Path following is a main and fundamental task for future lunar rover autonomous navigation. This study adopts genetic algorithm (GA) to optimise the parameters of a path-following fuzzy controller designed for a six-wheel lunar rover. Considering the influences of the orientation deviation and its variation rate to the controller performance, two quantisation factors and one scale factor are utilised to limit both the input and output variables. However, it is difficult to manually achieve the proper factors because they are coupling themselves complicatedly. They are adjusted and modified automatically during the path-following process based on GA to achieve the auto-tradeoff the parameter and its control performance. Those parameters are coded using floating-point encoding scheme, respectively. The minimum tracking error and the angular velocity are taken as the target function. After several iterations of crossover and mutation, the best parameters are determined aiming at achieving lower path tracking error with small angular velocity. Simulation on different paths and comparisons with traditional fuzzy controller results show the designed controller with optimised parameters has better performance than the one with manually regulated parameters.

Driving style is a key variable which we can influence in order to reduce consumption and pollutant emissions, but other variables also need to be taken into account, such as safety, comfort and travel time. There are different alternatives for obtaining the optimal speed and gear by taking into account the vertical profile of the road and vehicle characteristics. Of these alternatives, Dynamic Programming (DP) provides fairly satisfactory results. However, this calculation involves a high computation cost when it is used to calculate long routes, which poses practical problems when the route can be varied frequently or when unexpected traffic events make it necessary to recalculate the speed profile. This study proposes a solution that is closer to the optimal solution. The algorithm is based on simple action rules for elementary road profiles that have been previously obtained using DP. Furthermore, these rules are recalculated in order to fulfil a predefined travel time. The algorithm has been used in different traffic situations on a real route and differences with the optimal solution have been evaluated so that the conditions where it works better are assessed.

This study proposes a robust real-time system to detect vehicles that change lanes illegally based on tracking feature points. The algorithm in the system does not need to switch depending on the illumination conditions, such as day and night. The camera is assumed to be heading in the opposite direction to the traffic flow. Before starting, the system manager should initially designate several regions that are utilised for detection. Then, the proposed algorithm consists of three stages, such as extracting feature points of corners, tracking the feature points attached to vehicles and detecting a vehicle that violates legal lane changes. For the feature extraction stage, the authors used a robust and fast algorithm that can provide stable corners without distinguishing between day and night or weather conditions. Salient points are selected among the corner points for registration and tracking. Normalised cross-correlation is used to track the registered feature points. Finally, illegal change-of-lane is determined by the information obtained from the tracked corners without grouping them for segmentation. The proposed system showed excellent performance in terms of the accuracy and the computation speed.

Correlation degree between adjacent signalised intersections is considered as the most important component in subarea partition algorithm. In this study, contributing factors for subarea partition are selected by taking into consideration the differences with respect to cycle lengths, link length and path flow between upstream and downstream coordinated phases. Their impacts on performance index of subarea partition are further studied using numerical experiments. The study then proceeds to propose a correlation degree index (CI) as an alternative for the performance index in order to reduce the computational complexity. The relationship between CI and the contributing factors is established to predict the correlation degree. Finally, the model is validated using field survey data.

Human-centric driver fatigue monitoring systems (DFMS) with integrated sensing, processing and networking aim to find solutions for traffic accidents and other relevant issues. A novel, efficient combined features extraction approach from Pyramid Histogram of Oriented Gradients (PHOG) and contourlet transform (CT) for fatigue expression descriptions of vehicle drivers is proposed, and a random subspace ensemble (RSE) of linear perception (LP) classifiers as the base classifier is then exploited for the classification of three predefined fatigue expressions classes, namely, awake expressions, moderate fatigue expressions and severe fatigue expressions. Holdout and cross-validation experiments are created, and the results show that combined features by RSE of LP classifiers outperform the other seven classifiers, that is, PHOG features by LP classifier, CT features by LP classifier and combined features by five individual LP classifiers. With combined features and RSE of LP classifiers, the average classification accuracies of three fatigue expression classes are over 92% in both the holdout and cross-validation experiments. Among the three fatigue expression classes, the class of severe fatigue expressions is the most difficult to recognise, and the classification accuracy is over 84% in both the holdout and cross-validation experiments, which shows the effectiveness of the proposed feature extraction method and RSE of LP classifiers in developing DFMS.

During the last year eco-friendly driving and the development of new driver assistance systems that support eco-friendly driving are increasingly becoming important. One main objective of research in this area is finding ways of motivating drivers to behave ecologically beneficially in a sustainable way and identifying how these motives can be generated, for example, through in-vehicle assistance or information systems. One aim of the following study was to develop a matrix of the most important eco-friendly driving motives, moderating and influencing factors (e.g. trip purpose, annual mileage). Another objective was analysis of the influence of different driver characteristics on relevant motives and to deduce first hints for development of applications for generating these motives. The results of the questionnaire study demonstrate that three main motives ‘time’, ‘environment/consumption’ and ‘possibilities to change’ are selectively important and distinctive for various driver groups. The results therefore imply that different strategies and applications or systems might be necessary to change the driver behaviour and to convince them that the ‘eco-system’ will be beneficial for them. Furthermore, the results describe ideas of what kind of assistance or information systems the drivers would prefer as a support system. This information can help in the design of future eco-driving support systems.

