The introduction of autonomous vehicles (AV) will represent a milestone in the evolution of transportation and personal mobility. AVs are expected to significantly reduce accidents and congestion, while being economically and environmentally beneficial. However, many challenges must be overcome before reaching this ideal scenario. This study, which results from on-site visits to top research centres and a comprehensive literature review, provides an overall state-of-the-practice on the subject and identifies critical issues to succeed. For example, although most of the required technology is already available, ensuring the robustness of AVs under all boundary conditions is still a challenge. Additionally, the implementation of AVs must contribute to the environmental sustainability by promoting the usage of alternative energies and sustainable mobility patterns. Electric vehicles and sharing systems are suitable options, although both require some refinement to incentivise a broader range of customers. Other aspects could be more difficult to resolve and might even postpone the generalisation of automated driving. For instance, there is a need for cooperation and management strategies geared towards traffic efficiency. Also, for transportation and land-use planning to avoid negative territorial and economic impacts. Above all, safe and ethical behaviour rules must be agreed upon before AVs hit the road.

The connected automated vehicle (AV) technologies provide unprecedented opportunities for precisely controlling and optimising vehicle trajectories to improve traffic performance from the aspects of travel time reduction, driving comfort improvement, fuel consumption and emission savings and safety enhancement. Recently, connected and automated vehicle (CAV) trajectory optimisation research has become a hot topic. This study provides an overview of studies on CAV trajectory optimisation in the road traffic context, with a focus on the literature in the past decade. Rather than exhausting all related studies, this review focuses on categorising representative studies with several relevant criteria. On the basis of the review outcomes, research gaps and needs are discussed to facilitate future research.

Due to relative mobility, topology changes rapidly with frequent link breakage in vehicular ad hoc networks (VANETs). Clustering VANETs into small groups limits channel contention and controls the network topology efficiently. In this study, a novel cluster-based medium access control (CB-MAC) protocol is proposed for VANETs. The cluster formation process is defined. Moreover, cluster head election and cluster merging processes are described for efficient communication in the cluster as well as out of the cluster. The mechanism defined in IEEE 802.11 standard is specially designed for only direct communications and is not suitable for cluster-based communications. Therefore, new control packets are introduced and the existing control packet format is modified to support cluster-based communications. For effective MAC protocol design, the request to send (RTS)/clear to send (CTS) mechanism is not used for safety messages which are of broadcast nature. On the other hand, the RTS/CTS mechanism is used for non-safety data delivery to eliminate hidden node problem. Markov chain model-based analytical model is presented to explore the performance of the proposed CB-MAC protocol. The proposed protocol is validated by numerical studies. The numerical results exhibit that the proposed CB-MAC protocol improves system performance and satisfies the delay constraint of 100 ms for safety messages.

In this study, a model for bus frequency optimisation was presented, which determined the optimal bus frequencies aiming to minimise the users’ total travel cost. Unlike past researches, where the impacts of real-time information were ignored, the user behaviours affected by mobile applications were considered in this study. The effects of bus real-time information on user behaviours had been proved by some other researches. By assigning a user's trip to three stages (pre-trip, on-board and end-trip), four different user behaviours were taken into account in the model building process: shortest total travel time, shortest pre-trip time, shortest walking time and shortest riding time. In addition to the object bus line and stops on it, other bus lines and stops serving the same traffic zones were also considered. The demand was given in the form of an origin–destination (OD) matrix. Each value in the OD matrix represented the passenger amount from one zone to another. Finally, the illustrated model was tested by four cases and the results showed a good performance.

The quality of traffic data is crucial for modern transportation planning and operations. However, data could be missing for various reasons. Hence, the data imputation approaches which aim at predicting/replacing the missing data or bad data have been considered very important. The traditional traffic data imputation approaches mainly focus on using different probability models or regression methods to impute data, and they only take limited temporal or spatial information as inputs. Thus, they are not very accurate especially for data with a high missing ratio. To overcome the weaknesses of previous approaches, this study proposes an innovative traffic data imputation method, which first transforms the raw data into spatial-temporal images and then implements a deep-learning method on the images. The key idea of this approach is developing a convolutional neural network (CNN)-based context encoder to reconstruct the complete image from the missing source. To the best of the authors’ knowledge, this is the first time a CNN method has been incorporated for traffic data imputation. Experiments are conducted on three months of data from 256 loop detectors. Through comparison with two state-of-the-art approaches, the results indicate that this new approach increases the imputation accuracy greatly and has a stable error distribution.

