CN111179468A

CN111179468A - Unmanned vehicle fault detection method and device, computer equipment and storage medium

Info

Publication number: CN111179468A
Application number: CN201911425299.4A
Authority: CN
Inventors: 董钊瑞; 刘明; 王鲁佳
Original assignee: Shenzhen Yiqing Innovation Technology Co ltd
Current assignee: Shenzhen Yiqing Innovation Technology Co ltd
Priority date: 2019-12-31
Filing date: 2019-12-31
Publication date: 2020-05-19

Abstract

The application relates to a fault detection method, a fault detection device, computer equipment and a storage medium for an unmanned vehicle. When the running state of the unmanned vehicle is a fault, the running state of the unmanned vehicle is adjusted according to the corresponding fault type, so that the fault detection of the unmanned vehicle can be carried out more comprehensively, the accuracy of the fault detection of the unmanned vehicle is improved, the running state of the unmanned vehicle is adjusted according to the fault detection result of the unmanned vehicle obtained by the method, and the running safety of the unmanned vehicle can be improved.

Description

Unmanned vehicle fault detection method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of unmanned vehicle technology, and in particular, to an unmanned vehicle fault detection method, apparatus, computer device, and storage medium.

Background

The unmanned vehicle is an intelligent vehicle which senses the road environment through a vehicle-mounted sensing system, automatically plans a driving route and controls the vehicle to reach a preset target. The operation strategy of the unmanned vehicle usually needs to be processed in real time according to the running state of the unmanned vehicle, and compared with the traditional manned vehicle, the unmanned vehicle has higher requirements on fault detection.

The unmanned vehicle is provided with a vehicle-mounted terminal and a sensor, and in the traditional scheme, the vehicle-mounted terminal carries out fault detection on the unmanned vehicle through operation data acquired by the sensor on the unmanned vehicle. However, the sensor can only detect the fault of the vehicle body equipment of the unmanned vehicle, and when other parts of the unmanned vehicle have faults, the traditional scheme cannot detect the faults, so that certain danger exists, and the safety is low.

Disclosure of Invention

In view of the above, it is necessary to provide a method and apparatus for detecting a malfunction of an unmanned vehicle, a computer device, and a storage medium, which can improve safety.

An unmanned vehicle fault detection method, the method comprising:

acquiring fault detection information, wherein the fault detection information comprises a detection object and corresponding reference information; the detection object comprises vehicle body equipment, vehicle control software and external equipment;

acquiring operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to reference information corresponding to each detection object to obtain a fault detection result of each detection object;

determining the fault detection result of the unmanned vehicle according to the incidence relation among the fault detection results of all the detection objects;

determining the running state of the unmanned vehicle according to the fault detection result of the unmanned vehicle, and determining the corresponding fault type according to the fault detection result of the unmanned vehicle when the running state of the unmanned vehicle is a fault;

and adjusting the running state of the unmanned vehicle according to the fault type.

In one embodiment, when the detection object is a vehicle body device, the obtaining operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to reference information corresponding to each detection object, to obtain a fault detection result of each detection object includes:

receiving a controller area network data frame set sent by each vehicle body device;

analyzing the controller area network data frame set according to a controller area network bus protocol to obtain the operation data of each vehicle body device;

extracting reference operation data corresponding to each vehicle body device from the reference information;

comparing the operation data of each vehicle body device with the corresponding reference operation data; and obtaining the fault detection result of each vehicle body device.

In one embodiment, when the detection object is vehicle control software, the obtaining operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to reference information corresponding to each detection object, to obtain a fault detection result of each detection object includes:

sending a node detection request;

when response information of nodes of each process in the vehicle control software is received, acquiring operation information of each process according to the response information of the nodes of each process;

extracting reference operation information corresponding to each process from the reference information;

and comparing the running information of each process with the corresponding reference running information to obtain the fault detection result of each process.

In one embodiment, the external device includes a serial device and an ethernet device, and when the detection object is a serial device, the obtaining operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to reference information corresponding to each detection object, and obtaining the fault detection result of each detection object includes:

acquiring the identification and the current interface number of the serial device;

acquiring a reference interface number corresponding to the serial device in the reference information according to the identifier of the serial device;

determining the connection state of the serial device according to the current interface number of the serial device and the corresponding reference interface number;

and determining a fault detection result of the serial port equipment according to the connection state of the serial port equipment.

In one embodiment, the external device includes a serial device and an ethernet device, and when the detection object is the ethernet device, the obtaining operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to reference information corresponding to each detection object, and obtaining the fault detection result of each detection object includes:

sending a network detection request to the Ethernet device;

when response information of the Ethernet equipment is received, determining the network connection state of the Ethernet equipment according to the response information of the Ethernet equipment;

extracting network connection reference information corresponding to the network connection state of the Ethernet equipment from the reference information;

and comparing the network connection state of the Ethernet equipment with the network connection reference information to obtain a fault detection result of the Ethernet equipment.

In one embodiment, the determining the fault detection result of the unmanned vehicle according to the correlation between the fault detection results of the detection objects includes:

analyzing the fault detection result of each detection object according to the incidence relation among the fault detection results of each detection object to obtain the actual fault detection result of each detection object;

and generating a fault detection result of the unmanned vehicle according to the actual fault detection result of each detection object.

