Figure 1: Using vestibular cues as a subtle awareness "nudge" modality in L3 automated driving scenario.

Domain adaptation is required for automated driving models to generalize well across diverse road conditions. This paper explores a training method for domain adaptation to adapt PilotNet, an end-to-end deep learning-based model, for left-hand driving conditions using real-world Australian highway data. Four training methods were evaluated: (1) a baseline model trained on U.S. right-hand driving data, (2) a model trained on flipped U.S. data, (3) a model pretrained on U.S. data and then fine-tuned on Australian highways, and (4) a model pretrained on flipped U.S. data and then fine-tuned on Australian highways. This setup examines whether incorporating flipped data enhances the model adaptation by providing an initial left-hand driving alignment. The paper compares model performance regarding steering prediction accuracy and attention, using saliency-based analysis to measure attention shifts across significant road regions. Results show that pretraining on flipped data alone worsens prediction stability due to misaligned feature representations, but significantly improves adaptation when followed by fine-tuning, leading to lower prediction error and stronger focus on left-side cues. To validate this approach across different architectures, the same experiments were done on ResNet, which confirmed similar adaptation trends. These findings emphasize the importance of preprocessing techniques, such as flipped-data pretraining, followed by fine-tuning to improve model adaptation with minimal retraining requirements.

When Automated Vehicles (AVs) navigate dynamic, interactive driving scenarios, they must consider the spatio-temporal layout of surrounding traffic, including social interactions among agents, to accurately predict their trajectories. Existing approaches often fail to handle complex inter-agent interactions with the necessary adaptive attention to dynamic contexts. This paper introduces a multi-agent trajectory prediction algorithm that leverages attentive spatio-temporal modelling to capture interactions among agents. Our approach integrates weighted Distance Graph Attention Networks (wDGAT) with dynamic attention assignment and Multi-Head Attention (MHA)-based Transformers to learn multi-headed social interaction patterns, preserving this critical information throughout the learning pipeline. This enables efficient aggregation of information from any number of neighbouring agents, allowing for robust processing of complex, time-dependent data and consistent retrieval of spatio-temporal knowledge across extended prediction horizons. We validate our model through extensive experiments on the NGSIM (US-101 and I-80) highway datasets. The results demonstrate that our approach consistently achieves the lowest prediction error over a 5-second horizon, producing diverse outcomes for different agents and outperforming state-of-the-art methods. Numerical results demonstrate that, compared with state-of-the-art models, the proposed model reduces the average prediction root-mean-square error over a five-second time horizon by 40% and achieves a median performance gain of 20% on large-scale public datasets. Ablation studies further confirm the effectiveness of our algorithm.

Automated Vehicles (AVs) have been receiving increasing attention as a potential highly mechanised, intelligent, self-regulating futuristic mode of transport. AVs are predicted to address limitations and human factors associated with traditional modes of transportation. Beyond the typical operations of AVs which can perform rudimentary tasks, the intelligent embedded program fit in to process challenging scenarios and deep multi-dimensional/ agent intents and interaction of the roadway is the grey area yet to be explored to design an exclusive encoding of social functionality and operation in order to address human factors causing road crashes. The aim of this study is to design a data-driven prediction framework for AVs that utilises multiple inputs to prove a multimodal, probabilistic estimate of the future intentions and trajectories of surrounding vehicles in freeway operation. Our proposed framework is a deep multi-agent learning-based system designed to effectively capture social interactions between vehicles without relying on map information. Our approach excels in capturing the high-level behaviours of multiple vehicles and generating a multi-modal trajectory forecast. It employs a multi-headed neural architecture to learn from social interactions between vehicle pairs and generates diverse trajectories proportional to predicted target intents, thus enabling feature fusion. Additionally, a multi-head self-attention mechanism is incorporated for prediction refinement. We achieved a good prediction performance with a lower prediction error in real traffic data at highways. Evaluation of the proposed framework using the NGSIM (US-101 and I-80) and HighD datasets shows satisfactory prediction performance for long-term trajectory prediction of multiple surrounding vehicles. Additionally, the proposed framework has higher prediction accuracy and generalisability than state-of-the-art approaches.

