Advanced Driver Assistance System

Future intelligent environments and systems may need to interact with humans while simultaneously analyzing events and critical situations. Assistive living, advanced driver assistance systems, and intelligent command-and-control centers are just a few of these cases where human interactions play a critical role in situation analysis. In particular, the behavior or body language of the human subject may be a strong indicator of the context of the situation. In this paper we demonstrate how the interaction of a human observer's head pose and eye gaze behaviors can provide significant insight into the context of the event. Such semantic data derived from human behaviors can be used to help interpret and recognize an ongoing event. We present examples from driving and intelligent meeting rooms to support these conclusions, and demonstrate how to use these techniques to improve contextual learning.

Driver behavioral cues may present a rich source of information and feedback for future intelligent advanced driver-assistance systems (ADASs). With the design of a simple and robust ADAS in mind, we are interested in determining the most important driver cues for distinguishing driver intent. Eye gaze may provide a more accurate proxy than head movement for determining driver attention, whereas the measurement of head motion is less cumbersome and more reliable in harsh driving conditions. We use a lane-change intent-prediction system (McCall et al., 2007) to determine the relative usefulness of each cue for determining intent. Various combinations of input data are presented to a discriminative classifier, which is trained to output a prediction of probable lane-change maneuver at a particular point in the future. Quantitative results from a naturalistic driving study are presented and show that head motion, when combined with lane position and vehicle dynamics, is a reliable cue for lane-change intent prediction. The addition of eye gaze does not improve performance as much as simpler head dynamics cues. The advantage of head data over eye data is shown to be statistically significant (p < 0.01) 3 s ahead of lane-change situations, indicating that there may be a biological basis for head motion to begin earlier than eye motion during "lane-change"-related gaze shifts.

Modern cars are equipped with a variety of sensors, advanced driver assistance systems and user interfaces nowadays. To benefit from these systems and to optimally support the driver in his monitoring and decision making process, efficient human-machine interfaces play an important part. This paper describes the second release of iDriver, an iPad software solution which was developed to navigate and remote control autonomous cars, to give access to live sensor data and useful data about the car state, as there are, e.g., current speed, engine and gear state. The software was used and evaluated in our two fully autonomous research cars "Spirit of Berlin" and "Made in Germany".

For a decade, a lot of researches have focused on the development and the deployment of automated mobility services and means for road networks (urban, suburb, rural, highway). In the development of autonomous driving embedded systems, several stages are needed. The first one concerns the perception layers. The second one is dedicated to the risk assessment, the decision and strategy layers and the optimal path planning. The last one addresses the control/command parts. Based on the Autonomous Decision-Support Framework (ADSF) of the EU project Trustonomy, this paper proposes a risk assessment and decision-making framework to the second stage and improves an existing virtual co-pilot by combining a new emergency mode and corresponding trajectory planning algorithm. After introducing the project framework for risk management and the general co-pilot concept developed in the University Gustave Eiffel, the Decision-Support framework, implemented in RTMaps platform, is demonstrated within a realistic 3D simulation environment called Pro-SiVIC. Both the previous virtual copilot and the new emergency algorithm are combined and a switching strategy between the different modes is tested in a near-accident situation.

Traffic accidents due to human errors cause many deaths and injuries around the world. To help in reducing this fatality, in this research, a new module for Advanced Driver Assistance System (ADAS) for automatic driver drowsiness detection based on visual information and Artificial Intelligence is presented. The aim of this system is to locate, to track and to analyze the face and the eyes to compute a drowsiness index, working under varying light conditions and in real time. Examples of different images of drivers taken in a real vehicle are shown to validate the algorithm.

To make safe transitions from autonomous to manual control, a vehicle must have a representation of the awareness of driver state; two metrics which quantify this state are the Observable Readiness Index and Takeover Time. In this work, we show that machine learning models which predict these two metrics are robust to multiple camera views, expanding from the limited view angles in prior research. Importantly, these models take as input feature vectors corresponding to hand location and activity as well as gaze location, and we explore the tradeoffs of different views in generating these feature vectors. Further, we introduce two metrics to evaluate the quality of control transitions following the takeover event (the maximal lateral deviation and velocity deviation) and compute correlations of these post-takeover metrics to the pre-takeover predictive metrics.

