CN112747936B - Detection method of unmanned vehicle - Google Patents
Detection method of unmanned vehicle Download PDFInfo
- Publication number
- CN112747936B CN112747936B CN202011516107.3A CN202011516107A CN112747936B CN 112747936 B CN112747936 B CN 112747936B CN 202011516107 A CN202011516107 A CN 202011516107A CN 112747936 B CN112747936 B CN 112747936B
- Authority
- CN
- China
- Prior art keywords
- detection
- vehicle
- self
- checking
- sensor
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to the technical field of unmanned driving, in particular to a detection method of an unmanned vehicle. It comprises the following steps: s1, starting a vehicle; s2, self-checking the vehicle, judging whether a fault occurs or not, reporting if the fault occurs in the self-checking link, and then stopping the detection; if the self-checking link has no fault, continuing the next step; s3, the vehicle runs to a detection position, then other detection is automatically carried out on the vehicle through other detection equipment and/or a vehicle body sensor, whether a fault occurs or not is judged, if the fault occurs in the other detection link, reporting is carried out, and then detection is stopped; if the other inspection links have no fault, the vehicle is normal; and the other tests comprise vehicle control capability detection, vehicle-mounted sensor performance detection and sensor calibration goodness of fit detection. By adopting the method, professional personnel are not needed to participate in the detection, and the detection efficiency is higher.
Description
Technical Field
The invention relates to the technical field of unmanned driving, in particular to a detection method of an unmanned vehicle.
Background
The unmanned vehicle mainly carries out perception control through a vehicle-mounted perception control module, and then automatic driving is achieved. Through various daily losses of the unmanned vehicle such as operation and test, a sensing control module on the vehicle may slightly deflect and displace, the sensing performance is reduced, even faults occur, and the safety of the unmanned vehicle is affected by the above all, so that the operation risk is increased.
A conventional perception control module calibration scheme for an unmanned vehicle generally comprises that technicians are uniformly arranged to check indexes one by one after the vehicle is off-line so as to detect possible fault problems. However, such detection methods have problems of detection lag, low detection efficiency, and easy omission.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method for detecting the unmanned vehicle is high in detection efficiency, and professional personnel are not required to participate in detection.
The technical scheme adopted by the invention is as follows: a method of detecting an unmanned vehicle, comprising the steps of:
s1, starting a vehicle;
s2, self-checking the vehicle, judging whether a fault occurs or not, if the fault occurs in the self-checking link, reporting, and then stopping the detection; if the self-checking link has no fault, continuing the next step;
s3, the vehicle runs to a detection position, then other detection is automatically carried out on the vehicle through other detection equipment and/or a vehicle body sensor, whether a fault occurs or not is judged, if the fault occurs in the other detection link, reporting is carried out, and then detection is stopped; if the other inspection links have no fault, the vehicle is normal;
and the other tests comprise vehicle control capability detection, vehicle-mounted sensor performance detection and sensor calibration goodness of fit detection.
Preferably, the vehicle control capability detection comprises controlling vehicle starting, accelerating, braking starting, lane changing, decelerating, parking, reversing and steering, and then detecting whether the actions are accurate through other detection devices and/or vehicle body sensors.
Preferably, the sensor performance detection includes static obstacle detection, dynamic obstacle detection, and fixed-point parking.
Preferably, the static detection comprises the steps of:
a1, a vehicle runs according to a set route and meets a set static obstacle;
a2, scanning and detecting by a vehicle sensor, detecting the position and size of an obstacle, comparing a detection result with a set result, and judging that a static detection result is normal when the comparison result is within an error range; if the comparison result is out of the error range, the static detection result is judged to be abnormal, the condition is reported, and the detection is stopped.
Preferably, the dynamic detection comprises the steps of:
b1, the vehicle runs according to a set route and meets a set dynamic obstacle;
b2, scanning and detecting by a vehicle sensor, detecting the position, size and movement trend of the obstacle, comparing the detection result with a set result, and judging that the dynamic detection result is normal when the comparison result is within an error range; if the comparison result is out of the error range, the dynamic detection result is judged to be abnormal, the condition is reported, and the detection is stopped.
