Modeling Anticipation and Relaxation of Lane Changing Behavior Using Deep Learning

2021 ◽  
pp. 036119812110286
Author(s):  
Kequan Chen ◽  
Pan Liu ◽  
Zhibin Li ◽  
Yuxuan Wang ◽  
Yunxue Lu
Keyword(s):  
Short Term Memory ◽  
Trajectory Data ◽  
Lane Changing ◽  
Factors Affecting ◽  
Video Footage ◽  
Input Variables ◽  
Vehicle Trajectory ◽  
Lstm Network ◽  
Two Stages ◽  
The Impact

Modeling lane changing driving behavior has attracted significant attention recently. Most of the existing models are homogeneous and do not recognize the anticipation and relaxation phenomena occurring during the maneuver. To fill this gap, we adopted long short-term memory (LSTM) network and used large quantities of trajectory data extracted from video footage collected by an unmanned automated vehicle in Nanjing, China. Then, we divided complete lane changing behavior into two stages, that is, anticipation and relaxation. Description analysis of lane changing behavior revealed that the factors affecting the two stages are significantly different. In this context, two LSTM models with different input variables were proposed to predict the anticipation and the relaxation during the lane changing activity, respectively. The vehicle trajectory data were further divided into an anticipation dataset and a relaxation dataset to train the two LSTM models. Then we applied numerical tests to compare our models with two baseline models using real trajectory data of lane changing behavior. The results suggest that our models achieved the best performance for trajectory prediction in both lateral and longitudinal positions. Moreover, the simulation results show that the proposed models can precisely replicate the impact of the anticipation phenomenon on the target lane, and the relationship between the speed and spacing of the lane changing vehicle during the relaxation process can be reproduced with reasonable accuracy.

Modeling Speed Disturbance Absorption following Current State–Control Action–Expected State Chains

2005 ◽  
Vol 1934 (1) ◽  
pp. 83-93 ◽  
Author(s):  
Ruihua Tao ◽  
Heng Wei ◽  
Yinhai Wang ◽  
Virginia P. Sisiopiku
Keyword(s):  
Recovery Period ◽  
Control Action ◽  
State Control ◽  
Trajectory Data ◽  
Lane Changing ◽  
Car Following ◽  
Current State ◽  
Speed Advantage ◽  
Vehicle Trajectory ◽  
A Current

This paper explores driver behavior in a paired car-following mode in response to a speed disturbance from a front vehicle. A current state– control action–expected state (SAS) chain is developed to provide a framework for modeling of the hierarchy of expected actions incurred during the need for speed disturbance absorption. Three car-following scenarios and one lane-changing scenario are identified with defined perceptual informative variables to describe the process of speed disturbance absorption. Those variables include dynamic spacing versus the follower's speed, disturbance-effecting and -ending spacing, headway, acceleration– deceleration, speed recovery period, speed advantage, and lane-changing duration. A significant improvement in car-following modeling introduced in the paper is the integration of car-following and lane-changing behaviors in the SAS chain. Moreover, critical values of perceptual informative variables are statistically developed as a function of the follower's speed by using observed vehicle trajectory data. Furthermore, models that determine the probability of a lane change in response to a speed disturbance and models for acceptable lane-changing decision-making conditions at the adjacent lanes are developed on the basis of the analysis of observed vehicle trajectory data. The work presented in this paper provides an analysis of speed disturbance and speed absorption phenomena and car-following and lane-changing behaviors at the microscopic level. This work establishes the foundation for further research on multiple speed disturbance absorption and its impact on traffic stabilities at the macroscopic analysis level.

scholarly journals Gaze Tracking Based on Concatenating Spatial-Temporal Features

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 545
Author(s):  
Bor-Jiunn Hwang ◽  
Hui-Hui Chen ◽  
Chaur-Heh Hsieh ◽  
Deng-Yu Huang
Keyword(s):  
Short Term Memory ◽  
Image Data ◽  
Training Model ◽  
Point Estimation ◽  
Training Data ◽  
Gaze Tracking ◽  
Spatial Features ◽  
Temporal Features ◽  
Lstm Network ◽  
The Impact

