CN109808706A - Learning type assistant driving control method, device, system and vehicle - Google Patents
Learning type assistant driving control method, device, system and vehicle Download PDFInfo
- Publication number
- CN109808706A CN109808706A CN201910114537.3A CN201910114537A CN109808706A CN 109808706 A CN109808706 A CN 109808706A CN 201910114537 A CN201910114537 A CN 201910114537A CN 109808706 A CN109808706 A CN 109808706A
- Authority
- CN
- China
- Prior art keywords
- speed
- stage
- lane
- vehicle
- control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The present invention relates to a kind of learning type assistant driving control method, device, system and vehicles, core is method, it include: the stage 1: in driver's driving procedure, throttle, the brake, course changing control amount of the environmental data for including at least nearby vehicle and lane line under different situations and corresponding driver input are acquired, and training data Training Control model is obtained according to it；Stage 2: when auxiliary, which drives, opens, acquisition inputs trained Controlling model currently including at least nearby vehicle and the environmental data of lane line, and the corresponding control signal of Controlling model output is controlled vehicle driving.Compared with prior art, the present invention can be omitted setting of the driver to vehicle parameter, save the time, make system is more convenient to use, pass through the driving habit of learner driver simultaneously, system can be made to be more nearly driver usually to the control of vehicle to the control style of vehicle, meet expectation of the driver to system, system is made more to understand that user is more intelligent.
Description
Technical field
The present invention relates to automobile assistant driving field, more particularly, to a kind of learning type assistant driving control method, device,
System and vehicle.
Background technique
In recent years, various auxiliary drive function and are applied in high-end vehicles, and even some low side A grades of vehicles are also equipped with
Such as adaptive cruise and automatic lane-change function, wherein self-adaption cruise system (ACC) refers to be come using radar or camera
Detect front vehicles, according to driver to when vehicle speed and follow the bus away from setting, by control brake and throttle keeping and
The distance of front vehicles；After automatic lane-change system refers to that driver triggers steering request, system controls the steering torque of steering wheel
To realize that lane-change operates.
But current self-adaption cruise system is also more original, and driver is needed to carry out some parameters after open function
Setting, such as expectation speed per hour, following distance etc., when front is without vehicle, desirably speed per hour is travelled, when there is vehicle in front according to
The speed of front truck travels, and for a long time, driver may feel sleepy, since adaptive cruise can be to adjacent lane and preceding
Square bend is adjusted, to cause more dangerous consequence.
Likewise, existing automatic lane-change system, only can carry out lane change according to the torque of systemic presupposition during lane-change,
Can not be adjusted, but everyone amplitude for being able to bear or experience comfortable amplitude be it is inconsistent, if necessary
Allow each passenger to feel comfortably, those skilled in the art can the method expected be need for different passengers into
Row setting, this is clearly unpractical.
Summary of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide a kind of learning type auxiliary to drive
Sail control method, device, system and vehicle.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of learning type assistant driving control method, comprising:
Stage 1: in driver's driving procedure, the environment that nearby vehicle and lane line are included at least under different situations is acquired
Data and the throttle of corresponding driver input, brake, course changing control amount, and training data Training Control mould is obtained according to it
Type；
Stage 2: when auxiliary, which drives, opens, acquiring the environmental data currently including at least nearby vehicle and lane line, and
Trained Controlling model is inputted, the corresponding control signal of Controlling model output is controlled into vehicle driving.
In the stage 1, after collecting environmental data and control amount, it is based on throttle, brake, course changing control amount and operation
Speed, distance when state obtains follow the bus, steering torque and angular speed when lane-change, and it is excessively curved when speed, turn to,
And speed, distance when by environmental data and obtained follow the bus, steering torque and angular speed and mistake when lane-change
Speed, steering when curved are used as training data；
In the stage 2, speed, distance when the control signal of Controlling model output is follow the bus, steering when lane-change are turned round
Square and angular speed, and it is excessively curved when speed, turn to.