Preferably, the movement tendency includes a counter movement, a co-directional movement, a cross movement, a lane intrusion, and a falling object.
Preferably, the fixed-point parking includes the steps of:
c1, the vehicle stops according to a set position;
c2, detecting whether the vehicle is accurately parked by the other detection equipment and/or the vehicle body sensor, if the other detection equipment and/or the vehicle body sensor detects that the vehicle is not accurately parked, reporting, and stopping detection; if the other detection equipment and/or the vehicle body sensor detect that the parking is accurate, the positioning parking function is normal.
Preferably, the self-checking comprises hardware system self-checking, software system self-checking and communication self-checking, the hardware system self-checking comprises indicator light detection control self-checking, sound source control capability self-checking, vehicle overall state self-checking and trailer state self-checking, the software system self-checking comprises interaction self-checking with a management terminal, interaction self-checking with a TCS (traffic control system) and calibration self-checking with a high-precision map, and the communication self-checking comprises connectivity self-checking and communication quality self-checking.
Preferably, step S3 is followed by a back box status detection, which includes the steps of placing the box and detecting that the position device and/or the body sensor needs to record the impact condition of the box.
Preferably, the specific steps of the sensor calibration goodness of fit detection include:
d1, driving the vehicle to a detection area;
d2, detecting the marker in the detection area through a self sensor;
d3, comparing the detected result with a set result, and judging that the calibration goodness of fit of the sensor is normal when the comparison result is within an error range; and if the comparison result is out of the error range, judging that the calibration goodness of fit of the sensor is abnormal, reporting the condition, and stopping detection.
Compared with the prior art, the method has the following advantages that: according to the unmanned vehicle detection method, whether the recognition and response conditions of all the perception control modules of the unmanned vehicles are normal or not is detected through self-checking and other checks, so that the perception control modules of the unmanned vehicles in batches can be rapidly detected, and the detection automation level and the detection maintenance efficiency of the unmanned vehicle perception control equipment are improved. On the other hand, the basic functions of the unmanned vehicle can be evaluated relatively systematically and accurately, safety guarantee is provided for the unmanned vehicle to be inspected before real vehicle operation, and the test standard and specification of the unmanned vehicle sensing control equipment are improved. By adopting the method, the resource investment of manual detection sensing and control equipment every day can be greatly saved, the overall detection efficiency is improved in the standardized detection process, and unnecessary loss generated when the unmanned vehicle waits for detection is reduced.
Detailed Description
The present invention will be further described below by way of specific embodiments, but the present invention is not limited to the following specific embodiments.
The specific embodiment I is a detection method of an unmanned vehicle, which mainly comprises the steps of starting self-detection, other detection and back box detection, wherein:
the starting self-checking comprises hardware system self-checking, software system self-checking and communication self-checking, wherein:
the hardware system self-check comprises an indicator light detection control self-check, a sound source control capability self-check, a vehicle overall state self-check and a towing state self-check, and the indicator light self-check comprises a left steering lamp self-check, a right steering lamp self-check, a double-flashing lamp self-check, a brake lamp self-check and a fog lamp self-check; the sound source control capability self-checking comprises loudspeaker self-checking, electric loudspeaker self-checking and siren self-checking; the vehicle overall state self-checking comprises self-checking of tire pressure, oil quantity, electric quantity, water temperature, abnormal warning and the like; the self-checking of the towing state comprises self-checking of the weight of the towing, self-checking of the relative angle with the vehicle head and self-checking of the horizontality of the towing;
the software system self-checking comprises interacting self-checking with a management terminal, interacting self-checking with a TCS (unmanned card collection management system) and calibrating self-checking with a high-precision map;
the communication self-check comprises connectivity self-check and communication quality self-check.
