CN115993257B - Reliability determination method for automatic driving system - Google Patents
Reliability determination method for automatic driving system Download PDFInfo
- Publication number
- CN115993257B CN115993257B CN202310288341.2A CN202310288341A CN115993257B CN 115993257 B CN115993257 B CN 115993257B CN 202310288341 A CN202310288341 A CN 202310288341A CN 115993257 B CN115993257 B CN 115993257B
- Authority
- CN
- China
- Prior art keywords
- instruction
- speed
- value
- risk
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a reliability determination method of an automatic driving system, which relates to the field of general vehicles and is used for solving the problems that the existing reliability determination method is that an automatic driving simulation model is built, but an actual route test is still carried out, so that the difference between the result of the model test and the actual result is too large, and the accuracy is not high; according to the reliability determination method, an automobile provided with an automatic driving system is used as a test vehicle, an actual driving scene is selected to be simulated on the spot, a preset route is randomly generated in the simulation spot, then analysis is carried out on an analysis object, the test is carried out by adopting a real vehicle and the real scene, the situation is reflected to be more real, and the accuracy of the automatic driving reliability is improved; the reliability determination method can analyze the actual running condition of the analysis object by collecting the actual running condition in real time to obtain the reliability coefficient so as to judge the reliability of the analysis object, and has the advantages of high intelligent degree, high reliability and high accuracy.
Description
Technical Field
The present invention relates to the general field of vehicles, and in particular to a method for determining the reliability of an automatic driving system.
Background
With the development of vehicle intellectualization, automatic driving has been a trend, and before an automatic driving automobile realizes a road, a strict functional safety test must be performed, and a method, a device, equipment and a medium for determining the reliability of an automatic driving system are disclosed in the patent with the application number of CN 202210107033.0. According to the method, a scene simulation result of the automatic driving system is obtained through a constructed vehicle model, a sensor model, a control model of the automatic driving system and a scene model, a response surface of the scene variable and the scene simulation result is constructed based on the scene simulation result and each scene variable corresponding to the scene model, and further the failure probability corresponding to the automatic driving system is determined based on the response surface, a probability density function of each scene variable, a range of each scene variable and preset failure conditions, so that quantification of the reliability result of the automatic driving system is realized, powerful support is provided for development and improvement of the automatic driving system, and the technical problems that all test scenes cannot be exhausted in the prior art are solved, but the following defects still exist: according to the reliability determination method, the automatic driving simulation model is established, so that the automatic driving simulation model has the advantages of high scene coverage, safe test process, high test efficiency and the like, but an automobile provided with the automatic driving system is not arranged for carrying out actual route test, so that the difference between the result of the model test and the actual result is too large, and the accuracy of the detection result of the reliability of the automatic driving system is not high.
Disclosure of Invention
In order to overcome the above-mentioned technical problems, an object of the present invention is to provide a reliability determining method of an automatic driving system: the method comprises the steps of generating a parameter acquisition instruction in the running process of an analysis object through a determining platform, acquiring the analysis parameter of the analysis object through a data acquisition module, generating a detection instruction according to the analysis parameter through an information analysis module, and sounding an alarm and displaying a lighting lamp according to the detection instruction through an alarm regulation and control module.
