CN108549366B - Intelligent automobile road driving and virtual test parallel mapping experimental method - Google Patents
Intelligent automobile road driving and virtual test parallel mapping experimental method Download PDFInfo
- Publication number
- CN108549366B CN108549366B CN201810417326.2A CN201810417326A CN108549366B CN 108549366 B CN108549366 B CN 108549366B CN 201810417326 A CN201810417326 A CN 201810417326A CN 108549366 B CN108549366 B CN 108549366B
- Authority
- CN
- China
- Prior art keywords
- track
- intelligent automobile
- vehicle
- scene
- safety
- 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
- 238000002474 experimental method Methods 0.000 title claims abstract description 16
- 238000013507 mapping Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 22
- 230000008447 perception Effects 0.000 claims abstract description 20
- 238000004088 simulation Methods 0.000 claims abstract description 13
- 230000006399 behavior Effects 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 238000010835 comparative analysis Methods 0.000 claims description 2
- 230000003993 interaction Effects 0.000 claims description 2
- 101150050759 outI gene Proteins 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 41
- 238000011161 development Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
Images
Classifications
-
- 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
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to an intelligent automobile road driving and virtual test parallel mapping experiment method, aiming at improving the efficiency and safety of intelligent automobile testing. Firstly, acquiring track data of a vehicle driven by a driver, perception data of an automatic driving system and planning track data (note that the intelligent vehicle does not execute the planning track at the moment); then comparing the actual track with the planned track, and searching for a scene with significant difference between the two tracks; and reconstructing the scenes through the perception information of the intelligent automobile, performing scene playback and simulation prediction, respectively calculating the safety of the two tracks, and evaluating the safety. According to the method, an automatic driving system is not needed to control the vehicle, and the intelligent vehicle can be tested and tested as long as the intelligent vehicle runs on the road (namely, a human driver operates the vehicle). The method can improve the testing efficiency and ensure the testing safety.
Description
Technical Field
The invention belongs to the technical field of intelligent automobile testing, and particularly relates to a system for searching a scene with a difference between an intelligent automobile planned path and a driver driving path in the process that a driver drives an intelligent automobile to autonomously run on an actual road, constructing the same scene in a virtual environment, and performing scene playback and simulation testing to realize testing and evaluation on the running safety of the intelligent automobile.
Background
With the development of scientific technology, the intelligent automobile based on the automatic driving technology shows huge development potential in the aspects of the improvement of traffic safety, the prevention and the treatment of traffic jam and the like, and is the direction of the development of the automobile industry and traffic operation.
The automatic driving system of the intelligent automobile consists of three modules, namely environment perception module, planning decision module and vehicle control module. The environment perception module perceives the traffic parameters of traffic participants around the vehicle and identifies traffic environment information such as mark lines, signal control, weather conditions and the like through a sensor arranged on the intelligent vehicle. The planning decision module plans the driving path of the vehicle according to the information obtained by the environment sensing module, and simultaneously makes decisions on behaviors of acceleration, deceleration and the like of the vehicle. And the vehicle control module controls the driving direction and the speed of the vehicle according to the path planning and behavior decision of the planning decision module. The three modules are mutually connected, and progress is carried out layer by layer, and finally automatic driving is realized. The invention concerns the testing of intelligent vehicle planning decision modules.
When the intelligent automobile runs on a common road, the intelligent automobile needs to cope with various complex traffic environments and weather conditions, such as mixed traffic flow environments, heavy snow and haze weather. Therefore, the intelligent vehicle must undergo a comprehensive and rigorous test before getting on the road, otherwise there will be a safety risk. Currently, testing of driving levels of smart vehicles is mainly performed by open road testing, test site testing and virtual testing. The public road test has the most real test environment, but the test scene is uncontrollable, an extremely long test period is required, and potential safety hazards exist. The reports of landes indicate that because the scenario that smart cars are to face is infinite and traffic accidents are a very rare event, if the safety of smart cars is to be proven statistically significantly higher than human driving, about 100 cars are required, 24 hours a day, and 225 years of a year round without rest test at a speed of 25 miles per hour. In addition, the public road test has higher traffic safety risk, is subject to factors such as legal policies and the like, and is difficult to develop on a large scale. The test site test is often a function test under a simple traffic scene aiming at a single vehicle under a fixed scene, and is difficult to reproduce comprehensively and truly the complex environment which is possibly met by the intelligent vehicle on the actual road. The virtual test can improve the efficiency of the test, can guarantee the security of the test at the same time, but can not guarantee the authenticity of the test scene.
