CN113879324B - Intelligent driving vehicle sensor fault processing method and device - Google Patents
Intelligent driving vehicle sensor fault processing method and device Download PDFInfo
- Publication number
- CN113879324B CN113879324B CN202111256007.6A CN202111256007A CN113879324B CN 113879324 B CN113879324 B CN 113879324B CN 202111256007 A CN202111256007 A CN 202111256007A CN 113879324 B CN113879324 B CN 113879324B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- fault
- intelligent driving
- sensor
- driving vehicle
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
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
- B60W50/0205—Diagnosing or detecting failures; Failure detection models
-
- 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
- B60W50/023—Avoiding failures by using redundant parts
-
- 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
- B60W50/0205—Diagnosing or detecting failures; Failure detection models
- B60W2050/0215—Sensor drifts or sensor failures
Abstract
The invention provides a method and a device for processing faults of an intelligent driving vehicle sensor, wherein the method and the device for processing the faults of the intelligent driving vehicle sensor judge whether each vehicle-mounted sensor on an intelligent driving vehicle has faults or not, further determine whether the intelligent driving vehicle needs to be taken over according to the fault judgment result of each vehicle-mounted sensor, report a taking over request to a scene scheduling server in time when the intelligent driving vehicle needs to be taken over, receive environmental information around the vehicle, which is transmitted back by the scene scheduling server and sensed by a scene scheduling sensor pre-deployed in a driving environment, further take over an automatic driving task of the vehicle in time, and control the vehicle to continuously drive.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a method and a device for processing faults of a sensor of an intelligent driving vehicle.
Background
As the development, application and commercialization of intelligent driving technologies are accelerated, the safety of the intelligent driving technologies is receiving more and more attention. The existing intelligent driving vehicle mainly carries out environment sensing through a sensor sensing system of the vehicle, when a necessary sensor breaks down, sensing information provided by the sensor sensing system of the vehicle is not enough to support data required by intelligent driving of the vehicle, and the vehicle can only stop immediately at this time, so that driving safety can be influenced to a certain extent. Therefore, how to perform safety control on the intelligent driving vehicle under the condition of sensor failure is very important.
The existing sensor fault processing method for intelligently driving the vehicle generally judges whether the sensor has a fault or not based on a comparison result of sensing data and actual data of the sensor within a period of time, the fault detection mode has low accuracy and a complex process, and a final processing result still needs the vehicle to be parked close to the side, so that normal driving and driving safety are influenced.
Disclosure of Invention
The invention provides a sensor fault processing method and device for an intelligent driving vehicle, which are used for solving the defects that the sensor fault detection method for the intelligent driving vehicle in the prior art is low in accuracy, complicated in process and the fault processing result influences normal driving and driving safety.
In a first aspect, the present invention provides a method for handling a sensor fault of an intelligent driving vehicle, the method comprising:
judging whether each vehicle-mounted sensor on the intelligent driving vehicle breaks down or not;
determining whether to take over the intelligent driving vehicle or not according to the fault judgment result of each vehicle-mounted sensor, if so, reporting the fault information of the vehicle-mounted sensors to a scene scheduling server and initiating a take-over request;
acquiring sampling data of a scene scheduling sensor which is deployed at a corresponding position in advance by a scene scheduling server according to the position information of the intelligent driving vehicle initiating the takeover request;
and controlling the intelligent driving vehicle to normally run according to the sampling data of the scene scheduling sensor returned by the scene scheduling server.
According to the fault processing method of the intelligent driving vehicle sensor provided by the invention, whether each vehicle-mounted sensor on the intelligent driving vehicle has a fault or not is judged, and the fault processing method comprises the following steps:
respectively acquiring timestamp information of a latest frame of sampling data of each vehicle-mounted sensor on the intelligent driving vehicle;
the timestamp information is differenced with the current time to obtain a sampling time difference value;
and comparing the sampling time difference with a preset time interval threshold, and if the sampling time difference is greater than the time interval threshold, judging that the vehicle-mounted sensor has a fault.
According to the fault processing method for the intelligent driving vehicle sensor provided by the invention, whether the intelligent driving vehicle is taken over or not is determined according to the fault judgment result of each vehicle-mounted sensor, and the method comprises the following steps:
and determining whether the intelligent driving vehicle can normally run or not according to the fault judgment result of each vehicle-mounted sensor, and if the intelligent driving vehicle cannot normally run, determining to take over the intelligent driving vehicle.