The aim of the invention can be achieved by the following technical scheme:
the reliability determination method of the automatic driving system comprises the following steps:
step one: the method comprises the steps that a determining platform marks an automobile provided with an automatic driving system as an analysis object, a current position is set as a starting point, a randomly selected position is set as an end point, a preset route is obtained through the starting point and the end point, the automatic driving system controls the analysis object to run according to the preset route, an acquisition instruction is generated when the analysis object is started, and the acquisition instruction is sent to a data acquisition module;
step two: the data acquisition module receives the acquisition instruction and acquires all barriers including people, animals, motor vehicles, guardrails and the like within a preset range of the analysis object, and the distance analysis is performedThe method comprises the steps of marking the nearest obstacle as a preselected object, obtaining the distance between an analysis object and the preselected object, marking the distance as a distance value JL, setting the moving direction of the analysis object as a positive direction, obtaining the moving speed of the preselected object, marking the moving speed as a moving speed value YS, and substituting the distance value JL and the moving speed value YS into a formula
Obtaining a risk coefficient WX, wherein q1 and q2 are preset proportional coefficients of a distance value JL and a shift speed value YS respectively, and q1 is more than q2 is more than 1.326;
step three: the data acquisition module compares the risk coefficient WX to a risk threshold WXy:
if the risk coefficient WX is larger than the risk threshold WXy, generating a risk instruction, acquiring the number of times of generating the risk instruction and marking the number of times as a risk value WC;
step four: when the running speed of the analysis object reaches a preset speed for the first time, generating an analysis instruction by the determination platform, and sending the analysis instruction to the data acquisition module;
step five: the data acquisition module receives the analysis instruction and acquires the running speed of the analysis object in real time, and the running speed is compared with a preset maximum speed and a preset minimum speed respectively:
if the running speed is less than the minimum speed or the running speed is greater than the maximum speed, generating a dangerous speed instruction;
if the minimum speed is less than or equal to the running speed and less than or equal to the maximum speed, generating a constant speed instruction;
step six: the data acquisition module acquires the times of generating dangerous speed instructions and marks the times as a speed value SC, acquires the time difference between adjacent dangerous speed instructions and constant speed instructions and marks the time difference as a single-time value, does not acquire the time difference between the adjacent constant speed instructions and the dangerous speed instructions, acquires the sum of all the single-time values and marks the sum as a speed value SS, and substitutes the speed value SC and the speed value SS into a formula
Obtaining a dangerous speed value WS, wherein alpha 1 and alpha 2 are preset weight coefficients of a speed value SS and a speed value SC respectively, and alpha 1+alpha 2=1, alpha 1=0.52 and alpha2=0.48；
Step seven: determining that the platform generates a forming instruction when the analysis object reaches the end point, and sending the forming instruction to the data acquisition module;
step eight: the data acquisition module acquires a driving route of the analysis object after receiving the forming instruction, and draws the driving route and a preset route into a graph to acquire a drawn graph;
step nine: the data acquisition module acquires the number of intersecting points in the drawn graph and the total area of the graph formed by intersecting, marks the intersecting points as intersecting values JS and intersecting values JM respectively, and substitutes the intersecting values JS and the intersecting values JM into a formula
Obtaining a graph value TX, wherein β1 and β2 are preset weight coefficients of an intersection value JS and an intersection value JM respectively, and β1+β2=1, β1=0.35 and β2=0.65 are taken;
step ten: the data acquisition module sends the risk value WC, the risk value WS and the graphic value TX to the information analysis module;
step eleven: the information analysis module substitutes the risk value WC, the risk speed value WS and the graphic value TX into a formula
Obtaining a reliability coefficient KK, wherein δ1, δ2 and δ3 are preset weight factors of a risk value WC, a risk speed value WS and a graph value TX respectively, δ3 > δ2 > δ1 > 2.226, γ is a correction factor, and γ is 0.894;
step twelve: the information analysis module compares the reliability coefficient KK to a reliability threshold WXy:
if the risk coefficient WX is smaller than the reliable threshold WXy, generating an unreliable instruction and sending the unreliable instruction to an alarm regulation module;
if the risk coefficient WX is more than or equal to a reliable threshold WXy, generating a reliable instruction and sending the reliable instruction to an alarm regulation module;
step thirteen: the alarm regulation and control module sounds an alarm and lights a red light after receiving the unreliable instruction, and then a worker performs inspection optimization on the analysis object and lights a green light after receiving the reliable instruction.
As a preferred embodiment of the present invention, the determining platform is configured to control the analysis object to travel according to a preset route, generate a parameter acquisition instruction during the travel of the analysis object, and send the parameter acquisition instruction to the data acquisition module, where the parameter acquisition instruction includes an acquisition instruction, an analysis instruction, and a molding instruction;
the data acquisition module is used for acquiring analysis parameters of an analysis object after receiving a parameter acquisition instruction and sending the analysis parameters to the information analysis module, wherein the analysis parameters comprise a risk value WC, a risk value WS and a graph value TX;
the information analysis module is used for generating a detection instruction according to the analysis parameters and sending the detection instruction to the alarm regulation module, wherein the detection instruction comprises an unreliable instruction and a reliable instruction;
the alarm regulation and control module is used for sounding an alarm and displaying a lighting lamp according to the detection instruction.