An increasing safety and reducing road accidents, thereby saving lives are one of great interest in the context of Advanced Driver Assistance Systems. Apparently, among the complex and challenging tasks of future road vehicles is road lane detection or road boundaries detection. It is based on lane detection (which includes the localization of the road, the determination of the relative position between vehicle and road, and the analysis of the vehicle's heading direction). One of the principal approaches to detect road boundaries and lanes using vision system on the vehicle. However, lane detection is a difficult problem because of the varying road conditions that one can encounter while driving. In this paper, a vision-based lane detection approach capable of reaching real time operation with robustness to lighting change and shadows is presented. The system acquires the front view using a camera mounted on the vehicle then applying few processes in order to detect the lanes. Using a pair of hyperbolas which are fitting to the edges of the lane, those lanes are extracted using Hough transform. The proposed lane detection system can be applied on both painted and unpainted road as well as curved and straight road in different weather conditions. This approach was tested and the experimental results show that the proposed scheme was robust and fast enough for real time requirements. Eventually, a critical overview of the methods were discussed, their potential for future deployment were assist.

This paper presents Automind, an innovative in-vehicle safety advisor designed to operate entirely offline on embedded automotive hardware. Automind integrates automotive knowledge graphs (KGs) with aggressively quantized large language models (LLMs) to provide proactive, contextaware, and explainable safety guidance to drivers. Unlike traditional reactive Advanced Driver Assistance Systems (ADAS), Automind anticipates risks by correlating real-time vehicle telemetry, regulatory constraints, road topology, and environmental conditions. Through a compact streaming KG architecture and a 3-bit quantized LLM optimized for low-latency inference on embedded platforms, Automind achieves sub-300ms advisory latency with a memory footprint under 2GB, meeting ASIL-B safety standards. We demonstrate its necessity and impact through two realistic automotive scenarios, and propose an implementation roadmap, highlighting commercial and safety value across stakeholders.

This paper presents an advanced driver assistance system (ADAS) for lane keeping, together with an analysis of its performance and stability with respect to variations in driver behavior. The automotive ADAS proposed is designed to share control of the steering wheel with the driver in the best possible way. Its development was derived from an H2-Preview optimization control problem, which is based on a global driver-vehicle-road (DVR) system. The DVR model makes use of a cybernetic driver model to take into account any driver-vehicle interactions. Such a formulation allows 1) considering driver assistance cooperation criteria in the control synthesis, 2) improving the performance of the assistance as a cooperative copilot, and 3) analyzing the stability of the whole system in the presence of driver model uncertainty. The results have been experimentally validated with one participant using a fixed-base driving simulator. The developed assistance system improved lane-keeping performance and reduced the risk of a lane departure accident. Good results were obtained using several criteria for human-machine cooperation. Poor stability situations were successfully avoided due to the robustness of the whole system, in spite of a large range of driver model uncertainty.

In this article, the detection of a fault on the inner race of a roller bearing is presented as a problem of optimal estimation of a hidden fault, via measures delivered by a vibration sensor. First, we propose a linear model for the transmission of a vibratory signal to the sensor s diaphragm. The impact of shocks due to the default is represented by a stochastic drift term whose values are in a discrete set. To determine the state of the roller bearing, we estimate the value of this term using deterministic particle filtering.

Rear-end crashes are one of the leading types of crashes today. The anti-lock braking system (ABS) was designed to assist drivers during emergency braking situations by preventing wheel lock up, allowing drivers to retain control of the vehicle. Not all drivers have knowledge and experience with ABS, especially the haptic brake pedal feedback produced by ABS. There studies introduce a new method to train ABS using an emergency braking task on a simulator and an interactive exercise, Pedals Emergency Stop©. The interactive exercise was designed to prompt participants to press the brake pedal in a motion that is consistent with emergency braking and experience haptic ABS feedback. Participants that depressed the brake pedal quickly to the maximum travel and held that pedal position "passed" the trial. In Study 1, participants (N = 63) completed 15 trials, where it took on average three trials to "pass" for the first time, and 85% of the participants experienced their first "pass" within the first four trials. There were no differences observed between participants with previous knowledge and experience feeling ABS versus those who did not have prior knowledge and experience with ABS. The participants in this study thought that they had enough trials, that the exercise was a practical tool, and recommended the task for new drivers and refresher training, as well as for evaluating fitness to drive. Suggested improvements included a practice followed by three tests, all with four trials each; passing criteria of three out of four trials; and modifications to the feedback presented immediately after completing each trail. Study 2 was conducted (N = 38) to investigate the proposed "passing" criteria, where 95% passed on Test 1. The results revealed that the criteria to pass was reasonable. Future research should examine how the Pedals Emergency Stop© interactive exercise generalizes to on-road driving.

