CN109709956A - A kind of automatic driving vehicle speed control multiple-objection optimization with algorithm of speeding - Google Patents
A kind of automatic driving vehicle speed control multiple-objection optimization with algorithm of speeding Download PDFInfo
- Publication number
- CN109709956A CN109709956A CN201811600366.7A CN201811600366A CN109709956A CN 109709956 A CN109709956 A CN 109709956A CN 201811600366 A CN201811600366 A CN 201811600366A CN 109709956 A CN109709956 A CN 109709956A
- Authority
- CN
- China
- Prior art keywords
- speeding
- data
- ttc
- headway
- ngsim
- 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
Landscapes
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Feedback Control In General (AREA)
Abstract
The present invention develop a kind of automatic driving vehicle speed control multiple-objection optimization with algorithm of speeding.The algorithm proposes a kind of model for automobile with speed control of speeding based on deeply study, which not only imitates mankind's driving, but directly optimizes drive safety, efficiency and comfort.In conjunction with collision time, the distribution of time headway experience, acceleration, construct reflection drive safety, the reward function of efficiency and comfort, (Next Generation Simulation is emulated using the next generation, NGSIM) practical driving data training pattern in project, and modeling is compared with speeding on the behavior observed in NGSIM empirical data, intensified learning intelligent body by test in simulated environment and trial and error, learnt in a manner of maximizing progressive award safety, it is comfortable, efficiently control car speed.The result shows that proposition shows better safe and efficient and comfortable driving ability with speed control algorithm of speeding compared with human driver in the real world.
Description
Technical field
The present invention relates to automatic Pilots with control field of speeding, in particular to a kind of automatic driving vehicle speed control multiple target
Optimization with algorithm of speeding.
Background technique
It is the important component of automatic Pilot intelligent decision with control of speeding, including the speed selection under freely driving, vehicle
With the braking under the holding and emergency of spacing at any time.In the case where automatic Pilot and the mankind drive and coexist, automatically
It drives vehicle and makes the comfort level and letter that will improve passenger with control decision of speeding similar to human driver's (referred to as personalizing)
Ren Du, while other traffic participants also being facilitated to more fully understand and predict the behavior of automatic driving vehicle, it is driven automatically with realizing
Sail the secure interactive between mankind's driving.However traditional following-speed model is when being applied to automatically with speeding to control that there are many limitations
Property, such as the flexibility and accuracy of limited model, it is difficult to which the Driving Scene being generalized to other than nominal data and driver are applied to
Driving style and the Driving Scene etc. of the practical driver of vehicle cannot be reacted when automatic Pilot.
Deeply learn (Deep Reinforcement Learning, DRL) be widely used in industry manufacture,
Analogue simulation, robot control, optimization and scheduling and the fields such as game play, basic thought be by maximize intelligent body from
The accumulative reward value obtained in environment, to learn to the optimal policy for completing target.DRL method more lays particular emphasis on study and solves to ask
The strategy of topic, and non-logarithmic evidence is fitted, therefore its generalization ability is stronger, provides ginseng with control of speeding for automatic driving vehicle
It examines.
Summary of the invention
The purpose of the present invention is a kind of: automatic driving vehicle speed control multiple-objection optimizations with algorithm of speeding.The algorithm mentions
A kind of model for automobile with speed control of speeding is gone out, which directly optimizes drive safety, efficiency and comfort.In conjunction with
Collision time TTC, the distribution of time headway experience, acceleration (Jerk), construct reflection drive safety, efficiency and comfort
Reward function, using practical driving data training pattern in next generation's emulation (NGSIM) project, and by modeling with speeding
The behavior observed in behavior and NGSIM empirical data is compared, and intensified learning intelligent body passes through the test in simulated environment
And trial and error, learnt in a manner of maximizing progressive award safety, it is comfortable, efficiently control car speed.The result shows that with reality
Human driver in the world compares, and proposition shows better safe and efficient and comfortable driving with speed control algorithm of speeding
Ability.
The technical scheme adopted by the invention is that:
A kind of automatic driving vehicle speed control multiple-objection optimization with algorithm of speeding, steps are as follows:
Step 1: obtaining data.Using the data in NGSIM project, rested on same lane based on front truck and rear car and
Vehicle follows the criterion such as length > 15 second of event to extract with the event of speeding, based on extraction with the event of speeding, by a part as training
Data, another part is as test data.
