CN110497914B - Method, apparatus and storage medium for developing a model of driver behavior for autonomous driving - Google Patents
Method, apparatus and storage medium for developing a model of driver behavior for autonomous driving Download PDFInfo
- Publication number
- CN110497914B CN110497914B CN201910791480.0A CN201910791480A CN110497914B CN 110497914 B CN110497914 B CN 110497914B CN 201910791480 A CN201910791480 A CN 201910791480A CN 110497914 B CN110497914 B CN 110497914B
- Authority
- CN
- China
- Prior art keywords
- change data
- driver behavior
- vehicle
- data
- behavior model
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a method, equipment and a storage medium for developing a driver behavior model for automatic driving, wherein the method comprises the following steps of (1) establishing a basic model in a simulation environment according to a transfer relation between excitation input and theoretical output; (2) intervening the target vehicle in a field test scene by using the same excitation input as the basic model, and acquiring real output data of the target vehicle under the excitation input in the field test scene, wherein the real output data comprises target vehicle driver decision data and target vehicle operation change data; (3) and correcting the basic model by using the acquired real output data of the target vehicle in the field test scene. Compared with the method for training and acquiring the driver behavior model from massive data based on AI technical analysis in the prior art, the method provided by the invention is different, the driver behavior model approaching to the real driver behavior to the maximum extent is acquired, and an end-to-end algorithm and scheme are effectively extracted.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a method, equipment and a storage medium for developing a driver behavior model for automatic driving.
Background
The automatic driving vehicle is also called as unmanned vehicle, and is an intelligent vehicle for realizing unmanned driving through a computer system, and the intelligent vehicle is cooperated with an artificial intelligence system, a vision calculation system, a radar system, a monitoring device and a global positioning system, so that the computer system of the vehicle can automatically and safely operate the motor vehicle under the unmanned operation condition.
At present, some internet enterprises and automobile manufacturers rely on artificial intelligence or deep learning methods to obtain a prediction and decision model algorithm of an automatic driving vehicle, and the realization theory is as follows: road data in a driving scene is acquired through vehicle-mounted sensors (such as a video camera, a radar sensor, a laser range finder and the like), driver behavior data is acquired from the driving process of a vehicle, so that big data covering the scene and the driver behavior are formed, the scene and the driver behavior data are analyzed through AI, and accordingly, the algorithm is continuously iterated to finally obtain a solution from perception to execution of E2E. However, in practical situations, no matter how large amount of data has been collected by Waymo or domestic host computer factories, no effective end-to-end solution algorithm or scheme has been extracted, and the following two main reasons are considered for the reason: firstly, each scene is unique, and all scenes generated every moment on the earth cannot be exhausted in quantity; secondly, AI analysis cannot evaluate the behavior of surrounding vehicles (e.g., whether it is safe, efficient, compliant, etc.) based on data collected by sensors, and even continuous scene classification is difficult to achieve.
Disclosure of Invention
The embodiment of the invention provides a method, equipment and a storage medium for developing a driver behavior model for automatic driving, which are used for solving the problem that the driver behavior model developed in the existing automatic driving technology cannot effectively extract an end-to-end solution algorithm and scheme.
In order to solve the above technical problems, the present invention provides a driver behavior model development method for automatic driving, which includes the steps of,
(1) creating a base model in the simulation environment according to a transfer relationship between the excitation input and the theoretical output;
(2) intervening the target vehicle in a field test scene by using the same excitation input as the basic model, and acquiring real output data of the target vehicle under the excitation input in the field test scene, wherein the real output data comprises target vehicle driver decision data and target vehicle operation change data;
(3) and correcting the basic model by using the acquired real output data of the target vehicle in the field test scene.
In a preferred embodiment of the present invention, the step (3) of modifying the base model further comprises,
and judging whether the real output data of the target vehicle is different from the theoretical output in the field test scene, if so, updating the theoretical output data by using the real output data, and correcting the basic model by using the updated theoretical output data.
In a preferred embodiment of the present invention, further comprising said excitation input comprises an operational change parameter of the surrounding vehicle.
