Search

In the present studies of autonomous driving systems, motion planning of automated vehicles in complex traffic scenarios is a tough issue. The problem of adjusting automated vehicles driving style is a difficult one. To address the above issues, this article focuses on the spatio-temporal motion planning problem of automated vehicles in multi-vehicle conflict scenarios. A risk-field based motion planning method is proposed. By predicting the state of the vehicles in the traffic scenario, the risk field matrix is built for motion planning. The idea of path-velocity separation planning is adopted to divide the motion planning into two layers as path planning and trajectory planning. In path planning, static risk matrices serve as constraints. Considering the driving safety and comfort, the path cost function is designed to evaluate the candidate path group, obtained by longitudinal sampling and lateral sampling, to determine the target path. The dynamic risk matrices are used to construct the spatio-temporal graph corresponding to the target path, based on which dynamic planning and quadratic planning are introduced to solve the trajectory planning problem. Simulations were built to prove the practicability of the method. Results show that by adjusting risk threshold can change the aggressiveness of autonomous vehicles driving style.

Since vehicles are not restricted by lane lines when driving inside intersections, they travel freely and their paths have many possibilities, which are related to the traffic order of other road users. It is necessary to understand and describe vehicle paths through intersections. Previous studies on modeling vehicle paths through intersections have predominantly been limited to vehicles turning in one single direction or specific intersections, ignoring the application universality. This study set out to establish a unified model to describe non-conflict paths of vehicles through intersections. An entrance lane-based coordinate system with geometric parameters was established to describe the position relationships of entrance and exit lanes. Three-order Bezier curves with control parameters were used to describe vehicle paths. By extracting the parameter values from driving simulator-based experiments, the entrance and exit lane-based vehicle path model was proposed to represent the relationship between geometric and control parameters. Actual path data captured by an unmanned aerial vehicle were used for model validation, and results show the validity of the proposed model with a mean Root Mean Square Error of 0.4613 m between observed and fitted paths. More validation considering position distributions of path origins and destinations and angle deviations when entering and leaving intersections was performed. Cases from HighD open dataset also demonstrated the model’s potential for lane-changing scenarios. This study provides an exciting opportunity to commonly describe vehicle paths without conflicts at geometrically regular and irregular intersections and is hoped to have the possibility of planning local paths for autonomous vehicles.

There is a growing number of studies on the traffic control strategies of signal timings and vehicle trajectories at signalized intersections, while lane assignments are widely pre-specified and fixed. Meanwhile, existing strategies generally require a fully connected and automated vehicles (CAVs) environment. To fill up the gaps, this study contributes to a two-dimensional (spatiotemporal) control strategy by jointly optimizing traffic signals, lane settings, and vehicle trajectories at isolated signalized intersections under the mixed traffic of connected automated and human-driven vehicles. Specifically, based on the pseudo-platoons, signal timing plans and settings of approach lanes are jointly optimized by a piece-wise linear programming model. Then, vehicle trajectory control is integrated into the collaborative control framework to smooth vehicle trajectories. Three groups of numerical experiments are conducted to verify the effectiveness and efficiency of the proposed control method. Results show that the proposed algorithm outperforms the actuated control in terms of vehicle travel time under both under-saturated and over-saturated traffic conditions.

Graph representation learning is a hot topic in non-Euclidean data in various domains, such as social networks, biological networks, etc. When some data labels are missing, graph autoencoder and graph variational autoencoder can perform outstanding abilities on node clustering or link prediction tasks. However, most existing graph representation learning ignores data's multi-modal features and takes the node features and graph structure features as one view. Besides, most graph autoencoders only reconstruct the node feature matrix or adjacency matrix, which does not fully use the hidden representation information. In this paper, we propose a multi-view representation model based on graph autoencoder, which can employ the global structure topology, latent local topology, and feature relative information. Meanwhile, we add another decoder to reconstruct the node feature matrix as an auxiliary task. In this way, the proposed framework can utilize the learned representation sufficiently. We validate the effectiveness of our framework on four datasets, and the experimental results demonstrate superior performance compared with other advanced frameworks. [ABSTRACT FROM AUTHOR]