Based on experimental observations, there is a correlation between time and consecutive gaze positions in visual behaviors. Previous studies on gaze point estimation usually use images as the input for model trainings without taking into account the sequence relationship between image data. In addition to the spatial features, the temporal features are considered to improve the accuracy in this paper by using videos instead of images as the input data. To be able to capture spatial and temporal features at the same time, the convolutional neural network (CNN) and long short-term memory (LSTM) network are introduced to build a training model. In this way, CNN is used to extract the spatial features, and LSTM correlates temporal features. This paper presents a CNN Concatenating LSTM network (CCLN) that concatenates spatial and temporal features to improve the performance of gaze estimation in the case of time-series videos as the input training data. In addition, the proposed model can be optimized by exploring the numbers of LSTM layers, the influence of batch normalization (BN) and global average pooling layer (GAP) on CCLN. It is generally believed that larger amounts of training data will lead to better models. To provide data for training and prediction, we propose a method for constructing datasets of video for gaze point estimation. The issues are studied, including the effectiveness of different commonly used general models and the impact of transfer learning. Through exhaustive evaluation, it has been proved that the proposed method achieves a better prediction accuracy than the existing CNN-based methods. Finally, 93.1% of the best model and 92.6% of the general model MobileNet are obtained.

scholarly journals Impact of Uncertainty in the Input Variables and Model Parameters on Predictions of a Long Short Term Memory (LSTM) Based Sales Forecasting Model

2020 ◽  
Vol 2 (3) ◽  
pp. 256-270
Author(s):  
Shakti Goel ◽  
Rahul Bajpai
Keyword(s):  
Short Term Memory ◽  
Forecasting Model ◽  
Model Parameters ◽  
Prediction Errors ◽  
Short Term ◽  
Term Memory ◽  
Corona Virus ◽  
Long Short Term Memory ◽  
Input Variables ◽  
The Impact

A Long Short Term Memory (LSTM) based sales model has been developed to forecast the global sales of hotel business of Travel Boutique Online Holidays (TBO Holidays). The LSTM model is a multivariate model; input to the model includes several independent variables in addition to a dependent variable, viz., sales from the previous step. One of the input variables, “number of active bookers per day”, is estimated for the same day as sales. This need for estimation requires the development of another LSTM model to predict the number of active bookers per day. The number of active bookers is variable, so the predicted is used as an input to the sales forecasting model. The use of a predicted variable as an input variable to another model increases the chance of uncertainty entering the system. This paper discusses the quantum of variability observed in sales predictions for various uncertainties or noise due to the estimation of the number of active bookers. For the purposes of this study, different noise distributions such as normalized, uniform, and logistic distributions are used, among others. Analyses of predictions demonstrate that the addition of uncertainty to the number of active bookers via dropouts as well as to the lagged sales variables leads to model predictions that are close to the observations. The least squared error between observations and predictions is higher for uncertainties modeled using other distributions (without dropouts) with the worst predictions being for Gumbel noise distribution. Gaussian noise added directly to the weights matrix yields the best results (minimum prediction errors). One possibility of this uncertainty could be that the global minimum of the least squared objective function with respect to the model weight matrix is not reached, and therefore, model parameters are not optimal. The two LSTM models used in series are also used to study the impact of corona virus on global sales. By introducing a new variable called the corona virus impact variable, the LSTM models can predict corona-affected sales within five percent (5%) of the actuals. The research discussed in the paper finds LSTM models to be effective tools that can be used in the travel industry as they are able to successfully model the trends in sales. These tools can be reliably used to simulate various hypothetical scenarios also.

Modeling Integrated Lane-Changing Behavior

2003 ◽  
Vol 1857 (1) ◽  
pp. 30-38 ◽  
Author(s):  
Tomer Toledo ◽  
Haris N. Koutsopoulos ◽  
Moshe E. Ben-Akiva
Keyword(s):  
Empirical Work ◽  
Flow Characteristics ◽  
Lane Change ◽  
Trajectory Data ◽  
Lane Changing ◽  
Simulation Tools ◽  
Lane Changes ◽  
Trade Offs ◽  
Safety Studies ◽  
Vehicle Trajectory

The lane-changing model is an important component within microscopic traffic simulation tools. Following the emergence of these tools in recent years, interest in the development of more reliable lane-changing models has increased. Lane-changing behavior is also important in several other applications such as capacity analysis and safety studies. Lane-changing behavior is usually modeled in two steps: ( a) the decision to consider a lane change, and ( b) the decision to execute the lane change. In most models, lane changes are classified as either mandatory (MLC) or discretionary (DLC). MLC are performed when the driver must leave the current lane. DLC are performed to improve driving conditions. Gap acceptance models are used to model the execution of lane changes. The classification of lane changes as either mandatory or discretionary prohibits capturing trade-offs between these considerations. The result is a rigid behavioral structure that does not permit, for example, overtaking when mandatory considerations are active. Using these models within a microsimulator may result in unrealistic traffic flow characteristics. In addition, little empirical work has been done to rigorously estimate the parameters of lane-changing models. An integrated lane-changing model, which allows drivers to jointly consider mandatory and discretionary considerations, is presented. Parameters of the model are estimated with detailed vehicle trajectory data.