In one embodiment, the adjusting the driving state of the unmanned vehicle according to the fault type includes:

sending the running state of the unmanned vehicle to a remote control terminal;

when the running state of the unmanned vehicle is a fault, adjusting the running state of the unmanned vehicle according to the fault type to obtain an updated running state;

and receiving the adjustment control information of the remote control terminal, receiving a driving state adjustment instruction of the remote control terminal when the updated driving state does not accord with the adjustment control information, and adjusting the updated driving state according to the driving state adjustment instruction.

An unmanned vehicle fault detection device, the device comprising:

the fault detection information acquisition module is used for acquiring fault detection information, wherein the fault detection information comprises a detection object and corresponding reference information; the detection object comprises vehicle body equipment, vehicle control software and external equipment;

the fault detection module is used for acquiring operation information corresponding to each detection object, analyzing the operation information corresponding to each detection object according to reference information corresponding to each detection object, and obtaining a fault detection result of each detection object;

the fault result determining module is used for determining the fault detection result of the unmanned vehicle according to the incidence relation among the fault detection results of all the detection objects;

the fault type determining module is used for determining the running state of the unmanned vehicle according to the fault detection result of the unmanned vehicle, and determining the corresponding fault type according to the fault detection result of the unmanned vehicle when the running state of the unmanned vehicle is a fault;

and the running state adjusting module is used for adjusting the running state of the unmanned vehicle according to the fault type.

A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:

A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

According to the unmanned vehicle fault detection method, the unmanned vehicle fault detection device, the computer equipment and the storage medium, fault detection information comprising detection objects and corresponding reference information is obtained, operation information corresponding to each detection object is obtained, the operation information corresponding to each detection object is analyzed according to the reference information corresponding to each detection object, fault detection results of each detection object are obtained, the fault detection results of the unmanned vehicle are determined according to the incidence relation among the fault detection results of each detection object, and the operation state of the unmanned vehicle is determined according to the fault detection results of the unmanned vehicle. And when the running state of the unmanned vehicle is a fault, determining a corresponding fault type according to a fault detection result of the unmanned vehicle, and adjusting the running state of the unmanned vehicle according to the fault type. Different from the traditional scheme that running data of unmanned vehicle body equipment is collected through a sensor for fault detection, the method obtains fault detection results of three detection objects through detection of the vehicle body equipment, vehicle control software and external equipment, and determines the fault detection result of the unmanned vehicle according to the incidence relation among the fault detection results of the three detection objects, so that the fault detection of the unmanned vehicle can be carried out more comprehensively, the accuracy of the fault detection of the unmanned vehicle is improved, the running state of the unmanned vehicle is adjusted according to the fault detection result of the unmanned vehicle obtained by the method, and the running safety of the unmanned vehicle can be improved.

Drawings

FIG. 1 is a diagram illustrating an exemplary scenario for an unmanned vehicle fault detection method;

FIG. 2 is a schematic flow chart of a method for unmanned vehicle fault detection in one embodiment;

FIG. 3 is a schematic flow chart illustrating a method for detecting a failure of an unmanned vehicle body device according to an embodiment;

FIG. 4 is a schematic flow chart illustrating a method for unmanned vehicle control software fault detection in one embodiment;

FIG. 5 is a schematic flow chart illustrating a method for detecting a failure of an unmanned vehicle serial device in an embodiment;

FIG. 6 is a schematic flow chart illustrating a method for unmanned vehicle Ethernet device fault detection in one embodiment;

FIG. 7 is a schematic flow chart of a method for unmanned vehicle fault detection in another embodiment;

FIG. 8 is a block diagram showing the construction of an unmanned vehicle fault detection apparatus according to an embodiment;

FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The unmanned vehicle fault detection method can be applied to the application environment shown in fig. 1. In which an unmanned vehicle 102 communicates with a remote control terminal 104 through a network. The operation and maintenance personnel formulate the fault detection information related to the unmanned vehicle 102 through the remote control terminal 104. The fault detection information includes a detection object and corresponding reference information. The detection object comprises vehicle body equipment, vehicle control software and external equipment. The remote control terminal 106 sends the formulated fault detection information to the unmanned vehicle 102. After the unmanned vehicle 102 acquires the fault detection information, the operation information corresponding to each detection object is acquired, and the operation information corresponding to each detection object is analyzed according to the reference information corresponding to each detection object, so that the fault detection result of each detection object is obtained. The unmanned vehicle 102 determines the fault detection result of the unmanned vehicle 102 according to the incidence relation between the fault detection results of the detection objects, and determines the operation state of the unmanned vehicle 102 according to the fault detection result of the unmanned vehicle 102. Further, when the operation state of the unmanned vehicle 102 is a fault, the fault type of the unmanned vehicle 102 is determined according to the fault detection result of the unmanned vehicle 102, and the driving state of the unmanned vehicle 102 is adjusted according to the fault type of the unmanned vehicle 102. The remote control terminal 104 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices.

In one embodiment, as shown in fig. 2, there is provided a method for detecting a fault of an unmanned vehicle, which is described by taking the method as an example applied to the unmanned vehicle in fig. 1, and includes the following steps:

step 202, acquiring fault detection information, wherein the fault detection information comprises a detection object and corresponding reference information; the detection object includes a vehicle body device, vehicle control software, and an external device.

