CN114564003A - Automatic driving expected function safety perception performance limitation modification method and vehicle - Google Patents
Automatic driving expected function safety perception performance limitation modification method and vehicle Download PDFInfo
- Publication number
- CN114564003A CN114564003A CN202210131670.1A CN202210131670A CN114564003A CN 114564003 A CN114564003 A CN 114564003A CN 202210131670 A CN202210131670 A CN 202210131670A CN 114564003 A CN114564003 A CN 114564003A
- Authority
- CN
- China
- Prior art keywords
- sensor
- confidence
- auxiliary
- main
- scene
- 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.)
- Pending
Links
- 230000006870 function Effects 0.000 title claims abstract description 16
- 230000008447 perception Effects 0.000 title claims abstract description 15
- 238000002715 modification method Methods 0.000 title claims description 5
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 description 7
- 230000004888 barrier function Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0055—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots with safety arrangements
- G05D1/0077—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots with safety arrangements using redundant signals or controls
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for modifying safety perception performance limitation of an automatic driving expected function and a vehicle, wherein the method comprises the following steps: s1, aiming at different scenes, distributing confidence degrees to the required sensors; s2, setting a main sensor of each scene; s3, obtaining the confidence of each sensor in the current scene, and judging whether the confidence of the main sensor is smaller than the distribution confidence of the sensor in the scene; if not, the main sensor is not changed; if yes, go to step S4; s4, judging whether the confidence of the auxiliary sensor is smaller than the distribution confidence of the sensor in the scene; if not, taking the auxiliary sensor as a main sensor; if yes, go to step S5; s5, distributing the weights of the main sensor and the auxiliary sensor, and judging whether the product of the confidence coefficient of the auxiliary sensor and the weight of the auxiliary sensor is smaller than that of the main sensor; if not, the auxiliary sensor is used as a main sensor; if yes, the main sensor is unchanged. The invention can effectively relieve the potential danger of the automatic driving automobile caused by the limitation of the performance of the sensor.
Description
Technical Field
The invention relates to the field of expected function safety, in particular to a method for modifying safety perception performance limitation of an automatic driving expected function and a vehicle.
Background
Nowadays, automatic driving is moving towards higher-level driving assistance systems, in order to meet road-vehicle Safety, The conventional functional Safety standard ISO 26262 has been unable to cover The driving scenario where accidents are caused by performance limitations, The new functional Safety standard ISO 21448 is supplemented, making up for The portion Of ISO 26262 that cannot be covered, ISO 21448 defines SOTIF (Safety Of The integrated function) as a hazard caused by The expected functional specification design deficiency or performance limitations or The reasonably foreseeable misuse that is considered.
The perception module is the 'eyes' of the automatic driving automobile, the sensor is greatly influenced by the external environment, and once a problem occurs, the automatic driving automobile inevitably loses control. How to modify the function of the performance limitation of the perception module of the automatic driving automobile and ensure the effectiveness thereof is very important, otherwise, serious potential safety hazard is caused to the automatic driving automobile.
The sensor arrangement of a general automatic driving automobile aims at solving the problem that a fusion scheme is considered in functional safety if the sensor fails, and a redundancy scheme aims at solving the problem that the automobile is in a temporary blinding state after the sensor fails, so that potential danger exists if a driver cannot take over in time, and potential safety hazards exist in a higher-level driving system without the participation of the driver.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method for modifying safety perception performance limitation of an automatic driving expected function and a vehicle, and solves the problem that potential safety hazards exist due to the limitation of sensor performance of an automatic driving vehicle.
The invention provides a method for modifying safety perception performance limitation of an automatic driving expected function, which comprises the following steps of:
s1, aiming at different scenes, distributing confidence degrees to the required sensors;
s2, setting a main sensor of each scene, and setting the other sensors as auxiliary sensors;
s3, obtaining the confidence of each sensor in the current scene, and judging whether the confidence of the main sensor is smaller than the distribution confidence of the sensor in the scene; if not, the main sensor is not changed; if yes, go to step S4;
s4, judging whether the confidence of the auxiliary sensor is smaller than the distribution confidence of the sensor in the scene; if not, the auxiliary sensor is used as a main sensor; if yes, go to step S5;
s5, distributing the weight of the main sensor and the weight of the auxiliary sensor, and judging whether the product of the confidence coefficient of the auxiliary sensor and the weight of the auxiliary sensor is smaller than the product of the confidence coefficient of the main sensor and the weight of the main sensor; if not, the auxiliary sensor is used as a main sensor; if yes, the main sensor is unchanged.