The method integrates the open road test and the virtual test together, and tests and evaluates the automatic driving system of the intelligent vehicle through the parallel mapping experiment. The method provided by the invention solves the problems of potential safety hazard and low testing efficiency in public road testing, and can be used for testing the intelligent vehicle through parallel experiments as long as the intelligent vehicle provided with the environment perception and planning decision system runs on the road.
Disclosure of Invention
The method solves the technical problem that the key scenes in the driving of the intelligent vehicle are identified by comparing the actual trajectory output of the intelligent vehicle on the public road with the virtual trajectory calculated according to the planning decision of the intelligent vehicle under the specific scenes, and the automatic driving system of the intelligent vehicle is evaluated through the key scenes. Firstly, acquiring track data of a vehicle driven by a driver, perception data of an automatic driving system and planning track data; then comparing the actual track with the planned track, and searching for a scene with significant difference between the two tracks; and finally, carrying out playback and simulation prediction on the scenes to finish the safety evaluation of the intelligent vehicle.
The automatic driving system of the intelligent automobile generally comprises three modules of environment perception, decision planning and control execution. The method has the basic idea that when the intelligent automobile is driven by people on an open road, the environment sensing and planning decision module still works, but the control execution module does not work, so that a short-term planning track of the planning decision can be obtained, and because the intelligent automobile is not executed by an actuator, the intelligent automobile does not need to run according to the track, so that the real world traffic is not influenced, and the test safety is ensured. Meanwhile, the three modules of environment perception, planning decision and control execution are mapped into the virtual world, the planning track is executed in the virtual world, the dynamic state of the virtual world is influenced, closed-loop operation is formed in the virtual world, and the intelligent automobile is tested. Therefore, the method is called as a road driving and virtual testing parallel mapping experimental method, and the core idea of the method is shown in figure 3.
The invention provides an intelligent automobile road driving and virtual test parallel mapping experimental method, which comprises the following specific steps:
(1) collecting a driving track, perception information and a planning driving track given by an automatic driving system of an intelligent automobile:
acquiring a driving track given by an automatic driving system when a driver drives on an open road, wherein the driving track given by the automatic driving system comprises information such as vehicle position coordinates with time stamps, speed, steering angle and the like; acquiring perception information of an intelligent automobile, wherein the perception information comprises surrounding traffic information, environmental information and the like; acquiring a planned driving track given by an intelligent automobile through a sensing module and a planning decision module, wherein the planned driving track comprises short-term planned information such as vehicle position coordinates, speed, steering angle and the like;
(2) comparing a driving track given by an automatic driving system of the intelligent automobile with a planned driving track, and searching for a scene with a significant difference between the two tracks:
comparing and analyzing the acquired planned driving track information of the intelligent automobile and the driving track given by the automatic driving system, and screening out a scene with an obvious difference between the two tracks; at a certain momenttTwo traces are considered to be significantly different when any of the following is present:
(3) Scene playback and simulation prediction:
carrying out scene reconstruction on the scene in which the planned driving track information of the intelligent automobile in the step (2) and the driving track given by the automatic driving system have obvious difference; namely, because the environment sensing module of the intelligent automobile has a certain sensing range, and a sensing blind area can exist at the same time,in order to ensure that the reconstructed scene is consistent with the real scene as much as possible, the method is applied totScenes with significant differences in time are perceived by the vehicle's perception module over a period of timeToReconstructing the scene around the vehicle by the sensed environmental information;
after the scene reconstruction is completed, the method is carried outIs timed totIn the time period of the moment, the actual running track and the planned track of the intelligent automobile are played back, whether the two tracks have collision events with the obstacle or not is detected, the running safety index of the intelligent automobile is calculated, and meanwhile, the intelligent automobile is subjected to collision with the obstacle through traffic simulation softwaretToIn time intervals, simulating the behaviors of the intelligent automobile and other traffic participants; generating a planned driving track through an automatic driving system of the intelligent automobile based on the traffic environment information generated by the traffic simulation software, and forming real-time closed-loop interaction between the track planned by the automatic driving system and the traffic flow in the traffic simulation software; then, calculatetToAnd in a time period, the safety indexes of the actual running track and the planned running track of the intelligent automobile are obtained. Wherein,,;
(4) safety assessment of an automatic driving system of the intelligent automobile:
based on intelligent automobile actual driving track and planning track depositIn a scene with significant difference, the safety evaluation of the intelligent automobile automatic driving system is divided into two parts: one is comparative analysis of the playback track, i.e.TotSafety analysis within a time period; secondly, after the difference appears, the track of the vehicle is continuously driven for a period of time to compare and analyze, namelytToSafety analysis over a period of time. The safety analysis not only analyzes the safety of the own vehicle, but also analyzes the influence on the following fleet.