Although it’s very common nowadays to experience onboard adaptive cruise control systems (ACCS), most of them are initialized with fixed parameters and little consideration is taken to adapting to different drivers. In order to improve the ride comfort and operation familiarity of drivers when using the ACCS, driver’s personalized car-following (CF) characteristics should be considered in ACCS developments. In this paper, an ACCS framework with CF characteristics identification and application is designed, where the desired safety margin (DSM) model is utilized to describe driver’s CF behaviors. In view of the limited performance of on-board computers, a simple method for CF characteristics identification from the sight of driver’s physiology and psychology mechanism is proposed, which tries to estimate DSM model parameters on the basis of CF data. With the proposed method, the CF data under manual driving are collected and filtered for the identification of drivers’ response time, upper and lower limits of DSM and sensitivity factors for acceleration and deceleration iteratively. And the latest iteration results of DSM model parameters would then be applied into the ACCS when it’s enabled. Several naturalistic driving tests are adopted for the verification whose results support that, the proposed method could perform well in identifying drivers’ CF characteristics online by collecting and analyzing manual driving data with a much smaller resource consumption when compared with genetic algorithm (GA). Besides, with the increase of CF data volume, the identified results are also becoming more and more stable and robust. Therefore, the proposed ACCS framework is able to imitate different drivers.

An extension of a recent framework for analyzing scheduling disutility with perception errors is derived. In such framework, the traveler has (α,β,γ)scheduling preferences. Although the actual travel time of travelers is influenced by departure time, travelers make a route-choice decision on the basis of their perceived travel time. Thus, we mainly investigate the effects of perception errors on the optimal departure time. The optimal departure time and expected disutility are obtained on the basis of the proposed scheduling disutility model with perception errors. The inverse function curve of a standardized normal distribution is introduced to geometrically analyze the positive correlation between perception errors and optimal departure time. Our empirical example further illustrates that departure time as an endogenous variable affects the expectation and variance of perceived travel time and implies that perception errors are related to departure time. The linear relationship between the mean and variance of perceived travel time and the departure time is analyzed through an empirical illustration. The expected optimal disutility and departure time are derived, provided that the mean and variance of perception errors and departure time satisfy linear dependence. Finally, the results of the analysis of scheduling services with standardized normal distributions agree with the theoretical results and linear assumption in this study.

A vehicular communication system can provide motion information based on various sensors. Thus, adaptive cruise control (ACC) systems based on a reliable communication system can relieve traffic congestion in a platoon. However, acquiring vehicle information entails uncertainties because of the disturbance of traffic environment and vehicular communication systems, thereby influencing vehicle control performance. In this study, the desired safety margin (DSM) model is employed to investigate the influence of uncertainty on car-following performance, such as starting, emergency braking, and car-following processes. Based on the DSM model, the disturbance level on perceived safety margin is introduced to characterize the uncertainty of vehicle information. The stability criterion of the DSM model with the disturbance level is derived via linear stability theory. Analytical results indicate that a negative value of disturbance level will enlarge the stable region. By contrast, a positive value is conducive for maintaining the consensus state and achieving the high acceleration and deceleration of following vehicles in the starting process. Findings show that the disturbance in the vehicular system significantly influences car-following performance. To enhance the smoothness and stability of traffic flow evolution, a new control strategy is proposed in this study. Numerical experiments illustrate the effectiveness of the proposed control strategy in stabilizing traffic flow. This study highlights the need to resolve the stability of sensors and vehicular communication systems, and to develop the vehicular controller to help ACC systems improve vehicle control performance in the car-following process.