Further, the sensor with the highest confidence level in each scene is set as the main sensor.
Further, the primary sensor weight is greater than or equal to the secondary sensor weight.
The invention also provides a vehicle which adopts the method for modifying the safety perception performance limitation of the automatic driving anticipation function.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the invention can effectively relieve the potential danger of the automatic driving automobile caused by the limitation of the performance of the sensor.
Drawings
Fig. 1 is a flowchart of a safety awareness performance limitation modification method for an automatic driving anticipation function according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention 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 invention and are not intended to limit the invention. In addition, the technical features involved in the respective embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention provides a modification method for limiting the performance of an automatic driving expected function safety perception module and a vehicle, which are used for relieving potential harm caused by the failure of the perception module caused by the external environmental factors, and takes the influence of the failure of the automatic driving automobile perception module caused by the external environmental factors into consideration.
The invention provides a method for modifying safety perception performance limitation of an automatic driving expected function, which comprises the following steps as shown in figure 1:
s1, aiming at different scenes, distributing confidence degrees to the required sensors;
s2, setting a main sensor of each scene, and setting the other sensors as auxiliary sensors;
s3, obtaining the confidence of each sensor in the current scene, and judging whether the confidence of the main sensor is smaller than the distribution confidence of the sensor in the scene; if not, the main sensor is unchanged; if yes, go to step S4;
s4, judging whether the confidence of the auxiliary sensor is smaller than the distribution confidence of the sensor in the scene; if not, taking the auxiliary sensor as a main sensor; if yes, go to step S5;
s5, distributing the weight of the main sensor and the weight of the auxiliary sensor, and judging whether the product of the confidence coefficient of the auxiliary sensor and the weight of the auxiliary sensor is smaller than the product of the confidence coefficient of the main sensor and the weight of the main sensor; if not, the auxiliary sensor is used as a main sensor; if yes, the main sensor is unchanged.
Further, the sensor with the highest confidence level in each scene is set as the master sensor.
Further, the primary sensor weight is greater than or equal to the secondary sensor weight.
The embodiment of the invention assumes a sensing arrangement scheme of an automatic driving automobile, wherein 1 front camera, 1 front laser radar and 1 front millimeter wave radar are adopted in the forward direction, and 4-angle millimeter wave radars are adopted in the lateral direction. Specific parameters of each sensor are shown in table 1:
TABLE 1 sensor parameters
| Class of sensor | Number of | Description of the function | Detecting distance | Angle of view |
| Front camera | 1 | Detection target information and lane line information | 130-160m | 120° |
| Front laser radar | 1 | Detecting the distance of a target vehicle | 120-200m | 100° |
| Front millimeter wave radar | 1 | Detecting object information | 160-200m | 90° |
| Angular millimeter wave radar | 4 | Detecting adjacent lane target information | 60-70m | 120° |
Based on the above arrangement (assumption) scheme of the sensors, for these sensors, according to the flow of the expected functional safety, the influence caused by the dangerous behavior of the entire vehicle level is obtained from the unexpected behavior of the entire vehicle, the main reasons of the influence are analyzed, and the sensing limitations, i.e., the sensor performance defects and the external environmental influence suffered under the performance defects, are obtained, and table 2 is an example of the sensor performance limitations and the triggering conditions.
TABLE 2 sensor Performance limitations and trigger conditions
The use of the automobile sensor is classified into a forward sensor and a side sensor, wherein the forward sensor is used for sensing forward targets, including a front camera, a front laser radar and a front millimeter wave radar, and the side sensor is used for sensing side targets, namely targets of adjacent lanes (left and right), including 4-angle millimeter wave radars.
