvature corresponding to the vehicle steering control information. This effectively identifies abnormal situations even with small lateral deviations. Compared to traditional mechanisms that directly judge based on tracking deviation or steering deviation, this solution does not differentiate between the different tracking deviations during turns and straight-line driving, thus avoiding the balance between passability and safety issues. Furthermore, this solution does not utilize steering control information that may contain noise and delays. Instead, it uses theoretical steering control information calculated by a control algorithm to obtain the theoretical expected curvature. Then, it compares the relatively stable reference trajectory with frequently updated real-time positioning data to calculate the reference curvature of the projection points on the reference trajectory. This allows for a more accurate distinction between fault and normal states and effectively addresses the problem of false triggering caused by inconsistent tracking deviations when tracking reference trajectories of different shapes. This improves the passability of the driving system while ensuring its safety.

[0053] The vehicle lateral anomaly detection scheme provided in this disclosure acquires the vehicle's real-time position, reference trajectory, and steering control information; determines the reference curvature of the vehicle at its current position based on the real-time position and reference trajectory; determines the vehicle's desired curvature based on the steering control information; and performs anomaly detection on the vehicle based on the reference curvature and the desired curvature. By comparing the reference curvature of the reference trajectory projection point with the theoretical desired curvature corresponding to the vehicle's steering control quantity, lateral anomaly detection is achieved. This effectively detects anomalies when tracking reference trajectories of different shapes. Since the reference curvature is relatively stable and the desired curvature is a theoretically calculated value, it avoids the low accuracy caused by significant noise and delay in the feedback data, thus improving the accuracy of anomaly detection and ultimately enhancing vehicle driving safety.

[0054] For example, Figure 2 This is a flowchart illustrating another vehicle lateral anomaly detection method provided in an embodiment of the present disclosure. In one feasible implementation, the vehicle lateral anomaly detection method may further include the following steps:

[0055] Step 201: Obtain the steering feedback information corresponding to the steering control information.

[0056] The steering feedback information can be the actual information fed back by the vehicle's steering mechanism at the next moment, relative to the moment the steering control information is issued. A moment can be understood as a calculation cycle; the steering control information is issued in the previous calculation cycle, and the feedback information is obtained in the current calculation cycle. The steering feedback information can include feedback on the steering wheel angle or the front wheel angle.

[0057] Step 202: Determine the steering difference between the steering control information and the steering feedback information.

[0058] Since steering control information and steering feedback information can include steering wheel angle or front wheel angle, the steering difference can be the difference between the issued steering wheel angle and the feedback steering wheel angle, or it can be the difference between the issued front wheel angle and the feedback front wheel angle.

[0059] Step 203: Determine whether the steering difference is greater than or equal to the second threshold or whether the duration of the steering difference being greater than or equal to the second threshold has reached a preset time. If yes, proceed to step 204; otherwise, proceed to step 205.

[0060] The second threshold represents the maximum value of the steering difference, which can be set according to the actual situation. Since the steering difference can include the difference between the two steering wheel angles or the difference between the two front wheel angles, the second threshold can be set for the difference between the steering wheel angles or the front wheel angles. The preset time can be the shortest time set to avoid misjudgment caused by signal jitter in the steering command.

[0061] Specifically, after obtaining the steering difference, it can be determined whether the steering difference is greater than or equal to the second threshold. If so, it indicates that the chassis response to the steering command is in an abnormal state, and step 204 is executed; otherwise, step 205 is executed. Alternatively, it can be determined whether the duration of the steering difference being greater than or equal to the second threshold has reached a preset time. If so, it indicates that the difference between the steering control information issued and the steering feedback information fed back within the preset time has always exceeded the second threshold, and step 204 is executed; otherwise, step 205 is executed.

[0062] The rules for steering mechanism issues are relatively lenient, and the second threshold is generally set relatively high because the response of the steering mechanism is highly non-linear, especially during vehicle operation. The adjustment time of the steering mechanism differs significantly between small and large steering angles; typically, handling large steering angle changes requires a longer time to complete steering tracking. Therefore, a relatively high second threshold is usually set to filter out such cases.

[0063] Step 204: Determine if the vehicle is malfunctioning.

[0064] Step 205: Confirm that the vehicle is operating normally.

[0065] During vehicle operation, the performance of the steering mechanism is fundamental to ensuring the vehicle can accurately track the reference trajectory. Significant delays or deviations in the steering mechanism can seriously threaten vehicle safety. In the aforementioned solution, lateral anomaly detection can also be performed through a steering anomaly judgment mechanism, serving as a basic safety assessment method and increasing the accuracy of the judgment.

[0066] For example, Figure 3This is a flowchart illustrating another vehicle lateral anomaly detection method provided in an embodiment of the present disclosure. In one feasible implementation, the vehicle lateral anomaly detection method may further include the following steps:

[0067] Step 301: Obtain the vehicle's tracking deviation.

