CN113954863A - Vehicle track prediction method based on double-attention machine system and improved Social Gan - Google Patents
Vehicle track prediction method based on double-attention machine system and improved Social Gan Download PDFInfo
- Publication number
- CN113954863A CN113954863A CN202111044320.3A CN202111044320A CN113954863A CN 113954863 A CN113954863 A CN 113954863A CN 202111044320 A CN202111044320 A CN 202111044320A CN 113954863 A CN113954863 A CN 113954863A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- gan
- attention
- track
- target vehicle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000002093 peripheral effect Effects 0.000 claims abstract description 32
- 238000011176 pooling Methods 0.000 claims abstract description 31
- 230000007246 mechanism Effects 0.000 claims abstract description 26
- 230000002452 interceptive effect Effects 0.000 claims abstract description 11
- 230000001133 acceleration Effects 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 description 11
- 238000012549 training Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000010200 validation analysis 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
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a vehicle track prediction method based on a double attention machine mechanism and improved Social Gan, which is characterized in that track characteristics of a target vehicle and peripheral vehicles are input into a vehicle track prediction model to predict a running track of the target vehicle at a future moment, the vehicle track prediction model comprises a coding layer, a pooling layer, a driving intention prediction module and a decoding layer, the pooling layer comprises two attention modules and an improved Social Gan pooling module, one attention module acts on the track characteristics of the coded target vehicle to carry out attention weighting on related variables influencing the track of the target vehicle, the other attention module acts on the track characteristics of the coded peripheral vehicles to carry out attention weighting on the importance degree of the peripheral vehicles influencing the target vehicle, and the improved Social Gan pooling module is used for extracting interactive characteristics of the peripheral vehicles. The invention effectively improves the prediction precision and can be better applied to the field of automatic driving.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and relates to a vehicle track prediction method based on a double-attention machine mechanism and improved Social Gan.
Background
The development of the automatic driving technology pushes the construction pace of the smart city, and brings great influence on road traffic safety and urban traffic management.
In order to ensure the safe driving of the automatic driving automobile, the driving tracks of the surrounding vehicles need to be predicted, the automatic driving automobile can plan a path in advance by using the predicted tracks of the surrounding vehicles, and the driving safety of the automobile can be improved, and the riding comfort of passengers can also be improved.
In the prior art, only the track information of the surrounding vehicles is used for prediction, and the interactive information between the vehicles and the road cannot be effectively utilized, so that the prediction precision is low.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a vehicle track prediction method based on a double-attention machine mechanism and improved Social Gan, and the precision of peripheral vehicle track prediction is improved.
The present invention achieves the above-described object by the following technical means.
The vehicle track prediction method based on the double-attention machine system and the improved Social Gan is used for constructing a vehicle track prediction model based on the double-attention machine system and the improved Social Gan to predict the running track of a target vehicle at a future moment;
the vehicle track prediction model based on the double-attention mechanism and the improved Social Gan comprises a coding layer, a pooling layer, a driving intention prediction module and a decoding layer;
the encoding layer comprises n +1 LSTM encoders, wherein the 1 LSTM encoder encodes the input track characteristics of the target vehicle, and the n LSTM encoders encode the input track characteristics of n peripheral vehicles;
the pooling layer comprises two attention modules and a pooling module for improving Social Gan, wherein one attention module acts on the track characteristics of the coded target vehicle to carry out attention weighting on related variables influencing the track of the target vehicle, the other attention module acts on the track characteristics of the coded peripheral vehicle to carry out attention weighting on the importance of the peripheral vehicle influencing the target vehicle, and the pooling module for improving Social Gan is used for extracting interactive characteristics of the peripheral vehicle;
the driving intention prediction module is used for predicting the transverse and longitudinal driving intention of the target vehicle in the next time period and decoding the transverse and longitudinal driving intention through an LSTM decoder of a decoding layer.
Further, the improved Social Gan pooling module is used for extracting interactive features of surrounding vehicles, and specifically comprises: calculating the relative position and the relative speed of the current position of the target vehicle and the last time period and the relative position and the relative speed of each surrounding vehicle and the target vehicle; the relative positions and relative speeds of the target vehicle and the surrounding vehicles are independently processed by the multilayer perceptron, and then the interactive features of the surrounding vehicles are extracted by using maximum pooling.