The fault detection information is information formulated by operation and maintenance personnel through a remote control terminal. The fault detection information includes detection objects and reference information corresponding to each detection object. The detection object comprises body equipment of the unmanned vehicle, vehicle control software and external equipment. The vehicle body device is a device that the automobile itself has, such as a lamp, a horn, a battery, and the like. The vehicle control software is software for controlling each device in the unmanned vehicle. The external devices are other devices than the vehicle body device among all devices of the unmanned vehicle, such as various sensors.

Specifically, operation and maintenance personnel formulate fault detection information according to data generated when the body equipment, the vehicle control software and the external equipment of the unmanned vehicle normally operate. The unmanned vehicle is communicated with the remote control terminal through the network, and can acquire fault detection information issued by the remote control terminal, so that a detection object needing fault detection in the unmanned vehicle and corresponding reference information are acquired. For example, it is recorded in the fault detection information that the battery belongs to the vehicle body equipment, and when the battery temperature is higher than 60 degrees celsius, the battery temperature is too high, and a fault may exist.

And 204, acquiring operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to the reference information corresponding to each detection object to obtain a fault detection result of each detection object.

The operation information corresponding to each detection object is data information generated when each detection object operates.

Specifically, the unmanned vehicle acquires operation information corresponding to each detection object. And the unmanned vehicle extracts reference information corresponding to each detection object from the reference information, and compares the reference information corresponding to each detection object with the operation information corresponding to each detection object, so as to obtain a fault detection result of each detection object. For example, the reference information specifies: when the battery temperature is higher than 60 ℃, the battery temperature is excessively high and there may be a malfunction. And the temperature of the battery in the current vehicle obtained by the unmanned vehicle is 70 ℃, and it can be known that the current battery temperature is too high and a fault may exist.

And step 206, determining the fault detection result of the unmanned vehicle according to the incidence relation among the fault detection results of all the detection objects.

Specifically, the unmanned vehicle system is obtained by connecting a vehicle body device and an external device, and the operation of each device (including the vehicle body device and the external device) is controlled by vehicle control software, so that the vehicle body device, the external device and the vehicle control software have a correlation relationship, and fault detection results of each detection object mutually influence each other. For example, the vehicle body apparatus a is connected to the external apparatus B for receiving data output from the vehicle body apparatus a, and when the unmanned vehicle detects that there may be a failure in the vehicle body apparatus a and the external apparatus B, there is a possibility that only the vehicle body apparatus a has failed and the external apparatus B is normal. Therefore, after the unmanned vehicle detects each detection object to obtain the fault detection result of each detection object, the fault detection result of each fault detection object needs to be further analyzed according to the correlation between the fault detection results of each detection object to obtain the actual fault detection result of each detection object. Further, the unmanned vehicle generates a fault detection result of the unmanned vehicle according to the fault detection result implemented by each detection object.

And 208, determining the running state of the unmanned vehicle according to the fault detection result of the unmanned vehicle, and determining the corresponding fault type according to the fault detection result of the unmanned vehicle when the running state of the unmanned vehicle is a fault.

Specifically, the operating state of the unmanned vehicle includes a fault and a non-fault, and the operating state of the unmanned vehicle may be determined according to a fault detection result of the unmanned vehicle. When the running state of the unmanned vehicle is a fault, the corresponding fault type can be determined according to the fault detection result of the unmanned vehicle. For example, failure-vehicle body equipment failure-battery temperature is too high.

And step 210, adjusting the driving state of the unmanned vehicle according to the fault type.

Specifically, after the unmanned vehicle determines the type of the failure, the running state may be adjusted according to the type of the failure. For example, when the fault type of the unmanned vehicle is detected as: when the difference between the control instruction and the actual running state is too large, the running speed of the unmanned vehicle can be reduced, and the accidents caused by the fact that the unmanned vehicle is out of control when running at a high speed are avoided.

According to the unmanned vehicle fault detection method, fault detection information comprising detection objects and corresponding reference information is obtained, operation information corresponding to each detection object is analyzed according to the reference information corresponding to each detection object, a fault detection result of each detection object is obtained, the fault detection result of the unmanned vehicle is determined according to the incidence relation among the fault detection results of each detection object, and the operation state of the unmanned vehicle is determined according to the fault detection result of the unmanned vehicle. And when the running state of the unmanned vehicle is a fault, determining the fault type corresponding to the unmanned vehicle according to the fault detection result of the unmanned vehicle, and adjusting the running state of the unmanned vehicle according to the fault type. Different from the traditional scheme that running data of unmanned vehicle body equipment is collected through a sensor for fault detection, the method obtains fault detection results of three detection objects through detection of the vehicle body equipment, vehicle control software and external equipment, and determines the fault detection result of the unmanned vehicle according to the incidence relation among the fault detection results of the three detection objects, so that the fault detection of the unmanned vehicle can be carried out more comprehensively, the accuracy of the fault detection of the unmanned vehicle is improved, the running state of the unmanned vehicle is adjusted according to the fault detection result of the unmanned vehicle obtained by the method, and the running safety of the unmanned vehicle can be improved.

In one embodiment, as shown in fig. 3, when the detection object is a vehicle body device, step 204 includes:

step 302, receiving a controller area network data frame set sent by each vehicle body device;

step 304, analyzing the controller area network data frame set according to a controller area network bus protocol to obtain the operation data of each vehicle body device;

step 306, extracting reference operation data corresponding to each vehicle body device from the reference information;

and 308, comparing the running data of each vehicle body device with the corresponding reference running data to obtain a fault detection result of each vehicle body device.