A kind of learning type assists steering control device, including processor, memory, and is stored on memory and by institute
The program of processor execution is stated, the processor performs the steps of when executing described program
Stage 1: in driver's driving procedure, the environment that nearby vehicle and lane line are included at least under different situations is acquired
Data and the throttle of corresponding driver input, brake, course changing control amount, and training data Training Control mould is obtained according to it
Type；
Stage 2: when auxiliary, which drives, opens, acquiring the environmental data currently including at least nearby vehicle and lane line, and
Trained Controlling model is inputted, the corresponding control signal of Controlling model output is controlled into vehicle driving.
A kind of learning type auxiliary Ride Control System, including camera, radar sensor and control device, the control dress
It sets including processor, memory, and the program for being stored on memory and being executed by the processor, the processor executes
It is performed the steps of when described program
Stage 1: in driver's driving procedure, the environment that nearby vehicle and lane line are included at least under different situations is acquired
Data and the throttle of corresponding driver input, brake, course changing control amount, and training data Training Control mould is obtained according to it
Type；
Stage 2: when auxiliary, which drives, opens, acquiring the environmental data currently including at least nearby vehicle and lane line, and
Trained Controlling model is inputted, the corresponding control signal of Controlling model output is controlled into vehicle driving.
A kind of vehicle, including vehicle body, camera, radar sensor and control device, the camera, radar sensing
Device and control device are set on vehicle body, and the control device includes processor, memory, and is stored on memory
And the program executed by the processor, the processor perform the steps of when executing described program
Stage 1: in driver's driving procedure, the environment that nearby vehicle and lane line are included at least under different situations is acquired
Data and the throttle of corresponding driver input, brake, course changing control amount, and training data Training Control mould is obtained according to it
Type；
Stage 2: when auxiliary, which drives, opens, acquiring the environmental data currently including at least nearby vehicle and lane line, and
Trained Controlling model is inputted, the corresponding control signal of Controlling model output is controlled into vehicle driving.
Compared with prior art, vehicle parameter is set the invention has the following advantages: can be omitted driver
It sets, saves the time, make system is more convenient to use, while by the driving habit of learner driver, system can be made to vehicle
Control style is more nearly driver usually to the control of vehicle, meets expectation of the driver to system, system is made more to understand user
It is more intelligent.
Detailed description of the invention
Fig. 1 is the key step flow diagram of the method for the present invention；
Fig. 2 is the system block diagram in stage 1；
Fig. 3 is the system block diagram in stage 2.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
A kind of learning type assistant driving control method, as shown in Figure 1, comprising:
Stage 1: in driver's driving procedure, the environment that nearby vehicle and lane line are included at least under different situations is acquired
Data and the throttle of corresponding driver input, brake, course changing control amount, and training data Training Control mould is obtained according to it
Type；
Stage 2: when auxiliary, which drives, opens, acquiring the environmental data currently including at least nearby vehicle and lane line, and
Trained Controlling model is inputted, the corresponding control signal of Controlling model output is controlled into vehicle driving.
In stage 1, after collecting environmental data and control amount, it is based on throttle, brake, course changing control amount and operating status
Speed, distance when obtaining follow the bus, steering torque and angular speed when lane-change, and it is excessively curved when speed, turn to,
And speed, distance when by environmental data and obtained follow the bus, steering torque and angular speed and mistake when lane-change
Speed, steering when curved are used as training data；
In stage 2, speed, distance when the control signal of Controlling model output is follow the bus, steering torque when lane-change and
Angular speed, and it is excessively curved when speed, turn to.
Specifically, environmental data is acquired by camera and radar, camera and the current driving environment of radar detection, including
The turning radius of current lane, the distance apart from lane line, the speed of front vehicles and distance.These information are sent by bus
To vehicle network.Driver also has corresponding electronic control unit to vehicle accelerator, brake and the control of steering and is sent to vehicle
Network.