Recent advances in driver behavior analysis for Active Safety have led to the ability to reliably predict certain driver intentions. Specifically, researchers have developed Advanced Driver Assistance Systems that produce an estimate of a driver's intention to change lanes, make an intersection turn, or brake, several seconds before the act itself. One integral feature in these systems is the analysis of driver visual search prior to a maneuver, using head pose and eye gaze as a proxy to determine focus of attention. However it is not clear whether visual distractions during a goal-oriented visual search could change the driver's behavior and thereby cause a degradation in the performance of the behavior analysis systems. In this paper we aim to determine whether it is feasible to use computer vision to determine whether a driver's visual search was affected by an external stimulus. A holistic ethnographic driving dataset is used as a basis to generate a motion-based visual saliency map of the scene. This map is correlated with predetermined eye gaze data in situations where a driver intends to change lanes. Results demonstrate the capability of this methodology to improve driver attention and behavior estimation, as well as intent prediction.

joint work with A. Amditis (ICCS), F.Belloti (UoG) and M.Tarkiainen (VTT) during TEAM IP Outline o Intro: why automatic driving style recognition? o Problem formulation: from raw vehicle data to maneuver recognition o Related work overview: o Sorted by observables o Sorted by recognized classes of driving style o Methods o Reduced time series data representation: a promising research direction o TEAM application: A case study o Future work o Conclusions

The paper evaluates, from a physical-mathematical point of view, the pre-collision and post-collision vehicles' speeds, in case of side collisions, by preserving the amount of movement, taking into account the parameters resulting from the primary investigation of the scene. By reconstructing such road traffic accidents, the aim is to determine the kinematic quantities that influence the behavior of the vehicles involved in the accident, and to allow the analysis of the possibilities to avoid the collision. It also takes into account the situation in which the vehicles perform, in addition to the translational movement, a rotational movement around the vertical axes that pass through their centers of gravity. The developed working algorithm allows to change the input data (it can be applied to solve a large number of road traffic accident cases) and to obtain the results necessary for the reconstruction of such accidents. Thus, it is possible to establish the dynamics of this type of road accidents, which facilitates the assessment and comparison of different conditions taken into consideration.

This report is produced within the European project ITERATE (IT for Error Remediation And Trapping Emergencies), Grant agreement number 218496. The project started the 1st of January 2009 and will end 31st of December 2011. The objective of ITERATE is to develop and validate a unified model of driver behaviour (UMD) and driver interaction with innovative technologies in emergency situations. This model will be applicable to and validated for all the surface transport modes. Drivers' age, gender, education and experience and culture (whether regional or company/organisational) are factors that will be considered together with influences from the environment and the vehicle. Such a unified model of driver behaviour will be of great use when designing innovative technologies since it will allow for assessment and tuning of the systems in a safe and controllable environment without actually putting them to use in real traffic. At the concept stage, the model could guide designers in identifying potential problem areas whilst at the prototype stage, the model could inform on the scenarios to be used in system evaluation. In this way the systems will be better adapted to the drivers before being available on the market and will provide better support to the driver in emergency situations. Along the same lines, the model could be of use for authorities as a guide in assessing and approving innovative technologies without performing extensive simulator experiments or large scale field trials. ITERATE is based on the assumption that the underlying factors influencing human behaviour such as age, gender, culture etc. are constant between transport modes. This assumption allows for a unified model of driver behaviour, applicable to all surface transport modes, to be developed. This will be done within ITERATE and the model can be used to improve design and safety assessment of innovative technologies and make it possible to adapt these technologies to the abilities, needs, driving style and capacity of the individual driver. The model will also provide a useful tool for authorities to assess ITS which is missing today.

Automobiles are quickly becoming more complex as new sensors and support systems are being added to improve safety and comfort. The next generation of intelligent driver assistance systems will need to utilize this wide array of sensors to fully understand the driving context and situation. Effective interaction requires these systems to examine the intentions, desires, and needs of the driver for preemptive actions which can help prepare for or avoid dangerous situations. This manuscript develops a real-time on-road prediction system able to detect a driver's intention to change lanes seconds before it occurs. In-depth analysis highlights the challenges when moving intent prediction from the laboratory to the road and provides detailed characterization of on-road performance.

