CN110497914A - Driver behavior model development approach, equipment and the storage medium of automatic Pilot - Google Patents
Driver behavior model development approach, equipment and the storage medium of automatic Pilot Download PDFInfo
- Publication number
- CN110497914A CN110497914A CN201910791480.0A CN201910791480A CN110497914A CN 110497914 A CN110497914 A CN 110497914A CN 201910791480 A CN201910791480 A CN 201910791480A CN 110497914 A CN110497914 A CN 110497914A
- Authority
- CN
- China
- Prior art keywords
- data
- driver behavior
- behavior model
- target vehicle
- automatic pilot
- 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.)
- Granted
Links
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 kind of driver behavior model development approach, equipment and storage mediums for automatic Pilot, this approach includes the following steps, and (1) creates basic model according to the transitive relation between excitation input and theoretical output in simulated environment;(2) use excitation input identical with creation basic model intervenes target vehicle in field test scene, the true output data that the excitation in field test scene inputs lower target vehicle is obtained, the true output data includes target vehicle driver decision data and target vehicle operation delta data;(3) basic model is modified using the true output data of target vehicle under the field test scene of acquisition.The present invention in the prior art based on AI technology analyze, the method of training acquisition driver behavior model is resolutely different in the data huge from magnanimity, it obtains and levels off to the driver behavior model of true driving behavior to the full extent, effectively extract algorithm and scheme end to end.
Description
Technical field
The present invention relates to automatic Pilot technical fields, and in particular to a kind of driver behavior model for automatic Pilot is opened
Forwarding method, equipment and storage medium.
Background technique
Automatic driving vehicle is also known as automatic driving vehicle, is that one kind by computer system realizes unpiloted intelligent vehicle
, artificial intelligence, vision calculating, radar, monitoring device and global positioning system cooperative cooperating are relied on, the computer system of vehicle is made
System can manipulate motor vehicles to automatic safe in the case where unattended.
Currently, some Internet enterprises and automobile vendor rely on artificial intelligence or the method for deep learning is driven automatically to obtain
The prediction and decision model algorithm, realization theory for sailing vehicle are: by onboard sensor (for example, video camera, radar pass
Sensor and airborne laser range finder etc.) obtain driving scene in road data, from vehicle travel process obtain driving behavior number
According to the big data for covering scene and driving behavior is consequently formed, analyzes scene and driving behavior data by AI, and accordingly
Continuous iterative algorithm obtains one from the E2E solution for perceiving execution at last.But actual conditions are, no matter Waymo or
Domestic main engine plants have all had collected mass data, do not extract effective end-to-end solution annual reporting law and scheme, study carefully it
Reason mainly has following two points: first, each scene be it is unique, in quantity on the earth impossible to exhaust all the time
All scenes generated;Second, the behavior for the data assessment surrounding vehicles that AI analysis cannot be acquired according to sensor is (for example, be
It is no it is safe, whether efficiently, whether close rule etc.), or even scene classification is all difficult to accomplish.
Summary of the invention
The embodiment of the present invention provides a kind of for the driver behavior model development approach of automatic Pilot, equipment and storage Jie
Matter, with solve the driver behavior model developed in existing automatic Pilot technology cannot effectively extract end to end solution annual reporting law and
Protocol questions.
In order to solve the above-mentioned technical problems, the present invention provides a kind of driver behavior model exploitations for automatic Pilot
Method comprising following steps,
(1) basic model is created in simulated environment according to the transitive relation between excitation input and theoretical output;
(2) use excitation input identical with creation basic model intervenes target vehicle in field test scene, obtains
The excitation inputs the true output data of lower target vehicle in field test scene, and the true output data includes target vehicle
Driver's decision data and target vehicle run delta data;
(3) basic model is repaired using the true output data of target vehicle under the field test scene of acquisition
Just.
It further comprise that packet is modified to the basic model in step (3) in a preferred embodiment of the present invention
It includes,
Judge under the field test scene the true output data of target vehicle and the theoretical output whether difference, if
Have, using true output data renewal theory output data, and using updated theoretical output data to the basic model
It is modified.
It further comprise the operation variation ginseng that the excitation input includes surrounding vehicles in a preferred embodiment of the present invention
Number.
In a preferred embodiment of the present invention, further comprise excitation input further include road traffic information parameter and
Environmental information parameter.