As shown in Fig. 2, establishing model according to big data in the stage 1, highway auxiliary system accesses vehicle network, thus
Driver is obtained under different scenes to the operation information of vehicle, includes throttle position, throttle variable gradient, brake pedal pressure
The information such as power, brake pedal gradient, longitudinal acceleration, transverse acceleration, steering moment, steering angular velocity.Pass through statistic algorithm
Driver is calculated under a certain scene to the model of vehicle operating.
As shown in figure 3, when driver opens highway auxiliary system, system passes through camera and radar in the stage 2
Environmental information locating for current vehicle is obtained, using environmental information as input, is input in the model learnt in the stage 1, mould
Type exports vehicle control information according to current Driving Scene.
Claims (8)
1. a kind of learning type assistant driving control method characterized by comprising
Stage 1: in driver's driving procedure, the environmental data that nearby vehicle and lane line are included at least under different situations is acquired
And throttle, the brake, course changing control amount of corresponding driver's input, and training data Training Control model is obtained according to it；
Stage 2: when auxiliary, which drives, opens, acquisition inputs currently including at least nearby vehicle and the environmental data of lane line
The corresponding control signal of Controlling model output is controlled vehicle driving by trained Controlling model.
2. a kind of learning type assistant driving control method according to claim 1, which is characterized in that in the stage 1, adopt
After collection obtains environmental data and control amount, speed when obtaining follow the bus based on throttle, brake, course changing control amount and operating status,
Distance, steering torque and angular speed when lane-change, and it is excessively curved when speed, turn to,
And speed, distance when by environmental data and obtained follow the bus, steering torque and angular speed when lane-change, and it is excessively curved when
Speed, turn to be used as training data；
In the stage 2, speed, distance when the control signal of Controlling model output is follow the bus, steering torque when lane-change and
Angular speed, and it is excessively curved when speed, turn to.
3. a kind of learning type assists steering control device, which is characterized in that including processor, memory, and be stored in storage
The program executed on device and by the processor, the processor perform the steps of when executing described program
Stage 1: in driver's driving procedure, the environmental data that nearby vehicle and lane line are included at least under different situations is acquired
And throttle, the brake, course changing control amount of corresponding driver's input, and training data Training Control model is obtained according to it；
Stage 2: when auxiliary, which drives, opens, acquisition inputs currently including at least nearby vehicle and the environmental data of lane line
The corresponding control signal of Controlling model output is controlled vehicle driving by trained Controlling model.
4. a kind of learning type assistant driving control method according to claim 3, which is characterized in that in the stage 1, adopt
After collection obtains environmental data and control amount, speed when obtaining follow the bus based on throttle, brake, course changing control amount and operating status,
Distance, steering torque and angular speed when lane-change, and it is excessively curved when speed, turn to,
And speed, distance when by environmental data and obtained follow the bus, steering torque and angular speed when lane-change, and it is excessively curved when
Speed, turn to be used as training data；
In the stage 2, speed, distance when the control signal of Controlling model output is follow the bus, steering torque when lane-change and
Angular speed, and it is excessively curved when speed, turn to.
5. a kind of learning type assists Ride Control System, including camera, radar sensor and control device, which is characterized in that
The control device includes processor, memory, and the program for being stored on memory and being executed by the processor, described
Processor performs the steps of when executing described program
Stage 1: in driver's driving procedure, the environmental data that nearby vehicle and lane line are included at least under different situations is acquired
And throttle, the brake, course changing control amount of corresponding driver's input, and training data Training Control model is obtained according to it；
Stage 2: when auxiliary, which drives, opens, acquisition inputs currently including at least nearby vehicle and the environmental data of lane line
The corresponding control signal of Controlling model output is controlled vehicle driving by trained Controlling model.