PReVAL addresses the possible safety impacts of functions developed and demonstrated in the PReVENT integrated project. One of the major aims of the PReVAL project is the assessment of the work performed in the PReVENT subprojects. This deliverable reviews the evaluation results from the different PReVENT subprojects. The deliverable is both a deliverable for the PReVAL subproject and for the PReVENT IP (IP D10 “Validation results of first phase PReVENT projects”).

The aim of this study is to design and implement a system that detect driver sleepiness and warn driver in real-time using image processing and machine learning techniques.Viola-Jones detector was used for segmenting face and eye images from the camera-acquired driver video. Left and right eye images were combined into a single image. Thus, an image was obtained in minimum dimensions containing both eyes. Features of these images were extracted by using Gabor filters. These features were used to classifying images for open and closed eyes. Five machine learning algorithms were evaluated with four volunteer’s eye image data set obtained from driving simulator. Nearest neighbor IBk algorithm has highest accuracy by 94.76% while J48 decision tree algorithm has fastest classification speed with 91.98% accuracy. J48 decision tree algorithm was recommended for real time running. PERCLOS the ratio of number of closed eyes in one minute period and CLOSDUR the duration of closed eyes were calculated. The driver is warned with the first level alarm when the PERCLOS value is 0.15 or above, and with second level alarm when it is 0.3 or above. In addition, when it is detected that the eyes remain closed for two seconds, the driver is also warned by the second level alarm regardless of the PERCLOS value. Designed and developed real-time application can able to detect driver sleepiness with 24 FPS image processing speed and 90% real time classification accuracy. Driver sleepiness were able to detect and driver was warned successfully in real time when sleepiness level of driver is achieved the defined threshold values.

The design of active safety systems capable of helping avoiding a crash or reducing the collision severity requires data on how drivers behave in accident situations. These systems must be triggered when drivers actually need assistance. They must enhance insufficient reactions and limit unsuitable ones without being in conflict with drivers&#39; natural behavior. The Laboratory of Accidentology, Biomechanics and human behavior, PSA Peugeot Citroen - Renault (LAB), has conducted experiments on driving simulators and on test tracks to analyze driver&#39;s behavior in emergency situations. Two of these experiments concern front-to-rear accident situations, each one involving more than 100 representative common drivers. The first study was carried out on a simulator with different accident scenarios: an adverse vehicle stopped or driving slowly at the top of a hill, a vehicle coming into the driver&#39;s lane from a parking area, or a vehicle driving in front of the subject then sudden...

An increasing safety and reducing road accidents, thereby saving lives are one of great interest in the context of Advanced Driver Assistance Systems. Apparently, among the complex and challenging tasks of future road vehicles is road lane detection or road boundaries detection. It is based on lane detection (which includes the localization of the road, the determination of the relative position between vehicle and road, and the analysis of the vehicle's heading direction). One of the principal approaches to detect road boundaries and lanes using vision system on the vehicle. However, lane detection is a difficult problem because of the varying road conditions that one can encounter while driving. In this paper, a vision-based lane detection approach capable of reaching real time operation with robustness to lighting change and shadows is presented. The system acquires the front view using a camera mounted on the vehicle then applying few processes in order to detect the lanes. Using a pair of hyperbolas which are fitting to the edges of the lane, those lanes are extracted using Hough transform. The proposed lane detection system can be applied on both painted and unpainted road as well as curved and straight road in different weather conditions. This approach was tested and the experimental results show that the proposed scheme was robust and fast enough for real time requirements. Eventually, a critical overview of the methods were discussed, their potential for future deployment were assist.