Step 2: building reward function.It is proposed the feature of reflection automobile model- following control related objective (safety, comfortable, efficiency)
Amount.
Step 2.1: safety is reflected using collision time (TTC).TTC indicates the remaining time before two cars collision
Amount, formula areIt is wherein Sn-1, n (t) vehicle headway, △ Vn-1, n (t) are relative velocities.According to
NGSIM empirical data determines that secure threshold is 7 seconds, and carries out TTC feature construction:If TTC less than 7 seconds,
Then TTC characteristic index be negative value, with TTC approach zero, TTC feature will close to bear it is infinite, for close to collision the case where show
Most severe punishment.
Step 2.2: driving efficiency is measured using time headway (headway).By analyzing, logarithm normal distribution is adapted to obtain
The distribution of the training data taken, probability density function arex>0.According to being mentioned
The data taken can estimate that the average value mu and logarithm standard deviation σ of distribution variable x is respectively 0.4226 and 0.4365.By time headway
Feature construction is the probability density value of the time headway logarithm normal distribution of estimation: Fheadway=flognormal (headway
| μ=0.4226, σ=0.4365).According to the headstock temporal characteristics, about 1.3 seconds time headways correspond to high characteristic value, headstock
When away from it is too long or it is too short correspond to low characteristic value, therefore this feature value estimation high flow capacity spacing keeps behavior, while punishing dangerous
Or spacing too far keeps behavior.
Step 2.3: driver comfort, feature construction are measured using the change rate Jerk of acceleration are as follows:
Step 2.4: establishing comprehensive reward function.R=w1FTTC+w2Fheadway+ is established according to above step
W3Fjerk., wherein w1, w2, w3 be feature coefficient, be all set to 1.
Step 3: training pattern.Every time when training, sequence emulate in data with the event of speeding, training is repeated as many times, and is selected
The model of maximum average reward is obtained in test data as final mask.
Step 4: evaluation model.NGSIM data and DDPG model are evaluated using Indexes Comparisons such as TTC, headway and jerk
Simulate obtain with speed on for.
The invention has the advantages that
1. the automatic driving vehicle developed can be applied to automatic driving vehicle exploitation with control logic of speeding；
2. the algorithm model does not imitate mankind's driving, but directly optimizes drive safety, efficiency and comfort.
Detailed description of the invention
Fig. 1 is flow chart of the invention.
Fig. 2 NGSIM data are compared with DDPG model drive safety.
Fig. 3 NGSIM data are compared with driver comfort between DDPG model.
Specific embodiment
The algorithm proposes a kind of model for automobile with speed control of speeding based on deeply study, the model not mould
Apery class drives, but directly optimizes drive safety, efficiency and comfort.In conjunction with collision time TTC, time headway experience point
Cloth, acceleration (Jerk), construct reflection drive safety, and the reward function of efficiency and comfort is emulated using the next generation
(NGSIM) practical driving data training pattern in project, and by modeling with speed on for observed in NGSIM empirical data
To behavior be compared, intensified learning intelligent body is by test in simulated environment and trial and error, to maximize progressive award
Mode learn safety, it is comfortable, efficiently control car speed.The result shows that being mentioned compared with human driver in the real world
Out show better safe and efficient and comfortable driving ability with speed control algorithm of speeding.The result shows that with real world
Human driver compare, proposition shows better safe and efficient and comfortable driving ability with speed control algorithm of speeding.
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings, and steps are as follows:
Step 1: obtaining data.Using the data in next-generation emulation (NGSIM) project, rested on based on front truck and rear car
On same lane and vehicle follow the criterion such as length > 15 second of event extract with the event of speeding, based on extraction with the event of speeding, by one
Part is used as training data, and another part is as test data.
Step 2: building reward function.It is proposed the feature of reflection automobile model- following control related objective (safety, comfortable, efficiency)
Amount.
