Driver's Intention Research Articles

Lane Change Prediction Using Gaussian Classification, Support Vector Classification and Neural Network Classifiers

It is essential for a driver assistant system’s motion planning to take the vehicles moving in the surroundings into account. One of the most crucial driver intentions which should be predicted is lane changing. It has been investigated whether it is possible to reliably classify lane-changing maneuvers in a highway situation using learning algorithms such as Gaussian-classifier, SVM, and LSTM neural networks. Real vehicle trajectories are extracted from the NGSIM US-101 and I-80 datasets. The input for the classifiers is derived from the trajectory by selecting a subset of the features: lateral and longitudinal position coordinates, longitudinal acceleration, and velocity. In such an environment, the vehicle movement is limited, so it has been tested that how sufficient if only the mean and the variance of the derivative of lateral coordinate was taken as input for the classification had been tested. Different strategies for labeling the input sequences were tested.

Driver’s Intention Identification With the Involvement of Emotional Factors in Two-Lane Roads

Driver’s emotion is a psychological reaction to environmental stimulus. Driver intention is an internal state of mind, which directs the actions in the next moment during driving. Emotions usually have a strong influence on behavioral intentions. Therefore, emotion is an important factor that should be considered, to accurately identify driver’s intention. This study used the support vector machine (SVM) theory to develop a driver intention recognition model, with the involvement of driver’s emotions. Various materials including visual materials, auditory materials, and olfactory materials, were used to induce driver’s emotions. Real driving, virtual driving and computer simulation experiments were conducted to collect human-vehicle-environment dynamic data in two-lane roads. The results present that the proposed model can achieve high accuracy and reliability in recognizing driver’s intentions. Our findings of this study can be used to develop the personalized driving warning system and intelligent human-machine interaction in vehicles. This study would be of great theoretical significance for improving road traffic safety.

An ensemble deep learning approach for driver lane change intention inference

With the rapid development of intelligent vehicles, drivers are increasingly likely to share their control authorities with the intelligent control unit. For building an efficient Advanced Driver Assistance Systems (ADAS) and shared-control systems, the vehicle needs to understand the drivers’ intent and their activities to generate assistant and collaborative control strategies. In this study, a driver intention inference system that focuses on the highway lane change maneuvers is proposed. First, a high-level driver intention mechanism and framework are introduced. Then, a vision-based intention inference system is proposed, which captures the multi-modal signals based on multiple low-cost cameras and the VBOX vehicle data acquisition system. A novel ensemble bi-directional recurrent neural network (RNN) model with Long Short-Term Memory (LSTM) units is proposed to deal with the time-series driving sequence and the temporal behavioral patterns. Naturalistic highway driving data that consists of lane-keeping, left and right lane change maneuvers are collected and used for model construction and evaluation. Furthermore, the driver's pre-maneuver activities are statistically analyzed. It is found that for situation-aware, drivers usually check the mirrors for more than six seconds before they initiate the lane change maneuver, and the time interval between steering the handwheel and crossing the lane is about 2 s on average. Finally, hypothesis testing is conducted to show the significant improvement of the proposed algorithm over existing ones. With five-fold cross-validation, the EBiLSTM model achieves an average accuracy of 96.1% for the intention that is inferred 0.5 s before the maneuver starts.

Naturalistic Driver Intention and Path Prediction Using Recurrent Neural Networks

Understanding the intentions of drivers at intersections is a critical component for autonomous vehicles. Urban intersections that do not have traffic signals are a common epicenter of highly variable vehicle movement and interactions. We present a method for predicting driver intent at urban intersections through multi-modal trajectory prediction with uncertainty. Our method is based on recurrent neural networks combined with a mixture density network output layer. To consolidate the multi-modal nature of the output probability distribution, we introduce a clustering algorithm that extracts the set of possible paths that exist in the prediction output and ranks them according to probability. To verify the method’s performance and generalizability, we present a real-world dataset that consists of over 23 000 vehicles traversing five different intersections, collected using a vehicle-mounted lidar-based tracking system. An array of metrics is used to demonstrate the performance of the model against several baselines.