As a preferred implementation mode of the invention, the specific process of generating the parameter acquisition instruction by the determination platform is as follows:
the method comprises the steps of marking an automobile provided with an automatic driving system as an analysis object, setting a current position as a starting point, randomly selecting the position as an end point, obtaining a preset route through the starting point and the end point, controlling the analysis object to run according to the preset route through the automatic driving system, generating an acquisition instruction when the analysis object starts, generating an analysis instruction when the running speed of the analysis object reaches the preset speed for the first time, generating a forming instruction after the analysis object reaches the end point, and sending the acquisition instruction, the analysis instruction and the forming instruction to a data acquisition module.
As a preferred embodiment of the present invention, the specific process of the data acquisition module acquiring the analysis parameters is as follows:
after receiving the acquisition instruction, acquiring all barriers including people, animals, motor vehicles, guardrails and the like within a preset range of the analysis object, marking the barrier closest to the analysis object as a preselected object, and acquiring the distance between the analysis object and the preselected objectMarking the moving speed of the pre-selected object as a moving speed value YS, substituting the distance value JL and the moving speed value YS into a formula
Obtaining a risk coefficient WX, wherein q1 and q2 are preset proportional coefficients of a distance value JL and a shift speed value YS respectively, and q1 is more than q2 is more than 1.326;
the risk factor WX is compared to a risk threshold WXy:
if the risk coefficient WX is larger than the risk threshold WXy, generating a risk instruction, acquiring the number of times of generating the risk instruction and marking the number of times as a risk value WC;
the running speed of the analysis object is acquired in real time after the analysis instruction is received, and the running speed is compared with a preset maximum speed and a preset minimum speed respectively:
if the running speed is less than the minimum speed or the running speed is greater than the maximum speed, generating a dangerous speed instruction;
if the minimum speed is less than or equal to the running speed and less than or equal to the maximum speed, generating a constant speed instruction;
acquiring the times of generating dangerous speed instructions and marking the times as a speed value SC, acquiring the time difference between adjacent dangerous speed instructions and normal speed instructions and marking the time difference as a single-time value, acquiring the sum of all the single-time values and marking the sum as a speed value SS, and substituting the speed value SC and the speed value SS into a formula
Obtaining a dangerous speed value WS, wherein alpha 1 and alpha 2 are preset weight coefficients of a speed value SS and a speed value SC respectively, and alpha 1+alpha 2=1, alpha 1=0.52 and alpha 2=0.48 are taken;
after receiving the forming instruction, acquiring a driving route of the analysis object, and drawing the driving route and a preset route into a graph to acquire a drawing graph;
the number of intersecting points in the drawn graph and the total area of the graph formed by intersecting are obtained and marked as intersecting values JS and intersecting values JM respectively, and the intersecting values JS and the intersecting values JM are substitutedEnter into the formula
Obtaining a graph value TX, wherein β1 and β2 are preset weight coefficients of an intersection value JS and an intersection value JM respectively, and β1+β2=1, β1=0.35 and β2=0.65 are taken;
and sending the risk value WC, the risk value WS and the graphic value TX to an information analysis module.
As a preferred embodiment of the present invention, the specific process of generating the detection instruction by the information analysis module is as follows:
substituting the critical sub value WC, the critical speed value WS and the graphic value TX into a formula
Obtaining a reliability coefficient KK, wherein δ1, δ2 and δ3 are preset weight factors of a risk value WC, a risk speed value WS and a graph value TX respectively, δ3 > δ2 > δ1 > 2.226, γ is a correction factor, and γ is 0.894;
the reliability coefficient KK is compared with a reliability threshold WXy:
if the risk coefficient WX is smaller than the reliable threshold WXy, generating an unreliable instruction and sending the unreliable instruction to an alarm regulation module;
if the risk coefficient WX is more than or equal to the reliable threshold WXy, a reliable instruction is generated and sent to the alarm regulation and control module.