Pedestrian evacuation has long been a vital safety concern for any large indoor facility, for example, gymnasium or stadium. To efficiently simulate crowded pedestrian evacuation, an agent-based modelling approach in the cellular automata (CA) environment is proposed in this study. Different from a stand-alone CA method which roughly describes the external environment, the proposed agent-based modelling approach can describe individual behaviour more accurately. In order to verify the crowded pedestrian evacuation simulation and reflect the behaviour of pedestrian crowds’ evacuation, this study simulates four evacuation scenarios as follows: (i) an ordered activity area with no obstacles, (ii) an unordered activity area with no obstacles, (iii) an ordered activity area with obstacles and (iv) an unordered activity area with obstacles. The effects of the parameters on the evacuation simulation process and the effects of maximal endurance capability on the number of casualties are also analysed. Furthermore, the order of evacuation of pedestrians with different competitive capabilities is estimated. The simulation results show that the proposed modelling framework, principles and methods are effective, and the model has a strong capability to describe, represent and explain the reality of evacuation.

A procedure was developed for using Surrogate Safety Assessment Model (SSAM) and VISSIM for safety assessment at freeway merge areas. The simulated conflicts generated by the VISSIM simulation models and identified by the SSAM approach to those measured in the field using traditional traffic conflicts techniques. Of particular interest was to identify if the consistency between the simulated and the field-measured traffic conflicts could be improved by calibrating the VISSIM simulation models and adjusting the threshold values in SSAM. A two-stage procedure was proposed to calibrate and validate the VISSIM simulation models. The transferability of the calibrated simulation models was also tested. It was found that the two-stage calibration procedure reduced the mean absolute prevent error (MAPE) for total conflicts from 78.1 to 33.4%. More specifically, the MAPE value was reduced from 76.6 to 33.5% for the rear-end conflicts, and from 79.5 to 35.8% for the lane-change conflicts. Linear regression models and the Spearman rank correlation coefficient were also developed to study the relationship between the simulated and the observed conflicts. Data analysis results showed that there was a reasonable consistency between the simulated and the observed conflicts.

In many countries traffic emissions have significantly increased during the last two decades because of the increased number of vehicles. As such, traffic emissions have become the main source of air pollution in urban areas, where breaches of the EU limit values frequently occur. To reduce these emissions, local traffic measures can be implemented complementary to regional and national measures. In this study, the impact of various traffic measures at a single intersection is investigated using a traffic model and an emission model. The measures included are traffic demand control, banning heavy duty vehicles (HDVs) and speed restriction. It was found that reducing traffic demand by 20% led to about 23% reduction in terms of CO₂, NO _x and PM₁₀ emissions. Banning HDVs led to a significant reduction of NO _x and PM₁₀ emissions. Although speed restriction reduced both CO₂ and NO _x emissions by 16.1 and 13.4%, PM₁₀ emissions increased by 19%, mainly from HDVs.

The dilemma zone (DZ) has been discussed in traffic engineering over four decades, because it is positively correlated to potential accidents. The dynamic feature of DZs is indeed difficult resolved and handled only by traffic signal control. This study aims to develop a series of onboard algorithms for DZ avoidance and warning. Three algorithms, DZ estimation, DZ prediction and warning selection are developed. To increase DZ detection accuracy, inputs from roadways, drivers and vehicles are considered. The genetic systematic-rule is used to optimise the prediction of vehicle motion and the dynamical features of DZs. Experimental results show that the accuracy rates of DZ detection for all scenarios are higher than 90%. Such encouraging results show the reliability and operating practicability of the proposed development.

In this study, the problem of optimal freeway local ramp metering is address by using fuzzy logic control (FLC)-based ramp metering. The objective of optimal freeway local ramp metering is to minimise a weighted total-time spent-(WTTS)-based cost function, which measures the performance of freeway local ramp metering in terms of the WTTS by vehicles on both the freeway mainstream and on-ramp link. A simple and efficient local ramp metering algorithm based on Takagi–Sugeno type FLC algorithm is proposed. The input membership functions of the FLC controller are predefined, and human expert knowledge on freeway traffic flow behaviours is utilised to reduce the size of fuzzy rule base. The consequent parameters are fine-tuned by particle swarm optimisation and microscopic traffic simulations. Simulation studies with PARAMICS traffic simulation platform show the potential of the proposed approach in obtaining the optimal freeway local ramp metering strategies to strike a balance between traffic conditions on the mainstream and the on-ramp link.