According to the fault processing method for the intelligent driving vehicle sensor provided by the invention, whether the intelligent driving vehicle can normally run or not is determined according to the fault judgment result of each vehicle-mounted sensor, and the fault processing method comprises the following steps:
determining the vehicle-mounted sensor with the fault according to the fault judgment result of each vehicle-mounted sensor;
diagnosing the vehicle-mounted sensor with the fault, and determining a fault level according to a diagnosis result of the vehicle-mounted sensor with the fault;
and determining whether the intelligent driving vehicle can normally run or not according to the fault grade.
According to the fault processing method for the sensor of the intelligent driving vehicle, provided by the invention, the vehicle-mounted sensor with the fault is diagnosed, and the fault grade is determined according to the diagnosis result of the vehicle-mounted sensor with the fault, and the fault processing method comprises the following steps:
judging the importance of each vehicle-mounted sensor with faults, and determining the installation position of each vehicle-mounted sensor with faults;
and determining the fault grade according to the importance and the installation position of the vehicle-mounted sensor with the fault.
According to the fault handling method for the sensor of the intelligent driving vehicle, the fault grade comprises the following steps:
a light and micro fault, wherein the light and micro fault is a fault of only a low-importance vehicle-mounted sensor;
and the serious fault is that the vehicle-mounted sensor with high importance degree fails and/or the installation position of the failed vehicle-mounted sensor seriously influences normal running.
According to the fault processing method of the intelligent driving vehicle sensor, the scene scheduling sensor comprises a camera, a laser radar sensing unit, a millimeter wave radar sensing unit and an ultrasonic radar sensing unit.
In a second aspect, the present invention also provides an apparatus for processing a sensor fault of an intelligent driving vehicle, the apparatus comprising:
the fault judgment module is used for judging whether each vehicle-mounted sensor on the intelligent driving vehicle has a fault;
the driving judgment module is used for determining whether to take over the intelligent driving vehicle according to the fault judgment result of each vehicle-mounted sensor, reporting fault information of the vehicle-mounted sensors to the scene scheduling server and issuing a take-over request if the intelligent driving vehicle is determined to take over;
the acquisition module is used for acquiring the sampling data of the scene scheduling sensor which is deployed at the corresponding position in advance according to the position information of the intelligent driving vehicle initiating the takeover request by the scene scheduling server;
and the take-over control module is used for controlling the intelligent driving vehicle to normally run according to the sampling data of the scene scheduling sensor returned by the scene scheduling server.
According to the fault processing device for the intelligent driving vehicle sensor, the fault judgment module, the driving judgment module, the acquisition module and the take-over control module are all arranged in an automatic driving redundancy system, and the automatic driving redundancy system is arranged on an intelligent driving vehicle.
In a third aspect, the present invention further provides an intelligent driving vehicle, wherein the intelligent driving vehicle executes any one of the intelligent driving vehicle sensor fault processing methods when the intelligent driving vehicle is running.
In a fourth aspect, the present invention further provides an electronic device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for processing the failure of the sensor of the intelligent driving vehicle as described in any one of the above.
In a fifth aspect, the present invention also provides a non-transitory computer readable storage medium, on which a computer program is stored, which computer program, when executed by a processor, implements the steps of the intelligent-drive vehicle sensor fault handling method as described in any one of the above.
According to the method and the device for processing the faults of the sensors of the intelligent driving vehicle, whether the intelligent driving vehicle needs to be taken over is determined by judging whether the vehicle-mounted sensors on the intelligent driving vehicle have faults or not according to the fault judgment results of the vehicle-mounted sensors, when the intelligent driving vehicle needs to be taken over is determined, a take-over request is reported to the scene scheduling server in time, environment information around the vehicle, which is transmitted back by the scene scheduling server and sensed by the scene scheduling sensors pre-deployed in the driving environment, is received, the automatic driving task of the vehicle is taken over in time, and the vehicle is controlled to continue to run.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow diagram of a method for handling a sensor fault in an intelligent drive vehicle according to the present invention;
FIG. 2 is a schematic structural diagram of a sensor fault handling device for an intelligent driving vehicle provided by the invention;
FIG. 3 is a schematic diagram of the interaction of an unmanned vehicle, a scene scheduling server, and scene scheduling sensors in an intelligent driving environment;
FIG. 4 is a schematic diagram of a smart-driving vehicle sensor fault handling principle;
fig. 5 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 illustrates a method for processing a sensor fault of an intelligent driving vehicle according to an embodiment of the present invention, where the method includes:
s110: and judging whether each vehicle-mounted sensor on the intelligent driving vehicle breaks down or not.