The invention has the beneficial effects that:
according to the reliability determination method of the automatic driving system, a parameter acquisition instruction is generated in the driving process of an analysis object through a determination platform, the analysis parameter of the analysis object is acquired through a data acquisition module, a detection instruction is generated through an information analysis module according to the analysis parameter, and a sounding alarm and a lighting display are performed through an alarm regulation module according to the detection instruction; according to the reliability determination method, an automobile provided with an automatic driving system is used as a test vehicle, an actual driving scene is selected on the spot, a preset route is randomly generated in the simulation scene, and then an analysis object is analyzed;
the method comprises the steps that a dangerous coefficient is obtained through a data acquisition module, the dangerous coefficient is used for measuring the dangerous degree of an analysis object and a preselected object, the greater the dangerous coefficient is, the higher the dangerous degree is, the dangerous value is obtained through the dangerous coefficient, the dangerous value is used for representing the number of times of occurrence of the high dangerous degree, the dangerous speed value is obtained through the data acquisition module, the dangerous speed value is used for the comprehensive value of running at the dangerous running speed, the degree of running at the analysis object for a long time at the dangerous speed is represented, the greater the dangerous speed value is, the greater the degree of running at the dangerous speed is represented, the graph value is obtained through the data acquisition module, the greater the graph value is used for measuring the degree of deviation of an actual running route of the analysis object from a preset route, the greater the degree of deviation of the graph value is represented by the graph value, the information analysis module is used for comprehensively processing the dangerous value, the dangerous speed value and the graph value to obtain a reliable coefficient, the greater the reliable coefficient is used for measuring the reliability of automatic driving of the analysis object, and the smaller the reliable coefficient is represented by the reliability of automatic driving; the reliability determination method can analyze the actual running condition of the analysis object by collecting the actual running condition in real time to obtain the reliability coefficient so as to judge the reliability of the analysis object, and has the advantages of high intelligent degree, high reliability and high accuracy.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a schematic block diagram of a reliability determination method of an automatic driving system in the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: referring to fig. 1, the present embodiment is a reliability determining method of an autopilot system, including the following modules: the system comprises a data acquisition module, a determination platform, an information analysis module and an alarm regulation module, wherein:
the system comprises a determining platform, a data acquisition module and a control module, wherein the determining platform is used for controlling an analysis object to run according to a preset route, generating a parameter acquisition instruction in the running process of the analysis object and sending the parameter acquisition instruction to the data acquisition module, wherein the parameter acquisition instruction comprises an acquisition instruction, an analysis instruction and a forming instruction;
the data acquisition module is used for acquiring analysis parameters of an analysis object after receiving the parameter acquisition instruction and sending the analysis parameters to the information analysis module, wherein the analysis parameters comprise a risk value WC, a risk value WS and a graph value TX;
the information analysis module is used for generating a detection instruction according to the analysis parameters and sending the detection instruction to the alarm regulation module, wherein the detection instruction comprises an unreliable instruction and a reliable instruction;
and the alarm regulation and control module is used for sounding an alarm and displaying a lighting lamp according to the detection instruction.