In the invention, the safety index of the intelligent automobile in driving is TCC.
In the invention, the traffic simulation software is any one of VISSIM or TESS NG.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
1. the intelligent automobile road driving and virtual test parallel mapping experiment method provided by the invention integrates two test modes of open road test and virtual test, thereby improving the test efficiency and ensuring the test safety. In the experimental method, when the intelligent automobile runs on an actual road, the intelligent automobile is controlled by a driver instead of an automatic driving system, so that the safety of the test is guaranteed, and the problem of violation of laws and regulations does not exist. Meanwhile, as long as the intelligent automobile provided with the automatic driving system runs on an actual road, data can be continuously provided for the experiment, and compared with public road tests limited by time, place and laws and regulations, the test efficiency is greatly improved.
2. According to the intelligent automobile road driving and virtual test parallel mapping experimental method provided by the invention, for a key scene with a significant difference between an actual track and a planned track, the scene is replayed through intelligent automobile sensing data, the safety of the actual path and the intelligent automobile planned path are compared, the evolution of the intelligent automobile and surrounding traffic flow within a period of time after the difference track appears is deduced through simulation software, the safety evolution situation of the actual track and the planned track in a certain period of time in the future is analyzed, and a safety evaluation method based on scene replay and future state deduction is established, so that the safety evaluation of an intelligent automobile automatic driving system is more comprehensive and reliable.
Drawings
FIG. 1 is a flow chart of an intelligent vehicle road driving and virtual test parallel mapping experiment method provided by the invention;
FIG. 2 is a schematic diagram of each judgment index in step 2 of the present invention;
FIG. 3 is a diagram of the basic idea of a parallel mapping experiment;
fig. 4 is an interface for simulation prediction of a scene using VISSIM in embodiment 1;
fig. 5 is a typical scenario example in embodiment 1.
Detailed Description
The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and examples. The present embodiment is implemented on the premise of the technical solution of the present invention, but the scope of the present invention is not limited to the following embodiments.
Example 1
The implementation place of the embodiment is Shanghai city, data obtained by driving the intelligent automobile with automatic driving on the actual road of the Shanghai city by a plurality of drivers are compared with the actual track and the planned track, the scene with obvious difference in track is searched, and the safety of the intelligent automobile is evaluated by performing a parallel mapping experiment, and the method comprises the following detailed steps:
(1) collecting the running track, perception information and planning the running track of the vehicle:
the method comprises the steps of collecting a driving track of a driver driving the intelligent automobile on an actual road in Shanghai city, wherein the driving track comprises information such as vehicle position coordinates with time stamps, speed and steering angle. The method comprises the steps of collecting perception information of the intelligent automobile, wherein the perception information comprises surrounding obstacle position information, lane information and the like. The method comprises the steps of collecting planned driving tracks of the intelligent automobile, including planned information such as position coordinates, speed and steering angles of the intelligent automobile, which are given by a sensing module and a planning decision module.
(2) Comparing the vehicle running track with the planned track, and searching two scenes with obvious difference in track:
and comparing and analyzing the acquired vehicle running track information and a planned running track given by an automatic driving system, and screening out a scene with obvious difference between the two tracks. At a certain momenttThe two traces are considered to be significantly different when either:
(3) Scene playback and simulation prediction:
and reconstructing the scenes of all the searched scenes with obvious difference between the actual trajectories and the planned trajectories. To be attScenes with significant differences in time are perceived by the vehicle's perception module over a period of timeToAnd reconstructing the scene around the vehicle by the sensed environmental information to obtain the position and speed information of each vehicle and the position information of the fixed obstacle in the scene at each moment.
