Search

In recent years, advanced driver assistance systems (ADASs) have been used to improve the safety of vehicles by either providing additional information to the driver or by taking over complete control. The majority of ADASs currently being utilised run entirely on the vehicle, only having access to information provided by the sensors that are onboard the vehicle itself. Part of the next step in the evolution of ADAS is to incorporate information from other offsite sensors or obtain control inputs from infrastructure which can coordinate multiple vehicles simultaneously via a wireless interface. Wireless communication is inherently delayed and prone to dropped packets. This study looks at the effect of transport latencies and dropped packets on an off-site autoregressive steering controller supplying direct steering inputs to a vehicle. A fully non-linear vehicle simulation model is used to test the effect of delaying steering inputs and dropped packets to test the stability of the controller. The study shows that at dropped packet percentages of up to 40% adequate vehicle control is maintained, while transport latencies of up to 100 ms allow for moderately accurate vehicle control.

Advanced driver assistance systems (ADAS) become an integral part of almost all modern automotive systems. ADAS have been evolving over a decade and the expansion of vision-based ADAS is quite rapid mainly due to the recent advancements in camera technologies. Most of the vision-based ADAS applications have been developed focusing on structured environment parameters and being tested adequately for those environments whereas they cannot be applied with their current framework as such for non-structured environments due to various limitations. This study presents a comprehensive overview of challenges in expanding the vision-based ADAS for non-structured environments. The authors have proposed a segmentation detection method for pedestrians and cyclists in a non-structured road environment to improve the accuracy of the popular deep learning networks. This method uses upper body detection and a pairing technique that improves the average precision significantly without consuming much computational resources. This approach would help to transform the structured environment ADAS to non-structured environments with minimal modifications. With the proposed approach, they are able to increase the accuracy of certain object classes up to 49% for various popular deep learning networks.

This study demonstrates the need for a holistic safety-impact assessment of an advanced driver assistance system (ADAS) and its effect on eye-glance behaviour. It implements a substantial incremental development of the what-if (counterfactual) simulation methodology, applied to rear-end crashes from the SHRP2 naturalistic driving data. This assessment combines (i) the impact of the change in drivers’ off-road glance behaviour due to the presence of the ADAS, and (ii) the safety impact of the ADAS alone. The results illustrate how the safety benefit of forward collision warning and autonomous emergency braking, in combination with adaptive cruise control (ACC) and driver assist (DA) systems, may almost completely dominate the safety impact of the longer off-road glances that activated ACC and DA systems may induce. Further, this effect is shown to be robust to induced system failures. The accuracy of these results is tempered by outlined limitations, which future estimations will benefit from addressing. On the whole, this study is a further step towards a successively more accurate holistic risk assessment which includes driver behavioural responses such as off-road glances together with the safety effects provided by the ADAS.

Lane detection techniques have been widely studied in the last two decades and applied in many advance driver assistance systems. However, the development of a robust lane detection system, which can deal with various road conditions and efficiently evaluate its detection results in real time, is still of great challenge. In this study, a vision-based lane detection system with dynamic integration and online evaluation is proposed. To increase the robustness of the lane detection system, the integration system dynamically processes two lane detection modules. First, a primary lane detection module is designed based on the steerable filter and Hough transform algorithm. Then, a secondary algorithm, which combines the Gaussian mixture model for image segmentation and random sample consensus for lane model fitting, will be activated when the primary algorithm encounters a low detection confidence. To detect the colour and line style of the ego lanes and evaluate the lane detection system in real time, a lane sampling and voting technique is proposed. By combining the sampling and voting system system with prior lane geometry knowledge, the evaluation system can efficiently recognise the false detections. The system works robustly in various complex situations (e.g. shadows, night, and lane missing scenarios) with a monocular camera.

A gated branch neural network (GBNN) is proposed for modelling mandatory lane changing (MLC) behaviour at the on-ramps of highways. It provides a core algorithm for an MLC suggestion system for advanced driver assistance systems (ADAS), where the main challenge is the trade-off between computational speed and prediction accuracy for both non-merge and merge events. The GBNN algorithm employs a gated branch based on correlation analysis, scaled exponential linear units activation function, and adaptive moment estimation optimiser. The algorithm has been evaluated using the real-world dataset of U.S. Highway 101 and Interstate 80 from Federal Highway Administration's Next Generation Simulation (NGSIM). Input features are extracted from NGSIM and pre-processed by standardisation and principal component analysis. TensorFlow framework and Python are used as the development platform. Results show that the proposed GBNN algorithm with the Pearson correlation method has values of 97.7%, 96.3%, and 0.990 for non-merge accuracy, merge accuracy, and receiver operating characteristic score, respectively. It outperforms other traditional binary classifiers for MLC applications, and is more light-weight than a convolutional neural network (AlexNet) of deep learning algorithm. Owing to its compact architecture, the GBNN provides high accuracy and efficiency, demonstrating promising usage as an MLC suggestion system in ADAS.