In a preferred embodiment of the present invention, the incentive input further comprises road traffic information parameters and environmental information parameters.
In a preferred embodiment of the present invention, the environment information parameter further includes one or any combination of illuminance, weather, temperature, humidity, wind direction and wind speed; the road traffic information parameters comprise one or any combination of urban main road traffic information parameters, suburban road traffic information parameters, national road traffic information parameters, provincial road traffic information parameters and high-speed traffic information parameters.
In a preferred embodiment of the present invention, the incentive input further comprises an age parameter, a gender parameter, a physiological parameter, a psychological parameter, and a driving age parameter of the driver.
In a preferred embodiment of the present invention, the step (2) further comprises that the target vehicle operation change data comprises one or any combination of vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration change data, accelerator opening change data and brake pedal opening change data.
In a preferred embodiment of the present invention, the operation change parameters of the surrounding vehicles further include one or any combination of vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration change data, accelerator opening change data, and brake pedal opening change data.
In order to solve the technical problem, the present invention further provides a driver behavior model development device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the above-mentioned driver behavior model development method for automatic driving.
In order to solve the above technical problem, the present invention also provides a computer-readable storage medium having stored thereon a driver behavior model development program that, when executed by a processor, implements the above-described driver behavior model development method for autonomous driving.
The method, the device and the storage medium for developing the driver behavior model for automatic driving disclosed by the embodiment of the application are different from the method for training and acquiring the driver behavior model from massive data based on AI technical analysis in the prior art. Firstly, a basic model is established in a simulation environment according to a transfer relationship between an excitation input and a theoretical output under the excitation input, secondly, a target vehicle is interfered by the excitation input in a field test scene, the real output of the target vehicle under the field test scene is obtained, finally, the basic model is corrected by the real output under the field test scene, a driver behavior model approaching to the real driver behavior to the maximum extent is obtained, and an end-to-end algorithm and scheme are effectively extracted.
Drawings
FIG. 1 is a flow chart of a method of developing a driver behavior model in a first embodiment of the invention;
FIG. 2 is a model diagram of a first field test scenario;
FIG. 3 is a model diagram of a second field test scenario;
FIG. 4 is a model diagram for a third field test scenario;
fig. 5 is a block diagram showing the configuration of a driver behavior model development apparatus in the second embodiment of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
The present embodiment discloses a driver behavior model development method for automatic driving, which, as shown in fig. 1, includes the following steps,
(1) a base model is created in a simulation environment based on a transfer relationship between excitation inputs and theoretical outputs.
The theoretical output here is the driving behavior that a basic model creator judges in advance that there is a driving age of 4-10 years, and that driving behavior is good within the driving age, and experienced drivers make under the driving environment of the incentive input.
The excitation input here includes one or any combination of the following:
(A) the running variation parameters of the vehicles located around the target vehicle in the driving environment (including the front-rear direction of the same lane, the parallel running position of the left and right adjacent lanes, and the front-rear direction of the left and right adjacent lanes). Here, the operation change parameter of the surrounding vehicle includes one or any combination of vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration change data, accelerator opening change data, and brake pedal opening change data.
(B) Road traffic information parameters and environmental information parameters. The road traffic information parameter comprises one or any combination of an urban main road traffic information parameter, a suburban road traffic information parameter, a national road traffic information parameter, a provincial road traffic information parameter and a high-speed traffic information parameter; the environmental information parameter herein includes one or any combination of illuminance, weather, temperature, humidity, wind direction and wind speed.
(C) Age parameter, gender parameter, physiological parameter, psychological parameter and driving age parameter of the driver.
(D) A vehicle type parameter.
The base model creator creates a base model in a simulation environment based on a transfer relationship between an excitation input and a theoretical output at the excitation input.
(2) Intervening the target vehicle in the field test scenario using the same excitation input as the base model was created, and obtaining real output data of the target vehicle at the excitation input in the field test scenario, the real output data including target vehicle driver decision data and target vehicle operational change data. The target vehicle operation change data here includes one or any combination of vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration change data, accelerator opening change data, and brake pedal opening change data.