The vehicle body equipment is an equipment module of the automobile, such as an automobile door and window, a battery, a lamp and the like. Although some modules are single subsystems, the connections between modules are very important. For example, some subsystems need to control actuators and receive sensor feedback, and a Controller Area Network (CAN) bus CAN meet the data transmission requirements of the subsystems. The controller local area network bus protocol is a serial communication bus based on a message broadcast mode, and is used for realizing communication between Electronic Control Units (ECUs) in an automobile, sharing rotating speed, oil temperature and the like to the whole automobile, and realizing intelligent Control of the automobile, such as automatic door locking at high speed and automatic door opening when an airbag is popped up.

Specifically, when sending data, the node on the controller area network bus broadcasts the data to all nodes in the network in a message form specified by the controller area network bus protocol. The vehicle body equipment belongs to a node on a controller local area network bus, and sends a controller local area network data frame to the unmanned vehicle according to a controller local area network bus protocol. Further, after receiving the controller area network data frame set sent by each vehicle body device, the unmanned vehicle analyzes the controller area network data frame set according to the controller area network bus protocol, and can obtain the operation data of each vehicle body device. And the unmanned vehicle extracts the reference operation data corresponding to each vehicle body device from the reference information, and compares the operation data of each vehicle body device with the corresponding reference operation data to obtain the fault detection result of each vehicle body device.

In one embodiment, the controller area network bus sometimes has a small amount of error information caused by communication, and further judgment on the received error information is needed to eliminate the influence of communication errors. The controller area network bus comprises an error checking mechanism, namely, each node controller on the controller area network bus detects whether the operation information is wrong according to the reference information, and if the operation information is found to be wrong, the corresponding node sends an error mark. When the unmanned vehicle receives a plurality of pieces of error information containing error marks continuously transmitted from the same vehicle body equipment, the vehicle body equipment is considered to be possible to have faults.

In this embodiment, the fault detection is performed on the vehicle body equipment of the unmanned vehicle through the controller local area network bus technology, so that the fault detection result of the vehicle body equipment of the unmanned vehicle is obtained, the abnormal driving of the unmanned vehicle caused by the fault of the vehicle body equipment is avoided, and the driving safety of the unmanned vehicle is improved.

In one embodiment, as shown in fig. 4, when the detection object is vehicle control software, step 204 includes:

step 402, sending a node detection request;

404, when response information of the node of each process in the vehicle control software is received, acquiring operation information of each process according to the response information of the node of each process;

step 406, extracting reference operation information corresponding to each process from the reference information;

and step 408, comparing the running information of each process with the corresponding reference running information to obtain a fault detection result of each process.

The node detection request is a request sent by the unmanned vehicle to the nodes of each process of the vehicle control software, and is used for detecting whether the nodes can normally respond. When a node can respond normally, the corresponding process can be viewed according to the node. The process is the existing form of the running program in the system, the system resource condition occupied by the process can be known by checking the state information of the process, and the running state of the system is analyzed and adjusted, so that the system can run in a stable state.

Specifically, the unmanned vehicle sends a node detection request to nodes of each process in the vehicle control software, and waits for responses of the nodes of each process in the vehicle control software. When the unmanned vehicle fails to receive the response information of a certain node, the node may have a fault. And when the unmanned vehicle receives the response information of the nodes of each process, further judging the running state of the nodes of each process according to the response time of the nodes of each process. When the response time of a certain node is greater than the node response time threshold, then the node may have a fault.

Further, after the unmanned vehicle receives the response information of the node of each process in the vehicle control software, the operation information of each process can be acquired according to the response information of the node of each process. The running information of each process includes information such as time for each process to create, occupied CPU, occupied physical memory, and devices associated with each process. And extracting the reference operation information corresponding to each process from the reference information by the unmanned vehicle, and comparing the operation information of each process with the corresponding reference operation information to obtain the fault detection result of each process. For example, if the unmanned vehicle detects that a process occupies 30% of the CPU and the reference operation information records that the process occupies 20% of the CPU in the normal operation state, the process may have a fault.

In one embodiment, the unmanned vehicle may implement the detection of the node through an ROS (Robot Operating System). For example, a Rosnod ping command is sent to detect the connectivity of the nodes, and the time required for communication is used to determine whether the nodes are normal.

In one embodiment, for more important nodes, such as nodes controlling radar operation, the unmanned vehicle can subscribe and analyze the operation information thereof by using the Rostopic instruction, and monitor the operation information in real time.

In one embodiment, the running information of each process can be acquired through a system file under Linux. The basic commands for viewing the running information of the Process in Linux include ps (Process Status, Process state query command) and top. The ps command is used for checking static process running information, and the process running information corresponding to the ps command is displayed when the ps command is executed. the top command is used for viewing dynamic process running information, and dynamic changes of the running information of the process can be displayed in real time.

In this embodiment, the nodes of the processes in the vehicle control software are detected, the running information of the processes is checked, the vehicle control software of the unmanned vehicle is detected, the fault detection result of the vehicle control software of the unmanned vehicle is obtained, the abnormal running of the unmanned vehicle caused by the fault of the vehicle control software is avoided, and the running safety of the unmanned vehicle is improved.