Automated driving will have a big impact on society, creating new possibilities for mobility and reducing road accidents. Current developments aim to provide driver assistance in the form of conditional and partial automation. Computer vision, either alone or combined with other technologies such as radar or lidar, is one of the key technologies of advanced driver assistance systems (ADAS). The presence of vision technologies inside the vehicles is expected to grow as the automation levels increase. However, embedding a vision-based driver assistance system supposes a big challenge due to the special features of vision algorithms, the existing constrains and the strict requirements that need to be fulfilled. The aim of this study is to show the current progress and future directions in the field of vision-based embedded ADAS, bridging the gap between theory and practice. The different hardware and software options are reviewed, and design, development and testing considerations are discussed. Additionally, some outstanding challenges are also identified.

Automated lane detection is a vital part of driver assistance systems in intelligent vehicles. In this study, a multi-lane detection method based on omnidirectional images is presented to conquer the difficulties stemming from the limited view field of the rectilinear cameras. The contributions of this study are twofold. First, to extract the features of the lane markings under various illumination and road-surface scenarios, a feature extractor based on anisotropic steerable filter is proposed. Second, a parabola lane model is used to fit the straight as well as curved lanes. According to the parabola lane model, the straight lines and curves of feature maps can be represented as straight lines in a linear space coordinate system. Then lane modelling can be treated as an optimisation question in linear space and the parameters of lanes can be estimated by minimising the objection function. The method has been tested on publicly available data sets and the real car experiments. Experimental results show that the proposed method outperforms state-of-the-arts approaches and obtains a detection accuracy of 99% in real world scenes.

Road crashes are a growing concern of governments and are rising to become one of the leading preventable causes of death, especially in developing countries. The ubiquitous presence of smartphones provides a new platform on which to implement sensor networks and driver-assistance systems, as well as other intelligent transportation system (ITS) applications. In this study, existing approaches of using smartphones for ITS applications are analysed and compared. Particular focus is placed on vehicle-based monitoring systems, such as driving behaviour and style recognition, accident detection and road condition monitoring systems. Further opportunities for use of smartphones in ITS systems are highlighted, and remaining challenges in this emerging field of research are identified.

The use of advanced driver assistance systems is becoming increasingly common in road-going vehicles. One application of these driver assistance systems is in the automated detection of vulnerable road users, such as pedestrians, using automotive far-infrared imagery. Detection of pedestrians in infrared imagery can be quite difficult because of a number of factors such as the environment, pedestrian behaviour and also the physical limitations of currently available infrared sensors. This study presents a comprehensive review of the literature currently available in the area of pedestrian detection techniques in automotive infrared imagery. The challenges associated with automated detection of pedestrians in the automotive domain are first discussed. An overview of the general structure of pedestrian detection algorithms is then presented, followed by an in-depth analysis of existing literature in the area. Some proposals for future research in the area based on the methods described in this study are then offered.

A questionnaire study was conducted that probed driver safety-related attitudes towards driver assistance systems (DAS). 211 drivers participated in the questionnaire survey. The participant DAS experience ranged from almost none to a high level of experience. Drivers were asked about their risk-related safety-related attitudes towards 29 different systems that are currently available on the market. Potential influencing variables that were expected to affect driver safety-related attitudes towards DAS - gender, age, level of driver sensation seeking and driver DAS use experience - were considered: results show that, in terms of safety, there is great variation in how drivers evaluate the 29 systems. Consequently, systems functionality and the time when the system was launched are discussed. No general effects were found for gender and level of sensation seeking on safety-related attitudes towards DAS. Driver age correlated positively with indirect safety-related attitudes towards 26 of the 29 systems. Controlling the variable 'DAS use experience', 22 relations between age and attitudes towards DAS were found. RESULTS reveal that the more experience drivers have in using DAS, the higher they judge DAS in terms of safety. On the basis of the study results, research issues for future research on traffic safety related to DAS were identified. Language: en