In this paper, we propose and develop a multiple-camera 3D vehicle tracking system for traffic data collection at intersections. Assuming a simple 3D cuboid model for the vehicle, the developed system allows 3D vehicle dimension estimation using fusion of information from multiple cameras. Using a common rectangular road pattern, each camera is first individually calibrated and then jointly post-optimised. Then, the developed 3D vehicle tracking system takes synchronised images from multiple cameras as inputs and processes 2D image frames using object segmentation techniques to derive vehicle silhouettes. After 2D vehicle segmentation, objects in the 2D image frames are projected to the 3D real world to allow estimation of vehicle length and width. The height of the object is sought in the image view that would create the top quadrilateral of the vehicle that has the edge furthest away from the vehicle base quadrilateral. With Kalman filter based vehicle tracking, interested traffic data, such as vehicle count, are derived from the vehicle trajectory. Real-world experimental results for an intersection with two cameras have shown that the developed 3D vehicle tracking system can reliably estimate 3D vehicle dimensions and improve accuracy of traffic data collection compared to a single-camera system.

Drivers' reaction time of reading signs on expressways is a fundamental component of sight distance design requirements, and reaction time is affected by many factors such as information volume and concurrent tasks. We built cognitive simulation models to predict drivers' direction sign reading reaction time. Models were built using the queueing network-adaptive control of thought rational (QN-ACTR) cognitive architecture. Drivers' task-specific knowledge and skills were programmed as production rules. Two assumptions about drivers' strategies were proposed and tested. The models were connected to a driving simulator program to produce prediction of reaction time. Model results were compared to human results in sign reading single-task and reading while driving dual-task conditions. The models were built using existing modelling methods without adjusting any parameter to fit the human data. The models' prediction was similar to the human data and could capture the different reaction time in different task conditions with different numbers of road names on the direction signs. Root mean square error (RMSE) was 0.3 s, and mean absolute percentage error (MAPE) was 12%. The results demonstrated the models' predictive power. The models provide a useful tool for the prediction of driver performance and the evaluation of direction sign design.

This study investigates the path following control problem about distributed-drive self-driving vehicle through coordinated control of the autonomous front-wheel steering and the differential steering control, to improve the tracking performance. On the basis of the model predictive control algorithm and vehicle dynamic model, the preview time adaptive control of path following is proposed to realise path following with changing preview time in straight and turning conditions. Considering the characteristics of the distributed-drive self-driving vehicle, the differential torque control is utilised based on the reference heading angle to realise trajectory tracking under the condition of constant torque demands. To integrate the advantages of the two methods, coordinated control of trajectory tracking based on the autonomous steering and differential steering is performed by setting the weight coefficients method. MATLAB co-simulation with Carsim and road testing validation are executed, and both demonstrate that the coordinated control strategy can not only effectively improve the response speed and flexibility of steering, but also improve the reliability and accuracy of trajectory tracking.

To utilise high occupancy vehicle lanes better, high occupancy toll (HOT) lanes are introduced to counter against congestion on the urban highways. In such system, low occupancy vehicles (LOVs) are allowed to pay a toll and access to HOT lanes from general purpose (GP) lanes, so that the toll rate plays a key role in dynamically allocating LOVs over the HOT and GP lanes to improve the overall system performance. First, this study presents an improved random forest (RF) method to build the lane choice behaviour prediction model. Then, by using the 5 min historical traffic and toll data collected from Interstate 405 in the USA, the improved RF combined with cross-validation and grid search shows the highest accuracy of 88.7%, which is better than other four methods. Furthermore, a novel nested model with two levels is proposed to optimise the toll rates under different real-time traffic conditions. For the nested model, the experimental results show that the proposed dynamic pricing strategy can decrease the total delay and improve the efficiency significantly. To realise the pricing strategy, some Intelligent Transportation System technologies for HOT lane systems are described in detail and designed as the fundamental of the pricing strategy.

A new cooperative localisation method based on the Bayesian framework is proposed to obtain accurate and reliable vehicle localisation in intelligent transportation system applications. The new position estimation is achieved by the fusion of the filtered global positioning system (GPS) data, the inter-vehicle distance, and bearing angle. The simulation results indicate that the accuracy of vehicle localisation is effectively improved with the consideration of bearing angle, when compared with the fusion of GPS and inter-vehicle distance. A simulated scenario with multi-target dynamic environment is designed to discuss an appropriate number of nearby vehicles for cooperative localisation. The simulation results show that four nearby vehicles around the host vehicle for localisation is the most appropriate while balancing the accuracy and computing burden. Moreover, the proposed localisation method has also been proved to provide a well-robustness performance as well as localisation accuracy.