Sliding Mode Control of Vehicle Equipped with Brake-by-Wire System considering Braking Comfort

For passengers, the most common feeling during running on the bumpy road is continuous vertical discomfort, and when the vehicle is braking, especially the emergency braking, the instantaneous inertia of the vehicle can also cause a strong discomfort of the passengers, so studying the comfort of the vehicle during the braking process is of great significance for improving the performance of the vehicle. This paper presented a complete control scheme for vehicles equipped with the brake-by-wire (BBW) system aiming at ensuring braking comfort. A novel braking intention classification method was proposed based on vehicle braking comfort, which divided braking intention into mild brake, medium comfort brake, and emergency brake. Correspondingly, in order to improve the control accuracy of the vehicle brake system and to best meet the driver’s brake needs, a braking intention recognizer relying on fuzzy logic was established, which used the road condition and the brake pedal voltage and its change rate as input, output real-time driver's braking intention, and braking intensity. An optimal brake force distribution strategy for the vehicle equipped with the BBW system based on slip rate was proposed to determine the relationship between braking intensity and target slip ratio. Combined with the vehicle dynamics model, improved sliding mode controller, and brake force observer, the joint simulation was conducted in Simulink and CarSim. The cosimulation results show that the proposed braking intention classification method, braking intention recognizer, brake force distribution strategy, and sliding mode control can well ensure the braking comfort of the vehicle equipped with the BBW system under the premise of ensuring brake safety.

Human Behavior Model-Based Predictive Control of Longitudinal Brain-Controlled Driving

Using brain signals rather than limbs to drive a vehicle may not only help persons with disabilities to acquire driving ability, but also provide a new alternative interface for healthy people to control a vehicle. However, the longitudinal driving performance of brain-controlled vehicles (BCVs) at a relatively high speed is not good enough. In this paper, to improve the performance of the longitudinal brain-control driving, we propose a new predictive control method based on the models of human behaviors and vehicle dynamics. The proposed method is designed to maintain rear-end safety of BCVs and driver ride comfort while ensuring the maximum control authority of brain-control drivers. Driver-and-hardware-in-the-loop experiments are conducted with different subjects under three kinds of scenarios to validate the proposed method. The results show that the proposed method is effective in maintaining rear-end safety and driver ride comfort while preserving driver intention.

Attitudes of learner drivers toward safety at level crossings: Do they change after a 360° video-based educational intervention?

In light of the growing number of level crossing accidents and the limited prevention programmes, this study examined relationships among attitudes toward traffic rules, impulsiveness, and behavioural intentions at level crossings. It explored the behavioural effects of an educational programme newly developed within the framework of the Croatian national safety project “Implementation of measures to improve the safety of the most vulnerable traffic participants at level crossings“. The programme aimed to change risky attitudes and behavioural intentions of learner drivers at level crossings. It consists of a safety lecture accompanied by pictures, videos and the exposition to a 3D virtual reality film shot at a real level crossing, which allows the participant to experience, from the driver’s perspective, safe and risky crossings. The programme was implemented in 11 driving schools. First, 285 participants (62.8% men) answered a questionnaire measuring safety attitudes toward traffic and impulsiveness, then they attended a lecture and participated in the virtual reality experience. Finally, they answered a questionnaire measuring planned future behaviour at level crossings. The results showed that attitudes toward level crossing risk significantly predicted intended driving behaviour at level crossings. Furthermore, the 360° video-based educational intervention altered the relationships connecting attitudes toward level crossings and risky driving behaviour at level crossings. The practical implications of these results are discussed.

Continuous Car Driving Intent Detection Using Structural Pattern Recognition

The early detection of a driver's intention prior to the initiation of actual maneuvering is to offer effective means of assisting the driver in times of safety. Conventional approaches in predicting a driver's intention include framing the motion parameters of the car and driver as well as the eye gaze sequence of the driver into the Hidden Markov Model (HMM) for analysis. However, their power of describing driver behavior is not only limited but also their performance, indicated by the recognition rate relative to the amount of preceding time in early detection, is not satisfactory and needs further improvement. This paper presents an approach for early detection of a driver's intention by modeling and analyzing driver behavior by using structural pattern recognition based on context-free and context-sensitive grammars. We specifically structured a sequence of the driver's eye fixations as well as of the vehicle speed, steering angle and signaling into a sequence of symbolic vectors to form sentences representing a specific driver behavior. It turns out that the proposed approach resulted in an average of 70.5% and 80% recognition rates at the respective 2 and 1 second preceding time to the actual initiation of maneuvering behavior. This performance can be compared to 56.8% and 69% by the state-of-the-art conventional results.