For lateral sensing, a redundancy scheme is adopted in functional safety aiming at a lateral angle millimeter wave radar, the influence of the millimeter wave radar on the external environment is small, and the millimeter wave radar is sensitive to the temperature value of the external environment except for the parameter limit of the millimeter wave radar. Even if the millimeter wave radar fails, the vehicle only needs to jump to the MRC mode, such as: keeping the own lane unchanged and low-speed limp home (assuming the driver does not take over the vehicle), and so on.
For forward sensing, including preceding camera, preceding lidar, preceding millimeter wave radar, three kinds of sensors have different influences to different external environment conditions, all have different confidences under different external environment promptly. The method comprises the following specific steps:
1. the forward binocular camera is set based on the deflection angle principle of the two cameras, can identify the attribute of the barrier and calculate the distance of the barrier, has the characteristics of low cost, high identification degree and long detection distance, but has high requirement on illumination intensity and cannot be used in severe weather environments such as night, rain, snow, fog and the like.
2. Preceding laser radar is used for detecting the barrier around the vehicle, and detection range is wide, and detection distance is long, and the precision is high, but the penetrability is not strong, and easy being the false detection of haze/rain/snow etc. is the barrier.
3. Preceding millimeter wave radar is millimeter wave band radar equipment based on doppler effect, has characteristics with low costs, dynamic tracking, detection distance are far away, but the noise point is many, the resolution ratio is low, and the scope angle is little, easy false retrieval, miss detection static barrier, if: the speed reduction plate, the height limit rod and the like are mistakenly identified as the obstacles.
The invention sets percentages for different scenes by judging whether the sensor is suitable for use in certain scenes, and is used for defining the confidence level of the sensor. For example, the front camera, the front lidar, and the front millimeter wave radar have different confidences for the following environments, as shown in table 3 below:
TABLE 3 confidence of sensors under different scenarios
The invention assumes that the initial value of the sensor fusion scheme is that a front camera is used as a main sensor, a front laser radar/front millimeter wave radar is used as an auxiliary sensor, the main sensor and the auxiliary sensor simultaneously detect the information of a target object, and data during fusion is main information referred to when the main sensor is used as a vehicle. Defining the weight of the main/auxiliary sensor, and defining the weight of the main sensor as kMaster and slaveThe weight of the secondary sensor is kAuxiliary device。
Due to the influence of external environmental factors, the confidence data of the sensor can change constantly, namely the performance of the sensor is limited. Therefore, the order of the main sensor and the auxiliary sensor can be changed under the following two conditions:
1. when the confidence of the main sensor is not greater than the confidence of the main sensor in the scene, and the confidence of any auxiliary sensor is greater than the confidence of any auxiliary sensor in the scene, the auxiliary sensor with the highest confidence is taken as the main sensor;
2. and when the confidence coefficient of the primary sensor is not greater than that of the primary sensor in the scene, and the confidence coefficient of the secondary sensor is not greater than that of the secondary sensor in the scene, if the product of the confidence coefficient of the secondary sensor and the weight is greater than that of the primary sensor, the secondary sensor is taken as the primary sensor.
Therefore, the performance limitation of the sensor can be relieved, and the safety of the automatic driving automobile is improved.
It will be understood by those skilled in the art that the foregoing is merely a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included within the scope of the present invention.
Claims (4)
1. A safety perception performance limitation modification method for an automatic driving anticipation function is characterized by comprising the following steps:
s1, aiming at different scenes, distributing confidence degrees to the required sensors;
s2, setting a main sensor of each scene, and setting the other sensors as auxiliary sensors;
s3, obtaining the confidence of each sensor in the current scene, and judging whether the confidence of the main sensor is smaller than the distribution confidence of the sensor in the scene; if not, the main sensor is unchanged; if yes, go to step S4;
s4, judging whether the confidence of the auxiliary sensor is smaller than the distribution confidence of the sensor in the scene; if not, the auxiliary sensor is used as a main sensor; if yes, go to step S5;
s5, distributing the weight of the main sensor and the weight of the auxiliary sensor, and judging whether the product of the confidence coefficient of the auxiliary sensor and the weight of the auxiliary sensor is smaller than the product of the confidence coefficient of the main sensor and the weight of the main sensor; if not, the auxiliary sensor is used as a main sensor; if yes, the main sensor is not changed.