It further comprise the environmental information parameter include illuminance, weather, temperature in a preferred embodiment of the present invention
One of degree, humidity, wind direction, wind speed or any combination;The road traffic information parameter includes the main road traffic letter in city
Cease parameter, rural road traffic information parameter, national highway traffic information parameter, provincial highway traffic information parameter, high-speed transit information ginseng
One of number or any combination.
In a preferred embodiment of the present invention, further comprise it is described excitation input further include driver age parameter,
Gender parameter, physiological parameter, psychological parameter and driving age parameter.
It further comprise in step (2), it includes vehicle that target vehicle, which runs delta data, in a preferred embodiment of the present invention
Change in location data, speed change data, acceleration change data, steering angle delta data, yaw velocity delta data,
One of side acceleration delta data, accelerator open degree delta data, brake pedal aperture delta data or any combination.
It further comprise the operation running parameter of the surrounding vehicles include vehicle position in a preferred embodiment of the present invention
Set delta data, speed change data, acceleration change data, steering angle delta data, yaw velocity delta data, lateral
One of acceleration change data, accelerator open degree delta data, brake pedal aperture delta data or any combination.
In order to solve the above-mentioned technical problem, the present invention also provides a kind of driver behavior model development equipments, including deposit
In the memory and the program that can run on the processor, described program is by the place for reservoir, processor and storage
Reason device realizes the above-described driver behavior model development approach for automatic Pilot when executing.
In order to solve the above-mentioned technical problem, the present invention also provides a kind of computer readable storage medium, the computers
Driver behavior model exploitation program is stored on readable storage medium storing program for executing, the driver behavior model exploitation program is by processor
The above-described driver behavior model development approach for automatic Pilot is realized when execution.
The embodiment of the present application is disclosed to be situated between for the driver behavior model development approach of automatic Pilot, equipment and storage
Matter is analyzed, the method that training obtains driver behavior model in the data huge from magnanimity with AI technology is based in the prior art
It is resolutely different.Firstly, according to the transitive relation between the theoretical output under excitation input and excitation input in simulated environment
Basic model is created, intervenes target vehicle secondly, inputting in field test scene with the excitation, obtains under field test scene
The true output of target vehicle is obtained most finally, being modified using the true output under field test scene to basic model
It levels off to the driver behavior model of true driving behavior in big degree, effectively extracts algorithm and scheme end to end.
Detailed description of the invention
Fig. 1 is the flow chart of driver behavior model development approach in first embodiment of the invention;
Fig. 2 is the illustraton of model under the first field test scene;
Fig. 3 is the illustraton of model under second of field test scene;
Fig. 4 is the illustraton of model under the third field test scene;
Fig. 5 is the structural block diagram of driver behavior model development equipment in second embodiment of the invention.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples, so that those skilled in the art can be with
It more fully understands the present invention and can be practiced, but illustrated embodiment is not as a limitation of the invention.
The present embodiment discloses a kind of driver behavior model development approach for automatic Pilot, and shown referring to Fig.1, this is opened
Forwarding method includes the following steps,
(1) basic model is created in simulated environment according to the transitive relation between excitation input and theoretical output.
Theoretical output herein for basic model creation person's anticipation have 4~10 year driving age and within the driving age driving behavior it is good
The driving behavior that good, experienced driver makes under the driving environment that the excitation inputs.
Excitation input herein includes one of or any combination:
(A) be located at around target vehicle in driving environment (including with lane front-rear direction, left and right adjacent lane parallel position
Set and left and right adjacent lane front-rear direction) vehicle operation running parameter.The operation running parameter packet of surrounding vehicles herein
Include vehicle location delta data, speed change data, acceleration change data, steering angle delta data, yaw velocity variation
One of data, side acceleration delta data, accelerator open degree delta data, brake pedal aperture delta data or any group
It closes.
(B) road traffic information parameter and environmental information parameter.Road traffic information parameter herein includes city main stem
Road traffic information parameter, rural road traffic information parameter, national highway traffic information parameter, provincial highway traffic information parameter, high speed are handed over
One of logical information parameter or any combination;Environmental information parameter herein includes illuminance, weather, temperature, humidity, wind
To one of, wind speed or any combination.
(C) age parameter of driver, gender parameter, physiological parameter, psychological parameter and driving age parameter.
(D) type of vehicle parameter.
Basic model founder is according to the transitive relation between the theoretical output under excitation input and excitation input imitative
Basic model is created in true environment.