A two-lane mixed traffic flow model with drivers' intention to change lane based on cellular automata

Aiming at the shortcomings of the classic NaSch model and the two-lane lane change model (STCA), the viaduct was used as the simulation object on the basis of improving the rules and lane changing rules. Under the open boundary condition, a two-lane mixed traffic flow model considering the intention to enter the lane is established. Aim at the willingness of driver to enter lane research, this model puts forward the vehicle enter rules, which take into account the relevant factors that affect driver's intention to enter the road and quantify the influencing factors through the method of average input rate in queuing theory. Computer numerical simulation shows that the average input rate λ is determined by input rate λ and output rate μ, and is affected by the sensitivity parameter β, and is not greater than μ. The passing state of a road vehicle is determined by the output rate μ and is affected by β. At the same time, compared with the model that ignores the driver's intention to enter the road, the model proposed in this paper is closer to the actual traffic situation.

Modeling and Control Approach for Dual Clutch Transmission Vehicles Starting Process Based on State-Dependent Autoregressive With Exogenous Model

To solve the difficulties of modeling the starting system of dual clutch transmission (DCT) vehicles, a state-dependent autoregressive with exogenous variables (SD-ARX) model whose functional coefficients are approximated by sets of radial basis function (RBF) networks is proposed to describe the dynamic characteristics of DCT vehicles starting process in this study. The validity of this modelling approach is verified via a real vehicle test. On this basis, a nonlinear predictive controller based on SD-ARX model is designed. In addition, the physical constraints of this system, including control variables (change rate of engine torque and clutch torque) and state variables (engine speed and clutch speed), are also taken into account during the controller design process via limiting the relevant parameters in particle swarm optimization or setting saturation demand in control program. To verify the validity and merits of the proposed control approach, many sets of simulation analysis in different driving intentions are conducted. Simulation results shown that: the proposed control approach can well control the starting process of DCT vehicles and effectively reflect the demand of driver's intention; compared with the conventional control method, SD-ARX-MPC can improve the starting performance; the proposed approach is robust to a certain extent according to simulation results under changed starting conditions.

Coordinated Chassis Control of 4WD Vehicles Utilizing Differential Braking, Traction Distribution and Active Front Steering

This paper proposes a coordinated chassis control (CCC) utilizing four-wheel differential braking, electronically controlled real-time four-wheel drive (4WD) and active front steering (AFS), aiming to improve the driving performance and handling stability during cornering. First, the performance of the single system is tested; then the hierarchical-structure control algorithm is designed: a supervisory controller to monitor vehicle states and determine the desired yaw rate, upper-level controller to decide the desired longitudinal forces and the desired yaw moment based on the driver intention and the consideration of vehicle stability, and the control allocation layer to distribute the actual control inputs to the actuators applying an optimal control allocation algorithm. Simulations of moderate driving/aggressive deceleration scenarios and a comprehensive test on a handling road are conducted to validate the effectiveness of the proposed control algorithm. The results of the simulations suggest that the proposed algorithm can effectively improve the driving speed in limit cornering without losing lateral stability, and reduce the tire dissipation energy compared with other control algorithms such as the electronic stability control system, the four wheel independent brake system and an integrated chassis control system proposed in a previous research.