The key here is the setting of the field test scenario: the field test scene is designed according to experience and typical scenes of Chinese roads collected all year round, and comprises key elements such as road types, vehicle types, weather conditions, vehicle distribution conditions, vehicle behaviors and the like. Before the test is started, a test outline is compiled according to the requirements of the development of a driver behavior model, and the outline content comprises the contents of data acquisition definition, a single-scene vehicle operation change mode, a combined-scene vehicle operation change mode and the like. During testing, the test responsible person instructs the test vehicle (or called as 'surrounding vehicle') to change the running mode according to the requirements of the test outline, and the running mode is used as an incentive to collect the coping mode of the driver of the tested vehicle (or called as 'target vehicle'), including decision data of the driver and running change data of the tested vehicle.
(3) And correcting the basic model by using the acquired real output data of the target vehicle in the field test scene. The correction process comprises the steps of judging whether real output data and theoretical output of the target vehicle in a field test scene are different, if so, updating the theoretical output data by using the real output data, and correcting the basic model by using the updated theoretical output data.
Referring to fig. 2, a non-threat vehicle following scene model is shown:
under the scene of a field test SC1, the acceleration or deceleration of the vehicle is controlled by sensing the speed of the front vehicle, the distance between the accelerometers and other relevant information, so that the vehicle and the front vehicle are ensured to be kept at a safe and comfortable distance dx.
Under the scenario of the field test SC2, the host vehicle can maintain a certain safe vehicle distance ds at an acceptable deceleration and the preceding vehicle even if the preceding vehicle makes a certain degree of emergency braking without any precursor.
Here, the host vehicle needs to acquire at least data including: firstly, the speed of a front vehicle in the last time period; acceleration of the front vehicle in the last time period; the distance between the vehicle and the front vehicle in the previous time period; fourthly, estimating the parking distance of the front vehicle under the current speed; and fifthly, estimating the parking distance of the vehicle under the current speed. And outputs at least the following data: firstly, keeping the distance between the vehicle and the front vehicle in the current time period; acceleration of the vehicle in the current time period; and the speed of the vehicle in the current time period.
Under the scene of the field test SC1, the difference correction of the acceleration and deceleration strategies, the difference correction of the limiting experience value (or called a threshold experience value) and the like are included under the condition that the distance between the vehicle and the vehicle in front is kept. For example, in the field test SC1 scenario, when the host vehicle employs a deceleration strategy and an acceleration strategy is employed when creating the base model, the acceleration strategy is updated using the deceleration strategy in the scenario, and the base model is updated using the transfer relationship between the excitation input and the updated acceleration strategy in the scenario.
The scene of the field test SC2 includes the deceleration strategy difference correction and deceleration empirical value difference correction adopted by the host vehicle after the emergency braking of the front vehicle. For example, in the field test SC2 scenario, when the host vehicle deceleration is a1 and the base model is created, the host vehicle deceleration at the excitation input is a2(a2 is not equal to a1), the deceleration a1 is updated with the deceleration a2 in the scenario, and the base model is updated using the transfer relationship between the excitation input and the updated deceleration a2 in the scenario.
Referring to FIG. 3, a following scene model under a short-distance CUT-IN threat is shown:
under the scene of a field test SC3, the lane change intention of an abnormal vehicle in an adjacent lane is predicted by sensing the running track of the abnormal vehicle, and the full-authority hidden danger caused by the random lane change of the adjacent vehicle is avoided by actively shortening the distance between the vehicle and a front vehicle, and the vehicle and the front vehicle are finally maintained at a safe and compact vehicle distance dx.
On-site measurementUnder the scene of test SC4, even if the front vehicle does some emergency braking without any precursor, the vehicle can avoid by changing the lane and maintain a certain safe distance d between the front vehicle and the rear vehicle in the new laneFR，dRR。
Here, the host vehicle needs to acquire at least data including: firstly, changing the speed and the acceleration of a lane-changing vehicle in front of the lane-changing vehicle for N time periods; the distance between the front vehicle and the front vehicle in N time periods and the variation amplitude before the lane changing vehicle are changed; the distance between the vehicle and the front vehicle in the previous time period; fourthly, estimating the parking distance of the front vehicle under the current speed; possibility area of adjacent lane.
