Search

Correct ego-lane index estimation is essential for lane change and decision making for intelligent vehicles, especially in global navigation satellite system (GNSS)-challenged environments. To achieve this, we propose an ego-lane index estimation approach in an urban scenario based on particle filter (PF). The particles are initialized and propagated by dead reckoning with inertial measurement unit (IMU) and odometry. A lane-level map is used to navigate the particles taking advantage of topologic and geometric information of lanes. GNSS single-point positioning (SPP) can provide position estimation with meter-level accuracy in urban environments, which can limit drift introduced by dead reckoning for updating the weight of each particle. Light detection and ranging (LiDAR) is a common sensor in an intelligent vehicle. A LiDAR-based road boundary detection method provides distance measurements from the vehicle to the left/right road boundaries, which provides a measurement for importance weighting. However, the high precision of the LiDAR measurements may put a tight constraint on the distribution of particles, which can lead to particle degeneration with sparse particle sets. To deal with this problem, we propose a novel step that shifts particles laterally based on LiDAR measurements instead of importance weighting in the traditional PF scheme. We tested our methods on an urban expressway at a low traffic volume period to ensure road boundaries can be detected by LiDAR measurements at most time steps. Experimental results prove that our improved PF scheme can correctly estimate ego-lane index at all time steps, while the traditional PF scheme produces wrong estimations at some time steps. [ABSTRACT FROM AUTHOR]

Cooperative adaptive cruise control (CACC) has important significance for the development of the connected and automated vehicle (CAV) industry. The traditional proportional integral derivative (PID) platoon controller adjustment is not only time-consuming and laborious, but also unable to adapt to different working conditions. This paper proposes a learning control method for a vehicle platooning system using a deep deterministic policy gradient (DDPG)-based PID. The main contribution of this study is automating the PID weight tuning process by formulating this objective as a deep reinforcement learning (DRL) problem. The longitudinal control of the vehicle platooning is divided into upper and lower control structures. The upper-level controller based on the DDPG algorithm can adjust the current PID controller parameters. Through offline training and learning in a SUMO simulation software environment, the PID controller can adapt to different road and vehicular platooning acceleration and deceleration conditions. The lower-level controller controls the gas/brake pedal to accurately track the desired acceleration and speed. Based on the hardware-in-the-loop (HIL) simulation platform, the results show that in terms of the maximum speed error, for the DDPG-based PID controller this is 0.02–0.08 m/s less than for the conventional PID controller, with a maximum reduction of 5.48%. In addition, the maximum distance error of the DDPG-based PID controller is 0.77 m, which is 14.44% less than that of the conventional PID controller. [ABSTRACT FROM AUTHOR]

To date, automatic driving technology has become a hotspot in academia. It is necessary to provide a personalization of automatic driving decision for each passenger. The purpose of this paper is to propose a self-learning method for personalized driving decisions. First, collect and analyze driving data from different drivers to set learning goals. Then, Deep Deterministic Policy Gradient algorithm is utilized to design a driving decision system. Furthermore, personalized factors are introduced for some observed parameters to build a personalized driving decision model. Finally, compare the proposed method with classic Deep Reinforcement Learning algorithms. The results show that the performance of the personalized driving decision model is better than the classic algorithms, and it is similar to the manual driving situation. Therefore, the proposed model can effectively learn the human-like personalized driving decisions of different drivers for structured road. Based on this model, the smart car can accomplish personalized driving. [ABSTRACT FROM AUTHOR]

With the development of online cars, the demand for travel prediction is increasing in order to reduce the information asymmetry between passengers and drivers of online car-hailing. This paper proposes a travel demand forecasting model named OC-CNN based on the convolutional neural network to forecast the travel demand. In order to make full use of the spatial characteristics of the travel demand distribution, this paper meshes the prediction area and creates a travel demand data set of the graphical structure to preserve its spatial properties. Taking advantage of the convolutional neural network in image feature extraction, the historical demand data of the first twenty-five minutes of the entire region are used as a model input to predict the travel demand for the next five minutes. In order to verify the performance of the proposed method, one-month data from online car-hailing of the Chengdu Fourth Ring Road are used. The results show that the model successfully extracts the spatiotemporal features of the data, and the prediction accuracies of the proposed method are superior to those of the representative methods, including the Bayesian Ridge Model, Linear Regression, Support Vector Regression, and Long Short-Term Memory networks. [ABSTRACT FROM AUTHOR]

In road traffic accidents, the analysis of a vehicle's collision angle plays a key role in identifying a traffic accident's form and cause. However, because accurate estimation of vehicle collision angle involves many factors, it is difficult to accurately determine it in cases in which less physical evidence is available and there is a lack of monitoring. This paper establishes the mathematical relation model between collision angle, deformation, and normal vector in the collision region according to the equations of particle deformation and force in Hooke's law of classical mechanics. At the same time, the surface reconstruction method suitable for a normal vector solution is studied. Finally, the estimation model of vehicle collision angle is presented. In order to verify the correctness of the model, verification of multi-angle collision experiments and sensitivity analysis of laser scanning precision for the angle have been carried out using three-dimensional (3D) data obtained by a 3D laser scanner in the collision deformation zone. Under the conditions with which the model has been defined, validation results show that the collision angle is a result of the weighted synthesis of the normal vector of the collision point and the weight value is the deformation of the collision point corresponding to normal vectors. These conclusions prove the applicability of the model. The collision angle model proposed in this paper can be used as the theoretical basis for traffic accident identification and cause analysis. It can also be used as a theoretical reference for the study of the impact deformation of elastic materials.

Complex traffic situations and high driving workload are the leading contributing factors to traffic crashes. There is a strong correlation between driving performance and driving workload, such as visual workload from traffic signs on highway off-ramps. This study aimed to evaluate traffic safety by analyzing drivers' behavior and performance under the cognitive workload in complex environment areas. First, the driving workload of drivers was tested based on traffic signs with different quantities of information. Forty-four drivers were recruited to conduct a traffic sign cognition experiment under static controlled environment conditions. Different complex traffic signs were used for applying the cognitive workload. The static experiment results reveal that workload is highly related to the amount of information on traffic signs and reaction time increases with the information grade, while driving experience and gender effect are not significant. This shows that the cognitive workload of subsequent driving experiments can be controlled by the amount of information on traffic signs. Second, driving characteristics and driving performance were analyzed under different secondary task driving workload levels using a driving simulator. Drivers were required to drive at the required speed on a designed highway off-ramp scene. The cognitive workload was controlled by reading traffic signs with different information, which were divided into four levels. Drivers had to make choices by pushing buttons after reading traffic signs. Meanwhile, the driving performance information was recorded. Questionnaires on objective workload were collected right after each driving task. The results show that speed maintenance and lane deviations are significantly different under different levels of cognitive workload, and the effects of driving experience and gender groups are significant. The research results can be used to analyze traffic safety in highway environments, while considering more drivers' cognitive and driving performance.