[0068] The tracking deviation can be used to describe the trajectory tracking performance of a vehicle. In this embodiment of the disclosure, the tracking deviation may include lateral tracking deviation and / or heading tracking deviation. The lateral tracking deviation may be the straight-line distance between the center of the vehicle's rear axle and its projection point on the reference trajectory, and the heading tracking deviation may be the difference between the vehicle's heading angle and the heading angle corresponding to the projection point of the rear axle center on the reference trajectory.

[0069] Step 302: Determine whether the tracking deviation is greater than or equal to the third threshold. If yes, proceed to step 303; otherwise, proceed to step 304.

[0070] The third threshold can be the maximum value representing the lateral tracking deviation or the maximum value representing the heading tracking deviation. It can be adjusted based on some human debugging experience and driving data under normal vehicle driving conditions, or the maximum allowable tracking deviation can be adjusted in real time according to the actual driving conditions.

[0071] Specifically, after obtaining the tracking deviation, it can be determined whether the tracking deviation is greater than or equal to the third threshold. If the lateral tracking deviation or the heading tracking deviation is greater than or equal to the third threshold, step 303 can be executed; if both the lateral tracking deviation and the heading tracking deviation are less than the third threshold, step 304 can be executed.

[0072] Step 303: Determine if the vehicle is malfunctioning.

[0073] Step 304: Confirm that the vehicle is operating normally.

[0074] In the above scheme, vehicle lateral anomaly detection can also be performed through a tracking deviation anomaly judgment mechanism. This can be used as an additional safety judgment method. From the perspective of planning and control, it makes full use of existing planning and control information to design safety rules for judgment, thereby increasing the accuracy of judgment and improving system security.

[0075] During vehicle operation, the steering mechanism may malfunction and become uncontrollable, resulting in continuous positioning drift. In such cases, the system is in an abnormal state, but the steering angle issued and the steering angle feedback are not significantly different. Based on practical experience, especially on straight roads, even if the lateral tracking deviation between the vehicle and the reference trajectory is 3-5 meters, the steering difference generally will not exceed 5 degrees. Furthermore, when the system experiences a physical failure such as a tire blowout, the vehicle steering feedback signal may not accurately reflect the actual steering signal. The steering motor may still be rotating normally, but it can no longer drive the tires, rendering steering detection ineffective. Therefore, relying solely on simple steering anomaly detection methods may have limitations.

[0076] During vehicle driving system operation, tracking deviation often increases when facing large curvature curves such as S-curves and U-turns. Especially considering the safety of vehicles with trailers attached, the tractor unit needs to sacrifice some trajectory tracking accuracy to ensure the entire trailer convoy safely completes the turn. Therefore, while a small threshold set for tracking deviation judgment can guarantee driving safety on most road sections, it may still cause false alarms when tracking large curvature curves. However, if the threshold is set too high, the deviation is often not significant on straight sections, making it difficult to trigger alarms. Setting different tracking deviation thresholds for different road sections requires additional material and human resources for road network labeling. The current tracking deviation method cannot keep lateral tracking deviation within a small range for trajectories with various curvatures, significantly reducing detection effectiveness. Furthermore, setting the judgment threshold is difficult, and inaccurate threshold settings lead to inaccurate detection results, meaning that inaccurate detection results exist on special road sections or when the threshold is inaccurate.

[0077] The steering anomaly judgment method in steps 201-205 and the tracking deviation anomaly judgment method in steps 301-304 of this embodiment can be used as basic judgment methods. The above-mentioned methods based on steering angle and tracking deviation both rely on the accuracy of feedback signals. In order to avoid reducing accuracy due to noise or delay in the feedback signals, the anomaly judgment method based on comparing the reference curvature corresponding to the reference trajectory with the expected curvature corresponding to the vehicle steering control information in steps 101-104 can be used. This method can detect anomalies when the tracking deviation is small, and will not cause false triggering problems when tracking large curvature curve trajectories.

[0078] Optionally, when the noise and delay in the feedback signal are small, the vehicle anomaly detection method of this embodiment can also compare the actual curvature of the steering feedback information fed back by the vehicle with the above-mentioned reference curvature. That is, if the difference between the reference curvature and the actual curvature exceeds a threshold, it is determined that the vehicle has an anomaly.

[0079] In some embodiments, after determining that the vehicle has malfunctioned, the method of this disclosure may further include: using a preset malfunction handling mechanism to handle the malfunction of the vehicle, the preset malfunction handling mechanism including at least one of deceleration, stopping, and emergency braking.

[0080] The preset anomaly handling mechanism can be a pre-set method for handling vehicle anomalies, which can be configured according to actual conditions. Specifically, when an anomaly is detected, an alarm can be issued, and the vehicle anomaly can be handled based on the preset anomaly handling mechanism.