The starting self-check is completed by a system of the vehicle, so that the starting can be carried out after the starting without the running and moving of the vehicle;
the inspection is mainly performed on a set inspection site, and comprises vehicle control capability detection, vehicle-mounted sensor performance detection and sensor calibration goodness of fit detection, wherein:
the vehicle control capability detection comprises starting, accelerating, braking starting, lane changing, decelerating, stopping, backing and steering; for example, a specific simulation channel is built, a vehicle stops in front of the channel, the vehicle is started (self), accelerated to 20 yards (other detection: speedometer detection), braked at a marked line to start braking, decelerated to 0 yards (other detection: speedometer detection), braked to start (self), changed lanes (other detection: geomagnetic or ground induction coil), decelerated (self), stopped at the marked line to stop the vehicle (other detection: camera; self vision, laser, GPS, and the like), backed and steered (other detection: camera, geomagnetic and the like; self);
the vehicle control capability mainly controls the vehicle to run according to a set running route and is executed according to set operation at a set fixed point, and whether the operation is accurate or not can be detected by various other detection devices (such as a camera, a sensor and the like) in the execution process;
the performance detection of the vehicle-mounted sensor comprises static obstacle detection, dynamic obstacle detection and fixed-point parking, and the vehicle-mounted sensor mainly comprises one or more of an ultrasonic sensor, a millimeter wave sensor, a visual camera and a laser radar, and can also comprise other sensors;
the static obstacle detection is specifically that the vehicle runs according to a set route, static obstacles such as a triangular cone, a road fence and the like are arranged in the set route, when the vehicle runs to the road section, the vehicle needs to scan and detect through a sensor of the vehicle to obtain a scanning result, the scanning result mainly comprises the position and the size of the obstacle, and then the scanning result is compared with the set result to see whether the position and the size of the obstacle are within an error range, so that whether a sensor assembly runs normally can be confirmed;
the dynamic obstacle detection is specifically carried out according to a set route, dynamic obstacles such as a dummy simulating a pedestrian and a running vehicle can appear in the set route, when the vehicle runs to the road section, the vehicle needs to carry out scanning detection through a sensor of the vehicle to obtain a scanning result, the scanning result mainly comprises the approximate position and the movement trend of the dynamic obstacles such as opposite movement, same-direction movement, lane intrusion, falling objects and the like, and then the scanning result is compared with the set result to see whether the dynamic obstacles are in an error range, so that whether the sensor assembly runs normally can be confirmed;
the fixed-point parking is specifically that the vehicle parks according to a set position according to a self-positioning module (satellite positioning, inertial navigation, a wheel speed meter and a high-precision map), and then whether the parking position is accurate or not is judged through other detection equipment (a camera, a sensor and the like), so that whether the self-positioning module is accurate or not can be determined;
the sensor calibration goodness of fit detection specifically comprises the following steps: the vehicle travels to the detection area; detecting the marker in the detection area through a self-sensor; comparing the detected result with a set result, and judging that the calibration goodness of fit of the sensor is normal when the comparison result is within an error range; and if the comparison result is out of the error range, judging that the calibration goodness of fit of the sensor is abnormal, reporting the condition, and stopping detection.
The back of the body case detects and detects the back at self-checking and other, and the normal time that indicates the vehicle just can go on, is exactly that the actual work in-process, puts into the container and drags of vehicle on, then the vehicle sensor (can adopt the impact sensing equipment) of taking can detect the impact force, records this impact force, if break down in detecting next time, can trace back through the record.
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 skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A method of detecting an unmanned vehicle, comprising: it comprises the following steps:
s1, starting a vehicle;
s2, self-checking the vehicle, judging whether a fault occurs or not, if the fault occurs in the self-checking link, reporting, and then stopping the detection; if the self-checking link has no fault, continuing the next step;
s3, the vehicle runs to a detection position, then other detection is automatically carried out on the vehicle through other detection equipment and/or a vehicle body sensor, whether a fault occurs or not is judged, if the fault occurs in the other detection link, reporting is carried out, and then detection is stopped; if the other inspection links have no fault, the vehicle is normal;
s4, carrying out state detection, namely putting the container on a trailer of a vehicle, and recording the impact condition of the container by other detection position equipment and/or a vehicle body sensor;
and the other tests comprise vehicle control capability detection, vehicle-mounted sensor performance detection and sensor calibration goodness of fit detection.
