WO2024131084A1 - 图像输入输出系统故障的处理方法、装置、设备和介质 - Google Patents

图像输入输出系统故障的处理方法、装置、设备和介质 Download PDF

Info

Publication number
WO2024131084A1
WO2024131084A1 PCT/CN2023/111595 CN2023111595W WO2024131084A1 WO 2024131084 A1 WO2024131084 A1 WO 2024131084A1 CN 2023111595 W CN2023111595 W CN 2023111595W WO 2024131084 A1 WO2024131084 A1 WO 2024131084A1
Authority
WO
WIPO (PCT)
Prior art keywords
fault
image
output system
processing
image input
Prior art date
Application number
PCT/CN2023/111595
Other languages
English (en)
French (fr)
Inventor
王超
谢祥南
周学渊
赵彦东
Original Assignee
上海安亭地平线智能交通技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海安亭地平线智能交通技术有限公司 filed Critical 上海安亭地平线智能交通技术有限公司
Publication of WO2024131084A1 publication Critical patent/WO2024131084A1/zh

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures

Definitions

  • the present disclosure relates to fault handling technology, and in particular to a method, device, equipment and medium for handling faults of an image input and output system.
  • autonomous driving behavior decision-making is one of the key technologies for realizing autonomous driving functions.
  • Autonomous driving behavior decision-making refers to the autonomous driving vehicle sensing the surrounding environment information through sensors, comprehensively considering the surrounding environment, obstacles, vehicle merging and yielding rules, and matching with the experience knowledge in the autonomous driving library to make decisions on driving behaviors suitable for the current environment.
  • different types of failures such as sensor hardware failure and software failure may occur, resulting in the need for the vehicle to downgrade its autonomous driving function, resulting in a poor driving experience for users.
  • the embodiments of the present disclosure provide a method, apparatus, device and medium for processing image input and output system failures, which help reduce the occurrence of autonomous driving function degradation, thereby improving user experience.
  • a method for processing a fault of an image input and output system comprising: obtaining fault information of the image input and output system; based on the fault information, determining a target type and a target level to which a current fault belongs; and in response to the target level being a first preset level, performing fault recovery processing corresponding to the target type on the current fault.
  • a device for processing image input and output system faults including: a first acquisition module, used to acquire fault information of the image input and output system; a first determination module, used to determine, based on the fault information, a target type and a target level to which a current fault belongs; and a first processing module, used to perform fault recovery processing corresponding to the target type on the current fault in response to the target level being a first preset level.
  • a computer-readable storage medium stores a computer program, and the computer program is used to execute the method for processing a failure of an image input and output system as described in any of the above embodiments of the present disclosure.
  • an electronic device comprising: 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 method for handling image input and output system failures described in any of the above embodiments of the present disclosure.
  • FIG1 is an exemplary application scenario of the method for processing image input and output system failure provided by the present disclosure
  • FIG2 is a flow chart of a method for processing a fault of an image input and output system provided by an exemplary embodiment of the present disclosure
  • FIG3 is a flow chart of a method for processing a fault of an image input and output system provided by another exemplary embodiment of the present disclosure
  • FIG4 is a flowchart of a method for processing a failure of an image input and output system provided by yet another exemplary embodiment of the present disclosure
  • FIG5 is a schematic diagram of the structure of a device for processing a failure of an image input and output system provided by an exemplary embodiment of the present disclosure
  • FIG6 is a schematic diagram of the structure of a device for processing a failure of an image input and output system provided by another exemplary embodiment of the present disclosure
  • FIG7 is a schematic diagram of the structure of a first asynchronous fault processing module 507 provided by an exemplary embodiment of the present disclosure
  • FIG8 is a schematic structural diagram of a device provided by another exemplary embodiment of the present disclosure.
  • FIG. 9 is a schematic diagram of the structure of an application embodiment of the electronic device disclosed herein.
  • autonomous driving behavior decision-making is one of the key technologies for realizing the autonomous driving function.
  • Autonomous driving behavior decision-making refers to the autonomous driving vehicle sensing the surrounding environment information through sensors, comprehensively considering the surrounding environment, obstacles, vehicle merging and yielding rules, and matching with the experience knowledge in the autonomous driving library to make decisions on driving behaviors suitable for the current environment.
  • different types of faults such as hardware faults and software faults may occur, resulting in poor vehicle driving safety, thereby making the user's driving experience poor.
  • FIG. 1 is an exemplary application scenario of the method for processing image input and output system failure provided by the present disclosure.
  • the raw data collected by the image sensor can be transmitted to the video input/output (VIO) system.
  • the video input/output system can process the raw data to obtain processed image data, and can transmit the image data to the upper-layer application.
  • the upper-layer application can perceive the environment based on the image data for behavioral decision-making and control of autonomous driving.
  • the image input/output system fault processing method disclosed in the present invention (executed in the image input/output system fault processing device) can be used to monitor the image input/output system, obtain fault information of the image input/output system, and determine the target type and target level to which the current fault belongs based on the fault information.
  • the target type may include various faults and hardware physical faults (such as image sensor disconnection) in the image transmission or processing path of the image input/output system.
  • Various faults in the image transmission or processing path may include, for example, transmission process verification failure, image transmission protocol (MIPI) physical failure, image abnormality failure, transmission image size mismatch failure, memory write failure, data acquisition failure failure, data frame loss failure, etc., which can be set according to actual needs.
  • the target level can be set according to actual needs, for example, the target level may include a slight level, a general level, a single severe level, a fatal level, etc.
  • the first preset level refers to the level that can be recovered by itself at the bottom layer, which can be set according to actual needs.
  • the first preset level can be a minor level, and the target type is a certain fault inside the software.
  • the current fault can be recovered internally without reporting to the upper-level application, thereby avoiding the degradation of the autonomous driving function by the upper-level application and the need for the user to take over the vehicle immediately. This can help reduce the accidental degradation of the autonomous driving function and improve the user experience.
  • FIG2 is a flowchart of a method for processing a fault in an image input and output system provided by an exemplary embodiment of the present disclosure. This embodiment can be applied to electronic devices, such as a vehicle-mounted computing platform, as shown in FIG2, and includes the following steps:
  • Step 201 Obtain fault information of the image input and output system.
  • the video input/output (VIO) system (referred to as the system) is a system for processing the raw data collected by the image sensor to obtain image data
  • the image input/output system may include a hardware part and a software part.
  • the hardware part may include a hardware unit for image processing, such as an ISP (Image Signal Processing) unit, etc.
  • the software part may include software that controls the hardware unit to complete image processing, which is not specifically limited.
  • the fault information of the image input/output system may include fault type, fault level, fault occurrence time, image link where the fault occurs, fault description information and other fault related information, which may be set according to actual needs.
  • the fault type may include various faults in the image transmission or processing path of the image input/output system, hardware physical faults (also referred to as fatal faults, such as image sensor disconnection), and various faults in the image transmission or processing path may include, for example, transmission process verification failure fault, image transmission protocol (mipi) physical fault, image abnormality fault, transmission image size mismatch fault, memory write fault, data acquisition failure fault, data frame loss fault, etc., which may be set according to actual needs.
  • the fault level can be set according to actual needs, for example, it can include a minor level, a general level, a single serious level, a fatal level, etc.
  • Fault information can be obtained in any feasible way, for example, the system is provided with a detection and reporting function of various faults. When a fault is detected, the corresponding fault can be reported to the device. The specific setting can be based on actual needs.
  • step 201 may be executed by the processor calling a corresponding instruction stored in a memory, or may be executed by a first acquisition module executed by the processor.
  • Step 202 Determine the target type and target level of the current fault based on the fault information.
  • the correspondence between fault information and fault type and fault level can be determined and stored in advance according to the actual possible fault conditions. After the fault information is obtained, the target type and target level of the current fault can be determined based on the fault information and the correspondence.
  • step 202 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by the first determination module executed by the processor.
  • Step 203 In response to the target level being the first preset level, performing a fault recovery process corresponding to the target type on the current fault.
  • the first preset level refers to the level that can be self-recovered at the bottom layer, which can be set according to actual needs.
  • the first preset level can include at least one of a minor level, a general level, and a single severe level.
  • the target level is determined to be the first preset level, it means that the current fault may be a self-recoverable fault, and the current fault can be processed for fault recovery corresponding to the target type.
  • the target type is a certain fault inside the bottom layer software, which can be automatically recovered by the recovery software, the fault recovery can be performed by automatically recovering the bottom layer control software, so that it is not necessary to report to the upper layer application.
  • step 203 may be executed by the processor calling a corresponding instruction stored in a memory, or may be executed by a first processing module executed by the processor.
  • the method for handling image input and output system failures provided in the present embodiment, by classifying the failures of the image input and output system in autonomous driving into levels, can directly perform recovery processing at the bottom layer for failures of the first preset level that can be self-recovered at the bottom layer, such as minor failures, general failures, single serious failures, etc., occurring in the bottom layer software, without exposing them to the upper layer applications of autonomous driving, thereby avoiding degradation of the autonomous driving function by the upper layer applications and eliminating the need for users to immediately take over the vehicle, thereby helping to reduce the erroneous degradation of the autonomous driving function and helping to improve user experience.
  • FIG. 3 is a flowchart of a method for processing a failure of an image input and output system provided by another exemplary embodiment of the present disclosure.
  • the method of the embodiment of the present disclosure may further include the following steps:
  • Step 204 Acquire fault monitoring information of the image input and output system.
  • fault monitoring information refers to information obtained by monitoring, recording or counting fault conditions occurring in the image input and output system.
  • the fault monitoring information includes, for example but not limited to, fault status information, fault type, fault level, etc. of each fault that has been monitored.
  • the fault status information may include change information of the fault status of each fault type.
  • the fault status may include two states: fault occurrence and fault clearing.
  • the change information of the fault status of the fault type may be represented by the time of recording different fault states of the fault type, that is, the change information of the fault status of the fault type may include the time each time the fault state is a fault occurrence state and the time each time the fault state is a fault clearing state. Based on the fault status information, the occurrence of faults within a certain period of time may be determined, such as the occurrence frequency of any type of fault.
  • step 204 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by a fault monitoring module executed by the processor.
  • Step 205 Determine whether an asynchronous event triggering condition is met based on the fault monitoring information.
  • the asynchronous event triggering conditions can be set according to actual needs.
  • the asynchronous event triggering conditions are used to determine whether it is necessary to generate asynchronous events at present.
  • the generation of asynchronous events indicates that a fault that cannot be recovered autonomously at the bottom layer has occurred, and it is necessary to report it to the upper layer application through asynchronous events.
  • the asynchronous event triggering conditions may include the detection of fatal faults, multiple faults that occur frequently in a short period of time, frequent stability faults of the system, failure of fault recovery processing, and so on.
  • Fatal faults may be physical faults, such as camera disconnection.
  • fault recovery processing refers to a fault that originally belongs to the first preset level. When the bottom layer autonomous fault recovery processing is performed on it, the fault recovery is not successfully completed, resulting in an unresolved fault. Based on the matching of fault monitoring information with asynchronous event triggering conditions, it can be determined whether the asynchronous event triggering conditions are met.
