Steering detection method, device, apparatus and medium for autonomous vehicle

Abstract

The present application relates to the technical field of automatic driving, in particular to a steering detection method, device, equipment and medium for an automatic driving vehicle. The steering detection method comprises: acquiring a steering response delay of an automatic driving vehicle; periodically acquiring a steering instruction parameter and a corresponding actual steering parameter of the automatic driving vehicle according to the steering response delay; determining whether the automatic driving vehicle has steering in a corresponding period according to the actual steering parameter of each period; and determining whether the automatic driving vehicle has a steering failure in the corresponding period according to the steering instruction parameter and the actual steering parameter of the period in which no steering occurs. The steering detection scheme of the present application can efficiently and accurately detect various steering failure conditions of the automatic driving vehicle, realize online real-time monitoring of the steering state during the driving process of the automatic driving vehicle, and stably and accurately monitor without false detection. Moreover, the detection method is simple and easy to implement.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and more specifically, to a steering detection method, apparatus, device, and medium for autonomous vehicles. Background Technology

[0002] For autonomous vehicles, executing corresponding operations according to instructions is crucial. In particular, whether an autonomous vehicle accurately executes steering operations based on steering commands directly affects its driving safety.

[0003] Taking autonomous vehicles equipped with drive-by-wire chassis as an example, currently, drive-by-wire chassis itself has many redundancy measures, but it can only identify the components of the drive-by-wire chassis itself, and can only detect direct chassis faults.

[0004] In addition to direct chassis failures, the following steering failures may occur during the operation of autonomous vehicles: (1) the steering oil passage is blocked, causing the signal feedback to be powered but unable to actually perform steering; (2) one wheel drives into the groove, causing the steering to jam and no longer able to execute the steering command of autonomous driving; (3) mechanical parts such as the steering shaft break, causing the steering operation to be performed but unable to actually push the wheel to turn.

[0005] If the above-mentioned steering malfunctions are not identified in time, they can have disastrous consequences for autonomous vehicles. Currently, there is no effective method to detect all of these steering malfunctions.

[0006] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] In view of this, the present invention provides a steering detection method, device, equipment and medium for autonomous vehicles, which can efficiently and accurately detect various steering faults of autonomous vehicles, realize online real-time monitoring of steering status during the driving process of autonomous vehicles, with stable monitoring and no false detections, and the detection method is simple and easy to implement.

[0008] According to one aspect of the present invention, a steering detection method for an autonomous vehicle is provided, comprising: acquiring a steering response delay of the autonomous vehicle; periodically acquiring steering command parameters and corresponding actual steering parameters of the autonomous vehicle based on the steering response delay; determining whether the autonomous vehicle has steered within a corresponding period based on the actual steering parameters of each period; and determining whether the autonomous vehicle has experienced a steering failure within a corresponding period based on the steering command parameters and actual steering parameters of periods in which no steering has occurred.

[0009] In some embodiments, the actual steering parameters include the actual steering angle; determining whether the autonomous vehicle has turned within the corresponding period includes: based on the actual steering parameters of a current period, determining whether the unit change in the actual steering angle is less than a preset threshold; if so, determining that the autonomous vehicle has not turned within the current period.

[0010] In some embodiments, the steering command parameters include a steering command angle, and the actual steering parameters include an actual steering angle; determining whether the autonomous vehicle has experienced a steering malfunction in the corresponding period includes: based on the steering command parameters and actual steering parameters of a current period in which no steering has occurred, determining whether the angle difference between each set of steering command angles and actual steering angles is greater than an angle threshold; if so, determining that the autonomous vehicle has experienced a steering malfunction in the current period in which no steering has occurred.

[0011] In some embodiments, the time difference between the timestamp of the actual steering angle and the timestamp of the steering command angle in each set of steering command angles and actual steering angles corresponds to the steering response delay.

[0012] In some embodiments, periodically acquiring the steering command parameters and corresponding actual steering parameters of the autonomous vehicle includes: determining the duration of a detection window, wherein the duration of the detection window is greater than the steering response delay; and periodically acquiring the steering command parameters and actual steering parameters of the autonomous vehicle based on the duration of the detection window.

[0013] In some embodiments, before periodically acquiring the steering command parameters and corresponding actual steering parameters of the autonomous vehicle, the method further includes: determining the sampling period of the steering command parameters and the actual steering parameters based on the update period of the steering command parameters of the autonomous vehicle; the sampling period is greater than the update period and less than the steering response delay.