In this embodiment, judge whether each on-vehicle sensor breaks down on the intelligent driving vehicle, specifically include:
firstly, respectively acquiring timestamp information of a latest frame of sampling data of each vehicle-mounted sensor on the intelligent driving vehicle;
then, the timestamp information is differenced with the current time to obtain a sampling time difference value;
and finally, comparing the sampling time difference with a preset time interval threshold, and if the sampling time difference is greater than the time interval threshold, judging that the vehicle-mounted sensor has a fault.
Considering that the sampling data of the vehicle-mounted sensor needs to be continuously received by an automatic driving system on the vehicle, the vehicle-mounted sensor fault detection method provided by the embodiment does not need to analyze the data collected by the vehicle-mounted sensor, and only judges according to the timestamp information of the data, when the timestamp of the received latest frame of vehicle-mounted sensor data is compared with the current time, the time difference value exceeds the set time difference value threshold value, which indicates that the vehicle-mounted sensor cannot normally send the data, namely, a fault occurs, so that whether the sensor has a fault is judged according to the time interval of the latest data sending of the vehicle-mounted sensor. The fault judgment method is simpler and has higher accuracy.
S120: and determining whether to take over the intelligent driving vehicle or not according to the fault judgment result of each vehicle-mounted sensor, and reporting the fault information of the vehicle-mounted sensors to a scene scheduling server and starting a take-over request if the intelligent driving vehicle is determined to take over.
Specifically, determining whether to take over the intelligent driving vehicle according to the fault judgment result of each vehicle-mounted sensor comprises the following steps:
and determining whether the intelligent driving vehicle can normally run or not according to the fault judgment result of each vehicle-mounted sensor, and if the intelligent driving vehicle cannot normally run, determining to take over the intelligent driving vehicle.
Further, according to the fault judgment result of each vehicle-mounted sensor, whether the intelligent driving vehicle can normally run is determined, and the method specifically comprises the following steps:
firstly, determining a vehicle-mounted sensor with a fault according to the fault judgment result of each vehicle-mounted sensor;
then, diagnosing the vehicle-mounted sensor with the fault, and determining the fault level according to the diagnosis result of the vehicle-mounted sensor with the fault;
and finally, determining whether the intelligent driving vehicle can normally run or not according to the fault level.
Furthermore, diagnosing the vehicle-mounted sensor with the fault, and determining the fault level according to the diagnosis result of the vehicle-mounted sensor with the fault specifically comprises the following steps:
firstly, judging the importance of each vehicle-mounted sensor with faults, and determining the installation position of each vehicle-mounted sensor with faults;
and secondly, determining the fault grade according to the importance and the installation position of the vehicle-mounted sensor with the fault.
In order to accurately diagnose the fault level of the vehicle-mounted sensors on the current vehicle, importance division can be performed on all the vehicle-mounted sensors in advance, and it is determined which sensor or sensors are more important for normal running of the vehicle and which sensors are not particularly important for normal running of the vehicle, so that it can be determined which sensors need to be ensured to normally work under each fault level, and fault level division is realized.
The installation positions of the vehicle-mounted sensors refer to the positions of the vehicle-mounted sensors on the intelligent driving vehicle, and according to the installation positions of the vehicle-mounted sensors, the environment perception capability of the intelligent driving vehicle in which directions is weakened or even disabled can be judged.
According to the importance and the installation position of the vehicle-mounted sensor with the fault, the present embodiment sets six fault levels as follows:
first-stage failure: the normal running is not influenced, the unimportant vehicle-mounted sensor fails, the whole vehicle-mounted sensor sensing system can still sense the surrounding environment information, for example, millimeter wave radars arranged at the left side and the right side of an intelligent driving vehicle fail.
Secondary failure: the normal driving is slightly influenced, the surrounding environment information can still be sensed, only the sensing precision is reduced, for example, on the basis of the primary fault, the ultrasonic radar breaks down, and at the moment, the speed of the intelligent driving vehicle needs to be limited.
And (3) three-stage fault: normally driving is generally affected, and the sensing precision is further reduced, for example, on the basis of the secondary fault, the forward short-distance laser radar breaks down, and at the moment, the intelligent driving vehicle needs to be further limited in speed.