2. The automated driving anticipation functional safety-aware performance limit modifying method of claim 1, wherein a sensor with highest confidence in each scene is set as a master sensor.
3. The automated driving anticipation function safety perception performance limitation modifying method of claim 1, wherein the primary sensor weight is greater than or equal to the secondary sensor weight.
4. A vehicle employing the method of modifying an autodrive anticipation functional safety-aware performance limit according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210131670.1A CN114564003A (en) | 2022-02-14 | 2022-02-14 | Automatic driving expected function safety perception performance limitation modification method and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210131670.1A CN114564003A (en) | 2022-02-14 | 2022-02-14 | Automatic driving expected function safety perception performance limitation modification method and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114564003A true CN114564003A (en) | 2022-05-31 |
Family
ID=81713982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210131670.1A Pending CN114564003A (en) | 2022-02-14 | 2022-02-14 | Automatic driving expected function safety perception performance limitation modification method and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114564003A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116046417A (en) * | 2023-04-03 | 2023-05-02 | 西安深信科创信息技术有限公司 | Automatic driving perception limitation testing method and device, electronic equipment and storage medium |
| TWI824778B (en) * | 2022-10-17 | 2023-12-01 | 財團法人車輛研究測試中心 | System and method with safety of the intended functionality scene collection and self-update mechanism |
-
2022
- 2022-02-14 CN CN202210131670.1A patent/CN114564003A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI824778B (en) * | 2022-10-17 | 2023-12-01 | 財團法人車輛研究測試中心 | System and method with safety of the intended functionality scene collection and self-update mechanism |
| CN116046417A (en) * | 2023-04-03 | 2023-05-02 | 西安深信科创信息技术有限公司 | Automatic driving perception limitation testing method and device, electronic equipment and storage medium |
| CN116046417B (en) * | 2023-04-03 | 2023-11-24 | 安徽深信科创信息技术有限公司 | Automatic driving perception limitation testing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114564003A (en) | Automatic driving expected function safety perception performance limitation modification method and vehicle | |
| CN108909721B (en) | Vehicle yaw angle calculation method based on millimeter wave radar | |
| CN110843773B (en) | Device and method for controlling driving of vehicle | |
| CN109870680B (en) | Target classification method and device | |
| JP6332384B2 (en) | Vehicle target detection system | |
| US11505189B2 (en) | Vehicle SCC system based on complex information and method of controlling the same | |
| GB2558777A (en) | Vehicle collision avoidance | |
| US20100214085A1 (en) | Cooperative sensor-sharing vehicle traffic safety system | |
| CN104321665B (en) | Multi-surface model-based tracking | |
| US9123251B2 (en) | Image system for automotive safety applications | |
| US10482332B2 (en) | Pedestrian determining apparatus for determining whether an object is a pedestrian crossing ahead of an own vehicle | |
| US10814879B2 (en) | Determination apparatus and vehicle | |
| CN111142528B (en) | Method, device and system for sensing dangerous scene for vehicle | |
| CN102416954A (en) | Vehicle cruise control apparatus | |
| CN111582130B (en) | Traffic behavior perception fusion system and method based on multi-source heterogeneous information | |
| JP2018055426A (en) | Target detection system for vehicle | |
| CN111736153A (en) | Environment detection system, method, apparatus, and medium for unmanned vehicle | |
| CN111060911A (en) | Vehicle anti-collision recognition method based on scene analysis | |
| CN111796286A (en) | Brake grade evaluation method and device, vehicle and storage medium | |
| EP3467545A1 (en) | Object classification | |
| CN112101316A (en) | Target detection method and system | |
| Schiegg et al. | Object Detection Probability for Highly Automated Vehicles: An Analytical Sensor Model. | |
| KR102555916B1 (en) | Apparatus and method for identificating odm data reliability and vehicle including the same | |
| US11753014B2 (en) | Method and control unit automatically controlling lane change assist | |
| CN107886036B (en) | Vehicle control method and device and vehicle |
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 |