In this paper, an extended desired safety margin (DSM) car-following model is proposed by accounting for the effect of the variation of historical perceived risk and acceptable risk in terms of the DSM model. By conducting gray correlation analysis, an investigation is carried out into whether the variation of historical perceived risk and acceptable risk has important effects on the acceleration or deceleration of a target vehicle based on a real-vehicle test platform. Through simulated results, the dynamic performance of an extended DSM model is investigated in comparison with the DSM model. Conclusions show that the extended DSM model can better reflect the characteristics of traffic flow compared with the DSM model, and can improve the performance of the vehicle in the start, stop, and car-following processes. Numerical simulations further demonstrate that the extended DSM model can improve traffic safety via the changes of time-to-collision and safety margin when external disturbance is introduced into the leading vehicle. Thus, historical information about target vehicles should be considered to improve the performance of car-following in adaptive cruise control (ACC) and automotive platoon driving.

In the dynamic interaction of a driver-vehicle-environment system, risk perception of drivers changes dynamically, having significant impacts on driving behavior and vehicles movement. In China, because there is less construction of stop signs, as well as limited regulation of driving courtesy, traffic operation and safety issues at unsignalized intersections require harder concern. Thus, in this study, focus was on risk perception of drivers at unsignalized intersections in China and then analysis of vehicles movement with consideration of drivers’ risk perception. A total of 150 typical merging cases were selected at an unsignalized intersection in Kunming City. On the basis of cognitive psychology theory and an adaptive neuro-fuzzy inference system, quantitative models of drivers’ risk perception were established. Drivers’ acceptable risk perception levels were identified by using a self-developed data analysis method. On the basis of game theory, the relationship among the quantitative value of drivers’ risk perception, acceptable risk perception level, and vehicle motion state was analyzed; then the vehicles merging movement model was established. Finally, the vehicles merging movement model was validated by using data collected from real-world vehicle movements and driver decisions. Results showed that the developed vehicles movement model had both high accuracy and good applicability. This study could provide theoretical and algorithmic references for the microscopic simulation and vehicle active safety control system.

Forecasting of short-term traffic states on expressways by adopting spatial–temporal models has gained increasing attention. Traffic data from neighboring sites were demonstrated to provide valuable information for predicting traffic states at sites of interest. However, when one considers the need to analyze the multivariate nature of traffic states over spatial dimensions, as well as of different models for various times of day, the interaction effects between spatial–temporal patterns require further investigation. This study addressed this issue on a segment of Shanghai North–South Expressway. Temporal characteristics of traffic volumes and speeds were analyzed by dividing the time of day into ordinal periods with relatively stable states. Then, spatial vector autoregressive (VAR) models were constructed at typical analysis periods for volume and speed forecasting by considering different combinations of upstream and downstream impacts. The results showed that the impact of downstream traffic conditions on upstream traffic cannot be neglected, especially in peak periods. For off-peak periods, traffic states at a location largely depended on upstream states, while downstream states appeared to have fewer effects. In such cases, models incorporating only upstream states were proved able to achieve sufficient accuracy. In addition, encouraging forecasting results were found when VAR models were compared with traditional methods (e.g., autoregressive integrated moving average and historical average), which failed to consider the spatial component of spatial–temporal patterns. All analyses helped to demonstrate the applicability of VAR models and to provide practical guidance for incorporating spatial–temporal dynamics into forecasting of expressway traffic states.

Two types of delay variability have been commonly referred to at signalized intersections: arrival-time-dependent individual vehicle delay variability and average control delay variability. The former focuses on the delay experienced by individual vehicles, whereas the latter deals with the average consequence of signal control for the entire traffic flow during a given evaluation period. With a number of methods available for estimation, little research has been conducted to enable a comprehensive comparison of these two variability measures. This issue is addressed by a comparison of these two types of delay variability at isolated, fixed-time controlled intersections based on two analytical models accounting for the stochastic nature of traffic arrivals and overflow queues. The results show that in undersaturated conditions, individual vehicle delay tends to have a wider distribution and a larger variance compared with average control delay. In oversaturated conditions, the shapes of both types of delay distributions shift to the higher values with larger variances. Different arrival processes are found to have a significant influence on the pairwise delay distributions. In addition, the width of the delay distribution based on percentiles is used to quantify the delay uncertainty under different degrees of saturation. Compared with average control delay, individual vehicle delay is found to have a larger uncertainty in undersaturated conditions, whereas it becomes relatively certain in oversaturated conditions. All the analyses have special practical implications for enriched knowledge of stochastic arrival and departure processes at signals.