[0014] In some embodiments, after periodically acquiring the steering command parameters and corresponding actual steering parameters of the autonomous vehicle, the method further includes: storing the steering command parameters and actual steering parameters of the currently acquired cycle into a buffer; determining whether the autonomous vehicle has turned within the corresponding cycle, and acquiring the steering command parameters and actual steering parameters of the corresponding cycle from the buffer.

[0015] In some embodiments, the capacity of the buffer corresponds to the amount of data for one cycle of steering command parameters and actual steering parameters.

[0016] In some embodiments, before determining whether the autonomous vehicle has turned within the corresponding period, the method further includes: determining that the autonomous vehicle has entered an autonomous driving mode and that the target parameters of the autonomous vehicle meet the steering detection trigger condition; wherein the steering detection trigger condition is determined based on the configuration of the steering system of the autonomous vehicle.

[0017] In some embodiments, obtaining the steering response delay of the autonomous vehicle includes: performing a response test on the autonomous vehicle under autonomous driving conditions to obtain the relationship between the steering command parameters and actual steering parameters of the autonomous vehicle over time; and determining the steering response delay of the autonomous vehicle based on the relationship between the changes.

[0018] In some embodiments, after determining whether the autonomous vehicle has experienced a steering failure within a corresponding period, the method further includes: when the autonomous vehicle experiences a steering failure within a period, generating a steering failure detection result and reporting it to the autonomous driving module of the autonomous vehicle, so that the autonomous driving module can adjust the driving state of the autonomous vehicle based on the steering failure detection result.

[0019] According to another aspect of the present invention, a steering detection device for an autonomous vehicle is provided, comprising: a response delay acquisition module for acquiring the steering response delay of the autonomous vehicle; a steering parameter acquisition module for periodically acquiring steering command parameters and corresponding actual steering parameters of the autonomous vehicle based on the steering response delay; a steering detection module for determining whether the autonomous vehicle has steered in a corresponding period based on the actual steering parameters of each period; and a steering fault detection module for determining whether the autonomous vehicle has steered in a corresponding period based on the steering command parameters and actual steering parameters of a period in which no steering has occurred.

[0020] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory storing executable instructions; wherein, when the executable instructions are executed by the processor, they implement the steering detection method for an autonomous vehicle as described in any of the above embodiments.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided for storing a program, which, when executed by a processor, implements the steering detection method for an autonomous vehicle as described in any of the above embodiments.

[0022] The beneficial effects of this invention compared to the prior art include at least the following:

[0023] The steering detection scheme of the present invention can accurately obtain the steering command parameters and corresponding actual steering parameters for each cycle based on the steering response delay of the autonomous vehicle; based on the actual steering parameters for each cycle, it can conveniently determine whether the autonomous vehicle has turned within the corresponding cycle; and further determine whether the autonomous vehicle has a steering fault within the corresponding cycle based on the steering command parameters and actual steering parameters of the cycle in which no turning has occurred.

[0024] The steering detection scheme of this invention can efficiently and accurately detect various steering faults in autonomous vehicles, realize online real-time monitoring of steering status during the driving process of autonomous vehicles, ensure stable monitoring without false detections, and the detection method is simple and easy to implement.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0027] Figure 1 A schematic diagram illustrating the steps of the steering detection method for an autonomous vehicle in an embodiment of the present invention is shown.

[0028] Figure 2 This diagram illustrates the steps of determining whether an autonomous vehicle has turned within a corresponding period in an embodiment of the present invention.

[0029] Figure 3 This diagram illustrates the steps of determining whether an autonomous vehicle experiences a steering failure within a corresponding period, according to an embodiment of the present invention.

[0030] Figure 4 A flowchart illustrating the steering detection method for autonomous vehicles in an embodiment of the present invention is shown.

[0031] Figure 5 A schematic diagram of the steering detection device for an autonomous vehicle in an embodiment of the present invention is shown.

[0032] Figure 6 A schematic diagram of the structure of an electronic device in an embodiment of the present invention is shown. Detailed Implementation

[0033] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to fully and completely convey the concept of the exemplary embodiments to those skilled in the art.