Single vehicle accidents are commonly caused by fatigue and distraction and resulting in severe casualties and high economic costs. In order to evaluate driver recovery from run-off-road accidents, comprising of 80% of fatal crashes on rural roads, a simulator study in an advanced full-motion driving simulator was carried out. Drivers were given a secondary task to perform at six positions down the road (to simulate distraction), and an artificial yaw deviation was added to the vehicle to induce a run-off-road accident whilst the driver was distracted. The results show that the severity of the recovery manoeuvre was larger than similar events caused by the failure of automated lane keeping systems, leading to lane departures. Furthermore, significant learning effects was found, providing recommendations for further studies into run-off-road experiments.

managed by a core group with the participation of both the industry (Bosch, CRF, PSA, and BMW) and the academia (ICCS, TNO, Joint Research Centre). The main objective of the SP3 and the paper is the design and development of an innovative adaptive integrated human-machine interface for driver assistance, information and nomad systems. To address this objective different modules are described which monitor in real time the driver, the environment and the vehicle and to which the HMI is adapted. The information data flow, the communications and the interaction is ensured by a dedicated centralized module, namely the Interaction and Communication Assistant (ICA), which is considered as the main innovation and is

Because distraction contributes to a significant number of road fatalities, a great deal of work has already been conducted to design an algorithm able to make a diagnosis of the driver distractive state. This has been mainly achieved through the analysis of the driver’s gaze, steering behavior or psychophysiological indicators (Nakayama et al. 1999; Dong et al. 2011; Yang et al. 2012). Recently, some effort has been made to base the diagnosis on a driver model, by performing a parameter analysis or by analysing the model predictive performance (Hermannstädter and Yang 2013; Ameyoe et al. 2015). The present study falls into this category. Considering that distractive activities may influence the visual sampling of the environment, the control of the steering wheel, or both at the same time, a driver model that represents the visual and motor control of steering was chosen (Saleh et al. 2011; Mars et al. 2011). The visual component of the model combines visual anticipation and compen...

With many new devices to control the daily life products, we have our smartphones, when connected to a network with suitable supporting software is capable of controlling many other objects or devices it is connected to via the network. These Devices use any one of the protocols available for Internet communication to communicate between them. A Web controlled vehicle system is presented in this project work. It highlights the idea to develop a remote-controlled car which can be driven from within the car using the Internet over a secured server. This car has Ultrasonic sensors to measure the safety distance between itself and any other vehicle or any other obstacle. The main goal here is to minimize the work done or needed to drive a car with ease of driving experience. At the same time, the car will assure comfort and convenience to the controller. A miniature car including the above features has been developed which showed optimum performance in a simulated environment. Keywords—...

This paper presents a methodological approach for validation of advanced driver assistance systems (ADASs), especially concerning fault management. Tools in this methodology are the unique VEhicle-Hardware-In-the-Loop (VEHIL) test facility and the associated simulation tool PRESCAN. With VEHIL the development process and more specifically the validation phase of intelligent vehicles can be carried out safer, cheaper, more manageable, and more reliable. In VEHIL a complete vehicle is tested in the simulation loop, such that the safety and reliability of an ADAS can be tested to great accuracy and reliability.

This paper presents a robust optimal control approach for the wheel mobile robot system, which considers the effects of external disturbances, uncertainties, and wheel slipping. The proposed method utilizes an adaptive dynamic programming (ADP) technique in conjunction with a disturbance observer. Initially, the system's state space model is formulated through the utilization of kinematic and dynamic models. Subsequently, the ADP method is employed to establish an online adaptive optimal controller, which solely relies on a single neural network for the purpose of function approximation. The utilization of the disturbance observer in conjunction with the compensation controller serves to alleviate the effects of disturbances. The Lyapunov theorem establishes the stability of the complete closed-loop system and the convergence of the weights of the neural network. The proposed approach has been shown to be effective through simulation under the effect of the disturbances and the change of the desired trajectory.

Today, intelligent transport systems, especially systems that may assist the driver like Advanced Driver Assistance Systems (ADAS), present a high potential for the improvement of road safety and traffic capacity, as well as for the attenuation of traffic related environmental load. The EC co-funded ADVISORS research project dealt with the development of a comprehensive framework for the analysis, assessment and prediction of the implications of a range of ADAS, as well as with the development of implementation strategies for ADAS, which are expected to have a large positive impact on safety, traffic capacity and the environment. On this purpose, an integrated methodology, called Common Assessment Methodology (CAM) was developed and implemented. The main steps of this Common Assessment Methodology concerned identification of ADAS for evaluation; risk analysis; actor/stakeholder analysis; identification of criteria and appropriate weights; "operationalisation" by identifying specific indicators; overall analysis; ranking; and development of implementation strategies. In this paper, the Common Assessment Methodology is presented, its application within the ADVISORS project is demonstrated and the main findings are outlined, leading to useful input for the further development and implementation of Advanced Driver Assistance Systems.