Based on VANETs (Vehicle Ad-hoc Networks), a stable, reliable and low delay wireless network access environment is an inevitable element of vehicle safety applications. The IEEE 802.11p is a specially designed protocol for ITS (Intelligent Transportation Systems) for V2V and V2I communication. It provides 10MHz channel bandwidth and up to 27-Mbps data transmission rate. This paper analyzes the theoretical throughput and delay limit of the 802.11p protocol. Considering PLR (Packet Loss Rate) and delay of VANETs, we analyzed the theoretical highway capacity upper limit of 802.11p for V2V communication. The results show that 802.11p communication technology can increase highway capacity. If all of the vehicles are equipped with 802.11p communication technology, the increase in highway capacity is about 491 percent.

This paper measures the performance parameter of the automobile braking system with Electronic Vacuum Booster (EVB) through real vehicle experiment. According to the data collected from the experiment, the performance parameters of EVBs in different cars are not the same. The performance parameters of the EVB in both test cars can be separated into three parts. For example, when the desired braking intension, in other words the input signal of electronic vacuum booster, is less than 7, the braking effect is not obvious; when the desired braking intension is between 7∼40, the relationship between the desired braking intension and the acceleration is found to be linear variation; when the desired braking intension is greater than 40, the wheels will be locked and the acceleration is constant. Then we get the performance parameter of automobile braking system with electronic vacuum booster through linear regression. The results can be used for automatic brake control.

In order to get accurate navigation data via Strapdown Inertial Navigation System (SINS), calibration of misalignment angle between Inertial Measurement Unit (IMU) and vehicle is necessary. The misalignment angle model is simplified, assuming that vehicle travels on a horizontal plane. Due to the velocity of vehicle is small, equation of specific force is simplified. And then equation of misalignment angle is deduced on condition that vehicle travels on a horizontal plane, making straight motion ideally. Angular rate is used to discriminate that vehicle making straight motion. Steps for calibrate misalignment angle are established. In calibration experiment, data are collected and misalignment angle of vehicle-mounted IMU is calibrated using simple techniques of data processing. Analysis shows that, compensation of misalignment angle helps improving the accuracy of SINS. Position error of SINS solution is decreased and the acceleration of vehicle is more accurate.

To evaluate safety in intersections and find the relationship between conflict and accidents, a quantitative method for the severity of traffic conflict at intersection was proposed. Moving elements were assumed as rectangles. By using technology of imaging processing, kinematics parameters of vehicles were obtained. Supposed that movement units keep moving with current motion state, traffic conflict and time to collision (TTC) were determined using iterative method and analyzing positions of rectangles’ vertexes. According to the analysis of traffic conflict and brake performance of vehicles, non-complete braking time (TB) was selected to be critical value of conflict severity. Taking TTC and TB as parameters, quantitative value (Qs) was established. The severity of traffic conflict was quantified and classified by analyzing TTC and Qs. A case in Beijing was analyzed. The results indicated that quantitative result accorded with practical situation, and this method could be used in conflict detection and quantifying the severity of traffic conflict accurately.

The maximum clique problem is an NP hard combinatorial optimization problem, which is widely used in industrial and management processes. In order to approach the solution of the maximum clique problem, a deterministic annealing algorithm is proposed. When the barrier parameter is reduced from a large positive number to zero, the algorithm can track the minimum path of the obstacle problem to obtain a high-quality solution, which is a continuous method. The global convergence iteration of the Lagrange multiplier can be performed to obtain the minimum point of the obstacle problem in the feasible descent direction for any given positive value of the barrier parameter and has a desired property that it automatically satisfies the upper and lower bounds of variables if the steplength is a number that is between 0 and 1. Numerical results are provided to illustrate the efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]