[0034] The accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0035] Furthermore, the processes shown in the accompanying drawings are merely illustrative and do not necessarily include all steps. For example, some steps can be broken down, some steps can be combined or partially combined, and the actual execution order may change depending on the actual situation. The terms "first," "second," and similar terms used in the specific description do not indicate any order, quantity, or importance, but are only used to distinguish different components. It should be noted that, unless otherwise specified, embodiments of the present invention and features in different embodiments can be combined with each other.

[0036] The steering detection scheme of the present invention is applicable to various types of autonomous vehicles, especially autonomous vehicles equipped with steer-by-wire systems.

[0037] Figure 1 This illustrates the main steps of a steering detection method for an autonomous vehicle in one embodiment, with reference to... Figure 1 As shown, the steering detection method for an autonomous vehicle in this embodiment includes:

[0038] Step S110: Obtain the steering response delay of the autonomous vehicle.

[0039] Steering response delay refers to the time interval between the autonomous driving module issuing a steering command and the vehicle's steering system responding to that command and executing the relevant steering operation. By understanding the steering response delay, it becomes easier to accurately obtain the steering command parameters and actual steering parameters corresponding to each steering command.

[0040] Step S120: Based on the steering response delay, periodically acquire the steering command parameters and corresponding actual steering parameters of the autonomous vehicle.

[0041] The autonomous driving module of an autonomous vehicle has a set instruction update cycle; accordingly, the acquisition of steering instruction parameters and corresponding actual steering parameters of the autonomous vehicle is also performed periodically to achieve accurate detection while reducing redundant data and saving detection costs.

[0042] In addition, the amount of data for each acquired steering command parameter and corresponding actual steering parameter is determined based on the steering response delay, ensuring that the steering command parameters (which may contain multiple steering command parameters) and actual steering parameters corresponding to a single steering command are acquired accurately and in appropriate amounts, thereby improving the efficiency of subsequent detection of whether the autonomous vehicle has engaged in steering or experienced a steering malfunction in each cycle.

[0043] Step S130: Based on the actual steering parameters for each cycle, determine whether the autonomous vehicle has turned within the corresponding cycle.

[0044] Based on the changes in the actual steering parameters over a cycle, it is easy to determine whether an autonomous vehicle has turned within that cycle.

[0045] Step S140: Based on the steering command parameters and actual steering parameters of the cycle in which no steering occurred, determine whether the autonomous vehicle experienced a steering failure in the corresponding cycle.

[0046] For cycles in which no steering occurs, the amount of error between the steering command parameters and the actual steering parameters in that cycle can be used to easily determine whether the autonomous vehicle has experienced a steering failure during that cycle.

[0047] The above-mentioned steering detection scheme can efficiently and accurately detect various steering faults in autonomous vehicles, realize online real-time monitoring of steering status during the driving process of autonomous vehicles, ensure stable monitoring without false detections, and the detection method is simple and easy to implement.

[0048] In one embodiment, obtaining the steering response delay of an autonomous vehicle includes: conducting a response test on the autonomous vehicle under autonomous driving conditions to obtain the relationship between the steering command parameters and actual steering parameters of the autonomous vehicle over time; and determining the steering response delay of the autonomous vehicle based on the relationship.

[0049] The response test can specifically employ a step response test. By plotting the curves of the steering command angle and the actual steering angle over time, the steering response delay of the autonomous vehicle can be determined as a steady-state error value to guide the setting of subsequent detection windows.

[0050] In one embodiment, periodically acquiring steering command parameters and corresponding actual steering parameters of an autonomous vehicle includes: determining the duration of a detection window, wherein the duration of the detection window is greater than the steering response delay; and periodically acquiring steering command parameters and actual steering parameters of the autonomous vehicle based on the duration of the detection window.

[0051] The detection window duration is longer than the steering response delay, ensuring that the actual steering parameters acquired in each cycle correspond to the steering command parameters. Furthermore, the detection window duration is slightly longer than the steering response delay to ensure that the steering command parameters and actual steering parameters corresponding to a single steering command are acquired in each cycle.

[0052] In a specific implementation scenario, the steering response delay of an autonomous vehicle is approximately 400ms. Therefore, the detection window duration should be slightly longer than the steering response delay, and can be set to approximately 500ms. When acquiring the steering command parameters and actual steering parameters for one cycle, the timestamp of the current detection window (e.g., t1 to t2) can be used. 500 This involves obtaining the steering instruction parameters and actual steering parameters that match the timestamp of the current detection window, i.e., obtaining t1 to t2. 500 Steering command parameters and actual steering parameters during this period.