And outputs at least the following data: firstly, keeping the distance between the vehicle and the front vehicle in the current time period; acceleration of the vehicle in the current time period; the speed of the vehicle in the current time period; fourthly, the transverse position of the vehicle in the lane in the current time period.
The scene of the field test SC3 comprises the difference correction and the difference correction of the change rule function of the empirical vehicle distance values kept by the vehicle and the front vehicle under the condition that the front vehicle has different speeds.
Under the scene of the field test SC3, the situation comprises lateral control strategy difference correction, yaw rate empirical value difference correction, change rate difference correction and the like which are adopted by the host vehicle after the host vehicle brakes at different levels.
Referring to FIG. 4, it shows an active lane-changing overtaking scene model of the vehicle
Under the scene of a field test SC5, the vehicle is longitudinally and transversely controlled by sensing all relevant information such as the speed, the acceleration, the distance and the like of a front vehicle, a rear vehicle and an adjacent front vehicle, so that the vehicle and the adjacent vehicle are kept at a safe and comfortable distance (-dx, dRR and the like), and the vehicle can safely change to an expected adjacent lane even if the front vehicle carries out emergency braking to a certain extent without any precursor.
Here, the host vehicle needs to acquire at least data including: firstly, the speed of the car to be overtaken in the last time period;
secondly, the acceleration of the vehicle to be overtaken in the last time period is measured; the distance between the vehicle and the vehicle to be overtaken in the previous time period; fourthly, the speed of the to-be-driven vehicle in the last time period is advanced; the acceleration of the to-be-driven vehicle in the last time period is advanced; sixthly, the distance between the vehicle and the vehicle to be advanced in the last time period; seventhly, estimating the parking distance of the front vehicle at the current vehicle speed; and evaluating the stopping distance of the vehicle at the current vehicle speed.
And outputs at least the following data: firstly, the distance between the vehicle and the front vehicle in the current time period; the distance between the vehicle and the overtaken vehicle in the current time period; the distance between the vehicle and the adjacent vehicle in the current time period; acceleration of the vehicle in the current time period; the speed of the vehicle in the current time period.
Under the scene of a field test SC3, the method comprises the difference correction of transverse and longitudinal control strategies adopted by the vehicle when the front vehicle and the overtaken vehicle are at different relative positions and different relative vehicle speeds, and the difference correction of related empirical values.
Referring to fig. 5, the device includes a memory, a processor, and a program stored in the memory and executable on the processor, where the program, when executed by the processor, implements the driver behavior model development method for automatic driving as shown in fig. 1.
The present embodiment also discloses a computer-readable storage medium having stored thereon a driver behavior model development program which, when executed by a processor, implements the driver behavior model development method for automated driving as shown in fig. 1.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (10)
1. A driver behavior model development method for autonomous driving, characterized by: which comprises the following steps of,
(1) creating a base model in the simulation environment according to a transfer relationship between the excitation input and the theoretical output;
(2) intervening the target vehicle in a field test scene by using the same excitation input as the basic model, and acquiring real output data of the target vehicle under the excitation input in the field test scene, wherein the real output data comprises target vehicle driver decision data and target vehicle operation change data;
(3) and correcting the basic model by using the acquired real output data of the target vehicle in the field test scene.
2. The driver behavior model development method for autonomous driving according to claim 1, characterized in that: in the step (3), the modifying the basic model comprises,
and judging whether the real output data of the target vehicle is different from the theoretical output in the field test scene, if so, updating the theoretical output data by using the real output data, and correcting the basic model by using the updated theoretical output data.
3. The driver behavior model development method for autonomous driving according to claim 1, characterized in that: the excitation input includes an operational change parameter of the surrounding vehicle.
4. The driver behavior model development method for autonomous driving according to claim 3, characterized in that: the incentive input further includes a road traffic information parameter and an environmental information parameter.