Step 2.1: safety is reflected using collision time (TTC).TTC indicates the remaining time before two cars collision
Amount, formula areIt is wherein Sn-1, n (t) vehicle headway, △ Vn-1, n (t) are relative velocities.According to
NGSIM empirical data determines that secure threshold is 7 seconds, and carries out TTC feature construction:If TTC is less than 7
Second, then TTC characteristic index be negative value, with TTC approach zero, TTC feature will close to bear it is infinite, for close to collision the case where table
Now most severe punishment.
Step 2.2: driving efficiency is measured using time headway (headway).By analyzing, logarithm normal distribution is adapted to obtain
The distribution of the training data taken, probability density function arex>0.According to being mentioned
The data taken can estimate that the average value mu and logarithm standard deviation σ of distribution variable x is respectively 0.4226 and 0.4365.By time headway
Feature construction is the probability density value of the time headway logarithm normal distribution of estimation: Fheadway=flognormal (headway
| μ=0.4226, σ=0.4365).According to the headstock temporal characteristics, about 1.3 seconds time headways correspond to high characteristic value, headstock
When away from it is too long or it is too short correspond to low characteristic value, therefore this feature value estimation high flow capacity spacing keeps behavior, while punishing dangerous
Or spacing too far keeps behavior.
Step 2.3: driver comfort, feature construction are measured using the change rate Jerk of acceleration are as follows:
Step 2.4: establishing comprehensive reward function.R=w1FTTC is established according to above step 2.1, step 2.2, step 2.3
+ w2Fheadway+w3Fjerk., wherein w1, w2, w3 are the coefficients of feature, are all set to 1.
Step 3: training pattern.Every time when training, sequence emulate in data with the event of speeding, training is repeated as many times, and is selected
The model of maximum average reward is obtained in test data as final mask.
Step 4: evaluation model.NGSIM data and DDPG model are evaluated using Indexes Comparisons such as TTC, headway and jerk
Simulate obtain with speed on for.
Embodiment
By comparing experience NGSIM data and DDPG modeling obtain with speed on for, test the model can safely,
Efficiently, front truck is comfortably followed.
Obtain data.Using the data in NGSIM project, rested on same lane based on front truck and rear car and vehicle with
The criterion such as length > 15 second with event are extracted with the event of speeding.
In terms of drive safety, one has been randomly choosed from NGSIM data set with the event of speeding.Fig. 2, which is shown, to be observed
Speed, spacing and acceleration, and the corresponding index value generated by DDPG model.Driver in NGSIM data was at 10 seconds
Afterwards with the driving of very small following distance, and DDPG model remains that about 10 meters follow gap.
In terms of driver comfort, one has been randomly choosed in NGSIM data set with the event of speeding.Fig. 3, which is shown, to be observed
Speed, spacing, acceleration and Jerk value, and the correspondence index value generated by DDPG model.Driver in NGSIM data
Frequent acceleration change and big Jerk value are produced in driving procedure, and DDPG model can be kept close to constant acceleration
It spends and generates low Jerk value.
Based on the above, what is proposed shows preferably with speed control algorithm of speeding compared with human driver in NGSIM
Safe and efficient and comfortable driving ability.
Claims (1)
1. a kind of automatic driving vehicle speed control multiple-objection optimization with algorithm of speeding, which is characterized in that steps are as follows:
Step 1: obtaining data；Using the data in NGSIM project, rested on same lane based on front truck and rear car and vehicle
Follow the criterion such as length > 15 second of event to extract with the event of speeding, based on extraction with the event of speeding, by a part as training number
According to another part is as test data；
Step 2: building reward function；It is proposed the characteristic quantity of reflection automobile model- following control related objective (safety, comfortable, efficiency)；
Step 2.1: safety is reflected using collision time (TTC)；TTC indicates remaining time quantum before two cars collision,
Formula isIt is wherein Sn-1, n (t) vehicle headway, △ Vn-1, n (t) are relative velocities；According to NGSIM
Empirical data determines that secure threshold is 7 seconds, and carries out TTC feature construction:If TTC was less than 7 seconds, TTC
Characteristic index is negative value, with TTC approach zero, TTC feature will close to bear it is infinite, for close to collision the case where performance it is most severe
Punishment；
Step 2.2: driving efficiency is measured using time headway (headway)；By analyzing, logarithm normal distribution is adapted to acquisition
The distribution of training data, probability density function arex>0；According to extracted
Data can estimate that the average value mu and logarithm standard deviation σ of distribution variable x is respectively 0.4226 and 0.4365；By time headway feature
Be configured to estimation time headway logarithm normal distribution probability density value: Fheadway=flognormal (headway | μ=
0.4226, σ=0.4365)；According to the headstock temporal characteristics, about 1.3 seconds time headways correspond to high characteristic value, time headway
It is too long or it is too short correspond to low characteristic value, therefore this feature value estimation high flow capacity spacing keeps behavior, while punishing dangerous or mistake
Remote spacing keeps behavior；
Step 2.3: driver comfort, feature construction are measured using the change rate Jerk of acceleration are as follows:
Step 2.4: establishing comprehensive reward function；R=w1FTTC+w2Fheadway+w3Fjerk. is established according to above step,
Middle w1, w2, w3 are the coefficients of feature, are all set to 1；
Step 3: training pattern；Every time when training, sequence emulate in data with the event of speeding, training is repeated as many times, and selection is being surveyed
The model for trying to obtain maximum average reward in data is as final mask；
Step 4: evaluation model；NGSIM data and DDPG modeling are evaluated using Indexes Comparisons such as TTC, headway and jerk
Obtain with speed on for；
Using the Indexes Comparisons such as TTC, headway and jerk evaluate that NGSIM data and DDPG modeling obtain with speed on for.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811600366.7A CN109709956B (en) | 2018-12-26 | 2018-12-26 | Multi-objective optimized following algorithm for controlling speed of automatic driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811600366.7A CN109709956B (en) | 2018-12-26 | 2018-12-26 | Multi-objective optimized following algorithm for controlling speed of automatic driving vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109709956A true CN109709956A (en) | 2019-05-03 |
| CN109709956B CN109709956B (en) | 2021-06-08 |
Family
ID=66258357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811600366.7A Active CN109709956B (en) | 2018-12-26 | 2018-12-26 | Multi-objective optimized following algorithm for controlling speed of automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109709956B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321605A (en) * | 2019-06-19 | 2019-10-11 | 中汽研（天津）汽车工程研究院有限公司 | A kind of human-computer interaction coordination control strategy based on Multiple Velocity Model PREDICTIVE CONTROL |
| CN110347043A (en) * | 2019-07-15 | 2019-10-18 | 武汉天喻信息产业股份有限公司 | A kind of intelligent driving control method and device |
| CN110488802A (en) * | 2019-08-21 | 2019-11-22 | 清华大学 | A kind of automatic driving vehicle dynamic behaviour decision-making technique netted under connection environment |
| CN110716562A (en) * | 2019-09-25 | 2020-01-21 | 南京航空航天大学 | Decision-making method for multi-lane driving of unmanned vehicle based on reinforcement learning |
| 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 |
| CN112201069A (en) * | 2020-09-25 | 2021-01-08 | 厦门大学 | Deep reinforcement learning-based method for constructing longitudinal following behavior model of driver |
| CN112614344A (en) * | 2020-12-14 | 2021-04-06 | 中汽研汽车试验场股份有限公司 | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation |
| CN112677984A (en) * | 2019-10-18 | 2021-04-20 | 丰田自动车株式会社 | Method for generating vehicle control data, vehicle control device, and vehicle control system |