Four-stage failure: the normal running is seriously influenced, but the vehicle can be parked at the side by depending on the information sensed by the remaining non-fault vehicle-mounted sensors, for example, on the basis of the three-level fault, all the vehicle-mounted sensors on the left side of the intelligent driving vehicle fail (namely all the vehicle-mounted sensors fail).
And (3) five-stage fault: the normal running is seriously influenced, the intelligent driving vehicle can only sense the obstacle information of a road ahead, vehicle-mounted sensors in other directions except the position right ahead of the vehicle are invalid, and the intelligent driving vehicle can only run forwards at a low speed.
And (3) six-stage fault: the normal driving is seriously influenced, most or even all vehicle-mounted sensors on the intelligent driving vehicle break down at the moment, and the intelligent driving vehicle cannot sense the surrounding environment information and can only normally brake.
In this embodiment, the first-stage fault, the second-stage fault, and the third-stage fault are defined as a minor-stage fault, and the fourth-stage fault, the fifth-stage fault, and the sixth-stage fault are defined as a major-stage fault.
The minor fault is that only the vehicle-mounted sensor with low importance is in fault, the intelligent driving vehicle can still normally run at the moment, and the vehicle speed can be properly reduced according to the fault condition so as to ensure the running safety.
The serious-grade fault is that the vehicle-mounted sensor with high importance degree is in fault and/or the installation position of the vehicle-mounted sensor with the fault seriously influences normal running, and at the moment, the vehicle cannot run normally according to the rest vehicle-mounted sensors without the fault.
And if the automatic driving vehicle cannot normally run according to the fault level, reporting fault information of the vehicle-mounted sensor to a scene scheduling server and initiating a take-over request.
When the fault level reaches a serious fault condition, the intelligent driving vehicle cannot continue to normally run according to the vehicle-mounted sensor sensing system, and an automatic driving task is completed under the assistance of external environment sensing information, namely, the automatic driving task of the intelligent driving vehicle is taken over by external intervention control.
S130: and acquiring sampling data of a scene scheduling sensor which is pre-deployed at a corresponding position according to the position information of the intelligent driving vehicle initiating the takeover request by the scene scheduling server.
The embodiment receives a takeover request initiated by an intelligent driving vehicle through a scene scheduling server pre-deployed in an intelligent driving scene. And a plurality of scene scheduling sensors are deployed in the driving environment in advance, specifically, the scene scheduling sensors comprise cameras, laser radar sensing units, millimeter wave radar sensing units and ultrasonic radar sensing units, and can acquire surrounding environment information.
After the field Jing Diaodu server receives the takeover request of the fault vehicle, the position information of the intelligent driving vehicle needs to be acquired at first, the position of the fault vehicle is determined, then data acquired by a scene scheduling sensor pre-deployed at the corresponding position is acquired, namely environment perception information around the fault vehicle is acquired, and then the environment perception information is transmitted back to a redundant system on the intelligent driving vehicle.
S140: and controlling the intelligent driving vehicle to normally run according to the sampling data of the scene scheduling sensor returned by the scene scheduling server.
After the redundant system receives the environment sensing information near the fault vehicle returned by the scene scheduling server, the sampling data of the scene scheduling sensor at the corresponding position is used as new environment sensing data, namely the data basis for the intelligent driving vehicle to continuously run, so that the intelligent driving vehicle can be controlled to continuously run.
It should be noted that, in consideration of deployment difficulty and deployment cost of the scene scheduling sensor and the scene scheduling server, the method for processing the fault of the intelligent driving vehicle sensor provided by the embodiment is mainly suitable for a structured scene, that is, a closed driving environment, which refers to an environment without interference of other vehicles, such as a mining area, a port, and the like, and can be closed to allow only the intelligent driving vehicle to run.
Therefore, according to the fault processing method for the intelligent driving vehicle sensor provided by the embodiment of the invention, the fault grade is determined by detecting whether the vehicle-mounted sensor has a fault, whether the vehicle can normally run is judged according to the fault grade, when the vehicle cannot normally run, the vehicle is timely taken over, and the intelligent driving vehicle is assisted to continuously run by utilizing the sampling data of the scene scheduling sensor returned by the scene scheduling server, so that the problem that the vehicle stops at the side due to the fault of the vehicle-mounted sensor to influence the normal running of the vehicle is solved, and the driving safety and the driving reliability of the vehicle are improved.