The increasing number of information and assistance systems built into modern vehicles raises the demand for appropriate preparation of their output. On one side, crucial information has to be emphasized and prioritized, as well as relevant changes in the driving situation and surrounding environment have to be recognized and transmitted. On the other side, marginal alterations should be suitably filtered, while duplications of messages should be avoided completely. These issues hold in particular when assistance systems overlap each other in terms of their situation coverage. In this work it is described how such a consolidation of information can be meaningfully supported. The method is integrated in a system that collects messages from various data acquisition units and prepares them to be forwarded. Thus, subsequent actions can be taken on a consolidated and tailored set of messages. Situation assessment modules that rely on immediate estimation of situations are primary recipients of the messages. To meet their major demand-rapid decision taking-the method generates events by applying the concept of state machines. The state machines form the anchor to merge and fuse input, track changes, and generate output messages on higher levels. Besides this feature of consolidating vehicle data, the state machines also facilitate the transformation of continuous data to event messages for the rapid decision taking. Eventually, comprehensive driver support is facilitated, also enabling unprecedented features to improve road safety by decreasing the cognitive workload of drivers.

Computer Vision can provide a great deal of assistance to Intelligent Vehicles. In this paper an Advanced Driver Assistance Systems for Vehicle Detection is presented. A geometric model of the vehicle is defined where its energy function includes information of the shape and symmetry of the vehicle and the shadow it produces. A genetic algorithm finds the optimum parameter values. As the algorithm receives information from a road detection module some geometric restrictions can be applied. A multi-resolution approach is used to speed up the algorithm and work in real-time. Examples of real images are shown to validate the algorithm.

In last years, the European Union, Member States and the automotive industry have concentrated their efforts on improving road safety [1][2]. Avoiding accidents due to human errors is one of the main objectives of Advanced Driver Assistance Systems (ADAS). European traffic accidents figures show a very large number of collisions between pedestrians and vehicles. Every year, more than 200,000 pedestrians are injured, with over 6,000 killed. In spite of the incredibly high number of victims, the protection of pedestrians has received little attention by the research community [3]. The projects that have dealt with this problem are quite recent, as has been pointed out at the Fifth Framework Programme [1].

Cooperative Intelligent Transportation Systems (C-ITS) are being deployed in several cities around the world. Evaluation of their safety benefits in Field Operational Test (FOT) is needed to demonstrate its benefits and build public awareness and uptake. The result of the evaluation can tell us if the C-ITS algorithms that trigger the safety events, and consequently the Human-Machine Interface (HMI) messages, are appropriately fine-tuned to induce the expected driver behavior change formulated as hypothesis. In this paper we will introduce the safety hypotheses for seven driver safety use cases in the C-ITS pilot at the city of Ipswich in Brisbane, Australia. The safety performance indicators to test these hypotheses will be introduced as well. The main challenge in evaluating the safety benefits is only using the information collected from C-ITS units without augmentation from any other sensors. To validate data collection, we ran an experiment at the Mt Cotton training facility close to Brisbane and collected Cooperative Awareness Message (CAM) messages to analyze them and check whether the speed and acceleration information extracted from them is accurate enough to detect change in speed and breaking. The analysis results show that, we can detect the change in speed but the acceleration/braking pattern is very noisy and needs careful manipulation to retrieve the braking behavior.

Through the application of intelligent systems in driver assistance systems, the experience of traveling by road has become much more comfortable and safe. In this sense, this paper then reports the development of an intelligent driving assistant, based on vehicle telemetry and road accident risk map analysis, whose responsibility is to alert the driver in order to avoid risky situations that may cause traffic accidents. In performance evaluations using real cars in a real environment, the on-board intelligent assistant reproduced real-time audio-visual alerts according to information obtained from both telemetry and road accident risk map analysis. As a result, an intelligent assistance agent based on fuzzy reasoning was obtained, which supported the driver correctly in real-time according to the telemetry data, the vehicle environment and the principles of secure driving practices and transportation regulation laws. Experimental results and conclusions emphasizing the advantages o...