| WO2021073523A1 (en) * | 2019-10-15 | 2021-04-22 | 同济大学 | Method for estimating road capacity and connected automatic driving vehicle equivalent coefficient |
| CN112698578A (en) * | 2019-10-22 | 2021-04-23 | 北京车和家信息技术有限公司 | Automatic driving model training method and related equipment |
| WO2021165113A1 (en) * | 2020-02-17 | 2021-08-26 | Psa Automobiles Sa | Method for training at least one algorithm for a control device of a motor vehicle, method for optimising traffic flow in a region, computer program product, and motor vehicle |
| CN113353102A (en) * | 2021-07-08 | 2021-09-07 | 重庆大学 | Unprotected left-turn driving control method based on deep reinforcement learning |
| TWI745120B (en) * | 2019-10-18 | 2021-11-01 | 日商豐田自動車股份有限公司 | Vehicle control system, vehicle control device, and control method for a vehicle |
| CN113901718A (en) * | 2021-10-11 | 2022-01-07 | 长安大学 | Deep reinforcement learning-based driving collision avoidance optimization method in following state |
| CN113954865A (en) * | 2021-09-22 | 2022-01-21 | 吉林大学 | Following control method for automatically driven vehicle in ice and snow environment |
| CN113954874A (en) * | 2021-11-03 | 2022-01-21 | 同济大学 | Automatic driving control method based on improved intelligent driver model |
| CN114056332A (en) * | 2022-01-14 | 2022-02-18 | 清华大学 | Intelligent automobile following decision and control method based on cognitive risk balance |
| CN115123159A (en) * | 2022-06-27 | 2022-09-30 | 重庆邮电大学 | AEB control method and system based on DDPG deep reinforcement learning |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101606794A (en) * | 2009-07-17 | 2009-12-23 | 梁秀芬 | A kind of dynamic cinema seat equipment |
| US20100185369A1 (en) * | 2009-01-19 | 2010-07-22 | Jung-Woong Choi | Automatic transmission |
| CN102955884A (en) * | 2012-11-23 | 2013-03-06 | 同济大学 | Safety distance calibration method in full-speed areas during following operation of high-speed train |
| CN103101559A (en) * | 2013-02-16 | 2013-05-15 | 同济大学 | Full-speed field train interval real-time control method based on car-following behavior quality evaluation |
| CN103248545A (en) * | 2013-05-28 | 2013-08-14 | 北京和利时电机技术有限公司 | Ethernetcommunication method and system for special effect broadcast system of dynamic cinema |
| CN105654779A (en) * | 2016-02-03 | 2016-06-08 | 北京工业大学 | Expressway construction area traffic flow coordination control method based on vehicle-road and vehicle-vehicle communication |
| CN106926844A (en) * | 2017-03-27 | 2017-07-07 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track based on real time environment information |
| CN108313054A (en) * | 2018-01-05 | 2018-07-24 | 北京智行者科技有限公司 | The autonomous lane-change decision-making technique of automatic Pilot and device and automatic driving vehicle |
| CN108387242A (en) * | 2018-02-07 | 2018-08-10 | 西南交通大学 | Automatic Pilot lane-change prepares and executes integrated method for planning track |
| CN108492398A (en) * | 2018-02-08 | 2018-09-04 | 同济大学 | The method for early warning that drive automatically behavior based on accelerometer actively acquires |
| CN108932840A (en) * | 2018-07-17 | 2018-12-04 | 北京理工大学 | Automatic driving vehicle urban intersection passing method based on intensified learning |
-
2018
- 2018-12-26 CN CN201811600366.7A patent/CN109709956B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100185369A1 (en) * | 2009-01-19 | 2010-07-22 | Jung-Woong Choi | Automatic transmission |
| CN101606794A (en) * | 2009-07-17 | 2009-12-23 | 梁秀芬 | A kind of dynamic cinema seat equipment |
| CN102955884A (en) * | 2012-11-23 | 2013-03-06 | 同济大学 | Safety distance calibration method in full-speed areas during following operation of high-speed train |
| CN103101559A (en) * | 2013-02-16 | 2013-05-15 | 同济大学 | Full-speed field train interval real-time control method based on car-following behavior quality evaluation |
| CN103248545A (en) * | 2013-05-28 | 2013-08-14 | 北京和利时电机技术有限公司 | Ethernetcommunication method and system for special effect broadcast system of dynamic cinema |
| CN105654779A (en) * | 2016-02-03 | 2016-06-08 | 北京工业大学 | Expressway construction area traffic flow coordination control method based on vehicle-road and vehicle-vehicle communication |
| CN106926844A (en) * | 2017-03-27 | 2017-07-07 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track based on real time environment information |