The following describes the fault handling apparatus for a sensor of an intelligent driving vehicle provided by the present invention, and the fault handling apparatus for a sensor of an intelligent driving vehicle described below and the fault handling method for a sensor of an intelligent driving vehicle described above can be referred to in correspondence with each other.
Fig. 2 shows a device for processing a sensor fault of an intelligent driving vehicle, which comprises:
the fault judgment module 210 is used for judging whether each vehicle-mounted sensor on the intelligent driving vehicle has a fault;
the driving judgment module 220 is configured to determine whether to take over the intelligent driving vehicle according to a fault judgment result of each vehicle-mounted sensor, and if it is determined that the intelligent driving vehicle takes over, report fault information of the vehicle-mounted sensor to the scene scheduling server and initiate a take-over request;
an obtaining module 230, configured to obtain, by the scene scheduling server, according to the position information of the intelligent driving vehicle initiating the takeover request, sample data of a scene scheduling sensor pre-deployed at a corresponding position;
and the take-over control module 240 is used for controlling the intelligent driving vehicle to normally run according to the sampling data of the scene scheduling sensor returned by the scene scheduling server.
It should be noted that, in this embodiment, the failure determining module 210, the driving determining module 220, the obtaining module 230, and the takeover control module 240 are all disposed in an autopilot redundancy system, and the autopilot redundancy system is disposed on an intelligent driving vehicle.
Specifically, referring to fig. 3, the process of implementing the sensor fault handling function of the intelligent driving vehicle in the present embodiment may be macroscopically divided into three parts, where the first part is a scene scheduling server, and the scene scheduling server, when viewed functionally, includes a vehicle management module, a data management module and a front end module, the vehicle management module is used to supervise the intelligent driving vehicle, the data management module is used to store and manage received and processed data, and the front end module is used to display data.
The second part is a scene scheduling sensor which comprises a camera, a laser radar sensing unit, a millimeter wave radar sensing unit and an ultrasonic radar sensing unit and is used for sensing environmental information around a road.
The third part is an intelligent driving vehicle which mainly comprises an automatic driving system, an automatic driving redundancy system, a vehicle-mounted sensor system, a planning and decision system and a control system, wherein the automatic driving redundancy system is a newly added component, and the rest are functional components of the intelligent driving vehicle.
Referring to fig. 4, in the present embodiment, the scene scheduling server is mainly deployed in an intelligent driving environment, where the intelligent driving environment mainly refers to a structured scene, and by determining a range of the structured scene, the scene scheduling server is deployed in the structured scene, and importing a scene high-precision map, a front-end interface of the scene scheduling server may display positions and states of all vehicles in the scene in real time, so as to manage and monitor the intelligent driving vehicles.
The scene scheduling sensor is also deployed in a closed driving environment, a camera and a laser radar sensing unit (namely a laser radar sensor) are installed at a certain distance along a road and are connected with the scene scheduling server, the millimeter wave radar sensing unit and the ultrasonic radar sensing unit can be set according to needs, or other sensing equipment capable of sensing the external environment can be arranged, the scene scheduling sensor is controlled by the scene scheduling server, deployment of the scene scheduling sensor is achieved, and the scene scheduling sensor can transmit collected data to the scene scheduling server in real time.
After the scene scheduling server and the scene scheduling sensor are deployed, the intelligent driving vehicle is also required to be deployed to enter a closed driving scene, and vehicle information is registered in the scene scheduling server, so that the scene scheduling server can manage the registered vehicle after being started, and the position and the state of the vehicle are mainly monitored.
In addition, an automatic driving redundancy system is required to be deployed on the registered vehicle, the automatic driving redundancy system is a take-over auxiliary control decision-making system which is additionally arranged on the basis of an existing intelligent driving system of the intelligent driving vehicle, and the automatic driving redundancy system has the same function as the automatic driving system of the intelligent driving vehicle and can realize the function of monitoring the working state of the sensor sensing assembly.
When the intelligent driving vehicle runs, the automatic driving redundancy system can accurately determine whether the sensor fails or not based on timestamp information of data collected by the vehicle-mounted sensor, judges the fault level after monitoring that the sensor fails, determines whether the vehicle can run normally or not, and whether a driving task of the failed vehicle needs to be taken over or not, immediately reports the fault information to the scene scheduling server, and a front-end interface of the scene scheduling server can display specific fault information of the vehicle.