6. a kind of learning type according to claim 5 assists Ride Control System, which is characterized in that in the stage 1, adopt
After collection obtains environmental data and control amount, speed when obtaining follow the bus based on throttle, brake, course changing control amount and operating status,
Distance, steering torque and angular speed when lane-change, and it is excessively curved when speed, turn to,
And speed, distance when by environmental data and obtained follow the bus, steering torque and angular speed when lane-change, and it is excessively curved when
Speed, turn to be used as training data；
In the stage 2, speed, distance when the control signal of Controlling model output is follow the bus, steering torque when lane-change and
Angular speed, and it is excessively curved when speed, turn to.
7. a kind of vehicle, including vehicle body, camera, radar sensor and control device, the camera, radar sensor
It is set on vehicle body with control device, which is characterized in that the control device includes processor, memory, and storage
In the program executed on memory and by the processor, the processor performs the steps of when executing described program
Stage 1: in driver's driving procedure, the environmental data that nearby vehicle and lane line are included at least under different situations is acquired
And throttle, the brake, course changing control amount of corresponding driver's input, and training data Training Control model is obtained according to it；
Stage 2: when auxiliary, which drives, opens, acquisition inputs currently including at least nearby vehicle and the environmental data of lane line
The corresponding control signal of Controlling model output is controlled vehicle driving by trained Controlling model.
8. a kind of vehicle according to claim 7, which is characterized in that in the stage 1, collect environmental data and control
After amount processed, speed, distance when being obtained follow the bus based on throttle, brake, course changing control amount and operating status, steering when lane-change are turned round
Square and angular speed, and it is excessively curved when speed, turn to,
And speed, distance when by environmental data and obtained follow the bus, steering torque and angular speed when lane-change, and it is excessively curved when
Speed, turn to be used as training data；
In the stage 2, speed, distance when the control signal of Controlling model output is follow the bus, steering torque when lane-change and
Angular speed, and it is excessively curved when speed, turn to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910114537.3A CN109808706A (en) | 2019-02-14 | 2019-02-14 | Learning type assistant driving control method, device, system and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910114537.3A CN109808706A (en) | 2019-02-14 | 2019-02-14 | Learning type assistant driving control method, device, system and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109808706A true CN109808706A (en) | 2019-05-28 |
Family
ID=66606612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910114537.3A Pending CN109808706A (en) | 2019-02-14 | 2019-02-14 | Learning type assistant driving control method, device, system and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109808706A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110843746A (en) * | 2019-11-28 | 2020-02-28 | 的卢技术有限公司 | Anti-lock brake control method and system based on reinforcement learning |
| CN112009397A (en) * | 2020-07-31 | 2020-12-01 | 武汉光庭信息技术股份有限公司 | Automatic driving drive test data analysis method and device |
| CN112092825A (en) * | 2020-08-31 | 2020-12-18 | 英博超算(南京)科技有限公司 | Lane keeping method based on machine learning |
| CN112389451A (en) * | 2019-08-14 | 2021-02-23 | 大众汽车（中国）投资有限公司 | Method, device, medium, and vehicle for providing a personalized driving experience |
| CN113044036A (en) * | 2021-05-12 | 2021-06-29 | 中国第一汽车股份有限公司 | Control method and device for vehicle lane changing, electronic equipment and storage medium |