| CN108313054A (en) * | 2018-01-05 | 2018-07-24 | 北京智行者科技有限公司 | The autonomous lane-change decision-making technique of automatic Pilot and device and automatic driving vehicle |
| CN108387242A (en) * | 2018-02-07 | 2018-08-10 | 西南交通大学 | Automatic Pilot lane-change prepares and executes integrated method for planning track |
| CN108492398A (en) * | 2018-02-08 | 2018-09-04 | 同济大学 | The method for early warning that drive automatically behavior based on accelerometer actively acquires |
| CN108932840A (en) * | 2018-07-17 | 2018-12-04 | 北京理工大学 | Automatic driving vehicle urban intersection passing method based on intensified learning |
Non-Patent Citations (5)
| Title |
|---|
| MEIXIN ZHU，等: "Modeling car-following behavior on urban expressways in Shanghai: A naturalistic driving study", 《TRANSPORTATION RESEARCH PART C》 * |
| XUESONG WANG，等: "Drivers’ rear end collision avoidance behaviors under different levels of situational urgency", 《TRANSPORTATION RESEARCH PART C》 * |
| 王雪松，朱美新，邢祎伦: "基于自然驾驶数据的避撞预警对跟车行为影响", 《同济大学学报（自然科学版）》 * |
| 王雪松，朱美新，陈铭: "驾驶员前向避撞行为特征的降维及多元方差分析", 《同济大学学报（自然科学版）》 * |
| 王雪松，等: "中美两国道路交通事故信息采集技术比较研究", 《中国安全科学学报》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321605A (en) * | 2019-06-19 | 2019-10-11 | 中汽研（天津）汽车工程研究院有限公司 | A kind of human-computer interaction coordination control strategy based on Multiple Velocity Model PREDICTIVE CONTROL |
| CN110347043A (en) * | 2019-07-15 | 2019-10-18 | 武汉天喻信息产业股份有限公司 | A kind of intelligent driving control method and device |
| CN110347043B (en) * | 2019-07-15 | 2023-03-10 | 武汉天喻信息产业股份有限公司 | Intelligent driving control method and device |
| CN110488802A (en) * | 2019-08-21 | 2019-11-22 | 清华大学 | A kind of automatic driving vehicle dynamic behaviour decision-making technique netted under connection environment |
| CN110716562A (en) * | 2019-09-25 | 2020-01-21 | 南京航空航天大学 | Decision-making method for multi-lane driving of unmanned vehicle based on reinforcement learning |
| WO2021073523A1 (en) * | 2019-10-15 | 2021-04-22 | 同济大学 | Method for estimating road capacity and connected automatic driving vehicle equivalent coefficient |
| TWI745120B (en) * | 2019-10-18 | 2021-11-01 | 日商豐田自動車股份有限公司 | Vehicle control system, vehicle control device, and control method for a vehicle |
| CN112677984A (en) * | 2019-10-18 | 2021-04-20 | 丰田自动车株式会社 | Method for generating vehicle control data, vehicle control device, and vehicle control system |
| EP3809340A1 (en) * | 2019-10-18 | 2021-04-21 | Toyota Jidosha Kabushiki Kaisha | Method of generating vehicle control data, vehicle control device, and vehicle control system |
| US11673556B2 (en) | 2019-10-18 | 2023-06-13 | Toyota Jidosha Kabushiki Kaisha | Method of generating vehicle control data, vehicle control device, and vehicle control system |
| AU2020256407B2 (en) * | 2019-10-18 | 2022-03-03 | Toyota Jidosha Kabushiki Kaisha | Method of generating vehicle control data, vehicle control device, and vehicle control system |
| CN112677984B (en) * | 2019-10-18 | 2024-08-13 | 丰田自动车株式会社 | Method for generating control data for vehicle, control device for vehicle, and control system for vehicle |
| CN112698578A (en) * | 2019-10-22 | 2021-04-23 | 北京车和家信息技术有限公司 | Automatic driving model training method and related equipment |
| CN112698578B (en) * | 2019-10-22 | 2023-11-14 | 北京车和家信息技术有限公司 | Training method of automatic driving model and related equipment |
| 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 |
| WO2021165113A1 (en) * | 2020-02-17 | 2021-08-26 | Psa Automobiles Sa | Method for training at least one algorithm for a control device of a motor vehicle, method for optimising traffic flow in a region, computer program product, and motor vehicle |
| CN112201069A (en) * | 2020-09-25 | 2021-01-08 | 厦门大学 | Deep reinforcement learning-based method for constructing longitudinal following behavior model of driver |
| CN112201069B (en) * | 2020-09-25 | 2021-10-29 | 厦门大学 | Deep reinforcement learning-based method for constructing longitudinal following behavior model of driver |
| CN112614344B (en) * | 2020-12-14 | 2022-03-29 | 中汽研汽车试验场股份有限公司 | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation |
| CN112614344A (en) * | 2020-12-14 | 2021-04-06 | 中汽研汽车试验场股份有限公司 | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation |
| CN113353102A (en) * | 2021-07-08 | 2021-09-07 | 重庆大学 | Unprotected left-turn driving control method based on deep reinforcement learning |
| CN113353102B (en) * | 2021-07-08 | 2022-11-25 | 重庆大学 | Unprotected left-turn driving control method based on deep reinforcement learning |
| CN113954865A (en) * | 2021-09-22 | 2022-01-21 | 吉林大学 | Following control method for automatically driven vehicle in ice and snow environment |
| CN113954865B (en) * | 2021-09-22 | 2023-11-10 | 吉林大学 | Following control method for automatic driving vehicle in ice and snow environment |
| CN113901718A (en) * | 2021-10-11 | 2022-01-07 | 长安大学 | Deep reinforcement learning-based driving collision avoidance optimization method in following state |
| CN113954874A (en) * | 2021-11-03 | 2022-01-21 | 同济大学 | Automatic driving control method based on improved intelligent driver model |
| CN114056332B (en) * | 2022-01-14 | 2022-04-12 | 清华大学 | Intelligent automobile following decision and control method based on cognitive risk balance |
| CN114056332A (en) * | 2022-01-14 | 2022-02-18 | 清华大学 | Intelligent automobile following decision and control method based on cognitive risk balance |
| CN115123159A (en) * | 2022-06-27 | 2022-09-30 | 重庆邮电大学 | AEB control method and system based on DDPG deep reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109709956B (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109709956A (en) | A kind of automatic driving vehicle speed control multiple-objection optimization with algorithm of speeding | |
| CN109733415B (en) | Anthropomorphic automatic driving and following model based on deep reinforcement learning | |
| CN108595823B (en) | Autonomous main vehicle lane changing strategy calculation method combining driving style and game theory | |
| CN102109821B (en) | System and method for controlling adaptive cruise of vehicles | |
| CN109726804B (en) | Intelligent vehicle driving behavior personification decision-making method based on driving prediction field and BP neural network | |
| CN107168303A (en) | A kind of automatic Pilot method and device of automobile | |
| CN112906126B (en) | Vehicle hardware in-loop simulation training system and method based on deep reinforcement learning | |
| CN111409648B (en) | Driving behavior analysis method and device | |
| CN110956851B (en) | Intelligent networking automobile cooperative scheduling lane changing method | |
| CN115457782B (en) | Automatic driving vehicle intersection conflict-free cooperation method based on deep reinforcement learning | |
| Ni et al. | A unified perspective on traffic flow theory, part III: validation and benchmarking | |
| CN113901718A (en) | Deep reinforcement learning-based driving collision avoidance optimization method in following state | |
| CN114896869A (en) | Automatic driving test scene generation method based on personalized driver model | |
| CN115257789A (en) | Decision-making method for side anti-collision driving of commercial vehicle in urban low-speed environment | |
| CN117610681A (en) | Automatic driving automobile decision-making method based on imitation learning and discrete reinforcement learning | |
| CN114148349B (en) | Vehicle personalized following control method based on generation of countermeasure imitation study | |
| CN114492043B (en) | Personalized driver following modeling method considering perception limited characteristics | |
| CN114802306A (en) | Intelligent vehicle integrated decision-making system based on man-machine co-driving concept | |
| CN117877245A (en) | Novel heterogeneous mixed traffic flow model grading evaluation and construction method | |
| Guo et al. | Modeling, learning and prediction of longitudinal behaviors of human-driven vehicles by incorporating internal human DecisionMaking process using inverse model predictive control | |
| Teng et al. | Car following model based on driving risk field for vehicle infrastructure cooperation | |
| CN112801149B (en) | Multi-vehicle-queue control method based on deep reinforcement learning | |
| Liu et al. | Personalized Automatic Driving System Based on Reinforcement Learning Technology | |
| Wei et al. | A learning-based autonomous driver: emulate human driver's intelligence in low-speed car following | |
| CN116127853A (en) | Unmanned driving overtaking decision method based on DDPG (distributed data base) with time sequence information fused |
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 |