scholarly journals Post Text Processing of Chinese Speech Recognition Based on Bidirectional LSTM Networks and CRF

Electronics ◽  
2019 ◽  
Vol 8 (11) ◽  
pp. 1248 ◽  
Author(s):  
Li Yang ◽  
Ying Li ◽  
Jin Wang ◽  
Zhuo Tang
Keyword(s):  
Speech Recognition ◽  
Error Detection ◽  
Short Term Memory ◽  
Text Processing ◽  
Conditional Random Field ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Lstm Network ◽  
Two Stages

With the rapid development of Internet of Things Technology, speech recognition has been applied more and more widely. Chinese Speech Recognition is a complex process. In the process of speech-to-text conversion, due to the influence of dialect, environmental noise, and context, the accuracy of speech-to-text in multi-round dialogues and specific contexts is still not high. After the general speech recognition technology, the text after speech recognition can be detected and corrected in the specific context, which is helpful to improve the robustness of text comprehension and is a beneficial supplement to the speech recognition technology. In this paper, a text processing model after Chinese Speech Recognition is proposed, which combines a bidirectional long short-term memory (LSTM) network with a conditional random field (CRF) model. The task is divided into two stages: text error detection and text error correction. In this paper, a bidirectional long short-term memory (Bi-LSTM) network and conditional random field are used in two stages of text error detection and text error correction respectively. Through verification and system test on the SIGHAN 2013 Chinese Spelling Check (CSC) dataset, the experimental results show that the model can effectively improve the accuracy of text after speech recognition.

Longitudinal-Scanline-Based Arterial Traffic Video Analytics with Coordinate Transformation Assisted by 3D Infrastructure Data

2020 ◽  
pp. 036119812097125
Author(s):  
Terry Tianya Zhang ◽  
Mengyang Guo ◽  
Peter J. Jin ◽  
Yi Ge ◽  
Jie Gong
Keyword(s):  
High Resolution ◽  
Low Cost ◽  
Estimation Algorithm ◽  
Trajectory Data ◽  
Camera Model ◽  
Video Footage ◽  
Wide Range ◽  
Smart Mobility ◽  
Vehicle Trajectory ◽  
3D Lidar

High-resolution vehicle trajectory data can be used to generate a wide range of performance measures and facilitate many smart mobility applications for traffic operations and management. In this paper, a Longitudinal Scanline LiDAR-Camera model is explored for trajectory extraction at urban arterial intersections. The proposed model can efficiently detect vehicle trajectories under the complex, noisy conditions (e.g., hanging cables, lane markings, crossing traffic) typical of an arterial intersection environment. Traces within video footage are then converted into trajectories in world coordinates by matching a video image with a 3D LiDAR (Light Detection and Ranging) model through key infrastructure points. Using 3D LiDAR data will significantly improve the camera calibration process for real-world trajectory extraction. The pan-tilt-zoom effects of the traffic camera can be handled automatically by a proposed motion estimation algorithm. The results demonstrate the potential of integrating longitudinal-scanline-based vehicle trajectory detection and the 3D LiDAR point cloud to provide lane-by-lane high-resolution trajectory data. The resulting system has the potential to become a low-cost but reliable measure for future smart mobility systems.

scholarly journals An Approach of Linear Regression-Based UAV GPS Spoofing Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Lianxiao Meng ◽  
Lin Yang ◽  
Shuangyin Ren ◽  
Gaigai Tang ◽  
Long Zhang ◽  
...  
Keyword(s):  
Linear Regression ◽  
Short Term Memory ◽  
Stackelberg Game ◽  
Response Strategy ◽  
Security Threat ◽  
Detection Mechanism ◽  
Detection Scheme ◽  
Aerial Vehicle ◽  
Lstm Network ◽  
The Impact