5. The driver behavior model development method for autonomous driving according to claim 4, characterized in that: the environment information parameters comprise one or any combination of illuminance, weather, temperature, humidity, wind direction and wind speed; the road traffic information parameters comprise one or any combination of urban main road traffic information parameters, suburban road traffic information parameters, national road traffic information parameters, provincial road traffic information parameters and high-speed traffic information parameters.
6. The driver behavior model development method for autonomous driving according to claim 3, characterized in that: the incentive inputs further include an age parameter, a gender parameter, a physiological parameter, a psychological parameter, and a driving age parameter of the driver.
7. The driver behavior model development method for autonomous driving according to claim 1, characterized in that: in the step (2), the target vehicle operation change data includes one or any combination of vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration change data, accelerator opening change data and brake pedal opening change data.
8. The driver behavior model development method for autonomous driving according to claim 3, characterized in that: the running change parameters of the surrounding vehicles comprise one or any combination of vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration change data, accelerator opening change data and brake pedal opening change data.
9. A driver behavior model development device characterized in that: comprising a memory, a processor and a program stored in the memory and executable on the processor, the program, when executed by the processor, implementing a driver behavior model development method for autonomous driving as claimed in any of claims 1-8.
10. A computer-readable storage medium characterized by: the computer-readable storage medium has stored thereon a driver behavior model development program which, when executed by a processor, implements the driver behavior model development method for automated driving according to any one of claims 1 to 8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910791480.0A CN110497914B (en) | 2019-08-26 | 2019-08-26 | Method, apparatus and storage medium for developing a model of driver behavior for autonomous driving |
| PCT/CN2019/123508 WO2021036083A1 (en) | 2019-08-26 | 2019-12-06 | Driver behavior model development method and device for automatic driving, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910791480.0A CN110497914B (en) | 2019-08-26 | 2019-08-26 | Method, apparatus and storage medium for developing a model of driver behavior for autonomous driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110497914A CN110497914A (en) | 2019-11-26 |
| CN110497914B true CN110497914B (en) | 2020-10-30 |
Family
ID=68589647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910791480.0A Active CN110497914B (en) | 2019-08-26 | 2019-08-26 | Method, apparatus and storage medium for developing a model of driver behavior for autonomous driving |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110497914B (en) |
| WO (1) | WO2021036083A1 (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110497914B (en) * | 2019-08-26 | 2020-10-30 | 格物汽车科技(苏州)有限公司 | Method, apparatus and storage medium for developing a model of driver behavior for autonomous driving |
| CN111505965B (en) * | 2020-06-17 | 2020-09-29 | 深圳裹动智驾科技有限公司 | Method and device for simulation test of automatic driving vehicle, computer equipment and storage medium |
| CN112180921B (en) * | 2020-09-22 | 2021-07-30 | 安徽江淮汽车集团股份有限公司 | Automatic driving algorithm training system and method |
| CN113353087B (en) * | 2021-07-23 | 2022-08-30 | 上海汽车集团股份有限公司 | Driving assistance method, device and system |
| CN113706911B (en) * | 2021-08-25 | 2023-01-03 | 娄底职业技术学院 | Automatic driving method based on digital traffic scene |
| CN113859250B (en) * | 2021-10-14 | 2023-10-10 | 泰安北航科技园信息科技有限公司 | Intelligent networking automobile information security threat detection system based on driving behavior anomaly recognition |