[0053] In one embodiment, before periodically acquiring the steering command parameters and corresponding actual steering parameters of the autonomous vehicle, the method further includes: determining the sampling period of the steering command parameters and actual steering parameters based on the update period of the steering command parameters of the autonomous vehicle; wherein the sampling period is greater than the update period and less than the steering response delay.

[0054] The sampling period is longer than the update period, which ensures that the data acquired each time covers the steering command parameters corresponding to a steering command; and the sampling period is shorter than the steering response delay, which avoids the steering command parameters acquired at one time and the actual steering parameters spanning multiple steering commands, thus affecting the subsequent detection of whether steering / steering fault has occurred.

[0055] In a specific implementation scenario, the update cycle for the steering command parameters of the autonomous vehicle is 20ms; the sampling cycle for the steering command parameters and actual steering parameters can be set to 2 to 5 times the update cycle, for example, 100ms. Then, every 100ms, the steering command parameters and actual steering parameters for the duration of the detection window are acquired.

[0056] In one embodiment, after periodically acquiring the steering command parameters and corresponding actual steering parameters of the autonomous vehicle, the method further includes: storing the steering command parameters and actual steering parameters of the currently acquired cycle into a buffer; and when determining whether the autonomous vehicle has turned within the corresponding cycle, acquiring the steering command parameters and actual steering parameters of the corresponding cycle from the buffer.

[0057] The buffer capacity corresponds to the amount of data for one cycle of steering command parameters and actual steering parameters. That is, the buffer stores one cycle of data at a time; when the data for the next cycle needs to be stored, the existing data in the buffer can be discarded first to ensure that the storage of steering command parameters and actual steering parameters does not occupy excessive memory space. The memory space referred to here depends on the device executing the steering detection method; it refers to the memory space of the device executing the steering detection method. This device can be the autonomous driving module of an autonomous vehicle, an electronic unit integrated into the autonomous driving module, or an electronic unit communicating with the autonomous driving module, etc.

[0058] In one embodiment, before determining whether the autonomous vehicle has turned within the corresponding period, the method further includes: determining that the autonomous vehicle has entered an autonomous driving mode and that the target parameters of the autonomous vehicle meet the steering detection triggering condition; wherein the steering detection triggering condition is determined based on the configuration of the steering system of the autonomous vehicle.

[0059] The steering detection trigger condition is determined based on the configuration of the autonomous vehicle's steering system. For example, if an autonomous vehicle's steering system is configured so that automatic steering is not allowed when the vehicle speed is 0, then the corresponding detection trigger condition is set to "vehicle speed greater than 0," and the target parameter is "vehicle speed." Thus, when the autonomous vehicle enters autonomous driving mode and the vehicle speed is greater than 0, the steering detection logic of this invention is triggered to perform steering detection on the autonomous vehicle. As another example, if an autonomous vehicle's steering system is configured with chassis fault level requirements (e.g., steering detection is performed when the drive-by-wire chassis experiences a fault of level xxx, where the fault level of level xxx is higher than that of the axle jamming), then the corresponding detection trigger condition is set to "drive-by-wire chassis experiences a fault of level xxx," and the corresponding target parameter is the level xxx parameter of the drive-by-wire chassis. Thus, when the autonomous vehicle enters autonomous driving mode and the drive-by-wire chassis experiences a fault of level xxx, the steering detection logic of this invention is triggered to perform steering detection on the autonomous vehicle.

[0060] In one embodiment, the actual steering parameters include the actual steering angle; when determining whether the autonomous vehicle has turned within a corresponding period, the unit change in the actual steering angle within that period can be used to determine whether the autonomous vehicle has turned within that period.

[0061] Specifically, refer to Figure 2 As shown, determining whether an autonomous vehicle turns within a corresponding period includes:

[0062] Step S210: Based on the actual steering parameters of a current cycle, determine whether the change in each unit of the actual steering angle is less than a preset threshold.

[0063] Step S220: If yes, then determine that the autonomous vehicle did not turn during the current cycle;

[0064] Step S230: If not, determine that the autonomous vehicle has turned during the current cycle.