Today, the automobile industry and several research institutes develop automated vehicles for several driving applications. With increasing capabilities of automation, the driver can be more and more dispensed from the driving task and might want to use his nomadic devices to get entertained, read the news or do office work while driving. However, in some complex driving situations (such as road works, freeway exit ramps or lane closure because of car accidents), the automation still needs to safely hand over the control to the driver. These situations require a lot of attention by the driver who must not be tempted to ignore the warnings of the assistance system and to continue any task on the nomadic device until a critical situation originates. This study describes a method to link nomadic devices to vehicles to support a safe usage during highly automated driving and a first approach to ensure a safe transition between different automation modes. Therefore the automation system is connected to the nomadic device in the vehicle and has the ability to actively control the content on the screen. The proof of concept is demonstrated in a research vehicle that drives on a simulated motorway.

Forward collision avoidance systems have shown to be a particularly effective crash-avoidance technology. Multi-vehicle tracking capabilities play an important role in the real-world performance and effectiveness of such systems. In order to effectively and accurately track vehicles in a moving platform and in complicated road environments, the authors proposed a multi-vehicle tracking algorithm based on an improved particle filter. First, the authors used a vehicle disappearance detection and handling mechanism based on the normalised area of the minimum circumscribed rectangle of particle distributions. This mechanism is used to verify whether a new target is a vehicle and can also handle the vehicle exit during the tracking phase. Next, an improved particle filter-based framework, which includes a new process dynamical distribution, allowed for multi-vehicle tracking capabilities was used for vehicle tracking. Finally, an effective occlusion detection and handling mechanism was used to address the significant occlusion between vehicles. The combination of these added improvements in the algorithm results in the enhancement of the vehicle tracking rate in a variety of challenging conditions. Experimental tests carried out from different datasets show excellent performance in multi-vehicle tracking, in terms of accuracy in complex traffic situations and under different lighting conditions.

In this study, the authors analyse the exponential growth of advanced driver assistance systems based on video processing in the past decade. Specifically, they focus on how research and innovative ideas can finally reach the market as cost-effective solutions. They explore well-known computer vision methods for services like lane departure warning systems, collision avoidance systems and point out potential future trends according to a review of the state-of-the-art. Along this study, the authors' own contributions are described as examples of such systems from the perspective of real-time by design, pursuing a trade-off between the accuracy and reliability of the designed algorithms and the restrictive computational, economical and design requisites of embedded platforms.

Research on the acceptability of assistive systems for improving the safety of powered two-wheelers (PTWs) is a pressing issue. The use of safety-enhancing assistive systems for motorised vehicles, including advanced driver assistance systems and in-vehicle information systems is widespread in many countries. Yet, there is only a limited number of equivalent intelligent transport systems (ITS) for PTWs, namely advanced rider assistance systems and on-bike information systems. This study describes the methodological development of a specific tool for assessing motorcyclists’ acceptability of ITS, as part of the motorcyclists’ profiling questionnaire (MOPROQ). There were three stages of development. First, a literature review was undertaken to assess the current state of the art regarding ITS for PTWs and to determine the most relevant facets of acceptability that should be measured. Second, a series of focus group interviews were conducted to explore riders’ attitudes towards ITS. Finally, the focus group results were used to develop a large-scale survey (MOPROQ), which was administered to an initial sample of over 6000 riders internationally. The designed tool can be used as a basis for the determination of rider acceptability of ITS systems in the future.

The development of automotive technology has become increasingly important for preventing car accidents. Hence, as a basic research of driver assistance systems, a novel control method has been proposed for steering support. In particular, the stability and limitation of such a system is investigated for the safe and comfortable drive. First, the particle swarm optimisation (PSO)-based algorithm is used to search the optimal feedback gain under practical constraints for achieving tracking control. Moreover, to reduce the convergence time further, the PSO algorithm is combined with the technique of quantum computing. Simulation results indicate that the proposed feedback controller based on quantum PSO has the ability to provide efficient computational performance for trajectory tracking and stabilisation.

The driver assistance system part of the cognitive vehicle design can prevent rear, lateral and other collisions by using a collision warning system that integrates intelligent technology and human factors. To be effective, such a system should be able to analyse driving states including driver distraction and driver intent, assess the likelihood of collisions by working with surrogate safety measures and issue warnings to the driver. This study presents a longitudinal and lateral collision warning model that allows the inclusion of key surrogate safety measures such as distance between vehicles in longitudinal vehicle-following mode or envelopes of vehicles in the lateral direction during lane migration/change/merge movements. The model can take into account values of driver distraction and driver intent variables obtained on-line or from off-line devices. The formulation is also applicable to time-to-crash surrogate safety measure. A pattern recognition method is used for the identification of pre-crash condition while minimising false alarms. The surrogate safety model is presented and illustrative examples are provided. The surrogate safety measure-based warning system is mainly intended for on-line use in actual driving conditions. In addition, it can be used in driving simulators or for off-line safety studies in association with microsimulators of traffic.

In this contribution, the authors put forward a modelling framework for generic Advanced Driver Assistance Systems (ADAS) based on rolling horizon optimal control and design control algorithms for an Ecological Adaptive Cruise Control (EcoACC) system under this framework. The accelerations of EcoACC vehicles are determined by minimizing some predicted cost, and the optimal control problem is solved using a dynamic programming approach. The proposed algorithm is applied on a single lane ring road to examine the impacts of the EcoACC system employing the Eco-driving strategy comparison with a system employing an Efficient-driving strategy. Simulation results show that the Eco-driving strategy results in smoother vehicle behaviour compared to the driving strategies that only consider travel efficiency (Efficient-driving strategy). At the macroscopic level, the Eco-driving strategy results in a lower speed and lower flow at free traffic conditions, but a higher speed and higher flow at moderate congested conditions compared to the Efficient-driving strategy. From an environment perspective, the Eco-driving strategy results in a lower spatial CO₂ emission rate. However, in the ring-road scenario where the demand is not fixed, the impact of the EcoACC system on total CO₂ emissions is negative at moderate congested conditions, due to the high flow it supports.

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.

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.

This study assesses the technical feasibility, economic affordability and social acceptability of low-greenhouse gas (GHG) emissions intelligent transport systems (ITS) that could be implemented in the European road infrastructure over the next 40 years for passenger and freight traffic. Three ITS applications are considered: driver assistance systems and the automated highway system (AHS) for passenger traffic and commercial vehicle operations for freight traffic. These technologies are anticipated to lead to a more efficient use of the existing road network, while potentially reducing GHG emissions generated by vehicles. The impact of ITS on road capacity and vehicle's CO2 emissions is determined. Assessment is based on a reference system, which consists of the average new vehicle in the road network of the EU-27 countries. The various opportunities offered by the selected ITS technologies are specified and the major constraints for reducing GHG emissions are identified. Cost-effectiveness and sensitivity analysis is carried out. The results are validated by a suitably designed expert-based survey. It is found that ITS have the potential to improve capacity and reduce emissions. The most significant benefits are offered by the deployment of AHS. Social acceptability issues such as privacy and liability need to be further addressed to facilitate wide deployment of ITS.

Some advanced driver assistance systems require on-the-lane vehicle positioning on accurate digital maps. The combination of high precision global navigation satellite systems and inertial measurement is the most common technique to carry out this precise positioning since in some areas global positioning systems (GPS) signals are lost or degraded. However, real experimental validation of the navigation algorithms (beyond simulation) is one of the most important shortcomings in the state-of-the-art. In this study, a wide set of real experiments have been carried out on real roads, in urban and rural environments, using an instrumented car. A theoretical approach based on the uncertainty propagation law has been set out to evaluate the errors when using only inertial measurement systems and the maximum distance that can be travelled before exceeding the admissible error limits. Results show that it is better to correct GPS positioning when its signal is degraded than to wait until the signal is definitively lost. Furthermore, inertial measurement systems and GPS receivers of different levels of accuracy have been compared in order to determine whether they are suitable for new assistance applications. Experimental data are consistent with the theoretical approach. The work reported in this paper has been partly funded by the Spanish Ministry of Science and Innovation (SIAC project TRA2007-67786-C02-01 and TRA2007-67786-C02-02) and the CAM project SEGVAUTO. Publicado

In this study, the authors present a video-processing system that utilises a camera to detect and track vehicles to the rear at night. Vehicle detection is a pivotal component of camera-based advanced driver assistance systems (ADAS) such as collision warning, blind-spot monitoring and overtaking vehicle detection. When driving in dark conditions, vehicles to the rear are primarily visible by their headlamps. This system implements a low, static camera exposure to ensure headlamps appear distinct and not as enlarged bloomed regions. We further describe a method to identify vehicle headlamp pairs using region-growing thresholding and cross-correlation bilateral symmetry analysis. Images of vehicles at different yaw angles to the camera image plane, such as those turning, or engaging road bends, suffer from perspective distortion, which interferes with the symmetry between lamps. We perform a perspective transformation to correct for this, ensuring consistent detection performance throughout all road manoeuvres. False positives resulting from multiple vehicle situations are considered and addressed. Detected target vehicles are tracked using a Kalman filter which is updated by inter-frame cross-correlation.