| CN114132333A (en) * | 2021-12-14 | 2022-03-04 | 阿维塔科技(重庆)有限公司 | Intelligent driving system optimization method and device and computer readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105460015A (en) * | 2014-09-24 | 2016-04-06 | 株式会社万都 | Automatic driving controlling system and method |
| CN107139929A (en) * | 2017-05-15 | 2017-09-08 | 北理慧动（常熟）车辆科技有限公司 | A kind of estimation of heavy fluid drive vehicle broad sense resistance coefficient and modification method |
| CN108216233A (en) * | 2017-12-28 | 2018-06-29 | 北京经纬恒润科技有限公司 | A kind of scaling method and device of self-adaption cruise system control parameter |
| CN108803607A (en) * | 2018-06-08 | 2018-11-13 | 北京领骏科技有限公司 | A kind of multifunction emulation system for automatic Pilot |
| CN109032103A (en) * | 2017-06-09 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Test method, device, equipment and the storage medium of automatic driving vehicle |
| CN109213126A (en) * | 2018-09-17 | 2019-01-15 | 安徽江淮汽车集团股份有限公司 | Autonomous driving vehicle test macro and method |
| CN109515444A (en) * | 2017-09-18 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | Method and apparatus for exporting the driving performance index of pilotless automobile |
| CN109726447A (en) * | 2018-12-10 | 2019-05-07 | 北京百度网讯科技有限公司 | Pedestrian's evacuation method, device and storage medium around automatic driving vehicle |
| CN109884916A (en) * | 2019-02-26 | 2019-06-14 | 初速度（苏州）科技有限公司 | A kind of automatic Pilot Simulation Evaluation method and device |
| CN109993849A (en) * | 2019-03-22 | 2019-07-09 | 山东省科学院自动化研究所 | A kind of automatic Pilot test scene render analog method, apparatus and system |
| CN110015306A (en) * | 2018-01-10 | 2019-07-16 | 华为技术有限公司 | Driving locus acquisition methods and device |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5895435A (en) * | 1996-03-01 | 1999-04-20 | Toyota Jidosha Kabushiki Kaisha | Vehicle drive mode estimating device, and vehicle control apparatus, transmission shift control apparatus and vehicle drive force control apparatus including drive mode estimating device |
| WO2014057648A1 (en) * | 2012-10-12 | 2014-04-17 | 日産自動車株式会社 | Vehicle travel assist apparatus |
| US9361409B2 (en) * | 2013-01-10 | 2016-06-07 | International Business Machines Corporation | Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network |
| KR101592728B1 (en) * | 2014-07-08 | 2016-02-15 | 현대자동차주식회사 | Apparatus for driving simulatation of vehicle and method thereof |
| JP6074553B1 (en) * | 2015-04-21 | 2017-02-01 | パナソニックＩｐマネジメント株式会社 | Information processing system, information processing method, and program |
| US20160314224A1 (en) * | 2015-04-24 | 2016-10-27 | Northrop Grumman Systems Corporation | Autonomous vehicle simulation system |
| CN106314438B (en) * | 2016-08-15 | 2018-09-25 | 西北工业大学 | The detection method and system of abnormal track in a kind of driver driving track |
| CN107153916A (en) * | 2017-04-30 | 2017-09-12 | 安徽中科美络信息技术有限公司 | A kind of driving behavior evaluation method clustered based on FCM with BP neural network |
| CN107235044B (en) * | 2017-05-31 | 2019-05-28 | 北京航空航天大学 | A kind of restoring method realized based on more sensing datas to road traffic scene and driver driving behavior |
| US11029693B2 (en) * | 2017-08-08 | 2021-06-08 | Tusimple, Inc. | Neural network based vehicle dynamics model |
| KR102015076B1 (en) * | 2017-11-13 | 2019-08-27 | 주식회사 소네트 | Apparatus for autonomous driving algorithm development using everyday driving data and method thereof |
| KR20190097486A (en) * | 2018-02-12 | 2019-08-21 | 슈어소프트테크주식회사 | Automobile capable estimating driving inclination, method and system for estimating driving inclination |
| CN108819948B (en) * | 2018-06-25 | 2020-05-19 | 大连大学 | Driver behavior modeling method based on reverse reinforcement learning |
| CN110155073B (en) * | 2019-05-24 | 2020-06-09 | 合肥工业大学 | Driving behavior pattern recognition method and system based on preference of driver |
| CN110497914B (en) * | 2019-08-26 | 2020-10-30 | 格物汽车科技(苏州)有限公司 | Method, apparatus and storage medium for developing a model of driver behavior for autonomous driving |
-
2019
- 2019-08-26 CN CN201910791480.0A patent/CN110497914B/en active Active