The "ROADSCANNER" project addresses the need for increased accuracy and integrity Digital Maps (DM) utilizing the latest developments in GNSS, in order to provide the required datasets for novel applications, such as navigation based Safety Applications, Advanced Driver Assistance Systems (ADAS) and Digital Automotive Simulations. The activity covered in the current paper is the feasibility study, preliminary tests, initial product design and development plan for an EGNOS enabled vehicle probe. The vehicle probe will be used for generating high accuracy, high integrity and ADAS compatible digital maps of roads, employing a multiple passes methodology supported by sophisticated refinement algorithms. Furthermore, the vehicle probe will be equipped with pavement scanning and other data fusion equipment, in order to produce 3D road surface models compatible with standards of road-tire simulation applications. The project was assigned to NIKI Ltd under the 1st Call for Ideas in the frame of the ESA-Greece Task Force.

In this paper, we present a new fast method for matching stereo images acquired by a stereo sensor embedded in a moving vehicle. The method consists in exploiting the matching results obtained in one stereo pair (frame) for computing the disparity map of the following stereo pair. This can be achieved by finding a temporal relationship, which we named association, between consecutive frames. The disparity range of the current frame is deduced from the disparity map of the preceding frame and the association between the two frames. Dynamic programming technique is considered for matching the image features. The proposed approach is tested on virtual and real stereo image sequences and the results are satisfactory. The method is fast and able to provide about 20 millions disparity maps per second on a HP Pavilion dv6700 2.1GHZ.

This article presents a multisensor fusion strategy for a novel road-matching method designed to support real-time navigational features within advanced driver assistance systems. In road navigation, context, integrity, reliability and accuracy are essential qualities for road-matching methods. Particularly, managing multihypotheses is a useful strategy to treat ambiguous situations in the road-matching task. In this study, multisensor fusion and multimodal estimation are realized using a hybrid Bayesian network. To manage multihypothesis, multimodal estimation is proposed. Experimental results, using data from antilock braking system sensors, a differential global positioning system receiver, and an accurate digital roadmap illustrate the performance of the proposed approach, especially in ambiguous situations.

This paper presents a proposed method to study the driver's behavior and its awareness defects on motorway. The method is based on the calculation of the "guidance task demand" of car driving. Guidance during driving can be seen as a continuous tuning of the speed and position of the car by the driver. The formalization of guidance demand has been implemented by three time pressures representing the road anticipation and the near space collision avoidance. A preliminary validation of this method is carried out by some tests on a driving simulator.

This paper presents a proposed method to study the driver's behavior and its awareness defects on motorway. The method is based on the calculation of the "guidance task demand" of car driving. Guidance during driving can be seen as a continuous tuning of the speed and position of the car by the driver. The formalization of guidance demand has been implemented by three time pressures representing the road anticipation and the near space collision avoidance. A preliminary validation of this method is carried out by some tests on a driving simulator.

The successful integration of automation in systems that affect human experiences requires the user acceptance of those automated functionalities. For example, the human comfort felt during a ride is affected by the automated control behavior of the vehicle. The challenge presented in this paper is how to develop an intelligent agent that learns its users' driving preferences and adjusts the vehicle control in real time, accordingly, minimizing the number of otherwise required manual interventions. This is a hard problem since users' preferences can be complex, context dependent and do not necessarily translate to the language of machines in a simple and straightforward manner. Our solution includes (1) a simulation test bed, (2) an adaptive intelligent interface and (3) an adaptive agent that learns to predict user's driving discomfort and it also learns to compute corrective actions that maximize user acceptance of automated driving. Overall, we conducted three user studies with 94 subjects in simulated driving scenarios. Our results show that our intelligent agent learned to successfully predict how to adjust the automated driving style to increase user' acceptance by decreasing the number of user manual interventions.

The UDRIVE Naturalistic Driving Study (NDS) is the first large scale European project to observe driving behaviour directly in the field. Its goal was to identify risky driving behaviour, understand what drivers commonly do (everyday driving), why and when driver’s attention is diverted from the road (distracted driving), focus on power two wheelers (PTW), pedestrians and cyclists as they are road users that are exceptionally exposed to crashes (vulnerable road users; VRU) and learn about the properties of sustainable driving behaviour (eco-driving). One of the advantages of this project is the unique opportunity to observe critical events while they occur, and with the help of the records, go back in time and investigate what may have caused them. Drivers from France (FR), Germany (GE), Poland (PL), Spain (SP), the Netherlands (NL), and the UK volunteered to participate in this study. Mechanics equipped their vehicles with cameras and sensors and thus created a fleet of 200 vehicle...