(2) use excitation input identical with creation basic model intervenes target vehicle in field test scene, obtains
The excitation inputs the true output data of lower target vehicle in field test scene, which includes that target vehicle is driven
The person's of sailing decision data and target vehicle run delta data.The delta data of target vehicle operation herein includes vehicle location variation number
According to, speed change data, acceleration change data, steering angle delta data, yaw velocity delta data, side acceleration become
Change one of data, accelerator open degree delta data, brake pedal aperture delta data or any combination.
Key herein is the setting of field test scene: the typical field for the Chinese road rule of thumb and throughout the year collected
Scape closes to design field test scene, including road type, type of vehicle, weather conditions, vehicle distribution situation, vehicle behavior etc.
Key element.Test is worked out according to the demand of driver behavior model exploitation before starting and tests outline, and outline content includes acquisition number
According to contents such as definition, single scene vehicle operation variation pattern, combine scenes vehicle operation variation patterns.It tests and is responsible for when test
People commands test vehicle (or " surrounding vehicles ") to change the method for operation according to the requirement of test outline, acquires in this, as excitation
The coping style of tested vehicle (or " target vehicle ") driver, decision data and tested vehicle operation including driver become
Change data.
(3) basic model is repaired using the true output data of target vehicle under the field test scene of acquisition
Just.Makeover process includes judging whether the true output data of target vehicle and theory output are poor under field test scene herein
It is different, if so, using true output data renewal theory output data, and using updated theoretical output data to basic model
It is modified.
It show referring to Fig. 2 without threat follow the bus model of place:
Under field test SC1 scene, by perceive the relevant informations such as speed, acceleration meter spacing of front truck come to this vehicle into
The control of row acceleration or deceleration, it is ensured that Ben Che and front truck are maintained at a safety, comfortable spacing dx.
Under field test SC2 scene, even if front truck does a degree of emergency braking in the case where no any omen,
This vehicle also can keep certain safe distance between vehicles ds with an acceptable deceleration and front truck.
Herein, this vehicle at least needs to obtain data and have: the 1. front truck speed of last time cycle;2. the last time cycle
Front truck acceleration;3. this vehicle of last time cycle and the spacing of front truck;4. stopping distance valuation under front truck current vehicle speed;5. this
Stopping distance valuation under vehicle current vehicle speed.And at least export following data: the vehicle that 1. this vehicle of current time period and front truck are kept
Away from;2. this vehicle acceleration of current time period;3. this vehicle speed of current time period.
It include that this vehicle in the case where keeping and front truck spacing, repair by acceleration, deceleration strategy difference under field test SC1 scene
Just, limitation empirical value (or " threshold value empirical value ") difference amendment etc..For example, this vehicle is using deceleration under field test SC1 scene
Strategy, and using acceleration strategy when creating basic model then updates acceleration strategy with deceleration strategies under the scene, and using should
Excitation input under scene and the transitive relation between updated acceleration strategy update basic model.
It include the amendment of deceleration strategies difference, deceleration that this vehicle uses after front truck emergency braking under field test SC2 scene
Spend empirical value difference amendment etc..For example, under field test SC2 scene, this vehicle deceleration is a1, and when creating basic model, it should
It is a2 (a2 is not equal to a1) that excitation, which inputs lower this vehicle deceleration, then updates deceleration a1 with deceleration a2 under the scene, and make
Basic model is updated with the excitation input under the scene and the transitive relation between updated deceleration a2.
The follow the bus model of place being shown referring to Fig. 3 under short distance CUT-IN is threatened:
Under field test SC3 scene, its lane change is predicted by the driving trace of improper vehicle in perception adjacent lane
It is intended to, and full powers hidden danger caused by the adjacent random lane change of vehicle is avoided with the distance of front truck by positive this vehicle of shortenings,
Vehicle and front truck finally will be maintained at a safety, compact spacing dx.
Under field test SC4 scene, even if front truck does a degree of emergency braking in the case where no any omen,
This vehicle can also be avoided by lane change, and maintain certain safe distance between vehicles d with the forward and backward vehicle in new laneFR, dRR。
Herein, this vehicle at least needs to obtain data and have: 1. the speed variation of lane change Chinese herbaceous peony N number of time cycle and acceleration become
Change amplitude;2. lane change Chinese herbaceous peony N number of time cycle with its leading vehicle distance and amplitude of variation;3. this Che Yuqian of last time cycle
The spacing of vehicle;4. stopping distance valuation under front truck current vehicle speed;5. adjacent lane exercises region.