- 2019-12-06 WO PCT/CN2019/123508 patent/WO2021036083A1/en active Application Filing
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105460015A (en) * | 2014-09-24 | 2016-04-06 | 株式会社万都 | Automatic driving controlling system and method |
| CN107139929A (en) * | 2017-05-15 | 2017-09-08 | 北理慧动（常熟）车辆科技有限公司 | A kind of estimation of heavy fluid drive vehicle broad sense resistance coefficient and modification method |
| CN109032103A (en) * | 2017-06-09 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Test method, device, equipment and the storage medium of automatic driving vehicle |
| CN109515444A (en) * | 2017-09-18 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | Method and apparatus for exporting the driving performance index of pilotless automobile |
| CN108216233A (en) * | 2017-12-28 | 2018-06-29 | 北京经纬恒润科技有限公司 | A kind of scaling method and device of self-adaption cruise system control parameter |
| CN110015306A (en) * | 2018-01-10 | 2019-07-16 | 华为技术有限公司 | Driving locus acquisition methods and device |
| CN108803607A (en) * | 2018-06-08 | 2018-11-13 | 北京领骏科技有限公司 | A kind of multifunction emulation system for automatic Pilot |
| CN109213126A (en) * | 2018-09-17 | 2019-01-15 | 安徽江淮汽车集团股份有限公司 | Autonomous driving vehicle test macro and method |
| CN109726447A (en) * | 2018-12-10 | 2019-05-07 | 北京百度网讯科技有限公司 | Pedestrian's evacuation method, device and storage medium around automatic driving vehicle |
| CN109884916A (en) * | 2019-02-26 | 2019-06-14 | 初速度（苏州）科技有限公司 | A kind of automatic Pilot Simulation Evaluation method and device |
| CN109993849A (en) * | 2019-03-22 | 2019-07-09 | 山东省科学院自动化研究所 | A kind of automatic Pilot test scene render analog method, apparatus and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110497914A (en) | 2019-11-26 |
| WO2021036083A1 (en) | 2021-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110497914B (en) | Method, apparatus and storage medium for developing a model of driver behavior for autonomous driving | |
| US10636295B1 (en) | Method and device for creating traffic scenario with domain adaptation on virtual driving environment for testing, validating, and training autonomous vehicle | |
| KR101963422B1 (en) | Collision-avoidance system for autonomous-capable vehicles | |
| CN108694367B (en) | Method, device and system for establishing driving behavior model | |
| US20190023208A1 (en) | Brake prediction and engagement | |
| US11645360B2 (en) | Neural network image processing | |
| CN111301419A (en) | Reinforcement learning based method for SAE4 level automated lane change | |
| US10752253B1 (en) | Driver awareness detection system | |
| Wachenfeld et al. | Virtual assessment of automation in field operation a new runtime validation method | |
| US11138452B2 (en) | Vehicle neural network training | |
| CN113147752A (en) | Unmanned driving method and system | |
| CN112955361A (en) | Prediction of expected driving behavior | |
| CN114077541A (en) | Method and system for validating automatic control software for an autonomous vehicle | |
| US11100372B2 (en) | Training deep neural networks with synthetic images | |
| CN113071515B (en) | Movable carrier control method, device, movable carrier and storage medium | |
| US11657635B2 (en) | Measuring confidence in deep neural networks | |
| US11429843B2 (en) | Vehicle operation labeling | |
| CN115136081A (en) | Method for training at least one algorithm for a controller of a motor vehicle, method for optimizing a traffic flow in a region, computer program product and motor vehicle | |
| US11340624B2 (en) | Vehicle neural network | |
| CN115176297A (en) | Method for training at least one algorithm for a control unit of a motor vehicle, computer program product and motor vehicle | |
| CN116901963A (en) | Brake control method and device for automatic driving vehicle, vehicle and medium | |
| CN114222689A (en) | Method for quantifying extreme traffic behavior | |
| US11745766B2 (en) | Unseen environment classification | |
| US10977783B1 (en) | Quantifying photorealism in simulated data with GANs | |
| US20220207348A1 (en) | Real-time neural network retraining |
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 |