[0081] It is understandable that the anomaly judgment method in steps 101-104, which compares the reference curvature corresponding to the reference trajectory with the expected curvature corresponding to the vehicle steering control information, the steering anomaly judgment method in steps 201-205, and the tracking deviation anomaly judgment method in steps 301-304, can be at least two of these methods combined and executed in a certain order. The order can be: first execute the steering anomaly judgment, then the tracking deviation anomaly judgment, and finally execute the anomaly judgment method that compares the reference curvature corresponding to the reference trajectory with the expected curvature corresponding to the vehicle steering control information; or at least two of these methods can be executed in parallel, depending on the actual situation.

[0082] The vehicle lateral anomaly detection method provided in this solution can be used to accurately determine in real time whether the lateral tracking function of a vehicle, especially an autonomous vehicle, is in an abnormal operating state caused by internal or external factors, such as uncontrolled steering mechanism, tire blowout, large delay of steering mechanism, abnormal operation of control program, etc., and can be distinguished from the situation of reduced tracking effect under normal operation. This can ensure the safety of the system's lateral tracking without affecting the normal driving of the vehicle.

[0083] This solution establishes an anomaly detection mechanism within the vehicle's control module. Based on relevant vehicle states, such as pose, control variables, and reference trajectories, it enables multi-layered safety assessments. Compared to designs that establish safety mechanisms in the chassis or upper-level modules, this approach is more robust and offers a more comprehensive assessment mechanism. Furthermore, this solution can identify potential adverse effects on lateral tracking performance under various fault conditions and categorizes them according to specific characteristics, establishing different assessment mechanisms for each. Compared to a single threshold assessment mechanism, this approach provides broader coverage and higher system security.

[0084] This solution provides a three-layer safety judgment mechanism. These three layers are independent and can be set with corresponding fault alarm information individually, or at least two can be used in combination. For example, a steering anomaly judgment mechanism and a tracking deviation anomaly judgment mechanism can be used in combination to make the entire driving system more flexible while ensuring safety. When the three-layer safety judgment mechanism is used in combination, a steering anomaly judgment can be performed first. Secondly, the vehicle's tracking deviation can be checked as a second line of defense. Finally, the anomaly detection is performed by comparing the expected curvature calculated by the control algorithm with the reference curvature of the projection point on the reference trajectory. This accurately detects faults and triggers the anomaly handling mechanism to ensure safety.

[0085] This vehicle anomaly detection scheme makes safety judgments based on control module information and vehicle kinematics. It can ensure lateral tracking safety as long as the vehicle is being driven, without relying on other parallel modules such as the chassis module. Its judgment mechanism is different from other parallel modules, complementing each other and improving the system's safety level. Furthermore, it can be triggered from the perspective of practical problems, providing better safety assurance in dealing with common sudden failures such as tire blowouts, steering mechanism anomalies, and positioning system anomalies. It can effectively balance vehicle driving safety and passability.

[0086] Figure 4 This is a schematic diagram of a vehicle lateral anomaly detection device provided in an embodiment of this disclosure. The device can be implemented by software and / or hardware, and is generally integrated into an electronic device. Figure 4 As shown, the device includes:

[0087] Information module 401 is used to acquire the vehicle's real-time location, reference trajectory, and steering control information;

[0088] Reference module 402 is used to determine the reference curvature of the vehicle at the current position based on the real-time position and the reference trajectory;

[0089] The desired module 403 is used to determine the desired curvature of the vehicle based on the steering control information.

[0090] The detection module 404 is used to perform anomaly detection on the vehicle based on the reference curvature and the desired curvature.

[0091] Optionally, the reference module 402 is used for:

[0092] Based on the real-time location and the reference trajectory, a preset curvature algorithm is used to determine the reference curvature of the vehicle at the current location. The preset curvature algorithm includes the three-point method or the model tracking method.

[0093] Optionally, when the preset curvature algorithm is the three-point method, based on the real-time position and the reference trajectory, the reference module 402 is used to:

[0094] Determine the projection point, the previous reference point, and the next reference point of the real-time position in the reference trajectory;

[0095] The Euclidean distance between each pair of points is determined based on the coordinates of the projection point, the previous reference point, and the next reference point.

[0096] The reference curvature of the vehicle at its current position is determined based on the Euclidean distance between each pair of points.

[0097] Optionally, the desired module 403 is used for:

[0098] The steering control information and the vehicle's wheelbase are input into the vehicle steering kinematics model to obtain the vehicle's desired curvature. The steering control information includes the vehicle's steering wheel angle or front wheel angle issued by the control module.