[0065] Within the current cycle, if each unit change in the actual steering angle is less than a preset threshold, it can be determined that the autonomous vehicle has not steered. For cycles in which no steering is determined to have occurred, subsequent checks for steering malfunctions will continue to identify situations where the autonomous vehicle issued a steering command but failed to actually execute the steering due to a steering malfunction. For cycles in which steering is determined to have occurred, it indicates that the autonomous vehicle's steering is normal, and no further checks will be performed.

[0066] The specific calculation method for unit change can be configured as needed.

[0067] For example, in one embodiment, the unit change can be configured as the change in angular velocity in seconds; correspondingly, the preset threshold is configured as an angular velocity threshold (e.g., 1° / s). Thus, in this embodiment, if the difference between the maximum and minimum values ​​of the actual steering angle is less than 1° within one second of the current cycle, it can be determined that the autonomous vehicle has not steered.

[0068] For example, in one embodiment, the unit change can be configured as the angle change between every two actual steering angles; correspondingly, the preset threshold is configured as an angle threshold (the setting of the angle threshold is related to the detection period; corresponding to the angular velocity threshold of 1° / s in the above embodiment, the detection period in this embodiment is 100ms, that is, the time interval between every two adjacent actual steering angles is 0.1s, so the angle threshold can be set to 0.1°). Therefore, in this embodiment, if the difference between every two actual steering angles in the current period is less than 0.1°, it can be determined that the autonomous vehicle has not turned.

[0069] In other embodiments, the specific value of the preset threshold can be set according to the severity of the autonomous driving scenario, and is not limited to 1° / s or 0.1° as listed above.

[0070] In one embodiment, the steering command parameters include the steering command angle, and the actual steering parameters include the actual steering angle. When determining whether an autonomous vehicle has experienced a steering failure within a corresponding cycle, the angle error between the actual steering angle and the steering command angle of that cycle can be used to determine whether the autonomous vehicle has experienced a steering failure within that cycle.

[0071] Specifically, refer to Figure 3 As shown, determining whether an autonomous vehicle experiences a steering malfunction within a corresponding period includes:

[0072] Step S310: Based on the steering command parameters and actual steering parameters of the current cycle in which no steering has occurred, determine whether the angle difference between each set of steering command angles and actual steering angles is greater than the angle threshold.

[0073] Step S320: If yes, then determine that the autonomous vehicle has experienced a steering failure during the current cycle in which no steering has occurred;

[0074] Step S330: If yes, then determine that the autonomous vehicle is driving normally during the current cycle in which no steering has occurred.

[0075] In each set of steering command angles and actual steering angles, the time difference between the timestamp of the actual steering angle and the timestamp of the steering command angle corresponds to the steering response delay.

[0076] For a current cycle in which no steering has occurred, error tracking calculation is performed on the actual steering angle and the corresponding steering command angle. If the angle difference between each set of steering command angles and actual steering angles is greater than the set angle threshold, it indicates that the autonomous vehicle issued a steering command in this cycle but did not actually turn successfully (this situation of issuing a steering command but not actually turning successfully can also be called "axle jamming"). Therefore, it is determined that the autonomous vehicle has a steering failure in this cycle.

[0077] By continuously tracking and calculating errors within a cycle, that is, determining that the autonomous vehicle has a steering fault when the angle difference between each set of steering command angles and the actual steering angles is greater than the angle threshold, the accuracy of detection can be avoided by avoiding data noise, thus achieving accurate detection of vehicle steering faults.

[0078] Furthermore, the angle threshold can be set according to the severity of the autonomous driving scenario. For example, in one embodiment, the angle threshold can be set to 2°; thus, if the angle difference between each set of steering command angles and the actual steering angles is greater than 2° in the corresponding cycle, it can be determined that the autonomous vehicle has experienced a steering failure in that cycle.

[0079] Furthermore, in the above embodiments, after determining whether the autonomous vehicle has experienced a steering failure within the corresponding period, the method further includes: when the autonomous vehicle experiences a steering failure within a period, generating a steering failure detection result and reporting it to the autonomous driving module of the autonomous vehicle, so that the autonomous driving module can adjust the driving state of the autonomous vehicle based on the steering failure detection result.

[0080] Based on the steering fault detection results, the autonomous driving module can plan a safe path to handle the malfunction and stop the vehicle. Therefore, combining the advantages of autonomous driving, it can perform gentle and safe control after identifying axle jamming, comprehensively sensing and planning to control the autonomous vehicle to stop flexibly.