Further, the driving intention prediction module inputs a complete track obtained by splicing the track of the attention-weighted target vehicle and the track of the pooled surrounding vehicle.
Still further, the driving intention prediction module is composed of two sets of LSTM layers and Softmax layers, the LSTM layers encode a complete trajectory and perform multi-classification using a Softmax activation function to obtain the next time period of lateral driving intention and longitudinal driving intention.
Further, the LSTM decoder inputs a track with driving intention formed by splicing the predicted driving intention and the complete track.
Still further, the driving intent is determined by setting a trajectory prediction time and an acceleration threshold.
Further, the trajectory characteristics of the target vehicle include position information, lane information, speed and acceleration information, and a lateral-longitudinal driving intention of the target vehicle.
Further, the trajectory feature of the nearby vehicle is position information of the nearby vehicle.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, a double-attention mechanism is adopted, the related variables of the target vehicle track data and the position information of the surrounding vehicles are respectively acted on, and the characteristics with large influence on the target vehicle track can be effectively extracted by redistributing the weight; the method comprises the steps that a Social Gan pooling module is improved, peripheral vehicles of a target vehicle are identified at any time t, and the relative position and the relative speed of the target vehicle and the relative position and the relative speed of each peripheral vehicle and the target vehicle are calculated; the relative position and the relative speed are connected with the LSTM hidden state of each vehicle, the LSTM hidden state is independently processed by a multilayer perceptron, the maximum pooling is used for calculating and outputting the pooling tensor of the target vehicle, and finally a plurality of possible predicted tracks are generated according to probability through a plurality of LSTM networks; by utilizing the vehicle track prediction method based on the double-attention mechanism and the improved Social Gan, the precision of predicting the track of the peripheral vehicle can be improved.
Drawings
FIG. 1 is a flow chart of a vehicle trajectory prediction method based on a dual attention machine mechanism and improved Social Gan according to the present invention;
FIG. 2 is a schematic view of the present invention illustrating the extraction of surrounding vehicles;
FIG. 3 is a block diagram of a vehicle trajectory prediction model according to the present invention;
FIG. 4 is a diagram of a pooling module in the vehicle trajectory model according to the present invention.
Detailed Description
In order to more fully explain the present invention in detail, the technical solutions in the present specification will be clearly and completely described below with reference to the specific embodiments of the present specification and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.
As shown in fig. 1, the vehicle trajectory prediction method based on a dual-attention mechanism and improved Social Gan of the present invention specifically includes the following steps:
s1, preprocessing the vehicle track data set, and constructing a training set, a verification set and a test set
Firstly, acquiring position information, lane information, speed and acceleration information of vehicles (including a target vehicle and surrounding vehicles) from a vehicle track data set; secondly, extracting transverse and longitudinal driving intentions of the target vehicle according to driving intention standards, wherein the transverse driving intentions are lane keeping, lane changing to the left and lane changing to the right, and the longitudinal driving intentions are acceleration, deceleration and uniform speed; and taking the position information, the lane information, the speed and acceleration information and the transverse and longitudinal driving intentions of the target vehicle as the input track characteristics of the target vehicle.
The specific driving intention standard is as follows: and setting track prediction time, wherein the lane id of the target vehicle changes within the prediction time, namely the lane change is carried out, and otherwise, the lane keeping state is carried out. Setting an acceleration threshold value as a standard for judging the longitudinal driving intention type of the target vehicle, and considering that the vehicle is accelerated to run when the acceleration of the target vehicle is greater than the set threshold value; when the target vehicle acceleration is smaller than the negative threshold value, the vehicle is considered to run in a decelerating mode; and the vehicle is considered to run at a constant speed in other cases.
As shown in fig. 2, the search area of the peripheral vehicle is divided, and the peripheral vehicles of the target vehicle are searched, wherein the dark-color vehicle is the target vehicle, the elliptic curve is the search area of the peripheral vehicle, the light-color vehicle included in the elliptic curve is the peripheral vehicle of the target vehicle, and the light-color vehicles outside the other elliptic curves are other vehicles not involved in the trajectory prediction of the target vehicle; and taking the position information of the surrounding vehicle as the input track characteristic of the surrounding vehicle.