And after the scene reconstruction is completed, carrying out scene playback. To pairIs timed totAnd playing back the actual running track and the planned track of the vehicle in the time period of the moment. In the playback, whether the two tracks have collision events with other vehicles or obstacles is firstly checked; then, the TTC index of each moment in the running process of the intelligent vehicle with the two tracks is calculated to obtain the minimum TTC index in the playback stage. In the event of a collision event,。
the evolution of the scene is then predicted by traffic simulation software. Using traffic simulation software VISSIM, the time when the two tracks have significant differencetThe state of the time scene is taken as the initial state, fortToAnd (4) performing simulation prediction on the behaviors of the intelligent automobile and other traffic participants in a time period. ComputingtToIn a time interval, obtaining the minimum TTC index of the prediction stage by the TTC index of each moment of the actual running track and the planned running track of the vehicle. In the event of a collision event,. In addition, the influence of the differential behavior on the whole traffic flow is calculated, so that the TTC of each vehicle in the whole fleet at each moment is calculated, and the minimum value is taken as the minimum TTC index of the fleet。
(4) Safety assessment of an automatic driving system of the intelligent automobile:
the safety performance of the automatic driving system of the intelligent automobile is evaluated from two aspects of playback and prediction through safety indexes obtained by scene playback and simulation prediction:
a) if the minimum TTC of the actual track is greater than the minimum TTC of the planned track during the playback phase, that isThe safety of the automatic driving system in the scene is lower than that of human driving; on the contrary, ifThe safety of the automatic driving system in the scene is higher than that of human driving;
b) if the difference between the safety of the two tracks in the playback scene is not large, and the minimum TTC of the actual track in the simulation prediction stage is larger than the minimum TTC of the planned track, namelyThe safety of the automatic driving system in the scene is lower than that of human driving; on the contrary, ifThe safety of the automatic driving system in the scene is higher than that of human driving;
c) if the safety difference between the two tracks of a single vehicle is not large, and the minimum TTC of the fleet of the actual tracks in the simulation prediction stage is larger than the minimum TTC of the fleet of the planned tracks, namelyThe safety of the automatic driving system in the scene is lower than that of human driving; on the contrary, ifThe safety of the automatic driving system in the scene is higher than that of human driving.
(5) A typical scenario example:
as shown in the scenario of FIG. 5, the actual trajectory of the test vehicle is the same as the planned trajectorytSignificant differences in time of day occur, so the scene is first reconstructed and then played back and predictive evaluated.
The lane change operation is performed because the driver of the test vehicle predicts the upcoming lane change behavior according to the behavior of the right front vehicle, and the automatic driving system does not predict the insertion behavior, so that the planning is made to continue running on the own lane. TTC index of actual track and planned track can be calculated by reviewing, and the stageThe safety of automatic driving at this stage is lower than that of human driving.
According to the predicted track, after the two tracks are obviously different, the actual track keeps safe running, in the predicted track, a test vehicle firstly carries out emergency braking operation due to the insertion of a front vehicle and carries out rear-end collision with the front vehicle at a different point, and the TTC is smaller than a safety threshold value; and then, the test vehicle is subjected to rear-end collision due to emergency braking operation, so that an accident occurs. This stageAnd isThe safety of automatic driving is lower than that of human driving.
Claims (3)
1. An intelligent automobile road driving and virtual test parallel mapping experimental method is characterized by comprising the following specific steps:
(1) collecting a driving track, perception information and a planning driving track given by an automatic driving system of an intelligent automobile:
acquiring a driving track given by an automatic driving system when a driver drives on an open road, wherein the driving track given by the automatic driving system comprises a vehicle position coordinate with a timestamp, a speed and a steering angle; acquiring perception information of an intelligent automobile, wherein the perception information comprises surrounding traffic flow information and environment information; acquiring a planned driving track given by an intelligent automobile through a sensing module and a planning decision module, wherein the planned driving track comprises short-term planned vehicle position coordinates, speed and steering angles;
(2) comparing a driving track given by an automatic driving system of the intelligent automobile with a planned driving track, and searching for a scene with a significant difference between the two tracks:
comparing and analyzing the acquired planned driving track information of the intelligent automobile and the driving track given by the automatic driving system, and screening out a scene with an obvious difference between the two tracks; at a certain momenttTwo traces are considered to be significantly different when any of the following is present:
(3) Scene playback and simulation prediction:
carrying out scene reconstruction on the scene in which the planned driving track information of the intelligent automobile in the step (2) and the driving track given by the automatic driving system have obvious difference; namely, because the environment sensing module of the intelligent automobile has a certain sensing range and a sensing blind area, the reconstructed scene is consistent with the real scene as far as possibletScenes with significant differences in time are perceived by the vehicle's perception module over a period of timeToReconstructing the scene around the vehicle by the sensed environmental information;
after the scene reconstruction is completed, the method is carried outIs timed totIn the time period of the moment, the actual running track and the planned track of the intelligent automobile are played back, whether the two tracks have collision events with the obstacle or not is detected, the running safety index of the intelligent automobile is calculated, and meanwhile, the intelligent automobile is subjected to collision with the obstacle through traffic simulation softwaretToIn time intervals, simulating the behaviors of the intelligent automobile and other traffic participants; traffic environment information generated based on traffic simulation software, through intelligent automobileThe automatic driving system generates a planned driving track and forms real-time closed-loop interaction between the track planned by the automatic driving system and a traffic flow in traffic simulation software; then, calculatetToIn a time period, safety indexes of an actual driving track and a planned driving track of the intelligent automobile are obtained;
(4) safety assessment of an automatic driving system of the intelligent automobile:
based on the scene that the actual running track and the planned track of the intelligent automobile have obvious difference, the safety evaluation of the automatic driving system of the intelligent automobile is divided into two parts: one is comparative analysis of the playback track, i.e.TotSafety analysis within a time period; secondly, after the difference appears, the track of the vehicle is continuously driven for a period of time to compare and analyze, namelytToSafety analysis within a time period; the safety analysis not only analyzes the safety of the own vehicle, but also analyzes the influence on the following fleet.
2. The method as claimed in claim 1, wherein the safety index of the intelligent vehicle is TCC.
3. The intelligent automobile road driving and virtual test parallel mapping experiment method as claimed in claim 1, wherein the traffic simulation software is any one of VISSIM or TESS NG.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810417326.2A CN108549366B (en) | 2018-05-04 | 2018-05-04 | Intelligent automobile road driving and virtual test parallel mapping experimental method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810417326.2A CN108549366B (en) | 2018-05-04 | 2018-05-04 | Intelligent automobile road driving and virtual test parallel mapping experimental method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108549366A CN108549366A (en) | 2018-09-18 |
CN108549366B true CN108549366B (en) | 2020-11-10 |
Family
ID=63513206
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810417326.2A Active CN108549366B (en) | 2018-05-04 | 2018-05-04 | Intelligent automobile road driving and virtual test parallel mapping experimental method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108549366B (en) |
Families Citing this family (41)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109358526B (en) * | 2018-10-15 | 2021-10-08 | 清华大学苏州汽车研究院(吴江) | Software in-loop testing method of automatic driving tracking algorithm based on simulation |
CN111090915B (en) * | 2018-10-19 | 2023-12-15 | 百度在线网络技术(北京)有限公司 | Automatic driving simulation method, device and storage medium |