2. The detection method of an unmanned vehicle according to claim 1, characterized in that: the vehicle control capability detection comprises controlling the vehicle to start, accelerate, brake to start, change lanes, decelerate, stop, reverse and turn, and detecting whether the actions are accurate through other detection equipment and/or a vehicle body sensor.
3. The detection method of an unmanned vehicle according to claim 1, characterized in that: the sensor performance detection includes static obstacle detection, dynamic obstacle detection, and fixed-point parking.
4. A detection method of an unmanned vehicle according to claim 3, characterized in that: the static detection comprises the following steps:
a1, a vehicle runs according to a set route and encounters a set static obstacle;
a2, scanning and detecting by a vehicle sensor, detecting the position and size of an obstacle, comparing a detection result with a set result, and judging that a static detection result is normal when the comparison result is within an error range; if the comparison result is out of the error range, the static detection result is judged to be abnormal, the condition is reported, and the detection is stopped.
5. A detection method of an unmanned vehicle according to claim 3, characterized in that: the dynamic detection comprises the following steps:
b1, the vehicle runs according to a set route and encounters a set dynamic obstacle;
b2, scanning and detecting by a vehicle sensor, detecting the position, size and movement trend of the obstacle, comparing the detection result with a set result, and judging that the dynamic detection result is normal when the comparison result is within an error range; if the comparison result is out of the error range, the dynamic detection result is judged to be abnormal, the condition is reported, and the detection is stopped.
6. The detection method of an unmanned vehicle according to claim 5, wherein: the movement tendency comprises opposite movement, same-direction movement, cross movement, lane invasion and high-altitude falling objects.
7. A detection method of an unmanned vehicle according to claim 3, characterized in that: the fixed-point parking method comprises the following steps:
c1, the vehicle stops according to a set position;
c2, detecting whether the vehicle is accurately parked by the other detection equipment and/or the vehicle body sensor, if the other detection equipment and/or the vehicle body sensor detects that the vehicle is not accurately parked, reporting, and stopping detection; if the other detection equipment and/or the vehicle body sensor detect that the parking is accurate, the positioning parking function is normal.
8. The detection method of an unmanned vehicle according to claim 1, characterized in that: the self-checking system comprises hardware system self-checking, software system self-checking and communication self-checking, wherein the hardware system self-checking comprises indicator light detection control self-checking, sound source control capability self-checking, vehicle overall state self-checking and trailer state self-checking, the software system self-checking comprises management terminal interaction self-checking, TCS interaction self-checking and high-precision map calibration self-checking, and the communication self-checking comprises connectivity self-checking and communication quality self-checking.
9. The detection method of an unmanned vehicle according to claim 1, characterized in that: the specific steps of the sensor calibration goodness of fit detection comprise:
d1, driving the vehicle to a detection area;
d2, detecting the marker in the detection area through a self sensor;
d3, comparing the detected result with a set result, and judging that the calibration goodness of fit of the sensor is normal when the comparison result is within an error range; if the comparison result is out of the error range, judging that the calibration goodness of fit of the sensor is abnormal, reporting the condition, and stopping detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011516107.3A CN112747936B (en) | 2020-12-21 | 2020-12-21 | Detection method of unmanned vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011516107.3A CN112747936B (en) | 2020-12-21 | 2020-12-21 | Detection method of unmanned vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112747936A CN112747936A (en) | 2021-05-04 |
| CN112747936B true CN112747936B (en) | 2023-01-10 |
Family