This study explores the effects of origin–destination (O–D) attributes on route choice with long-term GPS data collected by private vehicles in Toyota city, Japan. The non-linear fixed effects are captured by the piecewise specified structural tastes on costs in the utility functions. The multi-level random effects are captured by the multi-level random terms. This empirical analysis demonstrates that the incorporation of O–D attributes can enhance the route choice models significantly. The effects of both O–D distance and drivers’ familiarity with the O–D on route utilities are proved to be non-linear and non-monotonic. Besides the fixed effects, the multi-level random effects of OD attributes are also confirmed to be significant.

Design-hour volume (DHV) and directional DHV (DDHV) are important traffic forecast parameters for both planning and operational studies. They are used for roads and intersection design and operational analysis. Estimating these two parameters requires a record of hourly volumes for every hour in a year. Therefore, permanent traffic counters are usually used to keep a record of those hourly volumes. The use of permanent counters faces several challenges because of adjacent construction activities and hardware or communication failure. These challenges result in the missing part of the collected data. Moreover, estimating DHV and DDHV based on short-term traffic counts is often needed. In this research, an artificial intelligence approach is used to estimate DHV and DDHV for roadways with different functional classifications. An artificial neural network model, which utilises historical records of annual average daily traffic along with other road characteristics, such as number of lanes and functional classification, is developed. Results show that the model was able to achieve a highly accurate and reliable DHV and DDHV estimates.

With the development of traffic control theory, self-organising control has become one of the most promising techniques for traffic control. Among the various parameters of self-organising control, the queue length (number of vehicles) is a key one. Compared to the approaches using other detectors, vision-based approaches have a greater potential in queue length detection. However, the complicated traffic conditions (such as the changeable weather and the vehicle occlusion) and the large calculation of image processing have posed great challenges to the real-time application. Here, a fast video-based queue length detection approach is proposed. For each lane, according to the level of traffic congestion evaluated by the foreground area ratio, the corresponding vehicle counting method is adopted. When the traffic is determined congested, a fast area-based method for estimating the number of vehicles is adopted. Otherwise, a fast vehicle detection and counting method combining background difference and Adaboost classifier is adopted. The experiment results demonstrate that the proposed approach can handle actual traffic environment and has great potential for real-time application.

This study investigates empty vehicle redistribution algorithms for personal rapid transit and autonomous taxi services. The focus is on passenger service and operator cost. A new redistribution algorithm is presented in this study: index-based redistribution (IBR). IBR is a proactive method, meaning it takes into account both current demand and anticipated future demand, in contrast to reactive methods, which act based on current demand only. From information on currently waiting for passengers, predicted near-future demand and projected arrival of vehicles, IBR calculates an index for each vehicle station, and redistribution is done based on this index. Seven different algorithm combinations are evaluated using a test case in Paris Saclay, France (20 stations and 100 vehicles). A combination of simple nearest neighbours and IBR is shown to be promising. Its results outperform the other methods tested in peak and off-peak demand, in terms of average and maximum passenger waiting times as well as station queue length. The effect of vehicle fleet size on generalised cost is analysed. Waiting times, mileage and fleet size are taken into account while assessing this generalised cost.

Traffic signal control systems often operate with a fixed time strategy when practical conditions prohibit adaptive traffic control built upon real-time traffic data. One of the most important challenges to have good performance for a fixed time strategy is to optimally identify the breakpoints that divide one day into different partitions, which is a time-of-day (TOD) breakpoints optimisation problem. Various solutions to this problem have been proposed based on classic clustering methods. However, these methods require empirical adjustment since they are not capable of incorporating the temporal information among traffic data. In this study, the TOD breakpoints optimisation problem is formulated as a time series data partitioning problem. A recursive algorithm is proposed to partition one day into several time periods based on the dynamic programming reformulation of the original problem. The appropriate number of partitions is determined through the elbow method. Then the authors present a case study based on the real data from Qingdao City in China that evaluates the proposed method against the existing ones. From simulation experiments, they illustrate that the proposed method is more effective in terms of operational performance measures such as maximum queue length and delay time than the existing ones.