[0099] Optionally, the detection module 404 is used for:

[0100] Determine the curvature difference between the reference curvature and the desired curvature;

[0101] If the curvature difference is greater than or equal to the first threshold, it is determined that the vehicle is abnormal.

[0102] Optionally, the device further includes a second detection module for:

[0103] Obtain the steering feedback information corresponding to the steering control information;

[0104] Determine the steering difference between the steering control information and the steering feedback information;

[0105] If the steering difference is greater than or equal to the second threshold, or if the duration of the steering difference being greater than or equal to the second threshold reaches a preset time, then it is determined that the vehicle is malfunctioning.

[0106] Optionally, the device further includes a third detection module for:

[0107] The tracking deviation of the vehicle is obtained, and the tracking deviation includes lateral tracking deviation and / or heading tracking deviation;

[0108] If the tracking deviation is greater than or equal to the third threshold, the vehicle is determined to be abnormal.

[0109] Optionally, the device further includes a processing module for:

[0110] After determining that the vehicle has malfunctioned, a preset malfunction handling mechanism is used to handle the malfunction. The preset malfunction handling mechanism includes at least one of deceleration, stopping, and emergency braking.

[0111] The vehicle lateral anomaly detection device provided in this disclosure can execute the vehicle lateral anomaly detection method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0112] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Figure 5 As shown, the electronic device 500 includes a central processing unit (CPU) 501, which can execute various processes described in the foregoing embodiments according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0113] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0114] In particular, according to embodiments of this disclosure, the methods described above can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program tangibly contained on a readable medium thereof, the computer program containing program code for performing the aforementioned obstacle avoidance method. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511.

[0115] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0116] The units or modules described in the embodiments of this disclosure can be implemented in software or hardware. The described units or modules can also be located in a processor, and the names of these units or modules do not necessarily constitute a limitation on the unit or module itself.

[0117] In addition, this disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus described in the above embodiments; or it may be a standalone computer-readable storage medium not assembled into the device. The computer-readable storage medium stores one or more programs, which are used by one or more processors to execute the vehicle lateral anomaly detection method described in this disclosure.

[0118] In addition to the methods and devices described above, embodiments of this disclosure may also be computer program products, including computer program instructions that, when executed by a processor, cause the processor to perform the vehicle lateral anomaly detection method provided in the embodiments of this disclosure.

[0119] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0120] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply 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 limitations, 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.

[0121] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle lateral abnormality detection method characterized by comprising: The method comprises: obtaining a real-time position of a vehicle, a reference trajectory and steering control information; determining a reference curvature of the vehicle at a current position according to the real-time position and the reference trajectory; determining a desired curvature of the vehicle according to the steering control information, wherein the steering control information is theoretical steering control information calculated by a control algorithm, and the desired curvature is a theoretical desired curvature; performing anomaly detection on the vehicle according to the reference curvature and the desired curvature.

2. The method of claim 1, wherein, The method further comprises: obtaining a tracking deviation of the vehicle, wherein the tracking deviation comprises a lateral tracking deviation and / or a heading tracking deviation; and 3. The method of claim 2, wherein, determining that the vehicle is abnormal when the tracking deviation is greater than or equal to a third threshold value. After determining that the vehicle is abnormal, the method further comprises: performing abnormality processing on the vehicle by using a preset abnormality processing mechanism, wherein the preset abnormality processing mechanism comprises at least one of speed reduction, parking and emergency braking. The method comprises:

4. The method of claim 1, wherein, an information module configured to obtain a real-time position of a vehicle, a reference trajectory and steering control information; a reference module configured to determine a reference curvature of the vehicle at a current position according to the real-time position and the reference trajectory; 5. The method of claim 1, wherein, a determination module configured to determine a desired curvature of the vehicle according to the steering control information, wherein the steering control information is theoretical steering control information calculated by a control algorithm, and the desired curvature is a theoretical desired curvature; and an anomaly detection module configured to perform anomaly detection on the vehicle according to the reference curvature and the desired curvature. ​ 6. The method of claim 1, wherein, ​ ​ ​ ​ 7. The method according to claim 1 or 6, characterized in that, ​ ​ ​ 8. The method according to any one of claims 5-7, characterized in that, ​ ​ 9. A vehicle lateral abnormality detection device characterized by comprising: ​ ​ ​ The expected module is configured to determine an expected curvature of the vehicle according to the steering control information; wherein the steering control information is theoretical steering control information calculated by a control algorithm, and the expected curvature is a theoretical expected curvature; The detection module is configured to perform anomaly detection on the vehicle according to the reference curvature and the expected curvature.

10. An electronic device, comprising: The electronic device comprises: a processor; a memory for storing executable instructions of the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the vehicle lateral anomaly detection method according to any one of claims 1-8.

11. A computer readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is configured to execute the vehicle lateral anomaly detection method according to any one of claims 1-8.

Images