| CN113135185A (en) * | 2020-01-16 | 2021-07-20 | 奥迪股份公司 | Vehicle driving assistance system, vehicle including the same, and corresponding method and medium |
| CN113442856A (en) * | 2021-08-31 | 2021-09-28 | 国汽智控(北京)科技有限公司 | Control method and device based on adaptive platform and ROS2 and storage medium |
| CN113808382A (en) * | 2020-06-15 | 2021-12-17 | 奥迪股份公司 | Auxiliary driving system and method based on vehicle cut-in critical level prediction |
| CN114074673A (en) * | 2020-08-19 | 2022-02-22 | 威马智慧出行科技（上海）有限公司 | Control method and device for self-adaptive driving mode |
| CN116176600A (en) * | 2023-04-25 | 2023-05-30 | 合肥工业大学 | Control method of intelligent health cabin |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104590274A (en) * | 2014-11-26 | 2015-05-06 | 浙江吉利汽车研究院有限公司 | Driving behavior self-adaptation system and method |
| US20160023664A1 (en) * | 2014-06-09 | 2016-01-28 | Atieva, Inc. | Event Sensitive Learning Interface |
| CN106066644A (en) * | 2016-06-17 | 2016-11-02 | 百度在线网络技术（北京）有限公司 | Set up the method for intelligent vehicle control model, intelligent vehicle control method and device |
| CN107200017A (en) * | 2017-05-22 | 2017-09-26 | 北京联合大学 | A kind of automatic driving vehicle control system based on deep learning |
| CN107264534A (en) * | 2017-05-23 | 2017-10-20 | 北京理工大学 | Intelligent driving control system and method, vehicle based on driver experience's model |
| CN107368069A (en) * | 2014-11-25 | 2017-11-21 | 浙江吉利汽车研究院有限公司 | The generation method and generating means of automatic Pilot control strategy based on car networking |
| WO2018007079A1 (en) * | 2016-07-08 | 2018-01-11 | Jaguar Land Rover Limited | Improvements in vehicle speed control |
| WO2018173933A1 (en) * | 2017-03-23 | 2018-09-27 | 日本電気株式会社 | Information processing device, travel data processing method, vehicle, and program recording medium |
| US20180281813A1 (en) * | 2017-03-31 | 2018-10-04 | Panasonic Intellectual Property Management Co., Ltd. | Driving support method, data processor using the same, and driving support system using the same |
| CN108657189A (en) * | 2018-06-22 | 2018-10-16 | 南京航空航天大学 | Line operating mode automatic Pilot steering and its control method are moved based on BP neural network and safe distance |
-
2019
- 2019-02-14 CN CN201910114537.3A patent/CN109808706A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160023664A1 (en) * | 2014-06-09 | 2016-01-28 | Atieva, Inc. | Event Sensitive Learning Interface |
| CN107368069A (en) * | 2014-11-25 | 2017-11-21 | 浙江吉利汽车研究院有限公司 | The generation method and generating means of automatic Pilot control strategy based on car networking |
| CN104590274A (en) * | 2014-11-26 | 2015-05-06 | 浙江吉利汽车研究院有限公司 | Driving behavior self-adaptation system and method |
| CN106066644A (en) * | 2016-06-17 | 2016-11-02 | 百度在线网络技术（北京）有限公司 | Set up the method for intelligent vehicle control model, intelligent vehicle control method and device |
| WO2018007079A1 (en) * | 2016-07-08 | 2018-01-11 | Jaguar Land Rover Limited | Improvements in vehicle speed control |
| WO2018173933A1 (en) * | 2017-03-23 | 2018-09-27 | 日本電気株式会社 | Information processing device, travel data processing method, vehicle, and program recording medium |
| US20180281813A1 (en) * | 2017-03-31 | 2018-10-04 | Panasonic Intellectual Property Management Co., Ltd. | Driving support method, data processor using the same, and driving support system using the same |
| CN107200017A (en) * | 2017-05-22 | 2017-09-26 | 北京联合大学 | A kind of automatic driving vehicle control system based on deep learning |
| CN107264534A (en) * | 2017-05-23 | 2017-10-20 | 北京理工大学 | Intelligent driving control system and method, vehicle based on driver experience's model |
| CN108657189A (en) * | 2018-06-22 | 2018-10-16 | 南京航空航天大学 | Line operating mode automatic Pilot steering and its control method are moved based on BP neural network and safe distance |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112389451A (en) * | 2019-08-14 | 2021-02-23 | 大众汽车（中国）投资有限公司 | Method, device, medium, and vehicle for providing a personalized driving experience |