[0081] The following example, using an autonomous vehicle equipped with a steer-by-wire system, illustrates the specific implementation process of the steering detection method for autonomous vehicles.

[0082] The steer-by-wire system has an interface for receiving steering commands and an interface for feeding back the actual steering angle. Both interfaces are connected to the autonomous driving module. The main principle of the steering detection method is to first experimentally measure the key characteristic parameters of the autonomous vehicle's steering response under normal steering conditions, namely the steering response delay. Based on this, the steering command angle and actual steering angle of the autonomous vehicle are periodically acquired. Based on the actual steering angle, it is determined whether the autonomous vehicle meets the axle-locking characteristic, i.e., whether it has not turned within the corresponding period. If the axle-locking characteristic is met, the steering command angle and actual steering angle are then combined to determine whether the autonomous vehicle has experienced axle lock-up.

[0083] Figure 4 This illustrates the specific flow of a steering detection method for an autonomous vehicle in one embodiment, with reference to... Figure 4 As shown, in this embodiment, steering detection for autonomous vehicles specifically includes:

[0084] S410: Determine if the sampling period has ended. If not, end the process; otherwise, continue with the subsequent steps.

[0085] S420 collects the steering command angle and actual steering angle for the current cycle.

[0086] S430: Determine if the updated buffer has reached the set data volume. If yes, continue the subsequent process. If no, it indicates that the autonomous vehicle has not issued a steering command at this stage, so the process ends.

[0087] S440: Determine if all steering detection trigger conditions are met. If so, continue with the subsequent process; otherwise, end.

[0088] S450a calculates the unit change in the actual steering angle within the current cycle to help determine whether the autonomous vehicle has steered within the current cycle.

[0089] S450b: Determine whether all unit changes are less than a preset threshold. If so, continue with the subsequent process; otherwise, end.

[0090] S460a calculates the angle error between the actual steering angle and the steering command angle in the current cycle to help determine whether the autonomous vehicle has experienced a steering failure in the current cycle.

[0091] S460b: Determine if all angle errors are greater than the angle threshold. If so, continue with the subsequent process; otherwise, end.

[0092] S470, determine the current cycle of axle jamming, and report to the autonomous driving module.

[0093] The S480's autonomous driving module integrates perception and planning to park along a safe path.

[0094] The aforementioned steering detection method can efficiently and accurately detect various steering faults in autonomous vehicles, enabling real-time online monitoring of steering status during the driving process of autonomous vehicles. The monitoring is stable and without false detections, and the detection method is simple and easy to implement. In addition, when a steering fault is detected, it can be fed back to the autonomous driving module in real time, so that the autonomous driving module can control the vehicle to stop safely based on environmental perception and path planning, thus achieving redundant monitoring at the autonomous driving level.

[0095] This invention also provides a steering detection device for autonomous vehicles, which can be used to implement the steering detection method for autonomous vehicles described in any of the above embodiments. The features and principles of the steering detection methods described in any of the above embodiments can be applied to the steering detection device embodiments below. In the following steering detection device embodiments, the features and principles of steering detection for autonomous vehicles that have already been explained will not be repeated.

[0096] The steering detection device for autonomous vehicles can be the autonomous driving module of the autonomous vehicle, an electronic unit integrated into the autonomous driving module, or an electronic unit that communicates with the autonomous driving module, etc.

[0097] Figure 5 The main modules of a steering detection device for an autonomous vehicle in one embodiment are shown, with reference to... Figure 5 As shown, the steering detection device 500 for autonomous vehicles includes:

[0098] The response delay acquisition module 510 is used to acquire the steering response delay of the autonomous vehicle;

[0099] The steering parameter acquisition module 520 is used to periodically acquire the steering command parameters and corresponding actual steering parameters of the autonomous vehicle based on the steering response delay.

[0100] The steering detection module 530 is used to determine whether the autonomous vehicle has turned within the corresponding cycle based on the actual steering parameters of each cycle.

[0101] The steering fault detection module 540 is used to determine whether the autonomous vehicle has experienced a steering fault in the corresponding cycle based on the steering command parameters and actual steering parameters of the cycle in which no steering occurred.