An investigation on coordination of lane departure warning based on driver behaviour characteristics

As an important part of Advanced Driver Assistance Systems (ADAS), Lane Departure Warning System (LDWS) plays a significant role in lane departure prevention and reducing traffic accidents caused by lane departure. In order to improve the warning effect of the system as well as driver acceptance, this paper describes an LDWS algorithm for personalised driving assistance. The proposed combination algorithm consists of a multi-mode Time to Lane Crossing (TLC) and a Future Offset Distance (FOD) based on driver behaviour characteristics. To detect driver's lane change intention, the steering behaviour has been developed incorporating vehicle states and road curvature. Driving simulator tests are conducted to validate the lane departure warning algorithm with multi-mode based on TLC and FOD under various driving situations. The obtained test results are consistent with the expected performance.

An investigation on coordination of lane departure warning based on driver behaviour characteristics

As an important part of Advanced Driver Assistance Systems (ADAS), Lane Departure Warning System (LDWS) plays a significant role in lane departure prevention and reducing traffic accidents caused by lane departure. In order to improve the warning effect of the system as well as driver acceptance, this paper describes an LDWS algorithm for personalised driving assistance. The proposed combination algorithm consists of a multi-mode Time to Lane Crossing (TLC) and a Future Offset Distance (FOD) based on driver behaviour characteristics. To detect driver's lane change intention, the steering behaviour has been developed incorporating vehicle states and road curvature. Driving simulator tests are conducted to validate the lane departure warning algorithm with multi-mode based on TLC and FOD under various driving situations. The obtained test results are consistent with the expected performance.

Artificial Intelligence for Vehicle Behavior Anticipation: Hybrid Approach Based on Maneuver Classification and Trajectory Prediction

Innovative technologies and naturalistic driving data sources provide a great potential to develop reliable autonomous driving systems. Understanding the behaviors of surrounding vehicles is essential for improving safety and mobility of autonomous vehicles. Onboard sensors like Radar, Lidar and Camera are able to track surrounding vehicles motion and to get different features like position, velocity and yaw. This paper proposes a hybrid approach to integrate maneuver classification using neural networks and trajectory prediction using Long Short-term Memory (LSTM) networks to get the future positions of adjacent vehicles. In this study we use the Next Generation Simulation (NGSIM) public dataset that provides a real driving data. The proposed approach is validated experimentally using VEDECOM demonstrator data. The results demonstrate that the proposed approach is able to predict driver intention to change lanes on average 2.2 seconds in advance. The Root Mean Square (RMS) errors of lateral and longitudinal positions are 0.30 m and 3.1 m respectively. The results demonstrate a high performance compared to various existing methods.

A Two-Stage Learning Framework for Driver Lane Change Intention Inference

Abstract With the rapid development of intelligent vehicles, human drivers are sharing the control authority with the automation functionalities. The mutual understanding between the intelligent vehicle and the human driver is the key to the efficient multi-agent teaming and the collaborative driving system. In this study, a two-stage learning framework for spatial-temporal driver lane change intention inference is developed. The two-stage learning framework contains two separate parts. First, an operational level driving behavior recognition system based on the deep convolutional neural network (CNN) is developed to recognize the driver behaviors, including mirror checking and normal driving. Then, based on the driver behavior features from the CNN, the sequential feature vector will be used for the construction of driver intention inference model based recurrent neural networks (RNN) and long short-term memory (LSTM). The proposed model achieved a state-of-the-art result on the driver lane change intention inference task. Based on the naturalistic driving dataset, the model achieved over 91% accuracy for lane change and lane-keeping intention prediction. The two-stage learning framework can significantly increase the model flexibility and accuracy, which makes it easier to be implemented and updated in intelligent vehicles.

Critical Factors Influencing Acceptance of Automated Vehicles by Hong Kong Drivers

This study aimed to identify critical factors that influence acceptance of automated vehicles among drivers. The focus of this study was on automated vehicles (AVs) of level 3 (conditional driving automation) as defined by the Society of Automotive Engineers. A research model was proposed here by using the technology acceptance model (TAM) with trust, risk perception (perceived safety risk and perceived privacy risk), compatibility, and system quality. A cross-sectional structured questionnaire survey was used to collect quantitative data from 237 drivers in Hong Kong. The data were analyzed to test the proposed research model by structural equation modeling. The proposed research model was found to explain 68% of the variance in intention to use AVs. In contrast with the TAM constructs of perceived usefulness and perceived ease of use, the results of this study indicated that trust was the most important factor in shaping a positive attitude towards using AVs, which affected driver intention to use AVs. Also, trust was found to be influenced by perceived safety risk, compatibility, and system quality. This study is the first attempt to consider technological factors related to AVs (compatibility and system quality) in explaining AV acceptance among drivers and highlighted the importance of the technological factors in the context of driver acceptance of AVs. Based on the findings of this study, several recommendations are discussed to help AV developers and governments to improve driver attitudes towards adoption of AVs.

