CN110555476A - intelligent vehicle track change track prediction method suitable for man-machine hybrid driving environment - Google Patents
intelligent vehicle track change track prediction method suitable for man-machine hybrid driving environment Download PDFInfo
- Publication number
- CN110555476A CN110555476A CN201910809352.4A CN201910809352A CN110555476A CN 110555476 A CN110555476 A CN 110555476A CN 201910809352 A CN201910809352 A CN 201910809352A CN 110555476 A CN110555476 A CN 110555476A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- track
- lane change
- data
- relative
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Abstract
the invention discloses an intelligent vehicle track change prediction method suitable for a man-machine mixed driving environment, which comprises the following steps: s1, acquiring the track data of the running unmanned automobile on the highway section; s2, processing the acquired driving track data, acquiring the spatial information and the motion information of the vehicle and the data information of the relative state of the adjacent vehicle, screening lane change data according to the data information, and generating a sample database; s3, constructing a track change prediction model of the unmanned vehicle; s4, carrying out vehicle lane change track prediction model training to obtain an optimal lane change track prediction model structure, an optimal training sample capacity and an optimal historical sequence length; and S5, verifying the vehicle lane change track prediction model trained in the S4.
Description
Technical Field
the invention relates to the technical field of unmanned driving, in particular to an intelligent vehicle track change prediction method suitable for a man-machine mixed driving environment.
background
the man-machine hybrid driving traffic environment refers to a traffic environment in which manually driven vehicles and unmanned vehicles run in a hybrid mode in a future road system. With the rapid development of the automatic driving technology, in the foreseeable future, unmanned vehicles will enter the actual road traffic system and will operate in the man-machine hybrid driving traffic environment for a long time. The lane changing behavior is a basic driving task of traffic and has important significance on driving safety and traffic flow stability. However, the precision of the existing lane changing model cannot meet the practical use. At present, no document exists in the aspect of track change prediction of an unmanned vehicle based on deep learning in a man-machine hybrid driving environment.
The classical lane change behavior research mainly comprises two types of lane change intention prediction research and lane change track prediction research, and typical representatives of the classical lane change behavior research comprise a Gipps model, a cellular automaton model, a Markov model and the like. In order to reduce the calculation difficulty, the models simplify the lane changing behavior of the driver, so that the models cannot accurately reproduce the lane changing process of the vehicle and cannot meet the requirements of the lane changing behavior model of the unmanned vehicle in a man-machine mixed driving environment. In recent years, researchers have studied lane-change behavior using machine learning methods from a data-driven perspective, and most of the research has focused on lane-change intent prediction, and some research has focused on lane-change time prediction. With the development of automatic driving technology, track change trajectory prediction becomes a new research hotspot. However, the existing driverless vehicle lane changing behavior model still faces the problems that the model is too complicated and is not suitable for use or the accuracy is insufficient.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides an intelligent vehicle track change prediction method suitable for a man-machine hybrid driving environment.
The invention adopts the following technical scheme:
An intelligent vehicle track change track prediction method suitable for a man-machine mixed driving environment comprises the following steps:
S1, acquiring track data of the unmanned automobile travelling on the highway section;
S2, processing the acquired driving track data, acquiring the spatial information and motion information of the vehicle and the data information of the relative state of the adjacent vehicle, screening lane change data, and generating a sample database;
the data information of the relative state of the adjacent vehicles is specifically the relative state vector of the lane-switching vehicle i and the adjacent vehicle jwherein Δ xi,j(t),Δyi,j(t),Δvi,j(t) represents the relative x-axis coordinate, relative y-axis coordinate, and relative speed of vehicles i and j, respectively, at time t;
S3, constructing a track change prediction model of the unmanned vehicle, wherein the input variables of the model are 6N, and the output variables are 2;
S4, carrying out vehicle lane change track prediction model training to obtain an optimal lane change track prediction model structure, an optimal training sample capacity and an optimal historical sequence length;
And S5, verifying the vehicle lane change track prediction model trained in the S4.
the 6N input variables of the model are:
destination of lane change
designating a lane change destination of a lane change vehicle i at a time t- (N-1) τ, wherein N is 1,2, …, N and N are history sequence lengths, and τ is a time interval between input time sequences;
② infrastructure information M
taking the transverse x-axis coordinate of the median line of the lane with the nearest current position of the vehicle i as infrastructure information;
③ vehicle parameter Ci
the length and the width of the vehicle i are used for characterizing the vehicle type, namely:
Ci={Wi,Li}
In the formula, Wi、Liwidth and length of vehicle i, respectively;
State vector
Including the instant speed of the vehicle i itself, the direction and magnitude of the motion state in the lane change process, namely:
In the formula, xi(t-(n-1)τ),yi(t-(n-1)τ),vi(t- (n-1) tau) is the x-axis coordinate, the y-axis coordinate and the speed of the vehicle i at the time of t- (n-1) tau respectively;
vehicle parameter Cj
The length and width of the adjacent vehicle j are used for characterizing the vehicle type, namely:
Cj={Wj,Lj}
in the formula, Wj、Ljwidth and length of vehicle j, respectively;
Relative state vector
the relative speed of the vehicles i and j, and the direction and the amplitude of the relative motion state of the vehicles i and j in the lane changing process are included, namely:
in the formula,. DELTA.xi,j(t-(n-1)τ),Δyi,j(t-(n-1)τ),Δvi,jAnd (t- (n-1) tau) is the relative x-axis coordinate, the relative y-axis coordinate and the relative speed magnitude of the vehicles i and j at the moment of t- (n-1) tau respectively.
The output variables of the model are:
a model predicts a result x (T + T) of a position of a vehicle in an x-axis direction;
In the formula, T represents prediction delay and has the value range of 0.1-1.5 s;
and secondly, predicting the position of the vehicle in the y-axis direction by the model to obtain a result y (T + T).
in the step S4, RMSprop is used as an optimization method, and a back propagation algorithm is used as a basic method for calculating a gradient.
Preferably, the total number of training samples is not less than 50000, the total number of precision verification samples is not less than 10000, the track precision requirement is within 0.5m, and the sample sampling rate is between 1 Hz and 10 Hz.
Preferably, the spatial information of the vehicle itself specifically refers to road information and a road position where the vehicle is located; the motion information refers to speed information.
The invention has the beneficial effects that:
1. Compared with the traditional lane change track prediction method, the method accurately reproduces the lane change process of the driver, and has the advantages of simplicity and easiness in implementation due to the fact that the method is based on a deep learning method.
2. According to the invention, a deep learning modeling method is adopted, so that higher-dimensional input parameters can be processed, and the reduction of the real driving behavior is achieved by acquiring more input information. Meanwhile, the invention integrates the forecasting ability and the memory effect of the driver into a model. Therefore, compared with the traditional track changing track prediction method, the method has higher precision.
3. According to the method, from the data driving angle, model training is carried out through actual driving vehicle track data, and the obtained track changing track prediction model can be automatically adjusted according to the characteristics of the actual data, so that the method has good adaptivity and robustness.
4. the method can predict the driveway change track of the unmanned vehicle in the man-machine mixed driving environment, can be used as the basis of a driveway prediction model of the unmanned vehicle in the future realization of the completely unmanned vehicle environment, and has great practical popularization value.
drawings
FIG. 1 is a flow chart of the operation of the present invention;
FIGS. 2(a) and 2(b) are views of the research link of the present invention;
FIG. 3 is a schematic view of the model structure of the present invention;
FIG. 4 is a flow chart of a training sample of the present invention.
Detailed Description
the present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited to these examples.
Examples
As shown in fig. 1-3, an intelligent vehicle lane change trajectory prediction method suitable for a human-computer hybrid driving environment includes the following steps:
s1, acquiring the track data of the running unmanned automobile on the highway section;
s2, the acquired driving track data are processed to acquire the space information, the motion information and the data information of the relative state of the adjacent vehicle, and the lane changing data are screened out according to the data information to generate a sample database required by the model.
Firstly, preliminarily screening the obtained data, proposing vehicle data with missing information, obtaining the spatial information and the motion information of the vehicle and the data information of the relative state of the adjacent vehicle, screening the lane change data according to the information, and generating a sample database with the sequence length of N.
the vehicle space information includes a lane in which the vehicle is traveling and a position of the vehicle within the lane.
the vehicle motion information includes information such as vehicle speed, vehicle length, and vehicle width.
The relative state of the adjacent vehicles is mainly a relative state vector of the lane-changing vehicle i and the adjacent vehicle jWherein Δ xi,j(t),Δyi,j(t),Δvi,j(t) represents the relative x-axis coordinate, relative y-axis coordinate, and relative velocity of vehicles i and j, respectively, at time t.
screening the missing of historical data of the vehicle from the processed lane change data, and removing the lane change data with abnormal data in the data; and generating a sample library according to the required historical sequence length N.
s3, constructing a track change prediction model of the unmanned vehicle, wherein the input variables of the model are 6N, the output variables are 2, and N is the length of a sample sequence;
And (4) processing the data obtained in the step (S2) to obtain a training sample set and a precision verification sample set, wherein the number of the obtained training samples exceeds 110000, and the number of the obtained precision verification samples is 37440.
The 6 input variables of the model are:
Destination of lane change
The method comprises the steps of designating a lane change destination of a lane change vehicle i at a time t- (N-1) tau, wherein N is 1,2, …, N and N are historical sequence lengths, tau is a time interval between input time sequences, and a value range is 0.05-0.4s in consideration of the development of the current Intelligent networking vehicle (ICV) data acquisition technology and speed data precision requirements.
② infrastructure information M
Taking the transverse x-axis coordinate of the median line of the lane with the nearest current position of the vehicle i as infrastructure information;
③ vehicle parameter Ci
the length and the width of the vehicle i are used for characterizing the vehicle type, namely:
Ci={Wi,Li}
In the formula, Wi、Liwidth and length of vehicle i, respectively;
state vector
including the instant speed of the vehicle i itself, the direction and magnitude of the motion state in the lane change process, namely:
In the formula, xi(t-(n-1)τ),yi(t-(n-1)τ),vi(t- (n-1) tau) is the x-axis coordinate, the y-axis coordinate and the speed of the vehicle i at the time of t- (n-1) tau respectively;
Vehicle parameter Cj
The length and width of the adjacent vehicle j are used for characterizing the vehicle type, namely:
Cj={Wj,Lj}
In the formula, Wj、LjWidth and length of vehicle j, respectively;
Relative state vector
the relative speed of the vehicles i and j, and the direction and the amplitude of the relative motion state of the vehicles i and j in the lane changing process are included, namely:
In the formula,. DELTA.xi,j(t-(n-1)τ),Δyi,j(t-(n-1)τ),Δvi,j(t- (n-1) tau) is the relative x-axis coordinate, the relative y-axis coordinate and the relative speed of the vehicles i and j at the time of t- (n-1) tau respectively, and the calculation formulas are as follows:
Δxi,j(t-(n-1)τ)=xj(t-(n-1)τ)-xi(t-(n-1)τ)
in the formula, xi(t-(n-1)τ),xj(t- (n-1) τ) are x-axis coordinates of vehicles i and j at time t- (n-1) τ, respectively;
Δyi,j(t-(n-1)τ)=yj(t-(n-1)τ)-yi(t-(n-1)τ)
In the formula, yi(t-(n-1)τ,yj(t- (n-1) τ) are y-axis coordinates of the vehicles i and j at the time of t- (n-1) τ, respectively;
Δvi,j(t-(n-1)τ)=vj(t-(n-1)τ)-vi(t-(n-1)τ)
In the formula, vi(t-(n-1)τ,vj(t- (n-1) τ) is the speed magnitude of vehicles i and j at time t- (n-1) τ, respectively.
The 2 output variables of the model are respectively:
a model predicts a result x (T + T) of a position of a vehicle in an x-axis direction;
In the formula, T represents prediction delay and has the value range of 0.1-1.5 s;
And secondly, predicting the position of the vehicle in the y-axis direction by the model to obtain a result y (T + T).
s4, carrying out vehicle lane change track prediction model training to obtain an optimal lane change track prediction model structure, an optimal training sample capacity and an optimal historical sequence length;
Modeling the lane changing track by using different neural network model structures and different sample quantities, selecting a neural network structure with representative hidden layer number and each layer node number, and training each network structure by using different training data quantities respectively to obtain an optimal structure scheme and an optimal training sample quantity;
Under the condition of the optimal network structure and the optimal training sample size, training the track-changing track prediction models with different historical sequence lengths N, and selecting the optimal historical sequence length N.
and S5, verifying the vehicle lane change track prediction model trained in the S4.
verifying the trained optimal track-changing track prediction model by using verification sample data, and determining and calculating corresponding input variables, wherein the method comprises the following steps:M,Ci,Cj,wherein N is 1,2, …, N; inputting the variables into a lane-changing track prediction modelOutputting position prediction results x (T + T) and y (T + T) of the vehicle in the x-axis direction and the y-axis direction;
the error analysis index is Mean Square Error (MSE).
The invention is illustrated in detail by an embodiment of the method:
Firstly, actual driving vehicle track data on the U.S. I-101 expressway and I-80 expressway sections in an NGSIM data set are selected as original data for constructing a track change track sample library, and the original data comprise manual driving vehicle track data in a period of 7:50-8:35a.m. The study route is shown in fig. 2(a) and 2 (b).
Then processing the acquired driving track data, acquiring the spatial information and motion information of the vehicle, and calculating data containing the relative state of the adjacent vehicle; primary screening is carried out on the original data, and vehicle data with missing information are removed; judging adjacent vehicles according to the obtained data, and storing relevant information (including vehicle length, vehicle width, speed, position and the like); calculating the relative state of the obtained data with the adjacent vehicles, and screening lane change data; screening the missing of historical data of the vehicle from the processed lane change data, and removing the lane change data with abnormal data in the data; and generating a sample library according to the required historical sequence length N.
then, a long-term and short-term memory neural network-based prediction model for the track change of the unmanned vehicle is constructed, and the model structure is shown in FIG. 3.
and according to the input and output variables of the model, performing data processing on the original lane change track database to form a lane change track sample library of the manually-driven vehicle, wherein the lane change track sample library comprises a training sample set and a precision verification sample set, and more than 110000 training samples and 37440 precision verification samples are obtained.
randomly extracting 10,000 models under different historical sequence lengths N for testing to obtain a testing historical sequence length N which is 5;
modeling the lane change track by using different neural network model structures and different sample sizes, selecting a neural network structure with representative hidden layer number and each layer node number, and respectively training each network structure by using different training data sizes to obtain an optimal structure scheme 1LS1 and an optimal training sample size 110000;
Training LSTM-LC models with different historical sequence lengths N under the conditions of an optimal network structure 1LS1 and an optimal training sample size 110000, and selecting the optimal historical sequence length N to be 5;
and finally, performing precision verification on the trained LSTM-LC model by using 37440 precision verification samples.
The model verification result of the embodiment is ideal, and the mean square error of the constructed unmanned vehicle track change track prediction model based on the LSTM is 3.18m2This result is satisfactory in view of the complicated detailed operation and diversification of the situation in the lane change behavior of the vehicle.
In conclusion, the method for predicting the track change of the unmanned vehicle based on deep learning in the man-machine mixed driving environment is formed, the track change track of the unmanned vehicle can be rapidly and effectively predicted by using the measured data, a foundation is laid for developing a prediction model of the driving track of the unmanned vehicle, and the method has practical popularization value and is worthy of popularization.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (6)
1. An intelligent vehicle track change track prediction method suitable for a man-machine mixed driving environment is characterized by comprising the following steps:
S1, acquiring track data of the unmanned automobile travelling on the highway section;
S2, processing the acquired driving track data, acquiring the spatial information and motion information of the vehicle and the data information of the relative state of the adjacent vehicle, screening lane change data, and generating a sample database;
The data information of the relative state of the adjacent vehicles is specifically the lane-changing vehicle i and the adjacent vehiclesRelative state vector of vehicle jwherein Δ xi,j(t),Δyi,j(t),Δvi,j(t) represents the relative x-axis coordinate, relative y-axis coordinate, and relative speed of vehicles i and j, respectively, at time t;
S3, constructing a track change prediction model of the unmanned vehicle, wherein the input variables of the model are 6N, the output variables are 2, and N is the length of a sample sequence;
S4, carrying out vehicle lane change track prediction model training to obtain an optimal lane change track prediction model structure, an optimal training sample capacity and an optimal historical sequence length;
And S5, verifying the vehicle lane change track prediction model trained in the S4.
2. The intelligent vehicle track change prediction method suitable for the man-machine mixed driving environment according to claim 1, wherein 6N input variables of the model are as follows:
Destination of lane change
Designating a lane change destination of a lane change vehicle i at a time t- (N-1) τ, wherein N is 1,2, …, N and N are history sequence lengths, and τ is a time interval between input time sequences;
② infrastructure information M
taking the transverse x-axis coordinate of the median line of the lane with the nearest current position of the vehicle i as infrastructure information;
③ vehicle parameter Ci
The length and the width of the vehicle i are used for characterizing the vehicle type, namely:
Ci={Wi,Li}
In the formula, Wi、LiWidth and length of vehicle i, respectively;
State vector
Including the instant speed of the vehicle i itself, the direction and magnitude of the motion state in the lane change process, namely:
in the formula, xi(t-(n-1)τ),yi(t-(n-1)τ),vi(t- (n-1) tau) is the x-axis coordinate, the y-axis coordinate and the speed of the vehicle i at the time of t- (n-1) tau respectively;
Vehicle parameter Cj
the length and width of the adjacent vehicle j are used for characterizing the vehicle type, namely:
Cj={Wj,Lj}
in the formula, Wj、LjWidth and length of vehicle j, respectively;
relative state vector
The relative speed of the vehicles i and j, and the direction and the amplitude of the relative motion state of the vehicles i and j in the lane changing process are included, namely:
in the formula,. DELTA.xi,j(t-(n-1)τ),Δyi,j(t-(n-1)τ),Δvi,jand (t- (n-1) tau) is the relative x-axis coordinate, the relative y-axis coordinate and the relative speed magnitude of the vehicles i and j at the moment of t- (n-1) tau respectively.
3. The intelligent vehicle track change prediction method suitable for the man-machine mixed driving environment according to claim 1, wherein the output variables of the model are as follows:
a model predicts a result x (T + T) of a position of a vehicle in an x-axis direction;
In the formula, T represents prediction delay and has the value range of 0.1-1.5 s;
and secondly, predicting the position of the vehicle in the y-axis direction by the model to obtain a result y (T + T).
4. the intelligent vehicle lane change track prediction method suitable for the man-machine hybrid driving environment as claimed in claim 1, wherein in the step S4, RMSprop is adopted as an optimization method, and a back propagation algorithm is adopted as a basic method for calculating the gradient.
5. The intelligent vehicle track change track prediction method suitable for the man-machine mixed driving environment as claimed in claim 1, wherein the total number of training samples is not less than 50000, the total number of precision verification samples is not less than 10000, the track precision requirement is within 0.5m, and the sample sampling rate is between 1 Hz and 10 Hz.
6. the intelligent vehicle switching track prediction method suitable for the man-machine mixed driving environment according to claim 1, wherein the spatial information of the vehicle is specifically road information and a road position where the vehicle is located; the motion information refers to speed information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910809352.4A CN110555476B (en) | 2019-08-29 | 2019-08-29 | Intelligent vehicle lane change track prediction method suitable for man-machine hybrid driving environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910809352.4A CN110555476B (en) | 2019-08-29 | 2019-08-29 | Intelligent vehicle lane change track prediction method suitable for man-machine hybrid driving environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110555476A true CN110555476A (en) | 2019-12-10 |
CN110555476B CN110555476B (en) | 2023-09-26 |
Family
ID=68738437
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910809352.4A Active CN110555476B (en) | 2019-08-29 | 2019-08-29 | Intelligent vehicle lane change track prediction method suitable for man-machine hybrid driving environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110555476B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111114556A (en) * | 2019-12-24 | 2020-05-08 | 北京工业大学 | Lane change intention identification method based on LSTM under multi-source exponential weighting loss |
CN111243309A (en) * | 2020-01-10 | 2020-06-05 | 北京航空航天大学 | Expressway traffic flow full-sample trajectory reconstruction method based on automatic driving vehicle movement detection |
CN111310735A (en) * | 2020-03-18 | 2020-06-19 | 桂林电子科技大学 | Automobile track prediction method based on LSTM technology |
CN112965489A (en) * | 2021-02-05 | 2021-06-15 | 北京理工大学 | Intelligent vehicle high-speed lane change planning method based on collision detection |
CN113033899A (en) * | 2021-03-29 | 2021-06-25 | 同济大学 | Unmanned adjacent vehicle track prediction method |
US11433923B2 (en) | 2020-06-10 | 2022-09-06 | Toyota Motor Engineering & Manufacturing North America, Inc. | Systems and methods for long-term prediction of lane change maneuver |
CN115071704A (en) * | 2022-07-19 | 2022-09-20 | 小米汽车科技有限公司 | Trajectory prediction method, apparatus, medium, device, chip and vehicle |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN107315411A (en) * | 2017-07-04 | 2017-11-03 | 合肥工业大学 | A kind of lane-change method for planning track based on automatic driving vehicle under collaborative truck |
CN109460023A (en) * | 2018-11-09 | 2019-03-12 | 上海理工大学 | Driver's lane-changing intention recognition methods based on Hidden Markov Model |
CN109471436A (en) * | 2018-11-09 | 2019-03-15 | 上海理工大学 | Based on mixed Gaussian-Hidden Markov Model lane-change Model Parameter Optimization method |
CN109711557A (en) * | 2018-12-28 | 2019-05-03 | 西安航空学院 | A kind of wheelpath prediction technique, system, computer equipment and storage medium |
CN110085056A (en) * | 2019-04-24 | 2019-08-02 | 华南理工大学 | Vehicle lane-changing instantaneous risk recognition methods under a kind of highway bus or train route cooperative surroundings |
CN110146100A (en) * | 2018-02-13 | 2019-08-20 | 华为技术有限公司 | Trajectory predictions method, apparatus and storage medium |
-
2019
- 2019-08-29 CN CN201910809352.4A patent/CN110555476B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN107315411A (en) * | 2017-07-04 | 2017-11-03 | 合肥工业大学 | A kind of lane-change method for planning track based on automatic driving vehicle under collaborative truck |
CN110146100A (en) * | 2018-02-13 | 2019-08-20 | 华为技术有限公司 | Trajectory predictions method, apparatus and storage medium |
CN109460023A (en) * | 2018-11-09 | 2019-03-12 | 上海理工大学 | Driver's lane-changing intention recognition methods based on Hidden Markov Model |
CN109471436A (en) * | 2018-11-09 | 2019-03-15 | 上海理工大学 | Based on mixed Gaussian-Hidden Markov Model lane-change Model Parameter Optimization method |
CN109711557A (en) * | 2018-12-28 | 2019-05-03 | 西安航空学院 | A kind of wheelpath prediction technique, system, computer equipment and storage medium |
CN110085056A (en) * | 2019-04-24 | 2019-08-02 | 华南理工大学 | Vehicle lane-changing instantaneous risk recognition methods under a kind of highway bus or train route cooperative surroundings |
Non-Patent Citations (2)
Title |
---|
LING HUANG ET AL.: "Capturing Drivers" Lane Changing Behaviors on Operational Level by Data Driven Methods", 《IEEE ACCESS:SPECIAL SECTION ON ADVANCED BIG DATA ANALYSIS FOR VEHICULAR SOCIAL NETWORKS》 * |
季学武 等: "基于LSTM网络的驾驶意图识别及车辆轨迹预测", 《中国公路学报》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111114556A (en) * | 2019-12-24 | 2020-05-08 | 北京工业大学 | Lane change intention identification method based on LSTM under multi-source exponential weighting loss |
CN111243309A (en) * | 2020-01-10 | 2020-06-05 | 北京航空航天大学 | Expressway traffic flow full-sample trajectory reconstruction method based on automatic driving vehicle movement detection |
CN111310735A (en) * | 2020-03-18 | 2020-06-19 | 桂林电子科技大学 | Automobile track prediction method based on LSTM technology |
US11433923B2 (en) | 2020-06-10 | 2022-09-06 | Toyota Motor Engineering & Manufacturing North America, Inc. | Systems and methods for long-term prediction of lane change maneuver |
CN112965489A (en) * | 2021-02-05 | 2021-06-15 | 北京理工大学 | Intelligent vehicle high-speed lane change planning method based on collision detection |
CN113033899A (en) * | 2021-03-29 | 2021-06-25 | 同济大学 | Unmanned adjacent vehicle track prediction method |
CN113033899B (en) * | 2021-03-29 | 2023-03-17 | 同济大学 | Unmanned adjacent vehicle track prediction method |
CN115071704A (en) * | 2022-07-19 | 2022-09-20 | 小米汽车科技有限公司 | Trajectory prediction method, apparatus, medium, device, chip and vehicle |
CN115071704B (en) * | 2022-07-19 | 2022-11-11 | 小米汽车科技有限公司 | Trajectory prediction method, apparatus, medium, device, chip and vehicle |
Also Published As
Publication number | Publication date |
---|---|
CN110555476B (en) | 2023-09-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110555476A (en) | intelligent vehicle track change track prediction method suitable for man-machine hybrid driving environment | |
EP2610836B1 (en) | Device and method for the on-line prediction of the driving cycle in an automotive vehicle | |
CN107330217B (en) | Mesoscopic oil consumption prediction method based on RBFNN | |
CN113704956A (en) | Urban road online microscopic simulation method and system based on digital twin technology | |
CN110299011A (en) | A kind of traffic flow forecasting method of the highway arbitrary cross-section based on charge data | |
CN107346460A (en) | Following operating mode Forecasting Methodology based on the lower front truck operation information of intelligent network contact system | |
CN107310550A (en) | Road vehicles travel control method and device | |
CN113239986B (en) | Training method and device for vehicle track evaluation network model and storage medium | |
CN109272745A (en) | A kind of track of vehicle prediction technique based on deep neural network | |
Valera et al. | Driving cycle and road grade on-board predictions for the optimal energy management in EV-PHEVs | |
CN112633602B (en) | Traffic congestion index prediction method and device based on GIS map information | |
Suh et al. | Vehicle speed prediction for connected and autonomous vehicles using communication and perception | |
CN113642768A (en) | Vehicle running energy consumption prediction method based on working condition reconstruction | |
CN112749508B (en) | Road feel simulation method based on GMM and BP neural network | |
Shao et al. | Machine learning enabled traffic prediction for speed optimization of connected and autonomous electric vehicles | |
Amrani et al. | Train speed profiles optimization using a genetic algorithm based on a random-forest model to estimate energy consumption | |
CN114495486B (en) | Microcosmic traffic flow prediction system and microcosmic traffic flow prediction method based on hierarchical reinforcement learning | |
Wen et al. | Modeling human driver behaviors when following autonomous vehicles: An inverse reinforcement learning approach | |
EP4194249A1 (en) | Method for predicting energy consumption-recovery ratio of new energy vehicle, and energy saving control method and system | |
Rakow et al. | Investigation of the system-wide effects of intelligent infrastructure concepts with microscopic and mesoscopic traffic simulation | |
Gora | Designing urban areas using traffic simulations, artificial intelligence and acquiring feedback from stakeholders | |
Ni et al. | Research on Port truck trajectory completion based on Long Short-Term Memory model and Speed distribution characteristics | |
Wang | Simulation system for optimizing urban traffic network based on multi-scale fusion | |
CN113947922B (en) | Road network refined dynamic OD flow estimation method based on network segmentation | |
CN115909720B (en) | Traffic network state prediction method and system |
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 |