The development and evaluation of an integrated advisory interface for several advanced driver assistance systems (ADAS) is focused here. It was developed using an ecological interface design (EID) approach and was combined with the type of auditory warnings used in vehicles today to investigate multiple-staged warnings. The warning combination was evaluated using a fixed-base medium-fidelity driving simulator. The results suggest that the development of driver interfaces based on EID could benefit by being combined with the iterative nature of the user-centred design methods to make accurate assumptions on how the design is suitable for end-users in the context of use. Simulator results also show that participants drove with greater safety margins to lead vehicles and maintained better lateral positioning when driving with the interface, indicating that integrated multiple-staged warnings can have a positive effect on driver behaviour if correctly designed.

At urban intersections drivers handle multiple tasks simultaneously, making urban driving a complex task. An advanced driver assistance system may support drivers in this specific driving task, but the design details of such a system need to be determined before they can be fully deployed. A driving simulator experiment was conducted to determine the relationship between different subtasks of driving at urban intersections. Participants completed four drives, each comprising 20 comparable intersections with different traffic situations and encountered one unexpected braking event during the experiment. The effects of varying levels of event urgency on the relationship between different driving subtasks were studied. Furthermore, the influence of workload on this relationship was determined by giving half of the subjects an additional cognitive task. After the lead car braked unexpectedly, participants reduced speed and increased headway depending on the urgency of the braking event. Depending on the workload, participants returned to the normal speed and headway again after a number of intersections. Participants experiencing a high-workload drove more smoothly, except for those who had experienced the most urgent unexpected event. High workload additionally affected the length of the adjustments to the unexpected event.

Assessing the perceived usefulness of eco-driving assistance systems is of high interest for system developers and researchers in the development stage of such systems. This applies especially to systems that try to influence the driver's behaviour in everyday situations and generating their greatest benefit if regularly used. This study presents results of a survey simultaneously conducted in 11 European countries with more than 5000 respondents aiming at collecting needs and requirements for future eco-driving assistance systems. Such systems have the potential of changing driving behaviour in the long run for supporting a more fuel-efficient driving and reducing emissions caused by motorised traffic. Three different driver assistance systems are considered covering inefficiencies in pre-trip, on-trip and post-trip situations. Each system is assessed according to the factors of perceived usefulness, the expected environmental impact and the user's willingness to pay for it. The study will show that in general car drivers welcome the deployment of eco-driving assistance systems and rate them as useful. It likewise demonstrates that the acceptance of additional costs for the user is very low.

The widespread distribution of in-vehicle driver information systems on the market, and the emergence of advanced driver assistance systems are profoundly changing road transport and more specifically the driver environment and driving activity. Through Intelligent Transport Systems, a range of services are indeed offered to the driver with the objective of facilitating the driving task and improving travel safety. Despite the potential benefits to road safety, these developments raise numerous questions about their relevance, usability and acceptability for drivers and their impact on drivers' behaviour and attitudes. All this contributes to the necessity of encouraging a Human Centred Design approach, in which ITS are designed according to driver needs.

An assessment of additional steering torque as a haptic signal to give drivers feedback from the vehicle in order to give lane-departure alerts or to support lane keeping is described. In two studies, driver performance and vehicle response were assessed in a practical study of haptic feedback conducted on a test track in a specially equipped vehicle. The first study was conducted on a total of 30 drivers and examined variations on the amplitude of the haptic signals. In a second study, with another group of 30 drivers, the focus was on the gradient of the signal. The RESPONSE Code of Practice requires that the signals used in driver assistance systems should be tested on driver groups which might perform less well than the average driver. Hence, both younger drivers and older drivers have been included in these studies. The analyses compared the results of these subpopulations with those from a group of experienced middle-aged drivers. The results do not indicate that age and experience influence the reactions times or perceptions of the signals. This finding was replicated in the second study. Furthermore, the results of the two studies show clear effects of amplitude and gradient of the haptic signal on drivers' perception and reactions.