If the fault vehicle cannot normally run, the vehicle has a takeover requirement at the moment, the automatic driving redundancy system sends a takeover request to the scene scheduling server, the scene scheduling server calls road edge camera data and laser radar data at corresponding positions according to the position of the fault vehicle and transmits the road edge camera data and the laser radar data to the automatic driving redundancy system, the automatic driving redundancy system senses surrounding environment information through the data, and then path planning and decision making are carried out again through the cooperation of planning, decision making system and control system, so that the vehicle is controlled to normally run.
Therefore, the intelligent driving vehicle sensor fault processing device provided by the embodiment of the invention monitors the state of the vehicle-mounted sensor through the automatic driving redundancy system, and can accurately detect whether the vehicle-mounted sensor has a fault; meanwhile, a scene scheduling server is deployed in a structured scene to manage and monitor vehicles in the scene, and after the vehicles break down, the safety control of the vehicles can be realized by acquiring data collected by scene scheduling sensors around the vehicles and matching with the vehicles to plan and make decisions, so that the normal driving tasks of the vehicles are not influenced by task take-over and path re-planning; in addition, the safety control of the intelligent driving vehicle under the condition that the vehicle-mounted sensor fails is realized by combining the automatic driving redundancy system and the scheduling of the scene scheduling server, and the method can be applied to the treatment of the intelligent driving vehicle after the fault in the structured scene, so that the treatment process is safer.
In addition, the embodiment of the invention also provides an intelligent driving vehicle, and the intelligent driving vehicle executes the intelligent driving vehicle sensor fault processing method when driving so as to ensure that the vehicle-mounted sensor can continue to drive when the vehicle-mounted sensor has a fault.
Fig. 5 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 5: a processor (processor) 510, a communication Interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication Interface 520 and the memory 530 communicate with each other via the communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a smart-driven vehicle sensor fault handling method comprising: judging whether each vehicle-mounted sensor on the intelligent driving vehicle has a fault; determining whether to take over the intelligent driving vehicle or not according to the fault judgment result of each vehicle-mounted sensor, if so, reporting the fault information of the vehicle-mounted sensors to a scene scheduling server and initiating a take-over request; acquiring sampling data of a scene scheduling sensor which is deployed at a corresponding position in advance by a scene scheduling server according to the position information of the intelligent driving vehicle initiating the takeover request; and controlling the intelligent driving vehicle to normally run according to the sampling data of the scene scheduling sensor returned by the scene scheduling server.
In addition, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the smart driving vehicle sensor fault handling method provided by the above methods, the method comprising: judging whether each vehicle-mounted sensor on the intelligent driving vehicle has a fault; determining whether to take over the intelligent driving vehicle or not according to the fault judgment result of each vehicle-mounted sensor, if the intelligent driving vehicle is determined to take over, reporting the fault information of the vehicle-mounted sensors to a scene scheduling server and initiating a take-over request; acquiring sampling data of a scene scheduling sensor which is deployed at a corresponding position in advance by a scene scheduling server according to the position information of the intelligent driving vehicle initiating the takeover request; and controlling the intelligent driving vehicle to normally run according to the sampling data of the scene scheduling sensor returned by the scene scheduling server.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program that when executed by a processor is implemented to perform the above-provided smart driving vehicle sensor fault handling method, the method comprising: judging whether each vehicle-mounted sensor on the intelligent driving vehicle has a fault; determining whether to take over the intelligent driving vehicle or not according to the fault judgment result of each vehicle-mounted sensor, if so, reporting the fault information of the vehicle-mounted sensors to a scene scheduling server and initiating a take-over request; acquiring sampling data of a scene scheduling sensor which is deployed at a corresponding position in advance by a scene scheduling server according to the position information of the intelligent driving vehicle initiating the takeover request; and controlling the intelligent driving vehicle to normally run according to the sampling data of the scene scheduling sensor returned by the scene scheduling server.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. An intelligent driving vehicle sensor fault processing method is characterized by comprising the following steps:
judging whether each vehicle-mounted sensor on the intelligent driving vehicle has a fault; wherein, judge whether each on-vehicle sensor breaks down on the intelligent driving vehicle, include: respectively acquiring timestamp information of a latest frame of sampling data of each vehicle-mounted sensor on the intelligent driving vehicle; subtracting the timestamp information from the current time to obtain a sampling time difference value; comparing the sampling time difference with a preset time interval threshold, and if the sampling time difference is greater than the time interval threshold, judging that the vehicle-mounted sensor has a fault;
determining whether to take over the intelligent driving vehicle according to the fault judgment result of each vehicle-mounted sensor, and determining whether to take over the intelligent driving vehicle according to the fault judgment result of each vehicle-mounted sensor, wherein the method comprises the following steps: determining whether the intelligent driving vehicle can normally run or not according to the fault judgment result of each vehicle-mounted sensor, and if the intelligent driving vehicle cannot normally run, determining to take over the intelligent driving vehicle; if the intelligent driving vehicle is determined to take over, reporting fault information of the vehicle-mounted sensor to a scene scheduling server and initiating a take-over request, wherein the scene scheduling server is deployed in a structured scene, and the structured scene comprises a closed driving environment;
acquiring sampling data of a scene scheduling sensor which is deployed at a corresponding position in advance by the scene scheduling server according to the position information of the intelligent driving vehicle initiating the takeover request;
and controlling the intelligent driving vehicle to normally run according to the sampling data of the scene scheduling sensor returned by the scene scheduling server.