And at least export following data: the spacing that 1. this vehicle of current time period and front truck are kept;2. current time period
This vehicle acceleration;3. this vehicle speed of current time period;4. lateral position of this vehicle of current time period in lane.
Include under field test SC3 scene, under front truck difference speed, the spacing empirical value difference of Ben Che and front truck holding
Amendment, the revision of changing rule function difference.
It include that the crosswise joint strategy that this vehicle uses after the different grades of braking of front truck is poor under field test SC3 scene
Different amendment, the amendment of yaw velocity empirical value difference, the amendment of change rate difference etc..
This car owner is shown referring to Fig. 4 move lane change overtake other vehicles model of place
Under field test SC5 scene, pass through the speed, acceleration and spacing for perceiving front truck, being surpassed rear car and adjacent front truck
Etc. the control that all relevant informations to carry out this vehicle longitudinal and transverse direction, it is ensured that Ben Che and adjacent vehicle are maintained at a safety, relax
Suitable spacing (- dx and dRR etc.), even if front truck front truck does a degree of emergency braking sheet in the case where no any omen
Vehicle also can safe lane change to expected adjacent lane.
Herein, this vehicle at least needs to obtain data and have: 1. the last time cycle is quasi- by super rear car speed;
2. the last time cycle is quasi- by super rear car acceleration;3. this vehicle of last time cycle and the quasi- vehicle for being surpassed rear car
Away from;4. the last time cycle is quasi- by advanced vehicle speed;5. the last time cycle is quasi- by advanced vehicle acceleration;6. the last time
This vehicle in period and the quasi- spacing by advanced vehicle;7. stopping distance valuation under front truck current vehicle speed;8. stopping under this vehicle current vehicle speed
Vehicle is apart from valuation.
And at least export following data: the 1. spacing of this vehicle of current time period and front truck;2. this vehicle of current time period
With the spacing for being surpassed rear car;3. the spacing of this vehicle of current time period and adjacent front truck;4. this vehicle of current time period accelerates
Degree;5. this vehicle speed of current time period.
It include being in different relative positions and different opposite speeds in front truck and by super rear car under field test SC3 scene
When this vehicle horizontal, the longitudinally controlled tactful difference amendment and the different amendment of correlation experience value difference that use.
A kind of driver behavior model development equipment is also disclosed in the present embodiment, and referring to Figure 5, which includes storage
Device, processor and it is stored in the program that can be run in above-mentioned memory and on above-mentioned processor, the program is by the processor
The driver behavior model development approach for automatic Pilot as shown in Figure 1 is realized when execution.
A kind of computer readable storage medium is also disclosed in the present embodiment, and driving is stored on the computer readable storage medium
Member's behavior model develops program, and the driver behavior model exploitation program realizes use as shown in Figure 1 when being executed by processor
In the driver behavior model development approach of automatic Pilot.
Embodiment described above is only to absolutely prove preferred embodiment that is of the invention and being lifted, protection model of the invention
It encloses without being limited thereto.Those skilled in the art's made equivalent substitute or transformation on the basis of the present invention, in the present invention
Protection scope within.Protection scope of the present invention is subject to claims.
Claims (10)
1. a kind of driver behavior model development approach for automatic Pilot, it is characterised in that: it includes the following steps,
(1) basic model is created in simulated environment according to the transitive relation between excitation input and theoretical output;
(2) target vehicle is intervened in use excitation input identical with creation basic model in field test scene, is obtained on the spot
The excitation inputs the true output data of lower target vehicle in test scene, and the true output data includes that target vehicle drives
Member's decision data and target vehicle run delta data;
(3) basic model is modified using the true output data of target vehicle under the field test scene of acquisition.
2. being used for the driver behavior model development approach of automatic Pilot as described in claim 1, it is characterised in that: step
(3) in, to the basic model be modified including,
Judge under the field test scene the true output data of target vehicle and the theoretical output whether difference, if so,
The basic model is carried out using true output data renewal theory output data, and using updated theoretical output data
Amendment.
3. being used for the driver behavior model development approach of automatic Pilot as described in claim 1, it is characterised in that: described to swash
Encourage the operation running parameter that input includes surrounding vehicles.
4. being used for the driver behavior model development approach of automatic Pilot as claimed in claim 3, it is characterised in that: described to swash
Encouraging input further includes road traffic information parameter and environmental information parameter.