Example 2: referring to fig. 1, the present embodiment is a reliability determining method of an autopilot system, comprising the following steps:
step one: the method comprises the steps that a determining platform marks an automobile provided with an automatic driving system as an analysis object, a current position is set as a starting point, a randomly selected position is set as an end point, a preset route is obtained through the starting point and the end point, the automatic driving system controls the analysis object to run according to the preset route, an acquisition instruction is generated when the analysis object is started, and the acquisition instruction is sent to a data acquisition module;
step two: the data acquisition module receives the acquisition instruction and acquires all barriers including people, animals, motor vehicles, guardrails and the like within a preset range of the analysis object, marks the barrier closest to the analysis object as a preselected object, acquires the distance between the analysis object and the preselected object and marks the distance as a distance value JL, sets the moving direction of the analysis object as a positive direction, acquires the moving speed of the preselected object and marks the moving speed as a moving speed value YS,substituting the distance value JL and the shift speed value YS into a formula
Obtaining a risk coefficient WX, wherein q1 and q2 are preset proportional coefficients of a distance value JL and a shift speed value YS respectively, and q1 is more than q2 is more than 1.326;
step three: the data acquisition module compares the risk coefficient WX to a risk threshold WXy:
if the risk coefficient WX is larger than the risk threshold WXy, generating a risk instruction, acquiring the number of times of generating the risk instruction and marking the number of times as a risk value WC;
step four: when the running speed of the analysis object reaches a preset speed for the first time, generating an analysis instruction by the determination platform, and sending the analysis instruction to the data acquisition module;
step five: the data acquisition module receives the analysis instruction and acquires the running speed of the analysis object in real time, and the running speed is compared with a preset maximum speed and a preset minimum speed respectively:
if the running speed is less than the minimum speed or the running speed is greater than the maximum speed, generating a dangerous speed instruction;
if the minimum speed is less than or equal to the running speed and less than or equal to the maximum speed, generating a constant speed instruction;
step six: the data acquisition module acquires the times of generating dangerous speed instructions and marks the times as a speed value SC, acquires the time difference between adjacent dangerous speed instructions and constant speed instructions and marks the time difference as a single-time value, does not acquire the time difference between the adjacent constant speed instructions and the dangerous speed instructions, acquires the sum of all the single-time values and marks the sum as a speed value SS, and substitutes the speed value SC and the speed value SS into a formula
Obtaining a dangerous speed value WS, wherein alpha 1 and alpha 2 are preset weight coefficients of a speed value SS and a speed value SC respectively, and alpha 1+alpha 2=1, alpha 1=0.52 and alpha 2=0.48 are taken;
step seven: determining that the platform generates a forming instruction when the analysis object reaches the end point, and sending the forming instruction to the data acquisition module;
step eight: the data acquisition module acquires a driving route of the analysis object after receiving the forming instruction, and draws the driving route and a preset route into a graph to acquire a drawn graph;
step nine: the data acquisition module acquires the number of intersecting points in the drawn graph and the total area of the graph formed by intersecting, marks the intersecting points as intersecting values JS and intersecting values JM respectively, and substitutes the intersecting values JS and the intersecting values JM into a formula
Obtaining a graph value TX, wherein β1 and β2 are preset weight coefficients of an intersection value JS and an intersection value JM respectively, and β1+β2=1, β1=0.35 and β2=0.65 are taken;
step ten: the data acquisition module sends the risk value WC, the risk value WS and the graphic value TX to the information analysis module;
step eleven: the information analysis module substitutes the risk value WC, the risk speed value WS and the graphic value TX into a formula
Obtaining a reliability coefficient KK, wherein δ1, δ2 and δ3 are preset weight factors of a risk value WC, a risk speed value WS and a graph value TX respectively, δ3 > δ2 > δ1 > 2.226, γ is a correction factor, and γ is 0.894;
step twelve: the information analysis module compares the reliability coefficient KK to a reliability threshold WXy:
if the risk coefficient WX is smaller than the reliable threshold WXy, generating an unreliable instruction and sending the unreliable instruction to an alarm regulation module;
if the risk coefficient WX is more than or equal to a reliable threshold WXy, generating a reliable instruction and sending the reliable instruction to an alarm regulation module;
step thirteen: the alarm regulation and control module sounds an alarm and lights a red light after receiving the unreliable instruction, and then a worker performs inspection optimization on the analysis object and lights a green light after receiving the reliable instruction.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely illustrative and explanatory of the invention, as various modifications and additions may be made to the particular embodiments described, or in a similar manner, by those skilled in the art, without departing from the scope of the invention or exceeding the scope of the invention as defined in the claims.