This paper presents an early prediction framework to classify drivers’ intended intersection movements in a connected vehicle environment. Intersections are considered accident blackspots with major traffic violations that cause property damage, injuries and fatalities. An accurate perception of drivers’ intended movements at intersections is required for advanced red-light (ARLW) or turning warnings for vulnerable road users (TWVR). Early prediction of intersection movement and adequate warning assistance will ensure road users’ safety at the intersection. In this study, we adopted recurrent neural networks (RNN): long short-term memory (LSTM) and gated recurrent units (GRU) networks to predict driver intended movements at intersections using the vehicle kinematics extracted from the Cooperative Awareness Messages (CAMs). We used naturalistic driving data of the Ipswich Connected Vehicle Pilot (ICVP) project, Queensland, which was collected from 351 participants who drove their connected vehicles during the pilot period. The pilot study installed roadside equipment at 29 signalised intersections to enable the Cooperative Intelligent Transportation System (C-ITS) use cases. Vehicle speed, speed limit, longitudinal acceleration, lateral acceleration, and yaw rate are used as predictors and monitored in 100-millisecond intervals for 1s to 4s at different warning distances from the stop line. Separate prediction models are trained based on different monitoring windows. Furthermore, drivers’ intended intersection movements are predicted at two individual intersections to evaluate intersection-specific prediction performance and are found with improved prediction accuracy than overall prediction models trained with all 29 intersections data. Overall prediction models are useful for some intersections which lack available data for individual intersection-based prediction.

Human errors contribute to 94%(±2.2%) of road crashes resulting in fatal/non-fatal causalities, vehicle damages and a predicament in the pathway to safer road systems. Automated Vehicles (AVs) have been a potential attempt in lowering the crash rate by replacing human drivers with an advanced computer-aided decision-making approach. However, AVs are yet to progress in handling the unprecedented situations involving interactions with other road users. This raises a need for a sophisticated and robust methodological framework to predict human driver interaction and intention. It is of prime importance to develop a constructive knowledge on the existing literature for a proficient forward leap in the field. To address this, we aim to conduct a comprehensive review on motion prediction methods in automated driving context with a special emphasis on model-based and data-driven approaches. Over a hundred studies related to the motion prediction for AVs have been extensively reviewed. This study recommends that the field requires more intricate classification of motion prediction methods, as the conventional three-level categorisation scheme should be upgraded to a profound and present-day context. Therefore, we attempt to provide a clear categorisation of existing motion prediction solutions by adopting four principal strategies: 1. Prediction methods, 2. Classes, 3. Algorithms and 4. Datasets. An all-inclusive summary of the reviewed studies with their respective pros and cons are also presented. Furthermore, we summarise the standard evaluation metrics applied for road users’ intention estimation and trajectory prediction tasks. It is found that the recent studies are built upon multi-agent learning systems with interaction among multiple road users in the same road environment. These methods can provide reliable prediction performance in highly interactive situations over long periods of time. However, the limitation could be at the cost of higher computational complexity in comparison to conventional methods, which are simpler to design and computationally effective. It is also observed that the conventional methods can only operate over a narrow prediction horizon and seldom consider the interactions among the road users. This review contributes to knowledge in validation, addresses the discrepancies, to explicate the ambiguities and to streamline current research for a futuristic perspective beneficiary in motion prediction field.

Self-driving vehicles will soon be a reality, as main automotive companies have announced that they will sell their driving automation modes in the 2020s. This technology raises relevant controversies, especially with recent deadly accidents. Nevertheless, autonomous vehicles are still popular and attractive thanks to the improvement they represent to people's way of life (safer and quicker transit, more accessible, comfortable, convenient, efficient, and environment-friendly). This paper presents a review of motion planning techniques over the last decade with a focus on highway planning. In the context of this article, motion planning denotes path generation and decision making. Highway situations limit the problem to high speed and small curvature roads, with specific driver rules, under a constrained environment framework. Lane change, obstacle avoidance, car following, and merging are the situations addressed in this paper. After a brief introduction to the context of autonomous ground vehicles, the detailed conditions for motion planning are described. The main algorithms in motion planning, their features, and their applications to highway driving are reviewed, along with current and future challenges and open issues.

This article considers the problem of near-optimal trajectory generation for autonomous vehicles on highways. The goal is to select a predictive reference trajectory in the free evolution space, while avoiding both generating a pre-calculated set of candidate trajectories and decoupling path and velocity optimizations. Moreover, this trajectory aims at optimizing a decision process based on multi-criteria functions, which are not straightforward to design and can have a blackbox formulation. The main idea of this article is to use the decision evaluation function in the trajectory generator with a Simulated Annealing (SA) approach. The parameters of a sigmoid trajectory are optimized within Non-Collision Nominal Intervals (NCNI), which are defined as collision-free intervals under nominal conditions using a velocity-space representation.