5. being used for the driver behavior model development approach of automatic Pilot as claimed in claim 4, it is characterised in that: the ring
Border information parameter includes one of illuminance, weather, temperature, humidity, wind direction, wind speed or any combination;The road traffic
Information parameter includes the main road traffic information parameter in city, rural road traffic information parameter, national highway traffic information parameter, provincial highway
One of traffic information parameter, high-speed transit information parameter or any combination.
6. being used for the driver behavior model development approach of automatic Pilot as claimed in claim 3, it is characterised in that: described to swash
Encourage age parameter, gender parameter, physiological parameter, psychological parameter and the driving age parameter that input further includes driver.
7. being used for the driver behavior model development approach of automatic Pilot as described in claim 1, it is characterised in that: step
(2) in, target vehicle operation delta data includes vehicle location delta data, speed change data, acceleration change data, turns
To angle delta data, yaw velocity delta data, side acceleration delta data, accelerator open degree delta data, brake pedal
One of aperture delta data or any combination.
8. being used for the driver behavior model development approach of automatic Pilot as claimed in claim 3, it is characterised in that: the week
The operation running parameter for enclosing vehicle includes vehicle location delta data, speed change data, acceleration change data, steering angle change
Change data, yaw velocity delta data, side acceleration delta data, accelerator open degree delta data, brake pedal aperture to become
Change one of data or any combination.
9. a kind of driver behavior model development equipment, it is characterised in that: including memory, processor and be stored in the storage
In device and the program that can run on the processor, realization such as claim 1-8 when described program is executed by the processor
Described in any item driver behavior model development approaches for automatic Pilot.
10. a kind of computer readable storage medium, it is characterised in that: be stored with driver on the computer readable storage medium
Behavior model develops program, and the driver behavior model exploitation program realizes that claim 1-8 such as appoints when being executed by processor
The driver behavior model development approach of automatic Pilot is used for described in one.
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 true CN110497914A (en) | 2019-11-26 |
CN110497914B 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) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111505965A (en) * | 2020-06-17 | 2020-08-07 | 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 |
CN112180921A (en) * | 2020-09-22 | 2021-01-05 | 安徽江淮汽车集团股份有限公司 | Automatic driving algorithm training system and method |
WO2021036083A1 (en) * | 2019-08-26 | 2021-03-04 | 格物汽车科技(苏州)有限公司 | Driver behavior model development method and device for automatic driving, and storage medium |
CN113353087A (en) * | 2021-07-23 | 2021-09-07 | 上海汽车集团股份有限公司 | Driving assistance method, device and system |
CN113859250A (en) * | 2021-10-14 | 2021-12-31 | 泰安北航科技园信息科技有限公司 | Intelligent automobile information security threat detection system based on driving behavior abnormity identification |
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 |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113706911B (en) * | 2021-08-25 | 2023-01-03 | 娄底职业技术学院 | Automatic driving method based on digital traffic scene |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014057648A1 (en) * | 2012-10-12 | 2014-04-17 | 日産自動車株式会社 | Vehicle travel assist apparatus |
US20140195214A1 (en) * | 2013-01-10 | 2014-07-10 | International Business Machines Corporation | Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network |
US20160012163A1 (en) * | 2014-07-08 | 2016-01-14 | Hyundai Motor Company | Method and apparatus for driving simulation of vehicle |
CN105460015A (en) * | 2014-09-24 | 2016-04-06 | 株式会社万都 | Automatic driving controlling system and method |
US20160314224A1 (en) * | 2015-04-24 | 2016-10-27 | Northrop Grumman Systems Corporation | Autonomous vehicle simulation system |
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 |
US20190146514A1 (en) * | 2017-11-13 | 2019-05-16 | Sonnet Co., Ltd. | Apparatus for autonomous driving algorithm development using daily driving data and method using the same |
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 |
KR20190097486A (en) * | 2018-02-12 | 2019-08-21 | 슈어소프트테크주식회사 | Automobile capable estimating driving inclination, method and system for estimating driving inclination |
CN110155073A (en) * | 2019-05-24 | 2019-08-23 | 合肥工业大学 | Driving behavior mode identification method and system based on driver's preference |
Family Cites Families (8)
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 |
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 |
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 |