CN109255341B (en) * | 2018-10-30 | 2021-08-10 | 百度在线网络技术(北京)有限公司 | Method, device, equipment and medium for extracting obstacle perception error data |
CN111123731B (en) * | 2018-10-31 | 2022-12-02 | 阿波罗智能技术(北京)有限公司 | Method, device, storage medium and terminal equipment for simulating automatic driving vehicle |
CN111179585B (en) * | 2018-11-09 | 2021-12-07 | 上海汽车集团股份有限公司 | Site testing method and device for automatic driving vehicle |
CN109520744B (en) * | 2018-11-12 | 2020-04-21 | 百度在线网络技术(北京)有限公司 | Driving performance testing method and device for automatic driving vehicle |
CN109598066B (en) * | 2018-12-05 | 2023-08-08 | 百度在线网络技术(北京)有限公司 | Effect evaluation method, apparatus, device and storage medium for prediction module |
CN109557904B (en) * | 2018-12-06 | 2020-07-10 | 百度在线网络技术(北京)有限公司 | Test method, device, equipment and medium |
CN109375630A (en) * | 2018-12-06 | 2019-02-22 | 上海智梯信息科技有限公司 | A kind of intelligent driving test track seeking system and method |
CN111462475B (en) * | 2019-01-18 | 2021-12-10 | 上汽通用汽车有限公司 | Real-time interactive dynamic traffic flow test system |
CN109886474B (en) * | 2019-01-24 | 2023-02-10 | 同济大学 | Closed test field planning method for automatic driving vehicle test |
CN109765803A (en) * | 2019-01-24 | 2019-05-17 | 同济大学 | A kind of the simulation hardware test macro and method of the synchronic sky of the more ICU of autonomous driving vehicle |
CN109933856B (en) * | 2019-02-19 | 2023-07-07 | 百度在线网络技术(北京)有限公司 | Automatic driving decision planning data reproduction method and device |
CN109885929B (en) * | 2019-02-19 | 2023-07-07 | 百度在线网络技术(北京)有限公司 | Automatic driving decision planning data reproduction method and device |
CN110288160A (en) * | 2019-06-27 | 2019-09-27 | 北京华如科技股份有限公司 | A kind of situation dynamic prediction method based on parallel simulation |
CN110595798B (en) * | 2019-09-19 | 2022-04-05 | 北京百度网讯科技有限公司 | Test method and device |
CN110782125B (en) * | 2019-09-23 | 2023-05-02 | 同济大学 | Road safety risk assessment method for automatic driving automobile |
CN110781578B (en) * | 2019-09-23 | 2024-03-29 | 同济大学 | Intelligent network coupling algorithm testing and evaluating method based on accident scene |
CN110758403B (en) * | 2019-10-30 | 2022-03-01 | 北京百度网讯科技有限公司 | Control method, device, equipment and storage medium for automatic driving vehicle |
CN113112643A (en) * | 2020-01-13 | 2021-07-13 | 北京地平线机器人技术研发有限公司 | Evaluation method and device for predicted trajectory, electronic device and storage medium |
US11814080B2 (en) | 2020-02-28 | 2023-11-14 | International Business Machines Corporation | Autonomous driving evaluation using data analysis |
CN111367283B (en) * | 2020-03-11 | 2023-04-14 | 郴州职业技术学院 | Unmanned vehicle obstacle avoidance method and system based on obstacle configuration reconstruction |
CN111551382A (en) * | 2020-05-12 | 2020-08-18 | 中国科学院心理研究所 | System for testing vehicle distance control capability of driver and using method |
CN111767651B (en) * | 2020-06-28 | 2023-07-25 | 北京百度网讯科技有限公司 | Index prediction model construction method, index prediction method and device |
CN111879319B (en) * | 2020-06-29 | 2023-10-20 | 中国科学院合肥物质科学研究院 | Indoor test method and system for ground unmanned platform and computer equipment |
CN111914412B (en) * | 2020-07-21 | 2023-07-04 | 同济大学 | Automatic drivability limitation testing system and method based on error injector |
WO2022027304A1 (en) * | 2020-08-05 | 2022-02-10 | 华为技术有限公司 | Testing method and apparatus for autonomous vehicle |
CN112286206B (en) * | 2020-11-17 | 2024-01-23 | 苏州智加科技有限公司 | Automatic driving simulation method, system, equipment, readable storage medium and platform |
CN112307642B (en) * | 2020-11-17 | 2022-09-16 | 苏州智加科技有限公司 | Data processing method, device, system, computer equipment and storage medium |
CN112527633B (en) * | 2020-11-20 | 2021-10-01 | 北京赛目科技有限公司 | Automatic driving simulation test method and device for scene library |
CN112581633A (en) * | 2020-12-24 | 2021-03-30 | 北京亮道智能汽车技术有限公司 | In-loop virtual simulation test method and system for vehicle with automatic driving function |
CN112816954B (en) * | 2021-02-09 | 2024-03-26 | 中国信息通信研究院 | Road side perception system evaluation method and system based on true value |
CN113065685B (en) * | 2021-03-01 | 2023-10-17 | 沃行科技(南京)有限公司 | High-precision map traffic rule model based on automatic driving application scene and implementation method thereof |
CN112926135B (en) * | 2021-03-02 | 2024-01-23 | 北京百度网讯科技有限公司 | Scene information determination method, apparatus, device, storage medium, and program product |
CN113779864B (en) * | 2021-08-06 | 2024-04-26 | 同济大学 | Method and device for constructing running design area for automatic driving automobile |
CN113610166B (en) * | 2021-08-10 | 2023-12-26 | 吉林大学 | Method for establishing test scene library for intelligent vehicle |
CN113949996B (en) * | 2021-10-11 | 2022-10-28 | 重庆大学 | Data processing method and system for acquisition and playback of vehicle-road cooperative test scene |