[0102] Furthermore, the steering detection device 500 may also include modules that implement other process steps of the above-described steering detection method embodiments. The specific principles of each module can be referred to the descriptions of the above-described steering detection method embodiments, and will not be repeated here.

[0103] The steering detection device of the present invention can efficiently and accurately detect various steering faults in autonomous vehicles, realize online real-time monitoring of steering status during the driving process of autonomous vehicles, with stable monitoring and no false detections, and the detection method is simple and easy to implement; in addition, when a steering fault is detected, it can be fed back to the autonomous driving module in real time, so that the autonomous driving module can control the vehicle to stop safely based on environmental perception and path planning, realizing redundant monitoring at the autonomous driving level.

[0104] This invention also provides an electronic device. Figure 6 This illustrates the overall structure of the electronic equipment and its connection to vehicle components; see reference. Figure 6 As shown, the electronic device 600 includes a processor 600a and a memory 600b. The memory 600b stores executable instructions. When the executable instructions are executed by the processor 600a, the steering detection method for the autonomous vehicle described in any of the above embodiments is implemented.

[0105] The electronic device 600 of the present invention can be deployed in the autonomous driving module 610 of an autonomous vehicle, or formed as a functional unit in the autonomous driving module 610, or deployed in an autonomous vehicle and communicated with the autonomous driving module 610.

[0106] The electronic device 600 of the present invention can communicate with the chassis 630 of the autonomous vehicle via the CAN bus 620, and can efficiently and accurately detect various steering faults of the autonomous vehicle. It can realize online real-time monitoring of steering status during the driving process of the autonomous vehicle, with stable monitoring and no false detections, and the detection method is simple and easy to implement. In addition, when a steering fault is detected, it can be fed back to the autonomous driving module 610 in real time, so that the autonomous driving module 610 can control the vehicle to stop safely based on environmental perception and path planning, thereby realizing redundant monitoring at the autonomous driving level.

[0107] The electronic device 600 can also communicate with one or more external devices, which can be other control / execution components of the autonomous vehicle, to achieve coordinated control of the autonomous vehicle based on steering detection results.

[0108] This invention also provides a computer-readable storage medium for storing a program that, when executed, implements the steering detection method for an autonomous vehicle described in any of the above embodiments. In some possible implementations, various aspects of this invention can also be implemented as a program product comprising program code, which, when run on a terminal device, causes the terminal device to execute the steering detection method for an autonomous vehicle described in any of the above embodiments.

[0109] The storage medium of the present invention can be executed by the autonomous driving module of an autonomous vehicle, or by an electronic unit deployed in the autonomous driving module, or by a processor deployed in the autonomous vehicle and communicatively connected to the autonomous driving module.

[0110] When the storage medium of this invention is executed, it can efficiently and accurately detect various steering faults in autonomous vehicles, enabling real-time online monitoring of steering status during the driving process of autonomous vehicles. The monitoring is stable and without false detections, and the detection method is simple and easy to implement. In addition, when a steering fault is detected, it can be fed back to the autonomous driving module in real time, so that the autonomous driving module can control the vehicle to stop safely based on environmental perception and path planning, thereby achieving redundant monitoring at the autonomous driving level.

[0111] The storage medium may be a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the storage medium of the present invention is not limited thereto, and may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0112] The storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media include, but are not limited to: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0113] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable signal medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0114] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device, for example, via the Internet using an Internet service provider.

[0115] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A steering detection method for an autonomous vehicle, characterized in that, include: Obtain the steering response delay of autonomous vehicles; Based on the steering response delay, the steering command parameters and corresponding actual steering parameters of the autonomous vehicle are periodically acquired, including: determining the duration of the detection window, wherein the duration of the detection window is greater than the steering response delay; and based on the duration of the detection window, the steering command parameters and actual steering parameters of the autonomous vehicle are periodically acquired. Before periodically acquiring the steering command parameters and corresponding actual steering parameters of the autonomous vehicle, the method further includes: determining the sampling period of the steering command parameters and the actual steering parameters based on the update period of the steering command parameters of the autonomous vehicle, wherein the sampling period is greater than the update period and less than the steering response delay. Based on the actual steering parameters for each cycle, determine whether the autonomous vehicle turns within the corresponding cycle; Based on the steering command parameters and actual steering parameters of the cycle in which no steering occurred, it is determined whether the autonomous vehicle experienced a steering failure within the corresponding cycle.