A rather simple car driving simulator was created based on the available open source engine TORCS and used to analyze the basic features of human behavior in car driving within the car-following setups. Eight subjects with different skill in driving real cars participated in these experiments. They were instructed to drive a virtual car without overtaking the lead car driven by computer at a fixed speed and not to lose sight of it. Moreover, these experiments were conducted with four different speed including 60km/h, 80km/h, 100km/h, and 120km/h. Based on the collected data the distribution of the headway, velocity, acceleration, and jerk are constructed and compared with available experimental data collected previously by the analysis of the real traffic flow. A new model for car-following is proposed capture the found properties. As the main results we draw a conclusion that the human behavior in car driving should be categorized as a generalized intermittent control with noise-driven activation of the active phase. Besides, we hypothesize that the extended 1

Support action to contribute to the preparation of future community research programme in user centred Design for ECO-multimodal MOBILity D5.2 July, 2014 5 of 18 DECOMOBIL-Support action to contribute to the preparation of future community research programme in user centred Design for ECO-multimodal MOBILity D5.2 July, 2014 7 of 18 3. Place of the conference The conference place was selected on 27 May 2013, during the HUMANIST VCE General Assembly held in Munich, Germany, and was based on the proposal received from the DECOMOBIL Austrian Third Party FACTUM. The conference was therefore held at the Federal Ministry for Transport, Innovation and Technology which is situated in the heart of Vienna. The Festsaal Bundesamtsgebäude was selected for its ideal size so as to accommodate all the conference participants. DECOMOBIL-Support action to contribute to the preparation of future community research programme in user centred Design for ECO-multimodal MOBILity D5.2 July, 2014 9 of 18 Abstracts were submitted via the conference specific website platform. Each received abstract was then automatically added to the abstracts database with a copy being sent to the conference organisers. DECOMOBIL-Support action to contribute to the preparation of future community research programme in user centred Design for ECO-multimodal MOBILity D5.2 July, 2014 12 of 18 7.4. Special sessions Two special sessions were planned during the conference. The first selected subject was on Senior Driver Needs in Driving Aids. The Session was chaired by Bjorn Peters from VTI (Sweden) and aimed at addressing the background activities, the current initiatives and the future priorities of Senior Driver Needs in European research. Special focus was placed on the need for safety and comfort as well as expectations concerning driving assistance. A comparison was made between French and Swedish drivers during discussions with the lecturers and the audience. The following lectures were presented: o Older drivers' needs for safety and comfort systems in their cars-a focus group study among Swedish drivers by Bjorn Peters-VTI o Older drivers' needs and expectations concerning car driving assistance-a focus group study among French drivers by Thierry Bellet-IFSTTAR DECOMOBIL-Support action to contribute to the preparation of future community research programme in user centred Design for ECO-multimodal MOBILity D5.2 July, 2014 13 of 18 8. List of participants Eighty-nine participants were present during the conference. first name last name company Country Eva Aigner-Breuss KFV Austrian Road Safety Board

The knowledge about lanes and the exact position on the road is fundamental for many advanced driver assistance systems. In this paper, a novel iterative histogram based approach with occupancy grids for the detection of multiple lanes is proposed. In highway scenarios, our approach is highly suitable to determine the correct number of all existing lanes on the road. Additionally, the output of the laserscannner based lane detection is fused with a production-available vision based system. It is shown that both sensor systems perfectly complement each other to increase the robustness of a lane tracking system. The achieved accuracy of the fusion system, the laserscannner and video based system is evaluated with a highly accurate DGPS to investigate the performance with respect to lateral vehicle control applications.

This paper addresses the issue of enabling a comfortable highly automated driving style. Two studies have been conducted to identify metrics which can be used to parametrize a high-quality automated driving style for automobiles with regard to safety, functionality and comfort. The studies were set either in an urban and rural or a highway environment. Participants (N = 12 per study) manually drove a round course assuming either an everyday, a comfortable, or a dynamic driving style in randomized order. The obtained results emphasize the importance of maneuver-based analysis. Namely, a variety of maneuverspecific metrics, such as acceleration, jerk, quickness and headway distance in seconds, were identified, which are prerequisites to differentiate between the three driving styles. These metrics seem to be the essential components for the development of comfortable highly automated driving.