  • step 205 may be executed by the processor calling a corresponding instruction stored in a memory, or may be executed by a second determination module executed by the processor.
  • Step 206 In response to the fault monitoring information satisfying the asynchronous event triggering condition, a first asynchronous event corresponding to the fault monitoring information is generated.
  • the asynchronous events that need to be generated are different, which can be set according to actual needs. For example, if the fault monitoring information detects a single fatal fault, the first asynchronous event is a single fatal fault event; if the fault monitoring information detects multiple faults that occur frequently in a short period of time, the corresponding first asynchronous event is a short-term frequent fault event; if the fault monitoring information detects frequent stability faults of the system, the corresponding first asynchronous event is a stability fault event; and so on.
  • step 206 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by the first generating module executed by the processor.
  • Step 207 Perform fault processing according to the first asynchronous event.
  • different fault handling methods can be set for different first asynchronous events to solve the corresponding fault problems. For example, if the first asynchronous event is a single fatal fault event, the fault handling corresponding to the single fatal fault event is performed. For example, when a single fatal fault is a physical fault (such as a camera disconnection), the user needs to be prompted to handle it, then the output of the fault prompt information is controlled. If the fault type corresponding to the single fatal fault is a software fault, the corresponding software can be restarted, without specific limitation.
  • step 207 may be executed by the processor calling a corresponding instruction stored in a memory, or may be executed by a first asynchronous fault processing module executed by the processor.
  • the disclosed embodiment monitors fault conditions occurring in the image input and output system. When it is detected that the bottom layer cannot recover autonomously, it can quickly report to the upper layer application in real time through asynchronous events.
  • the upper layer application can quickly perform corresponding fault processing to solve the fault problem in time, ensure vehicle driving safety, and not affect the normal operation of the autonomous driving function, thereby helping to improve the accuracy of the downgraded operation and helping to further improve the user experience.
  • FIG. 4 is a flowchart of a method for processing a failure of an image input and output system provided by yet another exemplary embodiment of the present disclosure.
  • performing fault processing according to the first asynchronous event in step 207 includes:
  • Step 2071 In response to the first asynchronous event being a single fatal fault event and determining that the fault type corresponding to the first asynchronous event is a physical fault, outputting fault prompt information.
  • a single fatal fault event can correspond to a single physical fault (such as image sensor disconnection) or a single software fault (such as VIO link software failure).
  • Different fault handling methods can be used for different single fatal fault events.
  • step 2071 may be executed by the processor calling a corresponding instruction stored in a memory, or may be executed by the first processing unit executed by the processor.
  • Step 2072 In response to the first asynchronous event being a single fatal fault event and determining that the fault type corresponding to the first asynchronous event is a software fault, controlling to restart the image link of the image input and output system.
  • the image link (VIO link for short) of the image input and output system is a processing link for image signal processing in the image input and output system.
  • the image data required for subsequent different functions can be obtained through processing by the image input and output system.
  • Each viewing angle can correspond to at least one VIO link, and each VIO link can be responsible for completing the image processing of the raw data of the image sensor of its corresponding viewing angle to obtain the corresponding image data.
  • a single fatal fault event of a software fault it means that the current VIO link has a fault that cannot be quickly self-recovered, resulting in the inability to obtain image data.
  • the fault can be recovered by restarting (resetting) and other operations. Therefore, the image link of the image input and output system can be controlled to restart to achieve fault recovery.
  • step 2072 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by a second processing unit executed by the processor.
  • Step 2073 In response to the first asynchronous event being a short-term frequent failure event or a stability failure event, determining whether image data can be obtained within a preset time.
  • the preset time can be set according to actual needs, for example, it can include the current time and a certain length of time before the current time, and there is no specific limitation. Whether the image data can be obtained can be determined by monitoring the image data acquisition result of the upper-layer application, for example, the upper-layer application can be set to return the acquisition result to the device of the embodiment of the present disclosure each time after acquiring image data, or the device of the embodiment of the present disclosure can request the upper-layer application to obtain the result, which can be set according to actual needs.
  • step 2073 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by a third processing unit executed by the processor.
  • Step 2074 in response to image data being able to be obtained within a preset time, maintaining a normal working state of the image input and output system.
  • image data can be obtained within the preset time, it means that although the asynchronous event mechanism is currently triggered, the current system has returned to normal, or the system only has occasional instability. If the current autonomous driving related functions (such as autonomous driving behavior decision-making functions) are running, the normal working state of the image input and output system can be temporarily maintained to ensure the continued operation of autonomous driving related functions.
  • autonomous driving related functions such as autonomous driving behavior decision-making functions
  • step 2074 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by a fourth processing unit executed by the processor.
  • Step 2075 in response to the failure to obtain image data within a preset time, controlling to restart the image link of the image input and output system.
  • step 2075 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by the fifth processing unit executed by the processor.
  • the embodiments of the present disclosure can solve the faults by corresponding fault handling methods for different asynchronous events without affecting
  • the normal operation of the image input and output system can be maintained so that the autonomous driving function can operate normally, thereby avoiding functional downgrade, helping to improve the accuracy of the downgrade operation, and helping to further improve the user experience.
  • the method of the embodiment of the present disclosure may further include:
  • Step 301 in response to the first target function in which the image input and output system participates exiting, controlling to restart the image input and output system.
  • the first target function can be any function that needs to obtain image data from the image input and output system in the automatic driving, such as the automatic driving behavior decision function, which is not specifically limited.
  • the automatic driving behavior decision function After the first asynchronous event of the short-time frequent fault event or stability fault event of the system is triggered, if it is determined that the image data can be obtained normally within the preset time, the normal working state of the image input and output system can be maintained, and the image input and output system can be restarted, so that the first target function involved in the image input and output system can work normally without being degraded, and after the first target function is exited, restarting the image input and output system will not affect the first target function.
  • the image input and output system can be controlled to restart, which helps to avoid the fault corresponding to the asynchronous event (including short-time frequent fault event or stability fault event) triggered by it from happening again, so that the image input and output system can work safely in the future, and further improve the driving safety of the vehicle.
  • asynchronous event including short-time frequent fault event or stability fault event
  • step 301 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by the sixth processing unit executed by the processor.
  • the method further includes:
  • Step 208 In response to the processing result of the fault processing being a failure, determine the target image link where the current fault is located based on the fault information corresponding to the first asynchronous event.
  • the target image link where the current fault is located can be determined based on the image link where the fault occurred included in the fault information corresponding to the first asynchronous event.
  • step 208 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by a second processing module executed by the processor.
  • Step 209 in response to the target image link having a preconfigured alternative image link and the alternative image link being in a non-faulty state, determining the environmental information of the viewpoint corresponding to the target image link based on the image data acquired by the alternative image link and the alternative algorithm and/or alternative model corresponding to the preconfigured alternative image link.
  • the corresponding replacement image link can be configured in advance for each image link.
  • the image link corresponding to the front view camera it can be replaced by the image links corresponding to the left front view camera and the right front view camera, that is, the image data of the front view range is determined by combining the left front view image with the image data of the front view range covered by the right front view image, and the functions that require the front view image data in the various functions of the autonomous driving continue to participate, so that the corresponding functions of the autonomous driving can continue to run without being degraded.
  • the specific replacement image link can be set according to actual needs.
  • the replacement image link state can include two states: a non-fault state and a fault state.
  • the specific replacement image link state can be determined according to the fault state of each image link maintained in real time.
  • the state of each image link can be maintained in real time, which can be set according to actual needs.
  • the replacement algorithm and/or replacement model corresponding to the replacement image link refers to a perception algorithm or perception model for environmental perception based on the image data obtained by the replacement image link, which can be set according to actual needs.
  • the perception model can include, for example, a pre-trained target detection model, a semantic segmentation model, etc., which are not specifically limited.
  • the environmental information of the corresponding perspective of the target image link can be extracted from the image data obtained by the substitution image link, so that the function of the target image link can be completed based on the substitution image link and the corresponding algorithm model.
  • step 209 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by a third processing module executed by the processor.
  • the target image link when any target image link fails in the fault handling of the upper layer application, the target image link can be replaced by The image link replaces the function of the target image link so that the autonomous driving function in which the target image link participates can continue to run without being downgraded, which helps to further improve the accuracy of the downgrade operation and thus helps to further improve the user experience.
  • the target image link does have a fault and cannot be restored when the alternative image link is running, and the effect achieved by the alternative solution may be somewhat different from that of the target image link, when using the alternative image link, the output of fault alarm information can be controlled to prompt the user of the problem with the current system.
  • different levels of control can be performed on the autonomous driving function according to the level of the replacement effect of the alternative image link, such as allowing the user to partially take over the driving while retaining some autonomous driving functions.
  • the specific settings can be based on actual needs.
  • the method of the embodiment of the present disclosure may further include:
  • Step 210 In response to the target image link not having a preconfigured alternative image link or the preconfigured alternative image link being in a fault state, controlling the second target function in which the target image link participates to be degraded, and outputting degrade prompt information.
  • the second target function is the function in which the target image link participates in the autonomous driving function, such as the autonomous driving behavior decision-making function. If the target image link does not have a pre-configured alternative image link or the pre-configured alternative image link is in a faulty state, it may indicate that the function replacement has failed. At this time, in order to enable the vehicle to drive safely, the second target function in which the target image link participates may be controlled to be downgraded, and a downgrade prompt message may be output to prompt the user to take over driving in a timely manner, thereby helping to avoid traffic accidents.
  • step 210 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by a fourth processing module executed by the processor.
  • the disclosed embodiment of the present invention can downgrade the autonomous driving function after the situation that enables the autonomous driving function to continue to operate is eliminated, which helps reduce the occurrence of false triggering of the downgrade operation and thus helps improve the user experience.
  • the method of the embodiment of the present disclosure may further include:
  • Step 401 In response to a failure in the fault recovery process, a second asynchronous event is generated.