CN114627640B (en) * | 2022-01-21 | 2023-07-28 | 中国科学院深圳先进技术研究院 | Dynamic evolution method of intelligent network-connected automobile driving strategy |
CN114563196B (en) * | 2022-02-22 | 2022-12-16 | 上清童子(北京)投资顾问有限公司 | Method for checking usability and reliability of automatic driving automobile |
CN114838948B (en) * | 2022-03-04 | 2024-05-17 | 湖北国际物流机场有限公司 | Automatic merging test method and system for airport automatic driving guided vehicle |
CN114822042B (en) * | 2022-06-28 | 2022-09-02 | 深圳市华耀商品检验有限公司 | Information security test management system and method for vehicle-mounted terminal detection |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7330722B1 (en) * | 2004-03-03 | 2008-02-12 | At&T Corp. | System and method for testing automated provisioning and maintenance of Operations Support Systems |
CN102610092A (en) * | 2012-03-23 | 2012-07-25 | 天津大学 | Urban road speed predication method based on RBF (radial basis function) neural network |
CN106053091B (en) * | 2016-02-02 | 2018-07-06 | 北京理工大学 | A kind of piggyback pod comprehensive test device and test method based on virtual scene |
CN105788400B (en) * | 2016-03-07 | 2018-11-23 | 兵器工业卫生研究所 | A kind of special vehicle people-machine-environment comprehensive experimental system for simulating |
CN106991811B (en) * | 2017-05-03 | 2019-07-05 | 同济大学 | Expressway exit ring road upstream trackside road information optimum design method based on drive simulation experiment porch |
CN107506830A (en) * | 2017-06-20 | 2017-12-22 | 同济大学 | Towards the artificial intelligence training platform of intelligent automobile programmed decision-making module |
CN107403038B (en) * | 2017-07-05 | 2020-10-30 | 同济大学 | Intelligent automobile virtual rapid test method |
CN107315407B (en) * | 2017-08-31 | 2019-10-29 | 中国第一汽车股份有限公司 | A kind of automotive motor controller emulation test system |
-
2018
- 2018-05-04 CN CN201810417326.2A patent/CN108549366B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN108549366A (en) | 2018-09-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108549366B (en) | Intelligent automobile road driving and virtual test parallel mapping experimental method | |
CN109242251B (en) | Driving behavior safety detection method, device, equipment and storage medium | |
Zhou et al. | A framework for virtual testing of ADAS | |
CN112258841B (en) | Intelligent vehicle risk assessment method based on vehicle track prediction | |
CN114077541A (en) | Method and system for validating automatic control software for an autonomous vehicle | |
CN110781578B (en) | Intelligent network coupling algorithm testing and evaluating method based on accident scene | |
CN112819968B (en) | Test method and device for automatic driving vehicle based on mixed reality | |
CN113378305B (en) | Driverless trolley-based vehicle-road cooperative testing method and device | |
CN107871418A (en) | It is a kind of to be used to evaluate the man-machine experiment porch for driving reliability altogether | |
CN110047276A (en) | Method and device for determining congestion state of obstacle vehicle and related product | |
CN113887037B (en) | Automatic driving system evaluation method under network environment with different permeability | |
Plavšić et al. | Situation awareness assessment in critical driving situations at intersections by task and human error analysis | |
JP4814816B2 (en) | Accident occurrence prediction simulation apparatus, method and program, safety system evaluation apparatus and accident alarm apparatus | |
Yuan et al. | Key points of investigation and analysis on traffic accidents involving intelligent vehicles | |
CN112288023A (en) | Modeling method for aggressive driving recognition based on simulated driver and SVM algorithm | |
Yu et al. | The benefit of simulation test application on the development of autonomous driving system | |
CN108447306B (en) | Simulation method for real-time position sharing collision avoidance early warning among collision vehicles at uncontrolled intersection | |
Hu et al. | Automatic generation of intelligent vehicle testing scenarios at intersections based on natural driving datasets | |
Knodler Jr et al. | Tracking driver eye movements at permissive left-turns | |
You et al. | Using eye-tracking to help design HUD-based safety indicators for lane changes | |
CN115743172A (en) | High-interaction scene automatic driving decision method and system for simulating front vehicle to play game | |
Losa et al. | A procedure for validating fixed-base driving simulators | |
CN114872734A (en) | Automatic driving emergency decision-making method | |
CN109284889B (en) | Unmanned vehicle reaction agility evaluation method and device | |
CN106354883A (en) | Method and system for video information structure organization |
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 |