The Effects of Family Issues and Supervisor Support on Work Satisfaction and Work Innovation: A Driver Intention to Remain?

The Effects of Family Issues and Supervisor Support on Work Satisfaction and Work Innovation: A Driver Intention to Remain?

Queueing Network Based Driver Model for Varying Levels of Information Processing

With growing interest in the topic of smart computing and context-aware services, identifying driver's intention has become important in automotive industry. Among existing studies on driver assistance systems, few studies have used the concept of the levels of processing (LOP) to understand driver's information processing. This paper introduces experimental and computational studies that connect human behavior data to internal goal of a driver when an in-vehicle task involves visual search. In the case of consuming information displayed on a car instrument cluster, we considered two levels of information processing, perceptual and cognitive. Through an empirical study, we observed different human oculomotor behaviors that depend on the LOP by evaluating the reaction time (RT) and eye movement patterns. Further, we suggested different ways of information processing that can be represented as different routes in the underlying cognitive architecture of a queueing network. Simulation study demonstrated that trends in simulated oculomotor behavior were similar to those observed in the experiment, that is, RT at the cognitive LOP was shorter than that at the perceptual LOP, while eyes fixated for shorter duration and with lower frequency. In terms of application, this study reveals the possibility of using human-generated data for evaluating the innate purposes of drivers. Together with further development of sensors and invasive computing, the approach proposed in this paper could assist the realization of cognitive cars by understanding drivers’ intent using eye tracking technology.

Cooperative Trajectory Planning for Haptic Shared Control Between Driver and Automation in Highway Driving

This paper addresses the driver–automation shared driving control for lane keeping and obstacle avoidance of automated vehicles in highway traffic. The proposed shared control framework is established from a novel cooperative trajectory planning algorithm and a fuzzy steering controller. Based on polynomial functions, the cooperative trajectory planning is formulated by judiciously exploiting the information on the maneuver decision, the conflict management, and the driver monitoring. As a result, the planned trajectory of the vehicle is continuously adapted according to the driver's actions and intentions. By means of Lyapunov stability arguments, sufficient conditions in terms of linear matrix inequalities are given to design a Takagi–Sugeno fuzzy model-based controller. This robust steering controller provides a necessary assistive torque to track the planned vehicle trajectory. The new shared driving control framework allows reducing effectively the driver–automation conflict issue while offering the driver more freedom to swerve within a predefined lane. The advantages of the proposed approach are evaluated using both objective and subjective results, experimentally obtained from several human drivers and an advanced interactive dynamic driving simulator.

Analysis Factors Affect Turnover Intention Taxi Driver of PT. Citra Perdana Kendedes Malang

Turnover intention is defined as the intention or desire to leave an employee from his current job voluntarily to get a job elsewhere. It is needs to be the center of attention because of the height of it will induce turnover workers so that can disrupt company productivity. PT Citra Perdana Kendedes Malang is on of many the transportation service company. This study aims to identify and analyze the factors that influence the turnover intention of taxi driver of PT Citra Perdana Kendedes Malang. In this research the total population is taxi driver of PT Citra Perdana Kendedes Malang amount of 275 people with as many sample 70 people. Techniques sampling of this research is purposive sampling. Techniques of data analysis this research is used confirmatory factor analysis (CFA). Based on research result can be known that the factor of job stress, job satisfaction, leadership style, work environment, individual characteristic, organizational commitment, and compensation were comfirmed to have a significant effect on turnover intention of taxi driver. Job satisfaction, leadership style, and compensation have the biggest influence to turnover intention. Whereas organizational commitment has the lowest turnover intention.