A prominent security threat to unmanned aerial vehicle (UAV) is to capture it by GPS spoofing, in which the attacker manipulates the GPS signal of the UAV to capture it. This paper introduces an anti-spoofing model to mitigate the impact of GPS spoofing attack on UAV mission security. In this model, linear regression (LR) is used to predict and model the optimal route of UAV to its destination. On this basis, a countermeasure mechanism is proposed to reduce the impact of GPS spoofing attack. Confrontation is based on the progressive detection mechanism of the model. In order to better ensure the flight security of UAV, the model provides more than one detection scheme for spoofing signal to improve the sensitivity of UAV to deception signal detection. For better proving the proposed LR anti-spoofing model, a dynamic Stackelberg game is formulated to simulate the interaction between GPS spoofer and UAV. In particular, for GPS spoofer, it is worth mentioning that for the scenario that the UAV is cheated by GPS spoofing signal in the mission environment of the designated route is simulated in the experiment. In particular, UAV with the LR anti-spoofing model, as the leader in this game, dynamically adjusts its response strategy according to the deception’s attack strategy when upon detection of GPS spoofer’s attack. The simulation results show that the method can effectively enhance the ability of UAV to resist GPS spoofing without increasing the hardware cost of the UAV and is easy to implement. Furthermore, we also try to use long short-term memory (LSTM) network in the trajectory prediction module of the model. The experimental results show that the LR anti-spoofing model proposed is far better than that of LSTM in terms of prediction accuracy.

Lane-Changing Model with Explicit Target Lane Choice

2005 ◽  
Vol 1934 (1) ◽  
pp. 157-165 ◽  
Author(s):  
Tomer Toledo ◽  
Charisma F. Choudhury ◽  
Moshe E. Ben-Akiva
Keyword(s):  
Trajectory Data ◽  
Current Position ◽  
Lane Changing ◽  
Microscopic Traffic Simulation ◽  
Simulation Tools ◽  
Lane Changes ◽  
Proposed Model ◽  
Wide Range ◽  
Vehicle Trajectory ◽  
Better Than

The lane-changing model is an important component of microscopic traffic simulation tools. With the increasing popularity of these tools, a number of lane-changing models have been proposed and implemented in various simulators in recent years. Most of these models are based on the assumption that drivers evaluate the current and adjacent lanes and choose a direction of change (or no change) on the basis of the utilities of these lanes only. The lane choice set is therefore dictated by the current position of the vehicle and in multilane facilities would be restricted to a subset of the available lanes. Thus, existing models lack an explicit tactical choice of a target lane and therefore cannot explain a sequence of lane changes from the current lane to this lane. In this paper, a generalized lane-changing model that explicitly incorporates the choice of target lane is presented. The target lane is the lane that the driver perceives to be the best when a wide range of factors and goals are taken into account. The immediate direction in which a driver changes lanes is determined by the target lane choice. All parameters of the model were jointly estimated with detailed vehicle trajectory data. The model was validated and compared with an existing lane-changing model with the use of a microscopic traffic simulator. The results indicate that the proposed model performs significantly better than the previous model.

scholarly journals Comparison of Microscopic Drivers' Probabilistic Lane-changing Models With Real Traffic Microscopic Data

2012 ◽  
Vol 23 (4) ◽  
pp. 241-251
Author(s):  
Seyyed Mohammad Sadat Hoseini
Keyword(s):  
Probabilistic Models ◽  
Simulation Models ◽  
Real Data ◽  
Microscopic Level ◽  
Trajectory Data ◽  
Lane Changing ◽  
Traffic Models ◽  
Decision Factors ◽  
Vehicle Trajectory ◽  
Real Traffic

The difficulties of microscopic-level simulation models to accurately reproduce real traffic phenomena stem not only from the complexity of calibration and validation operations, but also from the structural inadequacies of the sub-models themselves. Both of these drawbacks originate from the scant information available on real phenomena because of the difficulty in gathering accurate field data. This paper studies the traffic behaviour of individual drivers utilizing vehicle trajectory data extracted from digital images collected from freeways in Iran. These data are used to evaluate the four proposed microscopic traffic models. One of the models is based on the traffic regulations in Iran and the three others are probabilistic models that use a decision factor for calculating the probability of choosing a position on the freeway by a driver. The decision factors for three probabilistic models are increasing speed, decreasing risk of collision, and increasing speed combined with decreasing risk of collision. The models are simulated by a cellular automata simulator and compared with the real data. It is shown that the model based on driving regulations is not valid, but that other models appear useful for predicting the driver’s behaviour on freeway segments in Iran during noncongested conditions.

Sign in / Sign up

Export Citation Format

Share Document