2. The method for processing the sensor fault of the intelligent driving vehicle as claimed in claim 1, wherein determining whether the intelligent driving vehicle can normally run according to the fault judgment result of each vehicle-mounted sensor comprises:
determining the vehicle-mounted sensor with the fault according to the fault judgment result of each vehicle-mounted sensor;
diagnosing the vehicle-mounted sensor with the fault, and determining a fault level according to a diagnosis result of the vehicle-mounted sensor with the fault;
and determining whether the intelligent driving vehicle can normally run or not according to the fault grade.
3. The method for processing the sensor fault of the intelligent driving vehicle as claimed in claim 2, wherein the step of diagnosing the vehicle-mounted sensor with the fault and determining the fault level according to the diagnosis result of the vehicle-mounted sensor with the fault comprises the following steps:
judging the importance of each vehicle-mounted sensor with a fault, and determining the installation position of each vehicle-mounted sensor with the fault;
and determining the fault grade according to the importance and the installation position of the vehicle-mounted sensor with the fault.
4. The smart-driven vehicle sensor fault handling method of claim 3, wherein the fault rating comprises:
a slight fault, wherein the slight fault is a fault of only a vehicle-mounted sensor with low importance;
and the serious fault is that the vehicle-mounted sensor with high importance degree fails and/or the installation position of the failed vehicle-mounted sensor seriously influences normal running.
5. The method as claimed in claim 1, wherein the scene scheduling sensor comprises a camera, a lidar sensing unit, a millimeter-wave radar sensing unit, and an ultrasonic radar sensing unit.
6. An intelligent driving vehicle sensor fault handling device, comprising:
the fault judgment module is used for judging whether each vehicle-mounted sensor on the intelligent driving vehicle has a fault; wherein, judge whether each on-vehicle sensor breaks down on the intelligent driving vehicle, include: respectively acquiring timestamp information of a latest frame of sampling data of each vehicle-mounted sensor on the intelligent driving vehicle; the timestamp information is differenced with the current time to obtain a sampling time difference value; comparing the sampling time difference with a preset time interval threshold, and if the sampling time difference is greater than the time interval threshold, judging that the vehicle-mounted sensor has a fault;
the driving judgment module is used for determining whether to take over the intelligent driving vehicle according to the fault judgment result of each vehicle-mounted sensor, and the driving judgment module comprises: determining whether the intelligent driving vehicle can normally run or not according to the fault judgment result of each vehicle-mounted sensor, and if the intelligent driving vehicle cannot normally run, determining to take over the intelligent driving vehicle; if the intelligent driving vehicle is determined to take over, reporting fault information of the vehicle-mounted sensor to a scene scheduling server and initiating a take-over request, wherein the scene scheduling server is deployed in a structured scene, and the structured scene comprises a closed driving environment;
the acquisition module is used for acquiring the sampling data of the scene scheduling sensor which is deployed at the corresponding position in advance according to the position information of the intelligent driving vehicle initiating the takeover request by the scene scheduling server;
and the take-over control module is used for controlling the intelligent driving vehicle to normally run according to the sampling data of the scene scheduling sensor returned by the scene scheduling server.
7. The device of claim 6, wherein the fault determination module, the driving determination module, the acquisition module and the take-over control module are all disposed in an autonomous driving redundant system, and the autonomous driving redundant system is disposed on the intelligent driving vehicle.