A trajectory data set containing only the input trajectory features of the target vehicle and the input trajectory features of the surrounding vehicles is calculated as 7: 1: the scale of 2 is divided into a training set, a validation set, and a test set. The test sets are further divided into a lane keeping test set, a left lane changing test set and a right lane changing test set according to different categories of transverse driving intentions.
S2, constructing a vehicle track prediction model based on a double-attention machine mechanism and improved Social Gan
A vehicle track prediction model based on a double-attention mechanism and improved Social Gan is shown in FIG. 3 and comprises an input layer, a coding layer, a pooling layer, a driving intention prediction module, a decoding layer and an output layer; the input layer is used for inputting the track of the target vehicle and the track of the peripheral vehicle into a double-attention machine mechanism and a vehicle track prediction model of the improved Social Gan; the coding layer comprises n +1 LSTM encoders, one LSTM encoder encodes the input track characteristics of the target vehicle, and n LSTM encoders encode the input track characteristics of n peripheral vehicles; the pooling layer comprises two attention modules and a pooling module for improving Social Gate, wherein one attention module is used for coding the track characteristics of the target vehicle and carrying out attention weighting on relevant variables influencing the track of the target vehicle, such as vehicle speed, acceleration and the like, the other attention module is used for coding the track characteristics of the peripheral vehicle and carrying out attention weighting on the importance of the peripheral vehicle influencing the target vehicle (for the prior art, see Shih S Y, Sun F K, Lee H. temporal Pattern attribution for diversified time series for acquiring [ J ]. Machine Learning,2019,108 (2261): 2261. 1441.), and the pooling module for improving Social Gate is used for extracting the interactive characteristics of the peripheral vehicle (for the prior art, see Guita A, Johnson J, Fei-Fei L, and IEEE. the Social gateway of Social gateway and 5. the compatibility of the peripheral vehicle and the compatibility of the Social gateway [ 5. the attention module for improving Social Gate and the attention of the target vehicle: [ 2255. the attention of the tracking of the peripheral vehicle The trajectory characteristics of the surrounding vehicles with the importance degrees weighted by attention are transmitted to a pooling module of an improved Social Gan, and the influence relationship between the surrounding vehicles and a target vehicle is highlighted by the attention mechanism, so that the interactive characteristics among the vehicles can be extracted more easily during pooling operation; the driving intention prediction module is used for predicting the transverse and longitudinal driving intentions of the target vehicle in the next time period, decoding the transverse and longitudinal driving intentions through an LSTM decoder of the decoding layer and finally outputting the transverse and longitudinal driving intentions through an output layer.
The specific process for constructing the vehicle track prediction model comprises the following steps:
s2.1, encoding the input track characteristics of the target vehicle and the input track characteristics of the peripheral vehicles by using an LSTM encoder;
s2.2, applying a double-attention mechanism (two attention modules), wherein one attention module acts on the track characteristics of the coded target vehicle to perform attention weighting on relevant variables influencing the track of the target vehicle, such as vehicle speed, acceleration and the like, and the other attention module acts on the track characteristics of the coded peripheral vehicle to perform attention weighting on the importance of the peripheral vehicle influencing the target vehicle;
s2.3, improving the pooling module of Social Gan
Calculating the relative position and the relative speed of the current position of the target vehicle and the last time period and the relative position and the relative speed of each surrounding vehicle and the target vehicle; the relative position and relative speed of the target vehicle and the surrounding vehicles are connected with the LSTM hidden state of each vehicle, are independently processed by a multilayer perceptron (MLP), and use the maximum pooling (MAX) to extract the interactive features of the surrounding vehicles, as shown in FIG. 4;
s2.4, splicing the track of the target vehicle weighted by attention and the track of the pooled surrounding vehicles to form a complete track, and then transmitting the complete track to a driving intention prediction module, wherein the driving intention prediction module consists of two groups of LSTM layers and Softmax layers and is respectively used for predicting the transverse driving intention and the longitudinal driving intention of the next time period, the LSTM layers encode the complete track and carry out multi-classification by using a Softmax activation function to obtain the predicted driving intention;
and S2.5, splicing the predicted driving intention with the complete track to form the track with the driving intention, transmitting the track with the driving intention into an LSTM decoder, wherein the decoder consists of a plurality of LSTM networks and can output a plurality of tracks which possibly exist.