Claims (1)
1. The reliability determination method of the automatic driving system is characterized by comprising the following steps of:
step one: the method comprises the steps that a determining platform marks an automobile provided with an automatic driving system as an analysis object, a current position is set as a starting point, a randomly selected position is set as an end point, a preset route is obtained through the starting point and the end point, the automatic driving system controls the analysis object to run according to the preset route, an acquisition instruction is generated when the analysis object is started, and the acquisition instruction is sent to a data acquisition module;
step two: the data acquisition module receives an acquisition instruction and then acquires all barriers within a preset range of an analysis object, marks the barrier closest to the analysis object as a preselected object, acquires the distance between the analysis object and the preselected object, marks the distance as a distance value, sets the moving direction of the analysis object as a positive direction, acquires the moving speed of the preselected object, marks the moving speed as a moving speed value, and analyzes the distance value and the moving speed value to obtain a danger coefficient;
step three: the data acquisition module compares the risk coefficient with a risk threshold value:
if the risk coefficient is greater than the risk threshold, generating a risk instruction, acquiring the times of generating the risk instruction and marking the risk instruction as a risk value;
step four: when the running speed of the analysis object reaches a preset speed for the first time, generating an analysis instruction by the determination platform, and sending the analysis instruction to the data acquisition module;
step five: the data acquisition module receives the analysis instruction and acquires the running speed of the analysis object in real time, and the running speed is compared with a preset maximum speed and a preset minimum speed respectively:
if the running speed is less than the minimum speed or the running speed is greater than the maximum speed, generating a dangerous speed instruction;
if the minimum speed is less than or equal to the running speed and less than or equal to the maximum speed, generating a constant speed instruction;
step six: the data acquisition module acquires the times of generating dangerous speed instructions and marks the times as a speed value, acquires the time difference between adjacent dangerous speed instructions and constant speed instructions and marks the time difference as a single-time value, acquires the sum of all the single-time values and marks the sum as a speed value, and analyzes the speed value and the speed value to obtain a dangerous speed value;
step seven: determining that the platform generates a forming instruction when the analysis object reaches the end point, and sending the forming instruction to the data acquisition module;
step eight: the data acquisition module acquires a driving route of the analysis object after receiving the forming instruction, and draws the driving route and a preset route into a graph to acquire a drawn graph;
step nine: the data acquisition module acquires the number of intersecting points in the drawn graph and the total area of the graph formed by intersecting, marks the intersecting points as intersecting values and intersecting surface values respectively, and analyzes the intersecting values and the intersecting surface values to obtain a graph value;
step ten: the data acquisition module sends the risk value, the risk speed value and the graph value to the information analysis module;
step eleven: the information analysis module analyzes the risk value, the risk speed value and the graph value to obtain a reliable coefficient;
step twelve: the information analysis module compares the reliability coefficient to a reliability threshold:
if the risk coefficient is less than the reliable threshold value, generating an unreliable instruction and sending the unreliable instruction to an alarm regulation module;
if the risk coefficient is more than or equal to the reliability threshold value, generating a reliability instruction and sending the reliability instruction to an alarm regulation module;
step thirteen: the alarm regulation and control module sounds an alarm and lights a red light after receiving the unreliable instruction, and then a worker performs inspection optimization on the analysis object and lights a green light after receiving the reliable instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310288341.2A CN115993257B (en) | 2023-03-23 | 2023-03-23 | Reliability determination method for automatic driving system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310288341.2A CN115993257B (en) | 2023-03-23 | 2023-03-23 | Reliability determination method for automatic driving system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115993257A CN115993257A (en) | 2023-04-21 |
| CN115993257B true CN115993257B (en) | 2023-05-30 |