This article considers the problem of high-level decision process for autonomous vehicles on highways. The goal is to select a predictive reference trajectory among a set of candidate ones, issued from a trajectory generator. This selection aims at optimizing multi-criteria functions, such as safety, legal rules, preferences and comfort of passengers, or energy consumption. This work introduces a new framework for Multi-Criteria Decision Making (MCDM). The proposed approach adopts fuzzy logic theory to deal with heterogeneous criteria and arbitrary functions. Moreover, the consideration of uncertain vehicle's sensors data is done using the Dempster-Shafer Theory with fuzzy sets in order to provide a risk assessment. Simulation results using datasets collected under the NGSIM program are presented on car following cases, and extended to lane changing situations.

Minimum energy expense and maximum safety with some comfort characterizes the definition of ideal human mobility. Recent technological advances in the autonomous vehicle driving systems not only enhance the safety and/or comfort levels but also present a significant opportunity for automated eco-driving. In this regard, a longitudinal controller for a smart and green autonomous vehicle (SAGA) is investigated. In principle, it is an eco-adaptive cruise control which aims at minimizing energy expenditure and maximizing energy regeneration. This paper presents detailed energy and powertrain analysis through the simulation of specific SAGA application concepts such as, dynamic programming-based offline acceleration optimization for a battery electric vehicle, or SAGA as a supervisory controller in combination with equivalent consumption minimization strategy for a hybrid electric vehicle. The main focus is on the evaluation of a vehicle energy manager which autonomously controls the longitudinal motion while actively balancing efficiency and safety. The comfort is not directly addressed in the conception but regarded as a quality criterion.

Autonomous driving relies on a wide range of domains of research. It faces rapid technological and theoretical advances, with various methods and process developments. For the interest of the high-level decision making subpart of autonomous vehicle architecture, the previous states of the art report a vast literature, from traditional mobile robotics to human-modelling approaches. The purpose of this paper is to survey the current and major algorithms in the specific field of artificial intelligence for autonomous vehicles. Such systems are particularly suited for high-level decision making since they must, by definition, be able to perceive and react to their environment in order to reach given objectives. The scope is reduced to highway driving applications, considering individual, collective, and cooperative decisions. Strengths and limitations of the reviewed methods are compared, with respect to the structure and constraints of the studied driving situations. Open questions are proposed as a reflection towards the next generation of decision-makers for autonomous vehicles.

This paper presents automatic parallel parking for a passenger vehicle, with highlights on a path-planning method and on experimental results. The path-planning method consists of two parts. First, the kinematic model of the vehicle, with corresponding geometry, is used to create a path to park the vehicle in one or more maneuvers if the spot is very narrow. This path is constituted of circle arcs. Second, this path is transformed into a continuous-curvature path using clothoid curves. To execute the generated path, control inputs for steering angle and longitudinal velocity depending on the traveled distance are generated. Therefore, the traveled distance and the vehicle pose during a parking maneuver are estimated. Finally, the parking performance is tested on a prototype vehicle.

This paper presents the experimental results of our path planning for a passenger vehicle in parallel parking problems. The generation of the path planning consists in two parts: create a simple geometric path for the parallel parking in one or more maneuvers by circle arcs and then transform it into a continuous-curvature path with the use of clothoids. Experimental results of the parking and of the localization of the vehicle confirm the chosen approach.

This paper presents an optimization of a conventional Adaptive Cruise Control system (ACC) for the specific use of electric vehicles with regenerative capacity, namely the Smart and Green ACC (SAGA). Longitudinal control strategies, that are developed for the driving assistances, mainly aim at optimizing the safety and the comfort of the vehicle occupants. Electric vehicles have the possibility, depending on the architecture, the speed and the braking demand, to regenerate a part of the electric energy during the braking. Moreover, the electric vehicle range is currently limited. The opportunity to adapt the braking of an ACC system to extend slightly the range must not be avoided. When the ACC is active, the vehicle speed is controlled automatically either to maintain a given clearance to a forward vehicle, or to maintain the driver desired speed, whichever is lower. We define how we can optimize both mode and what is the impact, in term of safety and strategy, including the knowledge of the future of the road, integrating a navigation system.

Simulation has been widely used to estimate the benefits of ADAS with embedded sensors or more recently Cooperative Systems based on Inter-Vehicular Communications. This paper presents the proposal of a new architecture built with the both SiVIC and RTMaps platforms in order to prototype, to test and to validate eco-driving applications. In this architecture, the innovation is mainly due to the real-time immersion of a real driver in a 3D virtual environment. In this “Hardware In the Loop” platform, major contributions have been made about vehicle modeling updating, interconnection between SiVIC and an HMD. Moreover, a first modeling of a consumption sensor is proposed and used in order to achieve some tests of fuel consumption on the virtual Satory's track. All these contributions have been tuned with on-road measurements to improve reality of the scenarios. We discuss the results of a simple eco-driving scenario implemented to validate our architecture's capabilities.

LIVIC-IFSTTAR develops driving assistance services in order to improve the driving safety. These systems are tested on several real prototypes equipped with sensors and perception, decision and control modules. But tests on real prototypes are not always available, effectively some hardware architectures could be too expensive to implement, scenario may lead to hazardous situations. Moreover, lots of reasons could lead to the inability to obtain both sensors and ground truth data for ADAS evaluation. However, safety applications must be tested in order to guaranty their reliability. For this task, simulation appears as a good alternative to the real prototyping and testing stages. In this context, the simulation must provide the same opportunities as reality, by providing all the necessary data to develop and to prototype different types of ADAS based on local or extended environment perception. The sensor data provided by simulation must be as noised and imperfect as those obtained with real sensors. To address this issue, the SiVIC platform has been developed; it provides a virtual road environment including realistic dynamic models of mobile entities (vehicles), realistic sensors, and sensors for ground truth. To test real embedded applications, an interconnection has been developed between SiVIC and third party applications (ie. RTMaps). In this way, the prototyped application can be directly embedded in real prototypes in order to test it in real conditions. A Full Speed Range ACC application is presented in this paper to illustrate the capabilities and the functionalities of this virtual platform.

This paper presents a vehicle trajectory controller for an automated vehicle with mechanical steering system, capable of continuously switching from fully automated to human controlled driving. When the driver wishes to correct the controller trajectory, the parameters of the P.I. based controller are adapted to ease the maneuver. The driver is kept informed on the planned trajectory via an incentive torque on the driving wheel. Implementation on test vehicle shows that the controller guaranties a rapid and accurate control in fully automated driving mode even on sharp curvature roads, and a quick and safe control transfer to the human when requested.

The boom in the number of active safety functions and driver assistance systems during the last several years has made vehicle design more and more difficult. To support the early development process, particularly the design of electronic and electric architectures, the capability to simulate and compute complete vehicle behavior is critically important and useful. This paper presents such a simulator, which consists of key components such as the drivetrain and controller subsystems. Then, after having presented the generic structure of a driver assistance system, concrete use cases of this simulator are given, which assess vehicle performance according to different functional and hardware architectures.

Overspeeding is both a cause and an aggravation factor of traffic accidents. Consequently, much effort is devoted to limiting overspeeding and, consequently, to increasing the safety of road networks. In this paper, a novel approach to computing a safe speed profile to be used in an adaptive intelligent speed adaptation (ISA) system is proposed. The method presents two main novelties. First, the 85th percentile of observed speeds (V85), estimated along a road section, is used as a reference speed, which is practiced and practicable in ideal conditions. Second, this reference speed is modulated in adverse weather conditions to account for reduced friction and reduced visibility distance. The risk is thus mitigated by modulating the potential severity of crashes by means of a generic scenario of accidents. Within this scenario, the difference in speed that should be applied in adverse conditions is estimated so that the highway risk is the same as in ideal conditions. The system has been tested on actual data collected on a French secondary road and implemented on a test track and a fleet of vehicles. The performed tests and the experiments of acceptability show a great interest for the deployment of such a system.

This paper discusses driving system design based on traffic rules. This allows fully automated driving in an environment with human drivers, without necessarily changing equipment on other vehicles or infrastructure. It also facilitates cooperation between the driving system and the host driver during highly automated driving. The concept, referred to as legal safety, is illustrated for highly automated driving on highways with distance keeping, intelligent speed adaptation, and lane-changing functionalities. Requirements by legal safety on perception and control components are discussed. This paper presents the actual design of a legal safety decision component, which predicts object trajectories and calculates optimal subject trajectories. System implementation on automotive electronic control units and results on vehicle and simulator are discussed.