2. The steering detection method as described in claim 1, characterized in that, The actual steering parameters include the actual steering angle; Determining whether the autonomous vehicle turns within the corresponding period includes: Based on the actual steering parameters of the current cycle, determine whether each unit change in the actual steering angle is less than a preset threshold. If so, it is determined that the autonomous vehicle did not turn during the current cycle.

3. The steering detection method as described in claim 1, characterized in that, The steering command parameters include the steering command angle, and the actual steering parameters include the actual steering angle. Determining whether the autonomous vehicle experiences a steering malfunction within a corresponding period includes: Based on the steering command parameters and actual steering parameters of the current cycle in which no steering has occurred, determine whether the angle difference between each set of steering command angles and actual steering angles is greater than the angle threshold. If so, it is determined that the autonomous vehicle experienced a steering failure during the current cycle in which no steering occurred.

4. The steering detection method as described in claim 3, characterized in that, In each set of steering command angles and actual steering angles, the time difference between the timestamp of the actual steering angle and the timestamp of the steering command angle corresponds to the steering response delay.

5. The steering detection method as described in claim 1, characterized in that, After periodically acquiring the steering command parameters and corresponding actual steering parameters of the autonomous vehicle, the method further includes: storing the steering command parameters and actual steering parameters of the currently acquired cycle into a buffer. The process involves determining whether the autonomous vehicle steers within a corresponding period and obtaining the steering command parameters and actual steering parameters for that period from the buffer.

6. The steering detection method as described in claim 5, characterized in that, The capacity of the buffer corresponds to the amount of data for the steering command parameters and actual steering parameters in one cycle.

7. The steering detection method as described in claim 1, characterized in that, Before determining whether the autonomous vehicle has turned within the corresponding period, the method further includes: It is determined that the autonomous vehicle has entered autonomous driving mode, and the target parameters of the autonomous vehicle meet the steering detection triggering conditions; The steering detection triggering condition is determined based on the configuration of the steering system of the autonomous vehicle.

8. The steering detection method as described in claim 1, characterized in that, The acquisition of the steering response delay of the autonomous vehicle includes: Under autonomous driving conditions, a response test is conducted on the autonomous vehicle to obtain the relationship between the steering command parameters and the actual steering parameters of the autonomous vehicle over time. Based on the aforementioned relationship, the steering response delay of the autonomous vehicle is determined.

9. The steering detection method according to any one of claims 1-8, characterized in that, After determining whether the autonomous vehicle experienced a steering malfunction within the corresponding period, the method further includes: When the autonomous vehicle experiences a steering failure within a cycle, a steering failure detection result is generated and reported to the autonomous driving module of the autonomous vehicle, so that the autonomous driving module can adjust the driving state of the autonomous vehicle based on the steering failure detection result.

10. A steering detection device for an autonomous vehicle, characterized in that, include: The response delay acquisition module is used to acquire the steering response delay of autonomous vehicles; A steering parameter acquisition module is used to periodically acquire the steering command parameters and corresponding actual steering parameters of the autonomous vehicle based on the steering response delay, including: determining the duration of a detection window, wherein the duration of the detection window is greater than the steering response delay; and periodically acquiring the steering command parameters and actual steering parameters of the autonomous vehicle based on the duration of the detection window. Before the steering parameter acquisition module periodically acquires the steering command parameters and corresponding actual steering parameters of the autonomous vehicle, it further includes: determining the sampling period of the steering command parameters and the actual steering parameters according to the update period of the steering command parameters of the autonomous vehicle, wherein the sampling period is greater than the update period and less than the steering response delay. The steering detection module is used to determine whether the autonomous vehicle has turned within the corresponding cycle based on the actual steering parameters of each cycle. The steering fault detection module is used to determine whether the autonomous vehicle has experienced a steering fault in the corresponding cycle based on the steering command parameters and actual steering parameters of the cycle in which no steering occurred.

11. An electronic device, characterized in that, include: processor; A memory, wherein executable instructions are stored; When the executable instructions are executed by the processor, they implement the steering detection method for an autonomous vehicle as described in any one of claims 1-9.

12. A computer-readable storage medium for storing a program, characterized in that, When the program is executed by the processor, it implements the steering detection method for autonomous vehicles as described in any one of claims 1-9.

Images