In one embodiment, as shown in fig. 5, the external device includes a serial device and an ethernet device, and when the detection object is a serial device, step 204 includes:

step 502, acquiring the identifier of the serial device and the current interface number;

step 504, acquiring a reference interface number corresponding to the serial device from the reference information according to the identifier of the serial device;

step 506, determining the connection state of the serial device according to the current interface number of the serial device and the corresponding reference interface number;

and step 508, determining a fault detection result of the serial device according to the connection state of the serial device.

With the development of automotive electronics technology, common controller area networks cannot meet the requirements of vehicle-mounted communication, and ethernet and USB are added on the basis of the controller area networks. In the unmanned vehicle system of the present embodiment, the vehicle body devices are connected via the controller area network, and the external devices other than the vehicle body devices are connected via the ethernet connection and the USB. Wherein the ethernet device is a device connected through an ethernet. The Serial device is a device connected via a Universal Serial Bus (USB). The USB device includes VID (Vendor ID, manufacturer ID) and PID (Product ID ). Both VID and PID may be used to uniquely identify a USB device. The interface number of the USB device is used to identify the functional interface corresponding to each USB device.

Specifically, the unmanned vehicle acquires the VID, the PID and the current interface number of the serial device. And the unmanned vehicle acquires the reference interface number corresponding to the serial port equipment from the reference information according to the identification of the serial port equipment. The reference interface number is a reference interface number corresponding to the USB device in a normal operating state. The unmanned vehicle compares the current interface number of the serial device with the corresponding reference interface number, and when the current interface number of the serial device is different from the corresponding reference interface number, the situation that the USB device is reconnected occurs in the operation process is shown. During the process of reconnection of the USB device, there may be data loss, which may cause other devices connected to the USB device to fail to work normally. When the current interface number of the serial port device is the same as the corresponding reference interface number, it indicates that the USB device is always working normally and has no fault in the running process.

In this embodiment, the fault detection result of the serial device of the unmanned vehicle is obtained by detecting the interface number corresponding to the serial device, so that the abnormal driving of the unmanned vehicle caused by the fault of the serial device is avoided, and the driving safety of the unmanned vehicle is improved.

In one embodiment, as shown in fig. 6, the external device includes a serial device and an ethernet device, and when the detection object is the ethernet device, step 204 includes:

step 602, sending a network detection request to an ethernet device;

step 604, when receiving the response information of the ethernet device, determining the network connection state of the ethernet device according to the response information of the ethernet device;

step 606, extracting network connection reference information corresponding to the network connection state of the Ethernet equipment from the reference information;

step 608, comparing the network connection status of the ethernet device with the network connection reference information to obtain a fault detection result of the ethernet device.

Among them, ethernet is a computer local area network technology. An ethernet device is a device connected through an ethernet. The network detection request is used for detecting whether the Ethernet equipment is normally connected. The response information of the ethernet includes a response time.

Specifically, the unmanned vehicle may send a network detection request to the ethernet device, waiting for a response from the ethernet device. When the unmanned vehicle fails to receive the response information of a certain Ethernet device, the Ethernet device is abnormal in network connection and may have a fault. Further, when the unmanned vehicle receives the response information of the ethernet device, the network connection state of the ethernet device can be further determined according to the response time of the ethernet device. The unmanned vehicle extracts network connection reference information corresponding to the network connection state of the ethernet device, for example, an ethernet device response time threshold value, from the reference information. When the response time of a certain ethernet device is greater than the response time threshold of the ethernet device, the network connection of the ethernet device is abnormal, and a fault may exist.

In one embodiment, the drone may use ping (Packet Internet Groper) commands to detect the ethernet device. Specifically, the drone vehicle may send one packet to each ethernet device via a ping command. After receiving the data packet sent by the unmanned vehicle, each ethernet device returns a data packet to the unmanned vehicle accordingly. The unmanned vehicle can detect whether the Ethernet equipment is normally connected according to whether each Ethernet equipment has a return data packet and the time for returning the data packet. When a data packet returned by certain Ethernet equipment is not received, the Ethernet equipment is indicated to be possible to disconnect the network. When the time for a certain ethernet device to return a data packet is too long, it indicates that the ethernet device may have a fault, resulting in an unsmooth network.

In one embodiment, the drone vehicle may also detect connectivity of the network by accessing a search engine. The method eliminates the possibility that the time for the Ethernet equipment to return the data packet is too long due to the unsmooth network, and reduces misjudgment.

In one embodiment, ping commands are not applicable in all situations. When there are ethernet devices that do not adapt to ping commands, packet capture techniques may be used to detect the network connection status of the ethernet devices. Specifically, the unmanned vehicle sends one data packet to each ethernet device. During the process of sending and receiving the data packet, the data packet may have errors in the sent data packet, and the data packet may also have errors in the received data packet, thereby causing the unmanned vehicle to malfunction. And the unmanned vehicle intercepts the data of the data packet in transmission by using a packet capturing technology, and analyzes the data packet to obtain the original data. The unmanned vehicle analyzes the original data and can judge whether the original data has abnormal data. When abnormal data exists in the original data, the unmanned vehicle can be positioned to the Ethernet equipment corresponding to the abnormal data through a packet capturing technology.

In the embodiment, the network connection state of the Ethernet equipment is detected to obtain the fault detection result of the Ethernet equipment in the unmanned vehicle, so that the abnormal driving of the unmanned vehicle caused by the fault of the Ethernet equipment is avoided, and the driving safety of the unmanned vehicle is improved.