  • the second asynchronous event may be a failure recovery processing event. For the current fault of the first preset level, if it cannot be recovered, it may indicate that the failure recovery processing result is a failure.
  • the second asynchronous event is similar to the first asynchronous event and is used to trigger the fault processing of the upper layer application. The details are not repeated here.
  • step 401 may be executed by the processor calling a corresponding instruction stored in a memory, or may be executed by a second generation module executed by the processor.
  • Step 402 Perform fault processing according to the second asynchronous event.
  • the fault can be handled through upper-level application control, such as controlling the restart of the image input and output system, which can be set according to actual needs.
  • the embodiment of the present disclosure can also quickly report to the upper-layer application in real time through an asynchronous event mechanism, and the upper-layer application can quickly handle the fault and solve the fault problem in a timely and rapid manner.
  • step 402 may be executed by the processor calling corresponding instructions stored in the memory, or may be executed by a second asynchronous fault processing module executed by the processor.
  • performing fault processing according to the second asynchronous event in step 402 includes: in response to the second asynchronous event being a fault recovery processing failure event, controlling to restart an image link of the image input and output system.
  • the upper-level application can solve the current fault by controlling and restarting the image link of the image input and output system, so that the image link can quickly restore normal function and enable the automatic driving function to operate normally.
  • an asynchronous fault handling application (or upper-layer asynchronous fault handling application or upper-layer asynchronous fault handling module) can be set in the upper-layer application to respond to asynchronous events and quickly perform corresponding fault handling at the upper layer.
  • the asynchronous events can include first asynchronous events and second asynchronous events, and can also include other asynchronous events set according to actual needs.
  • the disclosed embodiment can realize the collection and monitoring of faults in the underlying system software by classifying faults into levels and types.
  • the detection function helps to shield the reporting of most faults that can be quickly self-recovered, and based on the collected fault monitoring information, it can realize asynchronous reporting of non-self-recoverable faults through the asynchronous event mechanism, and realize real-time and rapid processing of asynchronous event faults.
  • function replacement can be implemented through an alternative image link to enable the autonomous driving function to continue to run, which helps to reduce the degradation rate of the autonomous driving function and help improve the user experience.
  • Any method for processing a fault of an image input and output system provided in the embodiments of the present disclosure may be executed by any appropriate device with data processing capabilities, including but not limited to: a terminal device and a server, etc.
  • any method for processing a fault of an image input and output system provided in the embodiments of the present disclosure may be executed by a processor, such as the processor executing any method for processing a fault of an image input and output system mentioned in the embodiments of the present disclosure by calling corresponding instructions stored in a memory. This will not be described in detail below.
  • FIG5 is a schematic diagram of a structure of an apparatus for processing image input and output system failure provided by an exemplary embodiment of the present disclosure.
  • the apparatus of this embodiment can be used to implement the corresponding method embodiment of the present disclosure.
  • the apparatus shown in FIG5 includes: a first acquisition module 501, a first determination module 502 and a first processing module 503.
  • the first acquisition module 501 is used to acquire fault information of the image input and output system; the first determination module 502 is used to determine the target type and target level to which the current fault belongs based on the fault information; the first processing module 503 is used to perform fault recovery processing corresponding to the target type on the current fault in response to the target level being a first preset level.
  • FIG. 6 is a schematic diagram of the structure of a device for processing a failure of an image input and output system provided by another exemplary embodiment of the present disclosure.
  • the apparatus of the embodiment of the present disclosure further includes:
  • a fault monitoring module 504 is used to obtain fault monitoring information of the image input and output system; a second determination module 505 is used to determine whether an asynchronous event triggering condition is satisfied based on the fault monitoring information; a first generation module 506 is used to generate a first asynchronous event corresponding to the fault monitoring information in response to the fault monitoring information satisfying the asynchronous event triggering condition, and report it to a first asynchronous fault processing module; a first asynchronous fault processing module 507 is used to perform fault processing according to the first asynchronous event.
  • FIG. 7 is a schematic diagram of the structure of a first asynchronous fault processing module 507 provided by an exemplary embodiment of the present disclosure.
  • the first asynchronous fault processing module 507 includes:
  • the first processing unit 5071 is used to control the output of fault prompt information in response to the first asynchronous event being a single fatal fault event and determining that the fault type corresponding to the first asynchronous event is a physical fault; the second processing unit 5072 is used to control the restart of the image link of the image input and output system in response to the first asynchronous event being a single fatal fault event and determining that the fault type corresponding to the first asynchronous event is a software fault; the third processing unit 5073 is used to determine whether image data can be obtained within a preset time in response to the first asynchronous event being a short-term frequent fault event or a stability fault event; the fourth processing unit 5074 is used to maintain the normal working state of the image input and output system in response to the image data being able to be obtained within the preset time; the fifth processing unit 5075 is used to control the restart of the image link of the image input and output system in response to the image data being unable to be obtained within the preset time.
  • the apparatus of the embodiment of the present disclosure further includes: a sixth processing unit 5076, configured to control restarting the image input and output system in response to the first target function in which the image input and output system participates being exited.
  • the apparatus of the embodiment of the present disclosure further includes:
  • the second processing module 508 is used to determine the target image link where the current fault is located based on the fault information corresponding to the first asynchronous event in response to the processing result of the fault processing being a failure; the third processing module 509 is used to determine the environmental information of the perspective corresponding to the target image link based on the image data obtained by the alternative image link and the pre-configured alternative algorithm and/or alternative model corresponding to the alternative image link in response to the target image link having a pre-configured alternative image link and the alternative image link being in a non-faulty state.
  • the apparatus of the embodiment of the present disclosure further includes: a fourth processing module 601, for controlling the degradation of a second target function in which the target image link participates, and outputting degradation prompt information in response to the target image link not having a preconfigured alternative image link or the preconfigured alternative image link being in a faulty state.
  • the apparatus of the embodiment of the present disclosure further includes:
  • the second generating module 602 is used to generate a second asynchronous event in response to a failure in the processing result of the fault recovery processing; the second asynchronous fault processing module 603 is used to perform fault processing according to the second asynchronous event.
  • the second asynchronous fault processing module 603 and the aforementioned first asynchronous fault processing module 507 may be the same module, or may be two independent modules, and may be specifically configured according to actual needs.
  • the second asynchronous fault processing module 603 is specifically configured to control restarting of the image link of the image input and output system in response to the second asynchronous event being a fault recovery processing failure event.
  • FIG8 is a schematic diagram of the framework of an automatic driving behavior decision function system provided by an exemplary embodiment of the present disclosure.
  • the automatic driving behavior decision function system may include an upper layer application, a hardware abstraction layer, a hardware driver layer and a hardware part.
  • the image input and output system fault processing device of the embodiment of the present disclosure in the hardware abstraction layer and the upper layer application, the image input and output system fault processing method of the embodiment of the present disclosure is completed.
  • the device may include device part 1 and device part 2, and device part 1 may include the above-mentioned first acquisition module, first determination module, first processing module, fault monitoring module, second determination module, first generation module, second generation module, etc., and device part 1 is set in the hardware abstraction layer.
  • Device part 2 may include the above-mentioned first asynchronous fault processing module and second asynchronous fault processing module, and device part 2 is set in the upper layer application.
  • the upper layer application may also include various upper layer applications of the automatic driving function, such as a perception application for environmental perception based on image data, which will not be described in detail.
  • the hardware may include an image sensor, an ISP unit for signal processing the raw data collected by the image sensor, various hardware processing units for image processing the image data, and so on.
  • the hardware driver layer includes software programs for driving various hardware.
  • the hardware abstraction layer is a software library related to the common points of various hardware drivers abstracted from the hardware driver layer.
  • Libcam represents a software library related to image sensors (cameras)
  • LIBVIO represents a software library related to VIO systems.
  • Each module of the device part 1 monitors hardware and software related faults of image sensors and VIO systems, and records and counts them. For faults that can be recovered autonomously and quickly at the bottom layer, the device part 1 can control or indirectly control the autonomous and rapid recovery of the bottom layer. For the detected faults that cannot be recovered autonomously and quickly at the bottom layer, asynchronous events (including the first asynchronous event and the second asynchronous event mentioned above) can be generated in real time, and can be reported to the device part 2 of the upper layer application in real time through an asynchronous mechanism.
  • Each module of the device part 2 can be responsible for responding to each asynchronous event and quickly and in real time perform corresponding asynchronous fault processing at the upper layer, such as controlling the restart of the VIO system, controlling the replacement image link to replace the target image link of the fault, etc., so that the autonomous driving function can operate normally.
  • a diagnosis report can be performed, the corresponding function of the autonomous driving can be controlled to be downgraded, and the user is prompted.
  • the specific handling of various situations please refer to the above content and will not be repeated here.
  • the electronic device 10 includes one or more processors 11 and a memory 12.
  • the processor 11 may be a central processing unit (CPU) or a computer having data processing capability and/or instruction execution capability. Other forms of processing units may control other components in the electronic device 10 to perform desired functions.
  • CPU central processing unit
  • Other forms of processing units may control other components in the electronic device 10 to perform desired functions.
  • the memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • Volatile memory may include, for example, random access memory (RAM) and/or cache memory (cache), etc.
  • Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.
  • One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute one or more computer program instructions to implement the methods and/or other desired functions of the various embodiments of the present disclosure described above.
  • the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected via a bus system and/or other forms of connection mechanisms (not shown).
  • the input device 13 may also include, for example, a keyboard, a mouse, etc.
  • the output device 14 can output various information to the outside, and the output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.
  • FIG9 only shows some of the components related to the present disclosure in the electronic device 10, omitting components such as a bus, an input/output interface, etc.
  • the electronic device 10 may further include any other appropriate components according to specific application scenarios.
  • embodiments of the present disclosure may also provide a computer program product, including computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the methods of various embodiments of the present disclosure described in the above “Exemplary Methods” section.
  • the computer program product may be written in any combination of one or more programming languages to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages.
  • the program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.
  • an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.
  • Computer readable storage media can adopt any combination of one or more readable media.
  • the readable medium can be a readable signal medium or a readable storage medium.
  • the readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above.
  • readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read-only memory
  • magnetic storage device or any suitable combination of the above.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Debugging And Monitoring (AREA)
  • Facsimiles In General (AREA)

Abstract

本公开实施例公开了一种图像输入输出系统故障的处理方法、装置、设备和介质，其中，方法包括：获取图像输入输出系统的故障信息；基于故障信息，确定当前故障所属的目标类型和目标等级；响应于目标等级为第一预设等级，对当前故障进行与目标类型对应的故障恢复处理。本公开实施例对于底层可快速自恢复的故障，可以在底层进行恢复处理，无需暴露到自动驾驶上层应用，避免上层应用由此进行的自动驾驶功能降级，也无需让用户因此立即接管车辆，从而可以减少自动驾驶功能的误降级，有助于提高用户体验。

Description

图像输入输出系统故障的处理方法、装置、设备和介质
本公开要求在2022年12月19日提交国家知识产权局、申请号为CN202211637384.9、发明名称为“图像输入输出系统故障的处理方法、装置、设备和介质”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及故障处理技术，尤其是一种图像输入输出系统故障的处理方法、装置、设备和介质。
背景技术
在自动驾驶领域，自动驾驶行为决策是自动驾驶功能实现的关键技术之一，自动驾驶行为决策是指自动驾驶车辆通过传感器感知周围环境信息，综合考虑周边环境、障碍物、车辆汇入及让行等规则，与自动驾驶库中的经验知识进行匹配，决策出适合当前环境下的驾驶行为。在自动驾驶过程中，可能会出现传感器硬件故障、软件故障等不同类型的故障，导致车辆需要进行自动驾驶的功能降级，从而使得用户驾驶体验较差。
发明内容
本公开的实施例提供了一种图像输入输出系统故障的处理方法、装置、设备和介质，有助于减少自动驾驶功能降级的情况发生，从而可以提升用户体验。
根据本公开实施例的一个方面，提供了一种图像输入输出系统故障的处理方法，包括：获取所述图像输入输出系统的故障信息；基于所述故障信息，确定当前故障所属的目标类型和目标等级；响应于所述目标等级为第一预设等级，对所述当前故障进行与所述目标类型对应的故障恢复处理。
根据本公开实施例的另一个方面，提供了一种图像输入输出系统故障的处理装置，包括：第一获取模块，用于获取图像输入输出系统的故障信息；第一确定模块，用于基于所述故障信息，确定当前故障所属的目标类型和目标等级；第一处理模块，用于响应于所述目标等级为第一预设等级，对所述当前故障进行与所述目标类型对应的故障恢复处理。
根据本公开实施例的再一方面，提供一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序用于执行本公开上述任一实施例所述的图像输入输出系统故障的处理方法。
根据本公开实施例的又一方面，提供一种电子设备，所述电子设备包括：处理器；用于存储所述处理器可执行指令的存储器；所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现本公开上述任一实施例所述的图像输入输出系统故障的处理方法。
基于本公开上述实施例提供的图像输入输出系统故障的处理方法、装置、设备和介质，通过将自动驾驶中的图像输入输出系统的故障进行等级划分，对于底层软件发生的轻微故障、一般故障、单个严重故障等在底层可自恢复的故障，可以直接在底层进行恢复处理，无需暴露到自动驾驶上层应用，避免上层应用由此进行的自动驾驶功能降级，也无需让用户因此立即接管车辆，从而可以助于减少自动驾驶功能的误降级，有助于提高用户体验。
附图说明
图1是本公开提供的图像输入输出系统故障的处理方法的一个示例性的应用场景；
图2是本公开一示例性实施例提供的图像输入输出系统故障的处理方法的流程示意图；
图3是本公开另一示例性实施例提供的图像输入输出系统故障的处理方法的流程示意图；
图4是本公开再一示例性实施例提供的图像输入输出系统故障的处理方法的流程示意图；
图5是本公开一示例性实施例提供的图像输入输出系统故障的处理装置的结构示意图；
图6是本公开另一示例性实施例提供的图像输入输出系统故障的处理装置的结构示意图；
图7是本公开一示例性实施例提供的第一异步故障处理模块507的结构示意图；
图8是本公开另一示例性实施例提供的装置的结构示意图；
图9是本公开电子设备一个应用实施例的结构示意图。
具体实施方式
为了解释本公开，下面将参考附图详细地描述本公开的示例实施例，显然，所描述的实施例仅是本公开的一部分实施例，而不是全部实施例，应理解，本公开不受示例性实施例的限制。
应注意到：除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本公开的范围。
本公开概述
在实现本公开的过程中，发明人发现，在自动驾驶领域，自动驾驶行为决策是自动驾驶功能实现的关键技术之一，自动驾驶行为决策是指自动驾驶车辆通过传感器感知周围环境信息，综合考虑周边环境、障碍物、车辆汇入及让行等规则，与自动驾驶库中的经验知识进行匹配，决策出适合当前环境下的驾驶行为。在自动驾驶过程中，可能会出现硬件故障、软件故障等不同类型的故障，导致车辆行驶安全性较差，从而使得用户驾驶体验较差。
示例性概述
图1是本公开提供的图像输入输出系统故障的处理方法的一个示例性的应用场景。
在自动驾驶场景，图像传感器采集的原始数据可以传输到图像输入输出(Video Input/Output，简称：VIO)系统，图像输入输出系统可以对原始数据进行一定的处理，获得处理后的图像数据，可以将图像数据传输给上层应用，上层应用可以基于图像数据进行环境感知，用于自动驾驶的行为决策与控制，利用本公开的图像输入输出系统故障的处理方法(在图像输入输出系统故障的处理装置中执行)，可以实现对图像输入输出系统进行监测，获取图像输入输出系统的故障信息，基于故障信息确定当前故障所属的目标类型和目标等级，目标类型可以包括图像输入输出系统的图像传输或处理通路出现的各种故障及硬件物理故障(比如图像传感器断连)，图像传输或处理通路出现的各种故障比如可以包括传输过程校验失败故障、图像传输协议(mipi)物理故障、图像异常故障、传输图像大小不匹配故障、内存写故障、获取数据失败故障、数据丢帧故障等等，具体可以根据实际需求设置。目标等级可以根据实际需求设置，比如目标等级可以包括轻微等级、一般等级、单个严重等级、致命等级，等等。确定了当前故障所属的目标类型和目标等级后，响应于目标等级为第一预设等级，可以对当前故障进行与目标类型对应的故障恢复处理，第一预设等级是指可在底层自行恢复的等级，可以根据实际需求设置，比如第一预设等级可以为轻微等级，目标类型为软件内部的某种故障，则对当前故障进行内部恢复即可，无需上报上层应用，避免上层应用由此进行的自动驾驶功能降级，也无需让用户因此立即接管车辆，从而可以助于减少自动驾驶功能的误降级，有助于提高用户体验。
示例性方法
图2是本公开一示例性实施例提供的图像输入输出系统故障的处理方法的流程示意图。本实施例可应用在电子设备上，具体比如车载计算平台上，如图2所示，包括如下步骤：
步骤201，获取图像输入输出系统的故障信息。
其中，图像输入输出(Video Input/Output，简称：VIO)系统(可以简称系统)是用于对图像传感器采集的原始数据进行处理获得图像数据的系统，图像输入输出系统可以包括硬件部分和软件部分。硬件部分可以包括用于进行图像处理的硬件单元，比如ISP(Image Signal Processing，图像信号处理)单元等。软件部分可以包括控制硬件单元完成图像处理的软件，具体不作限定。图像输入输出系统的故障信息可以包括故障类型、故障等级、故障发生时间、故障发生的图像链路、故障描述信息等故障相关信息，具体可以根据实际需求设置。故障类型可以包括图像输入输出系统的图像传输或处理通路出现的各种故障、硬件物理故障(也可称为致命故障，比如图像传感器断连)，图像传输或处理通路出现的各种故障比如可以包括传输过程校验失败故障、图像传输协议(mipi)物理故障、图像异常故障、传输图像大小不匹配故障、内存写故障、获取数据失败故障、数据丢帧故障等等，具体可以根据实际需求设置。故障等级可以根据实际需求设置，比如可以包括轻微等级、一般等级、单个严重等级、致命等级，等等。故障信息可以通过任意可实施的方式获取，比如系统中设置有各种故障的检测上报功能，当检测到发生故障时，可以向装置上报相应的故障，具体可以根据实际需求设置。
在一个可选示例中，该步骤201可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一获取模块执行。
步骤202，基于故障信息，确定当前故障所属的目标类型和目标等级。
其中，可以预先根据实际可能发生的故障情况，确定并存储故障信息与故障类型、故障等级的对应关系，当获取到故障信息后，基于故障信息及该对应关系可以确定当前故障所属的目标类型和目标等级。
在一个可选示例中，该步骤202可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一确定模块执行。
步骤203，响应于目标等级为第一预设等级，对当前故障进行与目标类型对应的故障恢复处理。
其中，第一预设等级是指可在底层自行恢复的等级，可以根据实际需求设置，比如第一预设等级可以包括轻微等级、一般等级、单个严重等级中的至少一种。当确定目标等级为第一预设等级时，表示当前故障可能为可自恢复的故障，则可以对当前故障进行与目标类型对应的故障恢复处理。比如目标类型为底层软件内部的某种故障，通过恢复软件可自动恢复，则可以在底层控制软件自动恢复即可进行故障恢复，从而可以不上报上层应用。
在一个可选示例中，该步骤203可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一处理模块执行。
本实施例提供的图像输入输出系统故障的处理方法，通过将自动驾驶中的图像输入输出系统的故障进行等级划分，对于底层软件发生的轻微故障、一般故障、单个严重故障等在底层可自恢复的第一预设等级的故障，可以直接在底层进行恢复处理，无需暴露到自动驾驶上层应用，避免上层应用由此进行的自动驾驶功能降级，也无需让用户因此立即接管车辆，从而可以助于减少自动驾驶功能的误降级，有助于提高用户体验。
图3是本公开另一示例性实施例提供的图像输入输出系统故障的处理方法的流程示意图。
在一个可选示例中，本公开实施例的方法还可以包括以下步骤：
步骤204，获取图像输入输出系统的故障监测信息。
其中，故障监测信息是指对图像输入输出系统所发生的故障情况进行监测并记录或统计获得的信息，故障监测信息例如但不限于包括监测到的已发生的各故障的故障状态信息、故障类型、故障等级等，故障状态信息可以包括每种故障类型的故障状态的变化信息，故障状态可以包括故障发生和故障清除两种状态，以一种故障类型为例，该故障类型的故障状态的变化信息比如可以通过记录的该故障类型的不同故障状态的时间表示，也即该故障类型的故障状态的变化信息可以包括每次故障状态为故障发生状态的时间、每次故障状态为故障清除状态的时间，基于故障状态信息可以确定一定时间内故障发生情况，比如任一种故障的发生频率。
在一个可选示例中，该步骤204可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的故障监测模块执行。
步骤205，基于故障监测信息，确定是否满足异步事件触发条件。
其中，异步事件触发条件可以根据实际需求设置，异步事件触发条件用于确定当前是否需要生成异步事件，生成异步事件表示当前出现了底层不能自主恢复的故障情况，需要通过异步事件上报上层应用。比如异步事件触发条件可以包括监测到致命故障、短时频发的多个故障、系统频发的稳定性故障、故障恢复处理失败，等等。致命故障比如可以为物理故障，如摄像头断连，短时频发的多个故障是指系统整体出现严重问题导致短时间内出现的大量故障，系统频发的稳定性故障表示系统出现稳定性问题导致持续监测到同一类型的故障，故障恢复处理失败是指原本属于第一预设等级的故障，在对其进行底层自主故障恢复处理时，未能成功完成故障恢复，导致故障未解决。基于故障监测信息与异步事件触发条件进行匹配，可以确定是否满足异步事件触发条件。
在一个可选示例中，该步骤205可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第二确定模块执行。
步骤206，响应于故障监测信息满足异步事件触发条件，生成故障监测信息对应的第一异步事件。
其中，若故障监测信息不同，则需要产生的异步事件不同，具体可以根据实际需求设置，比如若故障监测信息监测到单个致命故障，则第一异步事件为单个致命故障事件；若故障监测信息监测到短时频发的多个故障，则对应的第一异步事件为短时频发故障事件；若故障监测信息监测到系统频发的稳定性故障，则对应的第一异步事件为稳定性故障事件；等等。
在一个可选示例中，该步骤206可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一生成模块执行。
步骤207，根据第一异步事件，进行故障处理。
其中，针对不同的第一异步事件，可以设置不同的故障处理方式，以解决相应的故障问题。比如若第一异步事件为单个致命故障事件，则进行与单个致命故障事件对应的故障处理。比如当单个致命故障为物理故障(比如摄像头断连)，需要提示用户处理，则控制输出故障提示信息，若单个致命故障对应的故障类型为软件故障，可以控制重启相应的软件，具体不作限定。
在一个可选示例中，该步骤207可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一异步故障处理模块执行。
本公开实施例通过对图像输入输出系统所发生的故障情况进行监测，当监测到达到底层无法自主恢复的情况时，可以通过异步事件实时快速上报上层应用，由上层应用快速进行相应的故障处理，以及时解决故障问题，保证车辆行驶安全性，且可以不影响自动驾驶功能的正常运行，从而有助于提升降级操作的准确性，且有助于进一步提升用户体验。
图4是本公开再一示例性实施例提供的图像输入输出系统故障的处理方法的流程示意图。
在一个可选示例中，步骤207的根据第一异步事件，进行故障处理，包括：
步骤2071，响应于第一异步事件为单个致命故障事件，且确定出第一异步事件对应的故障类型为物理故障，控制输出故障提示信息。
其中，单个致命故障事件可以对应单个物理故障(比如图像传感器断开连接)或单个软件故障(比如VIO链路软件故障)，对于不同的单个致命故障事件，可以采用不同的故障处理方式，对于故障类型为物理故障的第一异步事件，表示当前软件无法自动恢复，需要进行物理恢复，因此可以进行诊断上报，并可以提示用户手动恢复。
在一个可选示例中，该步骤2071可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一处理单元执行。
步骤2072，响应于第一异步事件为单个致命故障事件，且确定出第一异步事件对应的故障类型为软件故障，控制重启图像输入输出系统的图像链路。
其中，图像输入输出系统的图像链路(简称VIO链路)是图像输入输出系统中图像信号处理的处理链路，对于车辆上的各视角的图像传感器(摄像头)所采集的原始数据，可以经过图像输入输出系统的处理获得后续不同功能需要的图像数据，每个视角可以对应至少一个VIO链路，每个VIO链路可以负责完成其对应视角的图像传感器原始数据的图像处理，获得对应的图像数据。对于软件故障的单个致命故障事件，表示当前VIO链路发生了不可快速自恢复的故障情形，导致无法获得图像数据，可以通过重启(reset)等操作进行故障恢复，因此可以通过控制重启图像输入输出系统的图像链路，实现故障恢复。
在一个可选示例中，该步骤2072可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第二处理单元执行。
步骤2073，响应于第一异步事件为短时频发故障事件或稳定性故障事件，确定预设时间内是否能够获得图像数据。
其中，预设时间可以根据实际需求设置，比如可以包括当前时间及当前时间之前的一定时长的在前时间，具体不作限定。是否能够获得图像数据可以通过监测上层应用的图像数据获取结果确定，比如可以设置上层应用每次获取图像数据后向本公开实施例的装置返回获取结果，或者可以由本公开实施例的装置向上层应用请求获取结果，具体可以根据实际需求设置。
在一个可选示例中，该步骤2073可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第三处理单元执行。
步骤2074，响应于预设时间内能够获得图像数据，保持图像输入输出系统的正常工作状态。
其中，若预设时间内能够获得图像数据，表示虽然当前触发了异步事件机制，但当前系统已经恢复正常，或者系统只是存在偶发不稳定情况，若当前自动驾驶的相关功能(比如自动驾驶行为决策功能)正在运行，可以暂时保持图像输入输出系统的正常工作状态，以保证自动驾驶相关功能的继续运行。
在一个可选示例中，该步骤2074可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第四处理单元执行。
步骤2075，响应于预设时间内无法获得图像数据，控制重启图像输入输出系统的图像链路。
其中，若预设时间内无法获得图像数据，表示当前系统发生了不可快速自恢复的故障情形，可以通过重启等操作进行故障恢复，因此控制重启图像输入输出系统的图像链路，有助于解决故障问题。
在一个可选示例中，该步骤2075可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第五处理单元执行。
本公开实施例针对不同的异步事件，可以通过对应的故障处理方式解决故障，在不影 响自动驾驶功能的情况下，可以保持图像输入输出系统的正常工作，以使自动驾驶功能能够正常运行，从而可以不进行功能降级，有助于提升降级操作的准确性，且有助于进一步提升用户体验。
在一个可选示例中，在步骤2074的响应于预设时间内能够获得图像数据，保持图像输入输出系统的正常工作状态之后，本公开实施例的方法还可以包括：
步骤301，响应于图像输入输出系统所参与的第一目标功能退出后，控制重启图像输入输出系统。
其中，第一目标功能可以为自动驾驶中需要从图像输入输出系统获取图像数据的任意功能，比如自动驾驶行为决策功能，具体不作限定。由于在触发了系统的短时频发故障事件或稳定性故障事件的第一异步事件之后，若确定出在预设时间内能够正常获得图像数据，可以保持图像输入输出系统的正常工作状态，可以不重启图像输入输出系统，从而可以使图像输入输出系统所参与的第一目标功能能够正常工作而不被降级，而在第一目标功能退出后，再进行图像输入输出系统的重启则可以不影响第一目标功能，此时，可以控制重启图像输入输出系统，从而有助于避免其在前触发的异步事件(包括短时频发故障事件或稳定性故障事件)对应的故障不再发生，使得图像输入输出系统后续能够安全工作，进一步提高车辆行驶安全性。
在一个可选示例中，该步骤301可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第六处理单元执行。
在一个可选示例中，在步骤207的根据第一异步事件，进行故障处理之后，还包括：
步骤208，响应于故障处理的处理结果为失败，基于第一异步事件对应的故障信息确定当前故障所在的目标图像链路。
其中，若故障处理的处理结果为失败，表示当前故障所在的目标图像链路发生了不可恢复的故障，可以基于第一异步事件对应的故障信息中所包括的故障发生的图像链路，确定出当前故障所在的目标图像链路。
在一个可选示例中，该步骤208可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第二处理模块执行。
步骤209，响应于目标图像链路具有预配置的替代图像链路，且替代图像链路为非故障状态，基于替代图像链路获取的图像数据、及预配置的替代图像链路对应的替代算法和/或替代模型，确定目标图像链路对应视角的环境信息。
其中，可以预先为各图像链路配置对应的替代图像链路，比如对于前视摄像头对应的图像链路，可以通过左前视角摄像头和右前视角摄像头分别对应的图像链路替代，即通过左前视角图像结合右前视角图像所覆盖的前视视角范围的图像数据，确定前视视角范围的图像数据，继续参与自动驾驶各功能中需要前视视角图像数据的功能，以使自动驾驶相应功能可以继续运行而不被降级。具体替代图像链路可以根据实际需求设置。替代图像链路状态可以包括非故障状态和故障状态两种状态，在实际应用中，具体的替代图像链路状态可以根据实时维护的各图像链路的故障状态确定。比如根据前述故障信息和故障监测信息，可以实时维护各图像链路的状态，具体可以根据实际需求设置。替代图像链路对应的替代算法和/或替代模型是指基于替代图像链路获得的图像数据进行环境感知的感知算法或感知模型，具体可以根据实际需求设置，感知模型比如可以包括预先训练获得的目标检测模型、语义分割模型，等等，具体不作限定。基于相应的替代算法和/或替代模型可以从替代图像链路获得的图像数据中提取目标图像链路对应视角的环境信息，从而基于替代图像链路及相应的算法模型，可以完成目标图像链路的功能。
在一个可选示例中，该步骤209可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第三处理模块执行。
本公开实施例当任一的目标图像链路在上层应用的故障处理失败后，可以通过替代图 像链路实现对该目标图像链路的功能的替代，以使目标图像链路所参与的自动驾驶功能能够继续运行，而不必被降级，有助于进一步提升降级操作的准确性，从而有助于进一步提升用户体验。
在一个可选示例中，由于替代图像链路运行时，目标图像链路确实存在故障且无法恢复，且替代方案实现的效果可能与目标图像链路具有一定的差异，因此，可以在使用替代图像链路时，控制输出故障报警信息，提示用户当前系统的问题。
在一个可选示例中，还可以根据替代图像链路的替代效果等级，对自动驾驶功能进行不同等级的控制，比如使用户部分接管驾驶，保留部分自动驾驶功能，具体可以根据实际需求设置。
在一个可选示例中，本公开实施例的方法还可以包括：
步骤210，响应于目标图像链路没有预配置的替代图像链路或者预配置的替代图像链路为故障状态，控制目标图像链路所参与的第二目标功能降级，并输出降级提示信息。
其中，第二目标功能为自动驾驶功能中目标图像链路参与的功能，比如自动驾驶行为决策功能，若目标图像链路没有预配置的替代图像链路或者预配置的替代图像链路为故障状态，可以表示功能替代失败，此时，为了使车辆能够安全行驶，可以控制目标图像链路所参与的第二目标功能降级，并可以输出降级提示信息，以及时提示用户接管驾驶，有助于避免发生交通事故。
在一个可选示例中，该步骤210可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第四处理模块执行。
本公开实施例在使自动驾驶功能能够继续运行的情况被排除后，可以对自动驾驶功能进行降级，有助于减少降级操作的误触发情况发生，从而有助于提升用户体验。
在一个可选示例中，在步骤203的响应于目标等级为第一预设等级，对当前故障进行与目标类型对应的故障恢复处理之后，本公开实施例的方法还可以包括：
步骤401，响应于故障恢复处理的处理结果为失败，生成第二异步事件。
其中，第二异步事件可以为故障恢复处理失败事件，对于第一预设等级的当前故障，若无法恢复，可以表示故障恢复处理结果为失败。第二异步事件与第一异步事件类似，用于触发上层应用的故障处理，具体不再赘述。
在一个可选示例中，该步骤401可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第二生成模块执行。
步骤402，根据第二异步事件，进行故障处理。
其中，若当前故障无法自恢复，可以通过上层应用控制进行故障处理，比如控制重启图像输入输出系统，具体可以根据实际需求设置。
本公开实施例针对第一预设等级的故障无法自恢复的情况，还可以通过异步事件机制实时快速上报上层应用，由上层应用快速进行故障处理，以及时快速解决故障问题。
在一个可选示例中，该步骤402可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第二异步故障处理模块执行。
在一个可选示例中，步骤402的根据第二异步事件，进行故障处理，包括：响应于第二异步事件为故障恢复处理失败事件，控制重启图像输入输出系统的图像链路。
其中，对于无法自恢复的故障，上层应用可以通过控制重启图像输入输出系统的图像链路，解决当前故障，以使图像链路快速恢复正常功能，使得自动驾驶功能能够正常运行。
在一个可选示例中，可以在上层应用设置异步故障处理应用(或称上层异步故障处理应用或上层异步故障处理模块)，用于响应异步事件在上层快速进行相应的故障处理，异步事件可以包括各第一异步事件和第二异步事件，还可以包括根据实际需求设置的其他异步事件。
本公开实施例通过对故障进行等级和类型划分，可以实现在底层系统软件故障收集监 测功能，有助于屏蔽可快速自恢复的大部分故障的上报，并可以基于收集的故障监测信息，通过异步事件机制，实现不可自恢复的故障情况的异步上报，实现对异步事件故障的实时快速处理，并可以在故障处理失败或故障自恢复失败情况下，通过替代图像链路实施功能替代，以使自动驾驶功能能够继续运行，有助于降低自动驾驶功能降级率，且有助于提升用户体验。
本公开的各实施例和各可选示例可以单独实施，也可以在不冲突的情况下，以任意组合方式结合实施，具体可以根据实际需求设置。
本公开实施例提供的任一种图像输入输出系统故障的处理方法可以由任意适当的具有数据处理能力的设备执行，包括但不限于：终端设备和服务器等。或者，本公开实施例提供的任一种图像输入输出系统故障的处理方法可以由处理器执行，如处理器通过调用存储器存储的相应指令来执行本公开实施例提及的任一种图像输入输出系统故障的处理方法。下文不再赘述。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
示例性装置
图5是本公开一示例性实施例提供的图像输入输出系统故障的处理装置的结构示意图。该实施例的装置可用于实现本公开相应的方法实施例，如图5所示的装置包括：第一获取模块501、第一确定模块502和第一处理模块503。
第一获取模块501，用于获取图像输入输出系统的故障信息；第一确定模块502，用于基于所述故障信息，确定当前故障所属的目标类型和目标等级；第一处理模块503，用于响应于所述目标等级为第一预设等级，对所述当前故障进行与所述目标类型对应的故障恢复处理。
图6是本公开另一示例性实施例提供的图像输入输出系统故障的处理装置的结构示意图。
在一个可选示例中，本公开实施例的装置还包括：
故障监测模块504，用于获取所述图像输入输出系统的故障监测信息；第二确定模块505，用于基于所述故障监测信息，确定是否满足异步事件触发条件；第一生成模块506，用于响应于所述故障监测信息满足所述异步事件触发条件，生成所述故障监测信息对应的第一异步事件，并上报第一异步故障处理模块；第一异步故障处理模块507，用于根据所述第一异步事件，进行故障处理。
图7是本公开一示例性实施例提供的第一异步故障处理模块507的结构示意图。
在一个可选示例中，第一异步故障处理模块507包括：
第一处理单元5071，用于响应于所述第一异步事件为单个致命故障事件，且确定出所述第一异步事件对应的故障类型为物理故障，控制输出故障提示信息；第二处理单元5072，用于响应于所述第一异步事件为单个致命故障事件，且确定出所述第一异步事件对应的故障类型为软件故障，控制重启所述图像输入输出系统的图像链路；第三处理单元5073，用于响应于所述第一异步事件为短时频发故障事件或稳定性故障事件，确定预设时间内是否能够获得图像数据；第四处理单元5074，用于响应于所述预设时间内能够获得所述图像数据，保持所述图像输入输出系统的正常工作状态；第五处理单元5075，用于响应于所述预设时间内无法获得所述图像数据，控制重启所述图像输入输出系统的图像链路。
在一个可选示例中，本公开实施例的装置还包括：第六处理单元5076，用于响应于所述图像输入输出系统所参与的第一目标功能退出后，控制重启所述图像输入输出系统。
在一个可选示例中，本公开实施例的装置还包括：
第二处理模块508，用于响应于故障处理的处理结果为失败，基于所述第一异步事件对应的故障信息确定当前故障所在的目标图像链路；第三处理模块509，用于响应于所述目标图像链路具有预配置的替代图像链路，且所述替代图像链路为非故障状态，基于所述替代图像链路获取的图像数据、及预配置的所述替代图像链路对应的替代算法和/或替代模型，确定所述目标图像链路对应视角的环境信息。
在一个可选示例中，本公开实施例的装置还包括：第四处理模块601，用于响应于所述目标图像链路没有预配置的替代图像链路或者预配置的所述替代图像链路为故障状态，控制所述目标图像链路所参与的第二目标功能降级，并输出降级提示信息。
在一个可选示例中，本公开实施例的装置还包括：
第二生成模块602，用于响应于故障恢复处理的处理结果为失败，生成第二异步事件；第二异步故障处理模块603，用于根据所述第二异步事件，进行故障处理。
其中，第二异步故障处理模块603与前述的第一异步故障处理模块507可以是同一模块，也可以是两个独立的模块，具体可以根据实际需求设置。
在一个可选示例中，第二异步故障处理模块603具体用于响应于所述第二异步事件为故障恢复处理失败事件，控制重启所述图像输入输出系统的图像链路。
在一个可选示例中，图8是本公开一示例性实施例提供的自动驾驶行为决策功能系统的框架示意图。在本示例中，自动驾驶行为决策功能系统可以包括上层应用、硬件抽象层、硬件驱动层和硬件部分，通过在硬件抽象层和上层应用设置本公开实施例的图像输入输出系统故障的处理装置，完成本公开实施例的图像输入输出系统故障的处理方法。其中，装置可以包括装置部分1和装置部分2，装置部分1可以包括上述第一获取模块、第一确定模块、第一处理模块、故障监测模块、第二确定模块、第一生成模块、第二生成模块等，装置部分1设置在硬件抽象层。装置部分2可以包括上述第一异步故障处理模块和第二异步故障处理模块，装置部分2设置在上层应用。上层应用除了本公开实施例的装置部分2之外，还可以包括自动驾驶功能的各种上层的应用，比如基于图像数据进行环境感知的感知应用，具体不再赘述。硬件可以包括图像传感器、用于对图像传感器采集的原始数据进行信号处理的ISP单元、用于对图像数据进行图像处理的各种硬件处理单元，等等。硬件驱动层包括用于驱动各硬件的软件程序，硬件抽象层是基于硬件驱动层抽象出的各硬件驱动的共同点相关的软件库，Libcam表示与图像传感器(摄像头)相关的软件库，LIBVIO表示VIO系统相关的软件库，装置部分1的各模块监测图像传感器、VIO系统的硬件和软件相关的故障，并进行记录和统计，对于底层可自主快速恢复的故障，装置部分1可以控制或间接控制底层的自主快速恢复，对于监测到的底层不可自主快速恢复的故障，可以实时生成异步事件(包括上述的第一异步事件和第二异步事件)，并可以通过异步机制实时快速上报上层应用的装置部分2，装置部分2的各模块可以负责响应各异步事件，在上层快速实时进行相应的异步故障处理，比如控制重启VIO系统、控制替代图像链路替代故障的目标图像链路，等等，以使自动驾驶功能能够正常运行。当确定故障处理失败且无法进行功能替代或者其他无法解决的故障时，可以进行诊断上报，控制自动驾驶相应功能进行降级，并提示用户。各种情况的具体处理参见前述内容，在此不再赘述。
本装置示例性实施例对应的有益技术效果可以参见上述示例性方法部分的相应有益技术效果，在此不再赘述。
示例性电子设备
图9是本公开电子设备一个应用实施例的结构示意图。本实施例中，该电子设备10包括一个或多个处理器11和存储器12。
处理器11可以是中央处理单元(CPU)或者具有数据处理能力和/或指令执行能力的 其他形式的处理单元，并且可以控制电子设备10中的其他组件以执行期望的功能。
存储器12可以包括一个或多个计算机程序产品，所述计算机程序产品可以包括各种形式的计算机可读存储介质，例如易失性存储器和/或非易失性存储器。易失性存储器例如可以包括随机存取存储器(RAM)和/或高速缓冲存储器(cache)等。非易失性存储器例如可以包括只读存储器(ROM)、硬盘、闪存等。在计算机可读存储介质上可以存储一个或多个计算机程序指令，处理器11可以运行一个或多个计算机程序指令，以实现上文中本公开的各个实施例的方法和/或其他期望的功能。
在一个示例中，电子设备10还可以包括：输入装置13和输出装置14，这些组件通过总线系统和/或其他形式的连接机构(未示出)互连。
此外，该输入装置13还可以包括例如键盘、鼠标等等。
该输出装置14可以向外部输出各种信息，该输出装置14可以包括例如显示器、扬声器、打印机、以及通信网络及其所连接的远程输出设备等等。
当然，为了简化，图9中仅示出了该电子设备10中与本公开有关的组件中的一些，省略了诸如总线、输入/输出接口等等的组件。除此之外，根据具体应用情况，电子设备10还可以包括任何其他适当的组件。
示例性计算机程序产品和计算机可读存储介质
除了上述方法和设备以外，本公开的实施例还可以提供一种计算机程序产品，包括计算机程序指令，计算机程序指令在被处理器运行时使得处理器执行上述“示例性方法”部分中描述的本公开各种实施例的方法中的步骤。
计算机程序产品可以以一种或多种程序设计语言的任意组合来编写用于执行本公开实施例操作的程序代码，所述程序设计语言包括面向对象的程序设计语言，诸如Java、C++等，还包括常规的过程式程序设计语言，诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。
此外，本公开的实施例还可以是计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令在被处理器运行时使得所述处理器执行本说明书上述“示例性方法”部分中描述的根据本公开各种实施例的方法中的步骤。
计算机可读存储介质可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以包括但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
以上结合具体实施例描述了本公开的基本原理，但是，在本公开中提及的优点、优势、效果等仅是示例而非限制，不能认为其是本公开的各个实施例必须具备的。另外，上述公开的具体细节仅是为了示例的作用和便于理解的作用，而非限制，上述细节并不限制本公开为必须采用上述具体的细节来实现。
本领域的技术人员可以对本公开进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本公开权利要求及其等同技术的范围之内，则本公开也意图包含这些改动和变型在内。

Claims (11)

  1. 一种图像输入输出系统故障的处理方法，包括：
    获取所述图像输入输出系统的故障信息；
    基于所述故障信息，确定当前故障所属的目标类型和目标等级；
    响应于所述目标等级为第一预设等级，对所述当前故障进行与所述目标类型对应的故障恢复处理。
  2. 根据权利要求1所述的方法，还包括：
    获取所述图像输入输出系统的故障监测信息；
    基于所述故障监测信息，确定是否满足异步事件触发条件；
    响应于所述故障监测信息满足所述异步事件触发条件，生成所述故障监测信息对应的第一异步事件；
    根据所述第一异步事件，进行故障处理。
  3. 根据权利要求2所述的方法，其中，所述根据所述第一异步事件，进行故障处理，包括：
    响应于所述第一异步事件为单个致命故障事件，且确定出所述第一异步事件对应的故障类型为物理故障，控制输出故障提示信息；
    响应于所述第一异步事件为单个致命故障事件，且确定出所述第一异步事件对应的故障类型为软件故障，控制重启所述图像输入输出系统的图像链路；
    响应于所述第一异步事件为短时频发故障事件或稳定性故障事件，确定预设时间内是否能够获得图像数据；
    响应于所述预设时间内能够获得所述图像数据，保持所述图像输入输出系统的正常工作状态；
    响应于所述预设时间内无法获得所述图像数据，控制重启所述图像输入输出系统的图像链路。
  4. 根据权利要求3所述的方法，其中，在响应于所述预设时间内能够获得所述图像数据，保持所述图像输入输出系统的正常工作状态之后，所述方法还包括：
    响应于所述图像输入输出系统所参与的第一目标功能退出后，控制重启所述图像输入输出系统。
  5. 根据权利要求2所述的方法，其中，在所述根据所述第一异步事件，进行故障处理之后，还包括：
    响应于故障处理的处理结果为失败，基于所述第一异步事件对应的故障信息确定当前故障所在的目标图像链路；
    响应于所述目标图像链路具有预配置的替代图像链路，且所述替代图像链路为非故障状态，基于所述替代图像链路获取的图像数据、及预配置的所述替代图像链路对应的替代算法和/或替代模型，确定所述目标图像链路对应视角的环境信息。
  6. 根据权利要求5所述的方法，还包括：
    响应于所述目标图像链路没有预配置的替代图像链路或者预配置的所述替代图像链路为故障状态，控制所述目标图像链路所参与的第二目标功能降级，并输出降级提示信息。
  7. 根据权利要求1所述的方法，其中，在所述响应于所述目标等级为第一预设等级，对所述当前故障进行与所述目标类型对应的故障恢复处理之后，所述方法还包括：
    响应于故障恢复处理的处理结果为失败，生成第二异步事件；
    根据所述第二异步事件，进行故障处理。
  8. 根据权利要求7所述的方法，其中，所述根据所述第二异步事件，进行故障处理， 包括：
    响应于所述第二异步事件为故障恢复处理失败事件，控制重启所述图像输入输出系统的图像链路。
  9. 一种图像输入输出系统故障的处理装置，包括：
    第一获取模块，用于获取图像输入输出系统的故障信息；
    第一确定模块，用于基于所述故障信息，确定当前故障所属的目标类型和目标等级；
    第一处理模块，用于响应于所述目标等级为第一预设等级，对所述当前故障进行与所述目标类型对应的故障恢复处理。
  10. 一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序用于执行上述权利要求1-8任一所述的图像输入输出系统故障的处理方法。
  11. 一种电子设备，所述电子设备包括：
    处理器；
    用于存储所述处理器可执行指令的存储器；
    所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现上述权利要求1-8任一所述的图像输入输出系统故障的处理方法。
PCT/CN2023/111595 2022-12-19 2023-08-07 图像输入输出系统故障的处理方法、装置、设备和介质 WO2024131084A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211637384.9 2022-12-19
CN202211637384.9A CN115743153A (zh) 2022-12-19 2022-12-19 图像输入输出系统故障的处理方法、装置、设备和介质

Publications (1)

Publication Number Publication Date
WO2024131084A1 true WO2024131084A1 (zh) 2024-06-27

Family

ID=85348512

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/111595 WO2024131084A1 (zh) 2022-12-19 2023-08-07 图像输入输出系统故障的处理方法、装置、设备和介质

Country Status (2)

Country Link
CN (1) CN115743153A (zh)
WO (1) WO2024131084A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115743153A (zh) * 2022-12-19 2023-03-07 上海安亭地平线智能交通技术有限公司 图像输入输出系统故障的处理方法、装置、设备和介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108958227A (zh) * 2018-08-09 2018-12-07 北京智行者科技有限公司 车辆故障诊断方法
CN109345658A (zh) * 2018-10-29 2019-02-15 百度在线网络技术（北京）有限公司 车辆系统故障的修复方法、装置、设备、介质和车辆
US20210331686A1 (en) * 2020-04-22 2021-10-28 Uatc, Llc Systems and Methods for Handling Autonomous Vehicle Faults
CN114620056A (zh) * 2022-03-25 2022-06-14 芜湖雄狮汽车科技有限公司 车辆传感器故障诊断方法、装置、车辆及存储介质
CN115442586A (zh) * 2021-06-01 2022-12-06 Oppo广东移动通信有限公司 图像处理芯片及应用于图像处理芯片的异常处理方法
CN115743153A (zh) * 2022-12-19 2023-03-07 上海安亭地平线智能交通技术有限公司 图像输入输出系统故障的处理方法、装置、设备和介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108958227A (zh) * 2018-08-09 2018-12-07 北京智行者科技有限公司 车辆故障诊断方法
CN109345658A (zh) * 2018-10-29 2019-02-15 百度在线网络技术（北京）有限公司 车辆系统故障的修复方法、装置、设备、介质和车辆
US20210331686A1 (en) * 2020-04-22 2021-10-28 Uatc, Llc Systems and Methods for Handling Autonomous Vehicle Faults
CN115442586A (zh) * 2021-06-01 2022-12-06 Oppo广东移动通信有限公司 图像处理芯片及应用于图像处理芯片的异常处理方法
CN114620056A (zh) * 2022-03-25 2022-06-14 芜湖雄狮汽车科技有限公司 车辆传感器故障诊断方法、装置、车辆及存储介质
CN115743153A (zh) * 2022-12-19 2023-03-07 上海安亭地平线智能交通技术有限公司 图像输入输出系统故障的处理方法、装置、设备和介质

Also Published As

Publication number Publication date
CN115743153A (zh) 2023-03-07

Similar Documents

Publication Publication Date Title
US9893963B2 (en) Dynamic baseline determination for distributed transaction
US9917741B2 (en) Method and system for processing network activity data
WO2024131084A1 (zh) 图像输入输出系统故障的处理方法、装置、设备和介质
US7328376B2 (en) Error reporting to diagnostic engines based on their diagnostic capabilities
US8713366B2 (en) Restarting event and alert analysis after a shutdown in a distributed processing system
JP2017517060A (ja) 障害処理方法、関連装置、およびコンピュータ
CN107431643A (zh) 监测存储集群元件
US10489232B1 (en) Data center diagnostic information
US9086968B2 (en) Checkpointing for delayed alert creation
WO2022057373A1 (zh) 一种双端口盘管理方法、装置、终端及存储介质
TWI691852B (zh) 用於偵測階層式系統故障之偵錯裝置及偵錯方法、電腦可讀取之記錄媒體及電腦程式產品
CN110017994B (zh) 自动驾驶车辆的异常检测方法、装置、系统、设备及介质
US20100107148A1 (en) Check-stopping firmware implemented virtual communication channels without disabling all firmware functions
US20150121144A1 (en) Synchronized debug information generation
US20090222687A1 (en) Method and system for telecommunication apparatus fast fault notification
CN114265724A (zh) 一种进程监控自动恢复装置和方法
KR102213676B1 (ko) 산술 연산 감시 기능을 구비하는 오토사 시스템용 단말 장치 및 오토사 시스템의 산술 연산 감시 방법
CN113672471A (zh) 一种软件监控方法、装置、设备及存储介质
CN108563530A (zh) 看门狗及其实现方法
CN106407081B (zh) 一种机箱管理系统及服务器
TWI469573B (zh) 系統錯誤處理方法與使用其之伺服器系統
CN114003426A (zh) 故障处理方法、系统和电子设备
JPH06175887A (ja) 障害監視／通知方式
KR101969393B1 (ko) 2단계 컨트롤을 통한 cctv 녹화기 와치독 시스템
JPH0424838A (ja) マルチプロセッサの障害管理方式

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23905264

Country of ref document: EP

Kind code of ref document: A1