Family
ID=85995263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310288341.2A Active CN115993257B (en) | 2023-03-23 | 2023-03-23 | Reliability determination method for automatic driving system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115993257B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109582022A (en) * | 2018-12-20 | 2019-04-05 | 驭势科技（北京）有限公司 | A kind of automatic Pilot strategic decision-making System and method for |
| CN112433519A (en) * | 2020-11-09 | 2021-03-02 | 温州大学大数据与信息技术研究院 | Unmanned driving detection system and vehicle driving detection method |
| CN114444208A (en) * | 2022-01-28 | 2022-05-06 | 中国第一汽车股份有限公司 | Method, device, equipment and medium for determining reliability of automatic driving system |
| CN115017742A (en) * | 2022-08-08 | 2022-09-06 | 西安深信科创信息技术有限公司 | Automatic driving test scene generation method, device, equipment and storage medium |
| CN115394079A (en) * | 2022-08-23 | 2022-11-25 | 湖南汽车工程职业学院 | Automatic driving danger prediction system based on artificial intelligence |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWM563380U (en) * | 2018-01-03 | 2018-07-11 | 大陸商上海蔚蘭動力科技有限公司 | Drive risk classification and prevention system for automatic drive and active drive |
-
2023
- 2023-03-23 CN CN202310288341.2A patent/CN115993257B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109582022A (en) * | 2018-12-20 | 2019-04-05 | 驭势科技（北京）有限公司 | A kind of automatic Pilot strategic decision-making System and method for |
| CN112433519A (en) * | 2020-11-09 | 2021-03-02 | 温州大学大数据与信息技术研究院 | Unmanned driving detection system and vehicle driving detection method |
| CN114444208A (en) * | 2022-01-28 | 2022-05-06 | 中国第一汽车股份有限公司 | Method, device, equipment and medium for determining reliability of automatic driving system |
| CN115017742A (en) * | 2022-08-08 | 2022-09-06 | 西安深信科创信息技术有限公司 | Automatic driving test scene generation method, device, equipment and storage medium |
| CN115394079A (en) * | 2022-08-23 | 2022-11-25 | 湖南汽车工程职业学院 | Automatic driving danger prediction system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115993257A (en) | 2023-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110675656B (en) | Intelligent vehicle lane change early warning method based on instantaneous risk identification | |
| US8077921B2 (en) | Apparatus for determining the presence of fog using image obtained by vehicle-mounted imaging device | |
| US8786697B2 (en) | Apparatus for determining the presence of fog using image obtained by vehicle-mounted imaging device | |
| EP2214149A2 (en) | Collision avoidance assisting system for vehicle | |
| JP2009509085A (en) | Vehicle start control method and driver support system based on sensor | |
| JP2002083297A (en) | Object recognition method and object recognition device | |
| JP2006184276A (en) | All-weather obstacle collision preventing device by visual detection, and method therefor | |
| JP6700373B2 (en) | Apparatus and method for learning object image packaging for artificial intelligence of video animation | |
| JPH0765294A (en) | Preventive safety device for vehicle | |
| CN112440910B (en) | Method and device for evaluating intelligent driving automobile | |
| JP2005092285A (en) | Vehicle driving status estimating device and driver's vehicle driving characteristic estimating device | |
| CN111610191B (en) | Road detection and repair system | |
| CN113050615B (en) | Driving safety control method and device, electronic equipment and storage medium | |
| CN115993257B (en) | Reliability determination method for automatic driving system | |
| CN114140767A (en) | Road surface detection method, device, equipment and storage medium | |
| JP2019125185A (en) | Passage-of-vehicle propriety determination method | |
| KR102130669B1 (en) | Response system and method to secure running vehicles on a bridge against strong wind | |
| CN112699748A (en) | Human-vehicle distance estimation method based on YOLO and RGB image | |
| CN108614579B (en) | Early warning method for collision avoidance overhead alternating current power line of unmanned aerial vehicle | |
| JP6681965B2 (en) | Apparatus and method for extracting learning target image for autonomous driving | |
| CN116620296B (en) | Danger avoiding method and system for intelligent automobile | |
| CN116594373B (en) | Automatic driving safety test system and method based on 5G technology | |
| CN117765796B (en) | Automatic driving teaching system, method and device | |
| CN117010754A (en) | Method and device for evaluating tunnel complexity driven by demand | |
| CN117197766A (en) | Method and device for detecting pavement pits, processor 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 201, 202, 301, No. 56-4 Fenghuang South Road, Huadu District, Guangzhou City, Guangdong Province, 510806 Patentee after: Heduo Technology (Guangzhou) Co.,Ltd. Address before: 100095 101-15, 3rd floor, building 9, yard 55, zique Road, Haidian District, Beijing Patentee before: HOLOMATIC TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| CP03 | Change of name, title or address |