In one embodiment, step 206 includes: analyzing the fault detection result of each detection object according to the incidence relation among the fault detection results of each detection object to obtain the actual fault detection result of each detection object; and generating a fault detection result of the unmanned vehicle according to the actual fault detection result of each detection object.

In the unmanned vehicle system, the fault detection results of the detection objects are separately detected, and the detection objects have a coupling relationship with each other, so that after the fault detection results of the separately detected detection objects are obtained, the fault detection results of the detection objects need to be summarized and further analyzed, and the fault detection result of the unmanned vehicle can be obtained.

Specifically, the unmanned vehicle may analyze the fault detection result of each detection object according to the association relationship between the fault detection results of each detection object, to obtain the actual fault detection result of each detection object. For example, when detecting vehicle control software, node a that detects a certain process does not respond; when detecting the external equipment, detecting that a certain external equipment A is disconnected; in the unmanned vehicle system, the device corresponding to the node a is the external device a, and therefore, in practice, the node a may not respond because the external device a is disconnected, and therefore, the finally obtained fault detection result is: failure-external device a disconnects.

In this embodiment, the fault detection results of the detection objects are further analyzed through the association relationship between the fault detection results of the detection objects to obtain the actual fault detection results of the detection objects, so that misjudgment can be reduced, the accuracy of fault detection of the unmanned vehicle is improved, and the driving safety of the unmanned vehicle is improved.

In one embodiment, step 210 includes: the running state of the unmanned vehicle is sent to a remote control terminal; when the running state of the unmanned vehicle is a fault, adjusting the running state of the unmanned vehicle according to the fault type to obtain an updated running state; and receiving the adjustment control information of the remote control terminal, receiving a driving state adjustment instruction of the remote control terminal when the updated driving state does not accord with the adjustment control information, and adjusting and updating the driving state according to the driving state adjustment instruction.

The remote control terminal is used for monitoring and controlling the unmanned vehicle, and the driving mode of the unmanned vehicle can be switched between an automatic mode and a manual mode.

Specifically, after the unmanned vehicle completes the fault detection of the unmanned vehicle, the running state of the unmanned vehicle is obtained. The unmanned vehicle sends the running state of the unmanned vehicle to the remote control terminal. When the running state of the unmanned vehicle is a fault, the unmanned vehicle can adjust the running state of the unmanned vehicle according to the fault type to obtain an updated running state. The remote control terminal can send adjustment control information to the unmanned vehicle and monitor the updated driving state of the unmanned vehicle. When the updated driving state of the unmanned vehicle does not accord with the adjustment control information, the remote control terminal sends a driving state adjustment instruction to the unmanned vehicle, and the unmanned vehicle can adjust the updated driving state according to the driving state adjustment instruction.

Further, for example, when a certain sensor of the unmanned vehicle is detected to be out of order, the unmanned vehicle cannot accurately judge the current road condition and can drive correctly according to the current road condition, and the unmanned vehicle can stop emergently to avoid accidents. And when the unmanned vehicle is on the lane, the unmanned vehicle cannot be parked at will. At this time, the remote control terminal sends a driving state adjustment instruction to the unmanned vehicle, controls the driving state of the unmanned vehicle, and controls the unmanned vehicle to stop after the unmanned vehicle drives to the safe area. And the operation and maintenance personnel maintain the faulty sensor in the unmanned vehicle.

In this embodiment, after the unmanned vehicle adjusts the driving state of the unmanned vehicle according to the fault type, the remote control terminal monitors the updated driving state of the unmanned vehicle, and the reasonability of the unmanned vehicle in adjusting the driving state is further improved by judging whether the updated driving state meets the adjustment control information, so that the driving safety of the unmanned vehicle is improved.

In one embodiment, as shown in fig. 7, there is provided a method for detecting a malfunction of an unmanned vehicle, which is described by taking the method as an example applied to the unmanned vehicle in fig. 1, and includes the following steps:

step 702, acquiring fault detection information, wherein the fault detection information comprises a detection object and corresponding reference information; the detection object includes a vehicle body device, vehicle control software, and an external device.

Step 704, determine whether the detection object is a vehicle body device.

Step 706, if yes, receiving a controller area network data frame set sent by each vehicle body device; analyzing the controller local area network data frame set according to a controller local area network bus protocol to obtain the operation data of each vehicle body device; extracting reference operation data corresponding to each vehicle body device from the reference information; comparing the operation data of each vehicle body device with the corresponding reference operation data; and obtaining the fault detection result of each vehicle body device.

In step 708, when the detection object is not a vehicle body device, it is determined whether the detection object is an external device.

Step 710, if not, the detection object is vehicle control software; sending a node detection request; when response information of nodes of each process in the vehicle control software is received, acquiring running information of each process according to the response information of the nodes of each process; extracting reference operation information corresponding to each process from the reference information; and comparing the running information of each process with the corresponding reference running information to obtain the fault detection result of each process.

And 712, when the detection object is an external device, judging whether the detection object is a serial device.

Step 714, if yes, acquiring the identifier of the serial device and the current interface number; acquiring a reference interface number corresponding to the serial device in the reference information according to the identifier of the serial device; determining the connection state of the serial device according to the current interface number of the serial device and the corresponding reference interface number; and determining a fault detection result of the serial device according to the connection state of the serial device.