S3, training a vehicle track prediction model based on a double-attention machine mechanism and improved Social Gan, and using a Root Mean Square Error (RMSE) as a loss function;
the specific steps of training the vehicle track prediction model are as follows: training a vehicle track prediction model, taking a predicted track with the maximum probability as an output value, taking a Root Mean Square Error (RMSE) as a loss function, and taking a negative log-likelihood function (NLL) as a key index of a verification set at each time step; wherein the loss function is:
wherein T ispredIs the predicted time step, (x)t,yt) Is the true position coordinates of the target vehicle, (x't,y′t) Are the predicted target vehicle position coordinates.
The method comprises the steps of training a vehicle track prediction model based on a double-attention machine mechanism and improved Social Gan by utilizing a training set, calculating the accuracy of the vehicle track prediction model by using a verification set in the training process, and then preventing the model from being over-fitted by combining the change characteristics of a loss function in the training process.
And S4, storing the vehicle track prediction model after training.
S5, testing a vehicle track prediction model based on a double-attention machine mechanism and improved Social Gan;
and (3) using the test set as the input of the trained vehicle track prediction model, predicting the possible track of the target vehicle, and testing the precision of the vehicle track prediction model.
S6, comparing and analyzing with other popular vehicle track prediction models;
comparing the test results of the vehicle track prediction model based on the double-attention mechanism and the improved Social Gan, which comprise the root mean square error RMSE, the average displacement error ADE and the final displacement error FDE, with the test results of other vehicle track prediction models; historical trajectory data with time step 3 is used to predict trajectories 5 time steps into the future.
The present invention has carried out a number of experiments to evaluate the effectiveness and advancement of the invention, and the results of comparison with other models are shown in table 1:
TABLE 1 comparison of RMSE values
As shown in Table 1, the vehicle trajectory prediction model based on the dual attention mechanism and the improved Social Gan proposed by the invention is superior to all other methods in all prediction time steps.
Compared with the existing track prediction method, the method adopts a double-attention machine mechanism to respectively act on the relevant variables of the target vehicle track data and the position information of the peripheral vehicles, and can effectively extract the characteristics with larger influence on the target vehicle track by redistributing the weight; the method comprises the steps that a pooling module of the Social Gan is improved, and at any time t, the relative position and the relative speed of the current position of a target vehicle and the last time period and the relative position and the relative speed of each peripheral vehicle and the target vehicle are calculated; the relative position and relative speed of the target vehicle and the surrounding vehicles are connected with the LSTM hidden state of each vehicle, are independently processed by a multilayer perceptron (MLP), and use the maximum pooling (MAX) to calculate and output a pooling tensor of interaction between the surrounding vehicles; and finally, generating a plurality of possible predicted tracks according to probability through a plurality of LSTM networks.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (8)
1. The vehicle track prediction method based on the double-attention machine system and the improved Social Gan is characterized in that a vehicle track prediction model based on the double-attention machine system and the improved Social Gan is constructed to predict the running track of a target vehicle at the future time;
the vehicle track prediction model based on the double-attention mechanism and the improved Social Gan comprises a coding layer, a pooling layer, a driving intention prediction module and a decoding layer;
the encoding layer comprises n +1 LSTM encoders, wherein the 1 LSTM encoder encodes the input track characteristics of the target vehicle, and the n LSTM encoders encode the input track characteristics of n peripheral vehicles;
the pooling layer comprises two attention modules and a pooling module for improving Social Gan, wherein one attention module acts on the track characteristics of the coded target vehicle to carry out attention weighting on related variables influencing the track of the target vehicle, the other attention module acts on the track characteristics of the coded peripheral vehicle to carry out attention weighting on the importance of the peripheral vehicle influencing the target vehicle, and the pooling module for improving Social Gan is used for extracting interactive characteristics of the peripheral vehicle;
the driving intention prediction module is used for predicting the transverse and longitudinal driving intention of the target vehicle in the next time period and decoding the transverse and longitudinal driving intention through an LSTM decoder of a decoding layer.