A driver fatigue monitoring and detection system with high accuracy could be a valuable countermeasure to decrease fatigue-related traffic accidents. This study proposes methods for drowsiness detection based on electroencephalogram (EEG) power spectrum analysis. First, a new algorithm is proposed for independent component analysis with reference (ICA-R) for electrooculography artefacts removal. Comparison is then carried out between the proposed ICA-R algorithm and an adaptive filter. Secondly, 75 EEG spectrum features are extracted from the cleaned EEG. Among all the EEG spectrum-related features, 40 key features are selected by support vector machine recursive feature elimination to improve the performance of the classifier. The validation results show that 86% of the driver's drowsiness states can be accurately detected among drivers, who participate a driving simulator study.

Calibrated simulation models taking into account adverse weather conditions can be used to optimise traffic management strategies, such as speed adaptation and signal timing optimisation. On snowy road conditions, car-following behaviour changes because drivers tend to accelerate more slowly, increase their following distance and drive with lower speeds. Such changes results in lower saturation flow rates at intersections. In order to simulate traffic on snowy road conditions in a valid way, the parameters of a simulation have to be calibrated for adverse weather. This study identifies the parameters of the car-following model in the microscopic simulator VISSIM that are sensitive to snowy road conditions and indicates valid parameter subspaces leading to a good match of simulation model output with observed saturation flow rates and start-up delays. In combination with green time of a signalised intersection, saturation flow rate is essential for correctly estimating road capacity.

This study proposes traffic queue-parameter estimation based on background subtraction, by means of an appropriate combination of two background models: a short-term model, very sensitive to moving vehicles, and a long-term model capable of retaining as foreground temporarily stopped vehicles at intersections or traffic lights. Experimental results in typical urban scenes demonstrate the suitability of the proposed approach. Its main advantage is the low computational cost, avoiding specific motion detection algorithms or post-processing operations after foreground vehicle detection.

A growing demand for well-defined telematics systems in the intelligent transport distribution of pharmaceutical drugs is envisaged driven by legislative demands to enable the safe handling of medicines in automotive distributions. The provision is accomplished by providing virtual intelligence to vehicles designated for this form of smart freight transportation. The system provides anytime/anywhere assets tracking while on the move, from departure to destination, supporting reliable courier operation at low labour. The tracking and tracing system provides the vehicle with sufficient intelligence to: be located remotely, track and trace assets and provide incidence reports. The authors’ architecture is intended to automatically broadcast adaptive logistic-distribution-plans between a central office and a vehicle. The proposed system represents an inexpensive and non-intrusive solution that exploits advanced technologies such as smart environment sensing, radio frequency identification, Wireless Fidelity (WiFi) and global positioning system, to support modern industrial needs. The authors describe and discuss the motivation and the benefits of using the system, including new hardware and software developments.

This study presents a novel framework by which the energy consumption of an electric vehicle (EV) or the zero-emissions range of a plug-in hybrid electric vehicle (PHEV) may be predicted over a route. The proposed energy prediction framework employs a neural network and may be used either ‘off-line’ for better estimating the real-world range of the vehicle or ‘on-line’ integrated within the vehicle's energy management control system. The authors propose that this approach provides a more robust representation of the energy consumption of the target EVs compared to standard legislative test procedures. This is particularly pertinent for vehicle fleet operators that may use EVs within a specific environment, such as inner-city public transport or the use of urban delivery vehicles. Experimental results highlight variations in EV range in the order of 50% when different levels of traffic congestion and road type are included in the analysis. The ability to estimate the energy requirements of the vehicle over a given route is also a pre-requisite for using an efficient charge blended control strategy within a PHEV. Experimental results show an accuracy within 20–30% when comparing predicted and measured energy consumptions for over 800 different real-world EV journeys.

In this study, the general problem of scalable and inter-operable Intelligent Transport Systems (ITSs) is addressed. Referring to a new proposal based on next generation networks promoting a pervasive, distributed and inter-operable service-oriented architecture, the authors comment on existing frontier technologies capable of deploying such systems. A new layered architecture for an EU-wide ITS is shown against the state-of-the-art ITS design; the presented solution is expected to overcome the actual limitations in pervasiveness of the collection layer and in virtualisation of users, connectivity, storage and calculus. The IPv6 global network (and especially the 6LoWPAN extension to embedded constrained devices), also delivered through wideband technologies, is seen as the enabling technology to support large-scale ITS; moreover a proposal to explicitly consider distributed calculus and high capacity storage for data and computationally intensive applications is presented.

Highly automated driving brings the next generation of driver assistance systems for increased safety and comfort. Automated vehicles execute part of the driving tasks whereas the driver is still involved in controlling the vehicle. Higher degrees of automation pose more strict requirements for perception systems in terms of performance and robustness. The HAVEit EU project investigates the application and validation of highly automated vehicle systems, technologies that are going to have a great impact on transport of the future. The purpose of this study is to examine in detail the problem of multi-sensor fusion for target tracking and road environment perception in an automated vehicle application. A series of algorithms are described for solving the data association and track estimation problems, both at sensor and central levels. The techniques that are used for multi-sensor lane estimation are also presented. Finally, results from simulated and real-time tests are given to demonstrate the performance of the algorithm.