Step 716, if no, detecting that the object is an ethernet device; sending a network detection request to the Ethernet equipment; when response information of the Ethernet equipment is received, determining the network connection state of the Ethernet equipment according to the response information of the Ethernet equipment; extracting network connection reference information corresponding to the network connection state of the Ethernet equipment from the reference information; and comparing the network connection state of the Ethernet equipment with the network connection reference information to obtain a fault detection result of the Ethernet equipment.

Step 718, analyzing the fault detection result of each detection object according to the incidence relation among the fault detection results of each detection object to obtain the actual fault detection result of each detection object; and generating a fault detection result of the unmanned vehicle according to the actual fault detection result of each detection object.

And 720, determining the running state of the unmanned vehicle according to the fault detection result of the unmanned vehicle, and sending the running state of the unmanned vehicle to the remote control terminal.

And step 722, when the running state of the unmanned vehicle is a fault, determining a corresponding fault type according to a fault detection result of the unmanned vehicle, and adjusting the running state of the unmanned vehicle according to the fault type to obtain an updated running state.

And 724, receiving the adjustment control information of the remote control terminal, receiving a driving state adjustment instruction of the remote control terminal when the updated driving state does not accord with the adjustment control information, and adjusting the updated driving state according to the driving state adjustment instruction.

In this embodiment, the fault detection information including the detection objects and the corresponding reference information is acquired, the detection objects are judged, fault detection is performed on each detection object respectively, fault detection results of each detection object are obtained, the fault detection results of each detection object are analyzed according to the incidence relation among the fault detection results of each detection object, so that the fault detection results of the unmanned vehicle are determined, the running state of the unmanned vehicle is determined according to the fault detection results of the unmanned vehicle, fault detection can be performed on the unmanned vehicle more comprehensively, and the accuracy of fault detection of the unmanned vehicle is improved. And when the running state of the unmanned vehicle is a fault, determining a corresponding fault type according to a fault detection result of the unmanned vehicle, and adjusting the running state of the unmanned vehicle according to the fault type to obtain an updated running state. When the updated driving state does not conform to the adjustment control information sent by the remote control terminal, the updated driving state is adjusted according to the driving state adjustment instruction sent by the remote control terminal, and the driving safety of the unmanned vehicle can be further improved.

It should be understood that although the various steps in the flow charts of fig. 2-7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-7 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.

In one embodiment, as shown in fig. 8, there is provided an unmanned vehicle fault detection apparatus 800 comprising: a fault detection information acquisition module 801, a detection object fault detection module 802, an unmanned vehicle fault result determination module 803, an unmanned vehicle fault type determination module 804 and a driving state adjustment module 805, wherein:

a fault detection information obtaining module 801, configured to obtain fault detection information, where the fault detection information includes a detection object and corresponding reference information; the detection object comprises vehicle body equipment, vehicle control software and external equipment;

the fault detection module 802 is configured to obtain operation information corresponding to each detection object, and analyze the operation information corresponding to each detection object according to reference information corresponding to each detection object to obtain a fault detection result of each detection object;

a failure result determining module 803, configured to determine a failure detection result of the unmanned vehicle according to an association relationship between failure detection results of the detection objects;

the fault type determining module 804 is configured to determine an operating state of the unmanned vehicle according to a fault detection result of the unmanned vehicle, and determine a corresponding fault type according to the fault detection result of the unmanned vehicle when the operating state of the unmanned vehicle is a fault;

and a driving state adjusting module 805, configured to adjust a driving state of the unmanned vehicle according to the fault type.

In one embodiment, the fault detection module 802 is further configured to receive a controller area network data frame set sent by each vehicle body device; analyzing the controller local area network data frame set according to a controller local area network bus protocol to obtain the operation data of each vehicle body device; extracting reference operation data corresponding to each vehicle body device from the reference information; comparing the operation data of each vehicle body device with the corresponding reference operation data; and obtaining the fault detection result of each vehicle body device.

In one embodiment, the failure detection module 802 is further configured to send a node detection request; when response information of nodes of each process in the vehicle control software is received, acquiring running information of each process according to the response information of the nodes of each process; extracting reference operation information corresponding to each process from the reference information; and comparing the running information of each process with the corresponding reference running information to obtain the fault detection result of each process.

In one embodiment, the failure detection module 802 is further configured to obtain an identifier of the serial device and a current interface number; acquiring a reference interface number corresponding to the serial device in the reference information according to the identifier of the serial device; determining the connection state of the serial device according to the current interface number of the serial device and the corresponding reference interface number; and determining a fault detection result of the serial device according to the connection state of the serial device.

In one embodiment, the failure detection module 802 is further configured to send a network detection request to the ethernet device; when response information of the Ethernet equipment is received, determining the network connection state of the Ethernet equipment according to the response information of the Ethernet equipment; extracting network connection reference information corresponding to the network connection state of the Ethernet equipment from the reference information; and comparing the network connection state of the Ethernet equipment with the network connection reference information to obtain a fault detection result of the Ethernet equipment.

In an embodiment, the failure result determining module 803 is further configured to analyze the failure detection result of each detection object according to the association relationship between the failure detection results of each detection object, so as to obtain the actual failure detection result of each detection object; and generating a fault detection result of the unmanned vehicle according to the actual fault detection result of each detection object.

In one embodiment, the driving state adjustment module 805 is further configured to send the operation state of the unmanned vehicle to the remote control terminal; when the running state of the unmanned vehicle is a fault, adjusting the running state of the unmanned vehicle according to the fault type to obtain an updated running state; and receiving the adjustment control information of the remote control terminal, receiving a driving state adjustment instruction of the remote control terminal when the updated driving state does not accord with the adjustment control information, and adjusting and updating the driving state according to the driving state adjustment instruction.

For specific limitations of the unmanned vehicle fault detection device, reference may be made to the above limitations of the unmanned vehicle fault detection method, which are not described herein again. All or part of each module in the unmanned vehicle fault detection device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of unmanned vehicle fault detection. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring fault detection information, wherein the fault detection information comprises a detection object and corresponding reference information; the detection object comprises vehicle body equipment, vehicle control software and external equipment; acquiring operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to reference information corresponding to each detection object to obtain a fault detection result of each detection object; determining the fault detection result of the unmanned vehicle according to the incidence relation among the fault detection results of all the detection objects; determining the running state of the unmanned vehicle according to the fault detection result of the unmanned vehicle, and determining the corresponding fault type according to the fault detection result of the unmanned vehicle when the running state of the unmanned vehicle is a fault; and adjusting the running state of the unmanned vehicle according to the fault type.

In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving a controller area network data frame set sent by each vehicle body device; analyzing the controller local area network data frame set according to a controller local area network bus protocol to obtain the operation data of each vehicle body device; extracting reference operation data corresponding to each vehicle body device from the reference information; comparing the operation data of each vehicle body device with the corresponding reference operation data; and obtaining the fault detection result of each vehicle body device.

In one embodiment, the processor, when executing the computer program, further performs the steps of: sending a node detection request; when response information of nodes of each process in the vehicle control software is received, acquiring running information of each process according to the response information of the nodes of each process; extracting reference operation information corresponding to each process from the reference information; and comparing the running information of each process with the corresponding reference running information to obtain the fault detection result of each process.

In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring the identification and the current interface number of the serial device; acquiring a reference interface number corresponding to the serial device in the reference information according to the identifier of the serial device; determining the connection state of the serial device according to the current interface number of the serial device and the corresponding reference interface number; and determining a fault detection result of the serial device according to the connection state of the serial device.

In one embodiment, the processor, when executing the computer program, further performs the steps of: sending a network detection request to the Ethernet equipment; when response information of the Ethernet equipment is received, determining the network connection state of the Ethernet equipment according to the response information of the Ethernet equipment; extracting network connection reference information corresponding to the network connection state of the Ethernet equipment from the reference information; and comparing the network connection state of the Ethernet equipment with the network connection reference information to obtain a fault detection result of the Ethernet equipment.

In one embodiment, the processor, when executing the computer program, further performs the steps of: analyzing the fault detection result of each detection object according to the incidence relation among the fault detection results of each detection object to obtain the actual fault detection result of each detection object; and generating a fault detection result of the unmanned vehicle according to the actual fault detection result of each detection object.

In one embodiment, the processor, when executing the computer program, further performs the steps of: the running state of the unmanned vehicle is sent to a remote control terminal; when the running state of the unmanned vehicle is a fault, adjusting the running state of the unmanned vehicle according to the fault type to obtain an updated running state; and receiving the adjustment control information of the remote control terminal, receiving a driving state adjustment instruction of the remote control terminal when the updated driving state does not accord with the adjustment control information, and adjusting the updated driving state according to the driving state adjustment instruction.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring fault detection information, wherein the fault detection information comprises a detection object and corresponding reference information; the detection object comprises vehicle body equipment, vehicle control software and external equipment; acquiring operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to reference information corresponding to each detection object to obtain a fault detection result of each detection object; determining the fault detection result of the unmanned vehicle according to the incidence relation among the fault detection results of all the detection objects; determining the running state of the unmanned vehicle according to the fault detection result of the unmanned vehicle, and determining the corresponding fault type according to the fault detection result of the unmanned vehicle when the running state of the unmanned vehicle is a fault; and adjusting the running state of the unmanned vehicle according to the fault type.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. An unmanned vehicle fault detection method, the method comprising:

2. The method according to claim 1, wherein when the detection objects are car body devices, the obtaining operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to the reference information corresponding to each detection object, to obtain the fault detection result of each detection object comprises:

and comparing the running data of each vehicle body device with the corresponding reference running data to obtain the fault detection result of each vehicle body device.

3. The method according to claim 1, wherein when the detection objects are vehicle control software, the obtaining operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to the reference information corresponding to each detection object to obtain the fault detection result of each detection object comprises:

sending a node detection request;

4. The method according to claim 1, wherein the external device includes a serial device and an ethernet device, and when the detection object is a serial device, the obtaining of the operation information corresponding to each detection object, and the analyzing of the operation information corresponding to each detection object according to the reference information corresponding to each detection object, to obtain the fault detection result of each detection object includes:

5. The method according to claim 1, wherein the external device includes a serial device and an ethernet device, and when the detection objects are ethernet devices, the obtaining operation information corresponding to each detection object, and analyzing the operation information corresponding to each detection object according to reference information corresponding to each detection object, and the obtaining of the fault detection result of each detection object includes:

sending a network detection request to the Ethernet device;

6. The method according to claim 1, wherein the determining the fault detection result of the unmanned vehicle according to the correlation between the fault detection results of the respective detection objects comprises:

7. The method of claim 1, wherein said adjusting the driving status of the unmanned vehicle according to the fault type comprises:

sending the running state of the unmanned vehicle to a remote control terminal;

8. An unmanned vehicle fault detection device, the device comprising:

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.