2. The vehicle trajectory prediction method based on the dual-attention mechanism and the improved Social Gan is characterized in that the improved Social Gan pooling module is used for extracting interactive features of surrounding vehicles, and specifically comprises the following steps: calculating the relative position and the relative speed of the current position of the target vehicle and the last time period and the relative position and the relative speed of each surrounding vehicle and the target vehicle; the relative positions and relative speeds of the target vehicle and the surrounding vehicles are independently processed by the multilayer perceptron, and then the interactive features of the surrounding vehicles are extracted by using maximum pooling.
3. The dual-attention mechanism and improved Social Gan based vehicle trajectory prediction method according to claim 1, wherein the driving intention prediction module inputs a complete trajectory after splicing the trajectory of the attention weighted target vehicle and the trajectory of the pooled surrounding vehicles.
4. The dual-attention mechanism and improved Social Gan vehicle trajectory prediction method according to claim 3, wherein the driving intent prediction module is composed of two sets of LSTM layer and Softmax layer, the LSTM layer encodes the complete trajectory and performs multi-classification using Softmax activation function to get the next time period of lateral driving intent and longitudinal driving intent.
5. The dual-attention mechanism and improved Social Gan vehicle trajectory prediction method according to claim 4, wherein the LSTM decoder inputs a predicted driving intention and a full trajectory spliced trajectory to form a trajectory with a driving intention.
6. The dual attention mechanism and improved Social Gan vehicle trajectory prediction method according to claim 5, wherein the driving intent is determined by setting a trajectory prediction time and an acceleration threshold.
7. The dual-attention mechanism and improved Social Gan vehicle trajectory prediction method according to claim 1, wherein the target vehicle trajectory features include target vehicle position information, lane information, speed and acceleration information, and longitudinal and lateral driving intent.
8. The dual-attention-machine-based and improved Social Gan vehicle trajectory prediction method according to claim 1, wherein the trajectory features of the nearby vehicle are position information of the nearby vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111044320.3A CN113954863B (en) | 2021-09-07 | 2021-09-07 | Vehicle track prediction method based on dual-attention mechanism and improved Social Gan |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111044320.3A CN113954863B (en) | 2021-09-07 | 2021-09-07 | Vehicle track prediction method based on dual-attention mechanism and improved Social Gan |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113954863A true CN113954863A (en) | 2022-01-21 |
| CN113954863B CN113954863B (en) | 2024-06-11 |
Family
ID=79460983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111044320.3A Active CN113954863B (en) | 2021-09-07 | 2021-09-07 | Vehicle track prediction method based on dual-attention mechanism and improved Social Gan |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113954863B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116890881A (en) * | 2023-09-08 | 2023-10-17 | 摩尔线程智能科技(北京)有限责任公司 | Vehicle lane change decision generation method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3650297A1 (en) * | 2018-11-08 | 2020-05-13 | Bayerische Motoren Werke Aktiengesellschaft | Method and apparatus for determining information related to a lane change of a target vehicle, method and apparatus for determining a vehicle comfort metric for a prediction of a driving maneuver of a target vehicle and computer program |
| CN112766561A (en) * | 2021-01-15 | 2021-05-07 | 东南大学 | Generating type confrontation track prediction method based on attention mechanism |
| US20210174668A1 (en) * | 2019-12-10 | 2021-06-10 | Samsung Electronics Co., Ltd. | Systems and methods for trajectory prediction |
| CN112949597A (en) * | 2021-04-06 | 2021-06-11 | 吉林大学 | Vehicle track prediction and driving manipulation identification method based on time mode attention mechanism |
| WO2021134172A1 (en) * | 2019-12-30 | 2021-07-08 | 华为技术有限公司 | Trajectory prediction method and related device |
| CN113313320A (en) * | 2021-06-17 | 2021-08-27 | 湖北汽车工业学院 | Vehicle track prediction method based on residual attention mechanism |