| CN110843746A (en) * | 2019-11-28 | 2020-02-28 | 的卢技术有限公司 | Anti-lock brake control method and system based on reinforcement learning |
| CN113135185A (en) * | 2020-01-16 | 2021-07-20 | 奥迪股份公司 | Vehicle driving assistance system, vehicle including the same, and corresponding method and medium |
| CN113808382A (en) * | 2020-06-15 | 2021-12-17 | 奥迪股份公司 | Auxiliary driving system and method based on vehicle cut-in critical level prediction |
| CN112009397B (en) * | 2020-07-31 | 2022-03-08 | 武汉光庭信息技术股份有限公司 | Automatic driving drive test data analysis method and device |
| CN112009397A (en) * | 2020-07-31 | 2020-12-01 | 武汉光庭信息技术股份有限公司 | Automatic driving drive test data analysis method and device |
| CN114074673A (en) * | 2020-08-19 | 2022-02-22 | 威马智慧出行科技（上海）有限公司 | Control method and device for self-adaptive driving mode |
| CN112092825A (en) * | 2020-08-31 | 2020-12-18 | 英博超算(南京)科技有限公司 | Lane keeping method based on machine learning |
| CN112092825B (en) * | 2020-08-31 | 2022-04-29 | 英博超算(南京)科技有限公司 | Lane keeping method based on machine learning |
| CN113044036A (en) * | 2021-05-12 | 2021-06-29 | 中国第一汽车股份有限公司 | Control method and device for vehicle lane changing, electronic equipment and storage medium |
| CN113442856A (en) * | 2021-08-31 | 2021-09-28 | 国汽智控(北京)科技有限公司 | Control method and device based on adaptive platform and ROS2 and storage medium |
| CN116176600A (en) * | 2023-04-25 | 2023-05-30 | 合肥工业大学 | Control method of intelligent health cabin |
| CN116176600B (en) * | 2023-04-25 | 2023-09-29 | 合肥工业大学 | Control method of intelligent health cabin |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109808706A (en) | Learning type assistant driving control method, device, system and vehicle | |
| CN108657189B (en) | Automatic driving steering system based on BP neural network and safe distance lane change working condition and control method thereof | |
| CN108569296B (en) | Method for self-adaptively matching auxiliary driving system and implementation module thereof | |
| CN108995653A (en) | A kind of driver's driving style recognition methods and system | |
| CN110001782A (en) | Automatic lane-change method, system and computer readable storage medium | |
| CN102112348B (en) | Vehicle controlling device | |
| CN109050533B (en) | Automatic lane changing control method and device for vehicle | |
| US20190071100A1 (en) | Autonomous driving adjustment method, apparatus, and system | |
| CN109572688A (en) | Drive assistance device | |
| EP1818231A2 (en) | Vehicle control system | |
| EP3647136B1 (en) | Vehicle traveling assistance method and vehicle traveling assistance device | |
| CN109436085B (en) | Driving style-based drive-by-wire steering system transmission ratio control method | |
| JPH11321690A (en) | Lane keep system | |
| CN110920405B (en) | Sliding energy recovery mode switching method and device based on comprehensive working conditions and automobile | |
| WO2019011268A1 (en) | Game theory-based driver auxiliary system decision-making method and system, and the like | |
| CN108974003A (en) | A kind of exchange method | |
| US20210016788A1 (en) | Device and Method for Interacting Between a Vehicle Capable of Being Driven in an at Least Partially Automated Manner and a Vehicle User | |
| JP4277907B2 (en) | Driving control device for automobile | |
| CN111252077A (en) | Vehicle control method and device | |
| CN110281940A (en) | The control method of travel assist system and vehicle | |
| CN111942353A (en) | Emergency braking control method for pure electric vehicle, vehicle control unit and control device | |
| JP2000025631A (en) | Lane keep system | |
| JP4941659B2 (en) | Vehicle reaction reaction force control device | |
| CN113619680B (en) | Autonomous driver feedback system and method | |
| CN115384539A (en) | Method and device for generating intelligent driving strategy of vehicle, vehicle and storage medium |
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 |