CN108819948B (en) * | 2018-06-25 | 2020-05-19 | 大连大学 | Driver behavior modeling method based on reverse reinforcement learning |
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 (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014057648A1 (en) * | 2012-10-12 | 2014-04-17 | 日産自動車株式会社 | Vehicle travel assist apparatus |
US20140195214A1 (en) * | 2013-01-10 | 2014-07-10 | International Business Machines Corporation | Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network |
US20160012163A1 (en) * | 2014-07-08 | 2016-01-14 | Hyundai Motor Company | Method and apparatus for driving simulation of vehicle |
CN105460015A (en) * | 2014-09-24 | 2016-04-06 | 株式会社万都 | Automatic driving controlling system and method |
US20160314224A1 (en) * | 2015-04-24 | 2016-10-27 | Northrop Grumman Systems Corporation | Autonomous vehicle simulation system |
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 |
US20190146514A1 (en) * | 2017-11-13 | 2019-05-16 | Sonnet Co., Ltd. | Apparatus for autonomous driving algorithm development using daily driving data and method using the same |
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 |
KR20190097486A (en) * | 2018-02-12 | 2019-08-21 | 슈어소프트테크주식회사 | Automobile capable estimating driving inclination, method and system for estimating driving inclination |
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 |
CN110155073A (en) * | 2019-05-24 | 2019-08-23 | 合肥工业大学 | Driving behavior mode identification method and system based on driver's preference |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021036083A1 (en) * | 2019-08-26 | 2021-03-04 | 格物汽车科技(苏州)有限公司 | Driver behavior model development method and device for automatic driving, and storage medium |
CN111505965A (en) * | 2020-06-17 | 2020-08-07 | 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 |
CN112180921A (en) * | 2020-09-22 | 2021-01-05 | 安徽江淮汽车集团股份有限公司 | Automatic driving algorithm training system and method |
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 |
CN113353087A (en) * | 2021-07-23 | 2021-09-07 | 上海汽车集团股份有限公司 | Driving assistance method, device and system |
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 |
CN113859250A (en) * | 2021-10-14 | 2021-12-31 | 泰安北航科技园信息科技有限公司 | Intelligent automobile information security threat detection system based on driving behavior abnormity identification |
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 |
Also Published As
Publication number | Publication date |
---|---|
WO2021036083A1 (en) | 2021-03-04 |
CN110497914B (en) | 2020-10-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110497914A (en) | Driver behavior model development approach, equipment and the storage medium of automatic Pilot | |
US11216748B2 (en) | Predictive control techniques for ground vehicles | |
CN113291308B (en) | Vehicle self-learning lane-changing decision-making system and method considering driving behavior characteristics | |
CN107169567B (en) | Method and device for generating decision network model for automatic vehicle driving | |
CN110562258B (en) | Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium | |
CN110304074B (en) | Hybrid driving method based on layered state machine | |
CN110427827A (en) | It is a kind of it is multiple dimensioned perception and Global motion planning under autonomous driving network | |
US11107002B2 (en) | Reinforcement learning based ground vehicle control techniques | |
CN111301419A (en) | Reinforcement learning based method for SAE4 level automated lane change | |
CN114077541A (en) | Method and system for validating automatic control software for an autonomous vehicle | |
CN107368069A (en) | The generation method and generating means of automatic Pilot control strategy based on car networking | |
CN111795832A (en) | Intelligent driving vehicle testing method, device and equipment | |
Yang et al. | A less-disturbed ecological driving strategy for connected and automated vehicles | |
Hu et al. | Lane-level navigation based eco-approach | |
CN116547187A (en) | Selecting driving maneuvers for at least partially automated driven vehicles | |
Baby et al. | Data-driven prediction and predictive control methods for eco-driving in production vehicles | |
CN115176297A (en) | Method for training at least one algorithm for a control unit of a motor vehicle, computer program product and motor vehicle | |
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 | |
CN115571108A (en) | Fuel-saving control method | |
CN108839655A (en) | A kind of cooperating type self-adaptation control method based on minimum safe spacing | |
US10977783B1 (en) | Quantifying photorealism in simulated data with GANs | |
Teng et al. | Car following model based on driving risk field for vehicle infrastructure cooperation | |
CN115096305A (en) | Intelligent driving automobile path planning system and method based on generation of countermeasure network and simulation learning | |
Hamilton et al. | Modeling and simulation of an autonomous-capable electrified vehicle: A review | |
Gupta | Look-ahead optimization of a connected and automated 48v mild-hybrid electric 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 |