Multiple sources of interference and low signal-to-interference ratio are two major challenges to speech-based intelligent driver assistant systems. They will have a serious impact on the performance of voice control commands. To solve this problem, this study proposes a speech enhancement method based on wavelet analysis and blind source separation in a complicated automobile environment. Firstly, according to the characteristics of typical speech signals, an automatic selection method of optimal wavelet basis is given to optimise the signal denoising performance. Secondly, the mixed signals are separated by a complex fast-independent component analysis (ICA) algorithm, and then the inverse short-time Fourier transform is utilised to obtain the separated signals in time domain. Finally, experiments are carried out to demonstrate the effectiveness of the proposed method. Results show that its performance in terms of a correlation coefficient can be improved by about 7% compared with that of the conventional method only using fast-ICA.

Four-wheel independent control electric vehicle has possessed tremendous potentials because the enhancement of driving performance and energy savings can be simultaneously carried out by independent and precise driving/braking/steering control. The study has proposed a comprehensive control strategy aiming at all normal conditions, which employs hierarchical architecture to reach the above-mentioned control. In the high-level controller, sliding mode control scheme is developed to figure out total force and yaw moment. In the low-level controller, energy-efficiency optimisation allocation is presented to reduce motor power losses and obtain energy recovery based on motor efficiency map, and then steering angle allocation is conducted to decrease the lateral force so as to reduce power losses caused by the tyre sideslip. Considering insufficient motor braking torque during large deceleration or even larger, the blended brake control strategy with the motor brake and electric hydraulic brake and further anti-skid brake system control via adopting fuzzy logic method are carried out. The torque and pressure are gained to deliver the corresponding actuators model established according to their physical characteristics. Through CarSim-MATLAB/Simulink-AMEsim co-simulation, results suggest that the developed strategy can boost the vehicle manoeuvrability and reduce energy consumption generated by motors and tyre sideslip under all the conventional occasions.

The management of container flows is one of the most challenging tasks for terminal managers. In this regard, the freights inside the containers have to be transported towards their requesting companies. This delivery is subject to many factors such as the vessel berthing time, yard assignment, time windows of the companies, availability of internal vehicles etc. Therefore, the time a given company waits for its requested containers is highly dependent on the management of the technical resources at the container terminal. To appropriately address the coordination of involved operations, a multi-stage approach is proposed. It is aimed at providing a complete schedule of all the involved processes and supporting the operational decisions related to the technical terminal resources in an integrated way, from the berth to the delivery of the freights inside containers to the requiring companies. The computational results indicate that this solution approach provides a suitable solution in all cases and is appropriate for supporting terminal managers when addressing strategic decisions involving the technical equipment.

To further improve fuel consumption performance of hybrid electric vehicles (HEVs) running on commute route in the face of time-varying traffic information, this paper investigates a real-time energy management strategy based on the adaptive equivalent consumption minimization strategy (A-ECMS) framework with traffic information recognition. The proposed management strategy integrates the global near optimization and the real-time performance. The simple traffic recognition is constructed by utilising k-means clustering algorithm to deal with the historical traffic data to form four clusters. The adaptive equivalence factor of the A-ECMS is designed as a three-dimensional mapping on each cluster and the system states by employing stochastic dynamic programming (SDP) policy iteration to solve offline the stochastic optimal control problem formulated by each cluster statistical characteristic. In real-time energy management controller online, the instantaneous power split is performed by the ECMS with a proper equivalent factor, which is obtained from mappings according to the cluster recognised by the current traffic situation and the state-of-charge (SOC). The effectiveness of the designed control strategy is verified by the simulation test conducted on GT-suite HEV simulator over real driving cycles.

Modern vehicular infotainment systems are becoming increasingly complex and are embracing a wide range of functionalities. Interacting with some of these functionalities, while driving, may increase the driver's workload and affect the execution of primary driving tasks. This article addresses this issue and proposes a practical application that could help overcome the problem as well as improve the driving experience. The applied method consists of developing a system capable of estimating the driving complexity in real time using variables already available in current vehicles, and responding according to the complexity reference, to apply countermeasures to the infotainment system. The intended purpose is to facilitate the interaction with the functionalities and reducing the amount of information offered to the driver in complex scenarios. A baseline system was built and tested, demonstrating the feasibility of its implementation in current vehicles.