8. An intelligent driving vehicle, characterized in that the intelligent driving vehicle executes an intelligent driving vehicle sensor fault handling method according to any one of claims 1 to 5 while driving.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111256007.6A CN113879324B (en) | 2021-10-27 | 2021-10-27 | Intelligent driving vehicle sensor fault processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111256007.6A CN113879324B (en) | 2021-10-27 | 2021-10-27 | Intelligent driving vehicle sensor fault processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113879324A CN113879324A (en) | 2022-01-04 |
| CN113879324B true CN113879324B (en) | 2023-04-07 |
Family
ID=79014698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111256007.6A Active CN113879324B (en) | 2021-10-27 | 2021-10-27 | Intelligent driving vehicle sensor fault processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113879324B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114485708A (en) * | 2022-01-18 | 2022-05-13 | 上汽通用五菱汽车股份有限公司 | Unmanned vehicle path planning method, system, electronic device and storage medium |
| CN114407932A (en) * | 2022-02-23 | 2022-04-29 | 武汉路特斯汽车有限公司 | Method for evaluating intelligent driving system capability |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140050470A (en) * | 2012-10-19 | 2014-04-29 | 현대모비스 주식회사 | Apparatus and method for stabilizing vehicle drive using fail safety function of wheel speed sensor |
| CN112572465A (en) * | 2019-09-12 | 2021-03-30 | 中车时代电动汽车股份有限公司 | Fault processing method for intelligent driving automobile sensing system |
| CN111025959B (en) * | 2019-11-20 | 2021-10-01 | 华为技术有限公司 | Data management method, device and equipment and intelligent automobile |
| CN112805648A (en) * | 2020-06-12 | 2021-05-14 | 百度时代网络技术（北京）有限公司 | Fail-safe handling system for autonomously driven vehicles |
| CN111984015B (en) * | 2020-08-26 | 2022-09-09 | 扬州大学 | Hybrid-enhanced-intelligence-based automatic driving vehicle implementation method |
-
2021
- 2021-10-27 CN CN202111256007.6A patent/CN113879324B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113879324A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113879324B (en) | Intelligent driving vehicle sensor fault processing method and device | |
| CN106840242B (en) | Sensor self-checking system and multi-sensor fusion system of intelligent driving automobile | |
| CN106354141B (en) | A kind of Ride Control System and method | |
| CN109895787B (en) | Control method and control device for vehicle driving | |
| CN110570538B (en) | Method, device and equipment for managing black box data in intelligent driving automobile | |
| EP3232285B1 (en) | Method and arrangement for monitoring and adapting the performance of a fusion system of an autonomous vehicle | |
| CN111077880B (en) | Vehicle fault diagnosis system and method | |
| CN112622930A (en) | Unmanned vehicle driving control method, device and equipment and automatic driving vehicle | |
| US20150210258A1 (en) | Method for carrying out a safety function of a vehicle and system for carrying out the method | |
| CN111665849B (en) | Automatic driving system | |
| US20220264081A1 (en) | Sensing performance evaluation and diagnosis system and sensing performance evaluation and diagnosis method for external-environment recognition sensor | |
| CN113110266B (en) | Remote control monitoring early warning method for automatic driving vehicle and storage medium | |
| CN113895450A (en) | Safety redundancy system and control method for unmanned vehicle sensing system | |
| CN107464416B (en) | Semi-automatic driving method and system for bus | |
| CN114194212B (en) | Fault diagnosis method, automatic driving domain controller and vehicle | |
| CN110794802B (en) | Fault diagnosis processing method and device | |
| CN111800314B (en) | Automatic driving fault monitoring system | |
| CN111800508B (en) | Automatic driving fault monitoring method based on big data | |
| CN110816443B (en) | Vehicle monitoring method and device and unmanned vehicle | |
| CN113696903A (en) | Vehicle control method and device, electronic equipment and storage medium | |
| US20240140489A1 (en) | Vehicle for performing minimal risk maneuver and operation method thereof | |
| CN114954413B (en) | Vehicle self-checking processing method, device, equipment and storage medium | |
| CN113858208B (en) | Robot detection method and device, electronic equipment and storage medium | |
| CN214896326U (en) | Unmanned mine card safety auxiliary system based on multi-perception fusion | |
| CN114755642B (en) | Radar line detection method and device, vehicle and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |