CN112373483B - Vehicle speed and steering prediction method based on forward neural network - Google Patents
Vehicle speed and steering prediction method based on forward neural network Download PDFInfo
- Publication number
- CN112373483B CN112373483B CN202011324075.7A CN202011324075A CN112373483B CN 112373483 B CN112373483 B CN 112373483B CN 202011324075 A CN202011324075 A CN 202011324075A CN 112373483 B CN112373483 B CN 112373483B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- steering
- neural network
- forward neural
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 42
- 238000003062 neural network model Methods 0.000 claims abstract description 40
- 238000004088 simulation Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000005070 sampling Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010998 test method Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 101001093748 Homo sapiens Phosphatidylinositol N-acetylglucosaminyltransferase subunit P Proteins 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/105—Speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
- B60W2050/0031—Mathematical model of the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Automation & Control Theory (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a vehicle speed and steering prediction method based on a forward neural network, which comprises the following steps: carrying out a simulated driving test and collecting vehicle data, wherein the vehicle data comprises the distance from a front vehicle, the speed, the steering wheel angle and a steering signal; establishing a forward neural network model, training the forward neural network model by using the collected vehicle data, and obtaining the forward neural network model for predicting the vehicle speed and steering after the vehicle data is tested to be qualified; and predicting the speed and the steering of the vehicle through the established forward neural network model for predicting the speed and the steering of the vehicle according to the distance between the vehicle and the front vehicle, the speed, the steering wheel angle and the steering signal. The method has the advantages that the method collects relevant data of vehicle running through a simulation driving test, establishes a forward neural network model for predicting vehicle speed and steering, can be used for simultaneously predicting vehicle speed and steering wheel angle, and has low requirements on data and small calculation amount.
Description
Technical Field
The invention relates to the technical field of traffic safety, in particular to a vehicle speed and steering prediction method based on a forward neural network.
Background
Today, the level of computer information technology and the level of traffic infrastructure are increasing, and the automobile industry is developing towards intellectualization and unmanned direction at an unprecedented speed. In the vehicle intelligent process, how to accurately predict the vehicle running state is an important problem. The accurate prediction of the vehicle track not only enables the vehicle to arrive at the destination in a faster and safer manner, but also can avoid a large number of human safety accidents. Therefore, the prediction of the driving state of the vehicle will be a very important research hotspot in the future. However, the vehicle itself is a complex nonlinear system, and the behavior of the driver is influenced by the driving experience, the driving environment, and other factors.
The patent CN201810947025.0 proposes a vehicle speed prediction method based on quantitative adaptive Kalman filtering, which is used in an intelligent networked transportation system, automatically identifies a running vehicle through a DSRC technology and obtains related data, and predicts the vehicle speed by combining with the Kalman filtering. Therefore, a prediction method is needed that requires less data, requires less computation, and can predict the vehicle speed and the steering wheel angle at the same time.
Disclosure of Invention
In order to solve the problems of the prior art, the main object of the present invention is to provide a vehicle speed and steering prediction method based on a forward neural network, which uses vehicle driving related data obtained by a simulation driver through a simulation driving test to establish a prediction model of a vehicle speed and a steering wheel angle, and predicts the vehicle speed, the steering wheel angle and a steering signal according to the model.
In order to achieve the above object, the present invention provides a method for predicting vehicle speed and steering based on a forward neural network, the method comprising the steps of: carrying out a simulated driving test and collecting vehicle data, wherein the vehicle data comprises the distance from a front vehicle, the speed, the steering wheel angle and a steering signal; establishing a forward neural network model, training the forward neural network model by using the acquired vehicle data, and obtaining the forward neural network model for predicting the vehicle speed and steering after the vehicle data is tested to be qualified; and predicting the speed and the steering of the vehicle through the established forward neural network model for predicting the speed and the steering of the vehicle according to the distance between the vehicle and the front vehicle, the speed, the steering wheel angle and the steering signal.
Further, in the simulated driving test, the simulated driving system adopts a 1:1 virtual city road condition, and the test time of the driver driving the simulated vehicle is not less than 2 hours. The 1:1 virtual city road condition is adopted to enhance the reliability of the test.
In the simulation driving test, a virtual laser radar is mounted right in front of the vehicle driven by the driver and used for detecting the distance of the vehicle in front of the same lane, and the detection angle is 90 degrees and the range is 100 m.
Further, the steering signal is divided into three states of straight movement, left turning and right turning, and is correspondingly represented by three different numerical values. In a preferred embodiment, three steering signals for straight, left and right turns are represented by 0,1,2, respectively.
Further, before establishing the forward neural network model, the method further comprises the step of processing the collected vehicle data, wherein the data processing mode is as follows: different variables in vehicle data collected by a simulation driving test are arranged and placed into the same data group, and each group of data comprises 30 variables, namely the distance between a vehicle and a front vehicle at the current sampling moment, the current vehicle speed, the current steering wheel corner, the current steering signal, and the distances between 4 vehicles corresponding to the previous 4 sampling moments, the vehicle speed, the steering wheel corner and the steering signal.
Further, before establishing the forward neural network model, classifying the acquired vehicle data, and using the vehicle data acquired 90% of the time period before the original data as a modeling data set for training the forward neural network model; and taking the vehicle data acquired in the last 10% time period of the original data as a test data set for testing the trained forward neural network model.
Furthermore, the established forward neural network model has 16 inputs, 3 outputs and 2 hidden layers, wherein each hidden layer comprises 40 nodes; when the forward neural network model is trained, the distances between 4 corresponding to the previous 4 sampling moments in each modeling data point of the modeling data set and a previous vehicle, the vehicle speed, the steering wheel angle and the steering signal are used as input variables, and the distances between each modeling data point of the modeling data set and the previous vehicle, the current vehicle speed, the current steering wheel angle and the current steering signal are used as output variables to train the forward neural network model for predicting the vehicle speed and steering.
Still further, the method of testing the established forward neural network model for predicting vehicle speed and steering is: and if the calculated steering signal is correct, the relative error of the vehicle speed is less than 15%, and the error of the steering wheel corner is less than 10%, the test data point is successfully predicted, otherwise, the test data point fails.
If the prediction success rate of the forward neural network model for predicting the vehicle speed and the steering is larger than 75%, the model is acceptable, otherwise, the model is modeled again.
Due to the adoption of the technical scheme, the invention achieves the following technical effects: the method has the advantages of low data requirement, less calculation amount, simple implementation and low cost.
Drawings
Fig. 1 is a schematic flow chart of modeling steps of a vehicle speed and steering prediction method based on a forward neural network according to the present invention.
Detailed Description
In order to make the technical solution of the embodiments of the present invention better understood, the technical solution of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by equivalent changes and modifications by one skilled in the art based on the embodiments of the present invention, shall fall within the scope of the present invention.
Referring to fig. 1, the present embodiment provides a vehicle speed and steering prediction method based on a forward neural network, which mainly includes establishing a forward neural network model for predicting vehicle speed and steering and using the model to predict vehicle speed and steering. Wherein the modeling process comprises the steps of:
s1, carrying out a test and acquiring data:
a simulated driver is used for carrying out a simulated driving test, and a 1:1 virtual city road condition is adopted in the simulated driving test, so that the reliability of the test is enhanced; a virtual laser radar is mounted right ahead a vehicle driven by a driver and used for detecting the distance of the vehicle in front of the same lane, the detection angle is 90 degrees, and the range is 100 m; the vehicle data needing to be collected in the simulation driving test comprise vehicle speed, steering wheel turning angle and steering signals, wherein the steering signals are divided into three states: straight, left-turn, right-turn, respectively represented by 0,1, 2; in the whole test process, the driver can not violate the traffic rules and the test time can not be less than 2 hours. The frequency of collecting vehicle data was 100 Hz.
S2, processing and classifying test data:
the vehicle data collected at S1 is processed and classified. The mode of processing the test data is to arrange different variable data in the test data into the same data group. Each group of data comprises 30 variables, namely the distance between the vehicle and the previous vehicle at the current sampling moment, the current vehicle speed, the current steering wheel angle, the current steering signal, and the distances between 4 vehicles corresponding to the previous 4 sampling moments, the vehicle speed, the steering wheel angle and the steering signal. The raw data is classified in such a way that data acquired in the last 10% of the time period of the raw test data is used as a test data set, and data acquired in the first 90% of the time period is used as a modeling data set.
S3, establishing a model:
and establishing a forward neural network model, wherein the established forward neural network model has 16 inputs, 3 outputs and 2 hidden layers, and each hidden layer comprises 40 nodes.
S4, training a model:
when the forward neural network model is trained, the distances between 4 corresponding to the first 4 sampling moments in data points (namely a group of data) in each modeling data set and a front vehicle, the vehicle speed, the steering wheel angle and the steering signal are used as input variables, the distances between the modeling points and the front vehicle, the current vehicle speed, the current steering wheel angle and the current steering signal are used as output variables, the forward neural network model for predicting the vehicle speed and steering is trained, and the MSE value of the output variables is minimized in the training process as a target. In this embodiment, the MSE value of the output variable after model training is 0.8.
S4, testing the model:
the method for testing the established forward neural network model for predicting the vehicle speed and the steering comprises the steps of calculating the current vehicle speed, the current steering wheel angle and the current steering signal through the model by taking the distances between 4 corresponding to the first 4 sampling moments in data points in each test data set and the vehicle ahead, the vehicle speed, the steering wheel angle and the steering signal as input variables of the trained forward neural network model for predicting the vehicle speed and the steering. If the prediction of the steering signal is correct, the relative error of the vehicle speed is less than 15%, and the error of the steering angle is less than 10%, the test data point is successfully predicted, otherwise, the test data point fails. If the success rate of data points of the whole test data set through the model prediction is larger than 75%, the model is acceptable, otherwise, the simulated driving test is carried out again.
The neural network model qualified in test is obtained by the method, when the neural network model is used for predicting the speed and the steering of a vehicle, the speed, the steering wheel steering angle and the steering signal of the vehicle can be predicted by the model according to the distance of the front vehicle of the vehicle, the vehicle speed, the steering wheel steering angle and the steering signal, and therefore the driver ability of a driver can be evaluated. Compared with the prior art, the method has the advantages of small calculated amount and low cost, and overcomes the limitation that the steering wheel angle cannot be predicted in the prior art.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention; also, the above description should be understood as being readily apparent to those skilled in the relevant art and can be implemented, and therefore, other equivalent changes and modifications without departing from the concept disclosed herein are intended to be included within the scope of the present invention.
Claims (6)
1. A vehicle speed and steering prediction method based on a forward neural network is characterized by comprising the following steps:
carrying out a simulated driving test and collecting vehicle data, wherein the vehicle data comprises the distance from a front vehicle, the speed, the steering wheel angle and a steering signal, and the steering signal is divided into three states of straight running, left turning and right turning and is correspondingly represented by three different numerical values; establishing a forward neural network model, training the forward neural network model by using the collected vehicle data, and obtaining the forward neural network model for predicting the vehicle speed and steering after the vehicle data is tested to be qualified; predicting the speed and the steering of the vehicle through the established forward neural network model for predicting the speed and the steering of the vehicle according to the distance between the vehicle and a front vehicle, the speed, the steering wheel angle and the steering signal; wherein:
Before the forward neural network model is established, the method also comprises the step of processing the acquired vehicle data, wherein the data processing mode is as follows: arranging different variables in vehicle data acquired by a driving simulation test into the same data group, wherein each group of data comprises 30 variables, namely the distance between a vehicle and a previous vehicle at the current sampling moment, the current vehicle speed, the current steering wheel corner, the current steering signal, and the distances between 4 vehicles corresponding to the previous 4 sampling moments, the vehicle speed, the steering wheel corner and the steering signal;
the established forward neural network model has 16 inputs, 3 outputs and 2 hidden layers, and each hidden layer comprises 40 nodes; when the forward neural network model is trained, the distances between 4 corresponding to the previous 4 sampling moments in each modeling data point of the modeling data set and a previous vehicle, the vehicle speed, the steering wheel angle and the steering signal are used as input variables, and the distances between each modeling data point of the modeling data set and the previous vehicle, the current vehicle speed, the current steering wheel angle and the current steering signal are used as output variables to train the forward neural network model for predicting the vehicle speed and steering.
2. The method as claimed in claim 1, wherein in the simulated driving test, the simulated driving system adopts 1:1 virtual city road conditions, and the test time for the driver to drive the simulated vehicle is not less than 2 hours.
3. The method for predicting the speed and the steering of the vehicle based on the forward neural network as claimed in claim 1, wherein in the simulation driving test, a virtual laser radar is mounted right in front of the vehicle driven by the driver and used for detecting the distance of the vehicle in front of the same lane, and the detection angle is 90 degrees and the range is 100 m.
4. The method of claim 1, wherein before the forward neural network model is built, the method further comprises classifying the collected vehicle data, and using the vehicle data collected 90% of the time period before the original data as a modeling data set for training the forward neural network model; and taking the vehicle data acquired in the last 10% time period of the original data as a test data set for testing the trained forward neural network model.
5. The forward neural network-based vehicle speed and steering prediction method according to claim 4, wherein the method of testing the established forward neural network model for predicting vehicle speed and steering is: and if the calculated steering signal is correct, the relative error of the vehicle speed is less than 15%, and the error of the steering wheel angle is less than 10%, the test data point is successfully predicted, and otherwise, the test data point fails.
6. The method as claimed in claim 5, wherein if the prediction success rate of the forward neural network model for predicting the vehicle speed and steering is greater than 75%, it means that the model is acceptable, otherwise, it is modeled again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011324075.7A CN112373483B (en) | 2020-11-23 | 2020-11-23 | Vehicle speed and steering prediction method based on forward neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011324075.7A CN112373483B (en) | 2020-11-23 | 2020-11-23 | Vehicle speed and steering prediction method based on forward neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112373483A CN112373483A (en) | 2021-02-19 |
| CN112373483B true CN112373483B (en) | 2022-07-29 |
Family
ID=74588876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011324075.7A Active CN112373483B (en) | 2020-11-23 | 2020-11-23 | Vehicle speed and steering prediction method based on forward neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112373483B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327430B (en) * | 2021-05-06 | 2022-11-01 | 天地（常州）自动化股份有限公司 | Method and device for predicting speed of underground trackless rubber-tyred vehicle based on LSTM |
| CN115923813B (en) * | 2023-03-13 | 2023-05-16 | 北京安录国际技术有限公司 | Driving behavior analysis method and system based on speed rapid change characteristics |
| CN117184105B (en) * | 2023-07-20 | 2024-03-26 | 清华大学 | Steering angular velocity prediction method and device based on multi-mode data fusion |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108944930A (en) * | 2018-07-05 | 2018-12-07 | 合肥工业大学 | A kind of automatic follow the bus method and system of drive simulating person's characteristic based on LSTM |
| CN109084992A (en) * | 2018-07-27 | 2018-12-25 | 长安大学 | Method based on engine bench test unmanned vehicle intelligence |
| CN110509957A (en) * | 2019-08-29 | 2019-11-29 | 交控科技股份有限公司 | A kind of train speed prediction technique and device |
| WO2020034630A1 (en) * | 2018-08-17 | 2020-02-20 | 东南大学 | Neural network-based cell delay prediction method and cell delay sensitivity calculation method |
| CN111738037A (en) * | 2019-03-25 | 2020-10-02 | 广州汽车集团股份有限公司 | Automatic driving method and system and vehicle |
| CN111797000A (en) * | 2020-05-27 | 2020-10-20 | 中汽数据有限公司 | Scene complexity evaluation method based on gradient lifting decision tree model |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105109491B (en) * | 2015-08-05 | 2017-08-04 | 江苏大学 | A kind of vehicle traveling course prediction device and Forecasting Methodology based on bend longitudinal curvature |
| CN109739218A (en) * | 2018-12-24 | 2019-05-10 | 江苏大学 | It is a kind of that outstanding driver's lane-change method for establishing model is imitated based on GRU network |
| CN109866752B (en) * | 2019-03-29 | 2020-06-05 | 合肥工业大学 | Method for tracking running system of dual-mode parallel vehicle track based on predictive control |
| CN111775949B (en) * | 2020-07-09 | 2023-11-21 | 中国人民解放军国防科技大学 | Personalized driver steering behavior auxiliary method of man-machine co-driving control system |
-
2020
- 2020-11-23 CN CN202011324075.7A patent/CN112373483B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108944930A (en) * | 2018-07-05 | 2018-12-07 | 合肥工业大学 | A kind of automatic follow the bus method and system of drive simulating person's characteristic based on LSTM |
| CN109084992A (en) * | 2018-07-27 | 2018-12-25 | 长安大学 | Method based on engine bench test unmanned vehicle intelligence |
| WO2020034630A1 (en) * | 2018-08-17 | 2020-02-20 | 东南大学 | Neural network-based cell delay prediction method and cell delay sensitivity calculation method |
| CN111738037A (en) * | 2019-03-25 | 2020-10-02 | 广州汽车集团股份有限公司 | Automatic driving method and system and vehicle |
| CN110509957A (en) * | 2019-08-29 | 2019-11-29 | 交控科技股份有限公司 | A kind of train speed prediction technique and device |
| CN111797000A (en) * | 2020-05-27 | 2020-10-20 | 中汽数据有限公司 | Scene complexity evaluation method based on gradient lifting decision tree model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112373483A (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112373483B (en) | Vehicle speed and steering prediction method based on forward neural network | |
| Altché et al. | An LSTM network for highway trajectory prediction | |
| CN110843789B (en) | Vehicle lane change intention prediction method based on time sequence convolution network | |
| CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
| US20190155291A1 (en) | Methods and systems for automated driving system simulation, validation, and implementation | |
| CN112099496A (en) | Automatic driving training method, device, equipment and medium | |
| CN107310550A (en) | Road vehicles travel control method and device | |
| CN114212110B (en) | Obstacle trajectory prediction method and device, electronic equipment and storage medium | |
| CN113076897B (en) | Game dynamic driving safety measurement and control method and terminal for intelligent network-connected automobile | |
| Valera et al. | Driving cycle and road grade on-board predictions for the optimal energy management in EV-PHEVs | |
| CN111845787A (en) | Lane change intention prediction method based on LSTM | |
| US20220383736A1 (en) | Method for estimating coverage of the area of traffic scenarios | |
| CN117454318B (en) | Bridge group space-time load distribution identification method based on multi-source data fusion | |
| KR20230159308A (en) | Method, system and computer program product for calibrating and validating an advanced driver assistance system (adas) and/or an automated driving system (ads) | |
| CN115523934A (en) | Vehicle track prediction method and system based on deep learning | |
| CN113933858A (en) | Abnormal detection method and device of positioning sensor and terminal equipment | |
| CN116917827A (en) | Proxy conversion in driving simulation | |
| CN112560782A (en) | Vehicle lane changing behavior identification method based on random forest algorithm | |
| CN114475656A (en) | Travel track prediction method, travel track prediction device, electronic device, and storage medium | |
| CN114495486A (en) | Microscopic traffic flow prediction system and method based on hierarchical reinforcement learning | |
| CN117268415A (en) | Intelligent vehicle path planning method and system integrating LTSM prediction model | |
| CN112002126A (en) | Method and system for predicting long-term trajectory of vehicle in complex scene | |
| CN115454082A (en) | Vehicle obstacle avoidance method and system, computer readable storage medium and electronic device | |
| Zareian et al. | A combined Apriori algorithm and fuzzy controller for simultaneous ramp metering and variable speed limit determination in a freeway | |
| CN112308171A (en) | Vehicle position prediction modeling method based on simulated driver |
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 |