-
2021
- 2021-09-07 CN CN202111044320.3A patent/CN113954863B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3650297A1 (en) * | 2018-11-08 | 2020-05-13 | Bayerische Motoren Werke Aktiengesellschaft | Method and apparatus for determining information related to a lane change of a target vehicle, method and apparatus for determining a vehicle comfort metric for a prediction of a driving maneuver of a target vehicle and computer program |
| US20210174668A1 (en) * | 2019-12-10 | 2021-06-10 | Samsung Electronics Co., Ltd. | Systems and methods for trajectory prediction |
| WO2021134172A1 (en) * | 2019-12-30 | 2021-07-08 | 华为技术有限公司 | Trajectory prediction method and related device |
| CN112766561A (en) * | 2021-01-15 | 2021-05-07 | 东南大学 | Generating type confrontation track prediction method based on attention mechanism |
| CN112949597A (en) * | 2021-04-06 | 2021-06-11 | 吉林大学 | Vehicle track prediction and driving manipulation identification method based on time mode attention mechanism |
| CN113313320A (en) * | 2021-06-17 | 2021-08-27 | 湖北汽车工业学院 | Vehicle track prediction method based on residual attention mechanism |
Non-Patent Citations (1)
| Title |
|---|
| 蔡英凤等, 江苏大学学报, vol. 41, no. 2, 31 March 2020 (2020-03-31), pages 125 - 130 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116890881A (en) * | 2023-09-08 | 2023-10-17 | 摩尔线程智能科技(北京)有限责任公司 | Vehicle lane change decision generation method and device, electronic equipment and storage medium |
| CN116890881B (en) * | 2023-09-08 | 2023-12-08 | 摩尔线程智能科技(北京)有限责任公司 | Vehicle lane change decision generation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113954863B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111046919B (en) | Surrounding dynamic vehicle track prediction system and method integrating behavior intention | |
| Yan et al. | Deep learning for vehicle speed prediction | |
| Cai et al. | Environment-attention network for vehicle trajectory prediction | |
| US20230060005A1 (en) | Method and Apparatus for Predicting Motion Track of Obstacle and Autonomous Vehicle | |
| CN112257850B (en) | Vehicle track prediction method based on generation countermeasure network | |
| CN111931902B (en) | Generating countermeasure network model and vehicle track prediction method using generating countermeasure network model | |
| CN111930110A (en) | Intent track prediction method for generating confrontation network by combining society | |
| CN111339867B (en) | Pedestrian trajectory prediction method based on generation of countermeasure network | |
| CN112004197B (en) | Heterogeneous Internet of vehicles switching method based on vehicle track prediction | |
| CN112099496A (en) | Automatic driving training method, device, equipment and medium | |
| CN112389436B (en) | Safety automatic driving track changing planning method based on improved LSTM neural network | |
| CN112949597B (en) | Vehicle track prediction and driving manipulation identification method based on time mode attention mechanism | |
| CN114202120A (en) | Urban traffic travel time prediction method aiming at multi-source heterogeneous data | |
| CN113076599A (en) | Multimode vehicle trajectory prediction method based on long-time and short-time memory network | |
| CN109086926B (en) | Short-time rail transit passenger flow prediction method based on combined neural network structure | |
| CN113159403B (en) | Intersection pedestrian track prediction method and device | |
| CN101964061B (en) | Binary kernel function support vector machine-based vehicle type recognition method | |
| CN115049009A (en) | Track prediction method based on semantic fusion representation | |
| CN114881339A (en) | Vehicle trajectory prediction method, system, computer device, and storage medium | |
| CN110194156A (en) | Intelligent network joins hybrid vehicle active collision avoidance enhancing learning control system and method | |
| CN113954863A (en) | Vehicle track prediction method based on double-attention machine system and improved Social Gan | |
| CN114368387B (en) | Attention mechanism-based driver intention recognition and vehicle track prediction method | |
| CN117237475A (en) | Vehicle traffic track generation method and device based on diffusion generation model | |
| CN117056765A (en) | Vehicle speed multi-time scale prediction method, system, equipment, medium and terminal | |
| CN115631629B (en) | Urban dynamic vehicle cloud construction method and system based on track prediction |
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 |