ID=75649316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011516107.3A Active CN112747936B (en) | 2020-12-21 | 2020-12-21 | Detection method of unmanned vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112747936B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113341955A (en) * | 2021-05-19 | 2021-09-03 | 吉利汽车研究院（宁波）有限公司 | Control method, device and equipment for automatic driving vehicle and storage medium |
| CN114394096A (en) * | 2022-01-28 | 2022-04-26 | 南京司凯奇汽车科技有限公司 | Longitudinal following retaining device for unmanned heavy truck |
| CN115219151B (en) * | 2022-07-13 | 2024-01-23 | 小米汽车科技有限公司 | Vehicle testing method, system, electronic equipment and medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105346483B (en) * | 2015-11-04 | 2018-07-17 | 常州加美科技有限公司 | A kind of man-machine interactive system of automatic driving vehicle |
| US11010852B2 (en) * | 2017-06-30 | 2021-05-18 | Lantern Unmanned Autonomous Systems, Llc | Unmanned autonomous container inspection |
| JP7212916B2 (en) * | 2018-07-03 | 2023-01-26 | 株式会社Zmp | Automatic test drive system for running vehicles |
| CN108871794A (en) * | 2018-07-04 | 2018-11-23 | 北京踏歌智行科技有限公司 | Mining automatic driving vehicle fault self-diagnosis method and device |
| CN109141920A (en) * | 2018-08-27 | 2019-01-04 | 山东省科学院自动化研究所 | Automatic driving vehicle rainy day environment sensing recognition capability test evaluation system and method |
| CN110689778A (en) * | 2019-09-06 | 2020-01-14 | 深圳果力智能科技有限公司 | Unmanned vehicle driving detection method and unmanned detection system |
| CN110716569A (en) * | 2019-10-30 | 2020-01-21 | 中国船舶重工集团公司第七一六研究所 | Unmanned vehicle automatic driving system suitable for container transportation |
| CN111063055A (en) * | 2019-12-24 | 2020-04-24 | 广东天创同工大数据应用有限公司 | Alarm grading method based on unmanned vehicle intelligent-association assisting system |
| CN111006879B (en) * | 2019-12-25 | 2021-11-02 | 畅加风行(苏州)智能科技有限公司 | Port environment-oriented man-machine hybrid driving automatic driving test method and test platform thereof |
-
2020
- 2020-12-21 CN CN202011516107.3A patent/CN112747936B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112747936A (en) | 2021-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112747936B (en) | Detection method of unmanned vehicle | |
| CN109080626B (en) | Vehicle fault processing method | |
| CN102991504B (en) | Method for determining and prewarning lane change safety of drivers | |
| CN111439199B (en) | reporting device | |
| US10996141B2 (en) | Method and an autonomous ground vehicle | |
| WO2017095614A1 (en) | Collision mitigated braking for autonomous vehicles | |
| CN109733283B (en) | AR-based shielded barrier recognition early warning system and recognition early warning method | |
| CN111524362A (en) | Vehicle safety driving guarantee system and method based on multi-data fusion | |
| KR102529392B1 (en) | Forward collision-avoidance assist performance inspection system and method thereof | |
| EP3675079A1 (en) | Danger warning method for vehicle, danger warning device for vehicle, and medium | |
| CN112950997B (en) | Emergency linkage method and system | |
| US11845435B2 (en) | Driving assistance device | |
| CN112129548A (en) | Automatic driving vehicle test system and AEBS (automatic guided vehicle) and FCWS (fiber channel sensing) test method | |
| CN111477011A (en) | Detection device and detection method for road intersection early warning | |
| CN113920485A (en) | Vehicle-mounted road pothole reminding method and system based on big data | |
| CN113112798A (en) | Vehicle overload detection method, system and storage medium | |
| CN110834587A (en) | Automobile longitudinal anti-collision system based on laser ranging | |
| CN116101269B (en) | Method, system and vehicle for safety monitoring of automatic parking process | |
| CN115985096A (en) | Evaluation system and method under road traffic scene of navigation driving assistance system | |
| CN114655113B (en) | Reporting device | |
| Beresnev et al. | The development of a blind spot monitoring system for commercial vehicles | |
| CN113808419A (en) | Method for determining an object of an environment, object sensing device and storage medium | |
| CN219257326U (en) | Vehicle and tunnel safety system with drive-by-wire chassis | |
| Ge et al. | A systematic approach to develop an autopilot sensor monitoring system for autonomous delivery vehicles based on the STPA method | |
| CN114954413B (en) | Vehicle self-checking processing method, device, equipment 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 |