This paper firstly reviews of the analysis of the nonlinear behavior of the vehicle lateral dynamics. The (αf, αf) phase plane is used in order to quantify the stability region of the vehicle under different forward speed, steering angle and road adhesion. The tire-road interaction forces are modeled using Pacejka's magic formula. In a second step, the exact linear sectors procedure is used for representation of nonlinear functions in order to derive a Takagi-Sugeno (TS) fuzzy model. This model copes the behavior of the lateral tire forces including the linear, decreasing and saturated regions. Thereafter, a Takagi-Sugeno fuzzy output feedback is designed for yaw motion control. The controller acts through the steering of the front wheels and the differential braking torque generation. The computation of the controller is performed in such a way that the trajectories of the controlled vehicle remain inside an invariant set even when it is under disturbance input. This is achieved using quadratic boundedness theory and Lyapunov stability. Simulation tests show that the controlled car is able to satisfactorily perform standard maneuvers such as the ISO3888-2 transient maneuver and the roundabout maneuver.

This paper discusses the design of an Advanced Driver Assistance System (ADAS) that ensures safety when traffic rules are respected by all road users. This concept, referred to as legal safety, is proposed as a basis that permits human and automated drivers to share the road infrastructure. It is illustrated for a Highly Automated driving System with speed keeping, distance keeping and lane changing functionalities on highways (HAS). The requirements legal safety places upon HAS components are presented, with a special focus on the co-pilot which calculates a safe trajectory for the vehicle based on perception of lanes and traffic signs and prediction of the trajectories of objects in the environment. A lane coordinate system is proposed as a powerful reference for the trajectory calculations of the co-pilot. The system controls the vehicle and communicates with the driver, according to an automation mode scheme inspired by the horse-rider metaphor (H-metaphor).

In this paper, a novel approach to compute advisory speeds to be used in an adaptive Intelligent Speed Adaptation system (ISA) is proposed. This method is designed to be embedded in the vehicles. It estimates an appropriate speed by fusing in real-time the outputs of ego sensors which detect adverse conditions with roadway characteristics transmitted by distant servers. The method presents two major novelties. First, the 85th percentile of observed speeds (V85) is estimated along a road, this speed profile is considered as a reference speed practised and practicable in ideal conditions for a lonely vehicle. In adverse conditions, this reference speed is modulated in order to account for lowered friction and lowered visibility distance (top-down approach). Second, this method allows us taking into account the potential seriousness of crashes using a generic scenario of accident. Within this scenario, the difference in speed that should be applied in adverse conditions is estimated so that global injury risk is the same as in ideal conditions.

This paper presents a framework for a fast prototyping of Advanced Driving Assistance Systems (ADAS). The simulation tool SiVIC is proposed for drastically reducing development time and costs of a vehicle system design.RTMaps®is used as a platform for easily encapsulating the system component algorithms and for effortlessly transferring them from a simulation environment to a physical vehicle. With these tools a Highly Autonomous Cooperative Driving System (HACS) has been designed. A perception component uses a combination of sensors to map the environment. In this paper a cooperative, extended perception with infrastructure-to-vehicle communication (I2V) will be proposed. A co-pilot integrates a fast Total Trajectory Exploration (TTE) method that finds a trajectory that is optimal with respect to the sensed environment. A simple controller on the vehicle actuators is used for guiding the vehicle on this trajectory. The cooperation between human and automation is managed by a Driving Mode Selection Unit (MSU) and a Human Machine Interface (HMI). In this paper a vehicle system which allows highly autonomous driving with human cooperation is called a co-system.

This paper presents the design and first test on a simulator of a vehicle trajectory-planning algorithm that adapts to traffic on a lane-structured infrastructure such as highways. The proposed algorithm is designed to run on a fail-safe embedded environment with low computational power, such as an engine control unit, to be implementable in commercial vehicles of the near future. The target platform has a clock frequency of less than 150 MHz, 150 kB RAM of memory, and a 3-MB program memory. The trajectory planning is performed by a two-step algorithm. The first step defines the feasible maneuvers with respect to the environment, aiming at minimizing the risk of a collision. The output of this step is a target group of maneuvers in the longitudinal direction (accelerating or decelerating), in the lateral direction (changing lanes), and in the combination of both directions. The second step is a more detailed evaluation of several possible trajectories within these maneuvers. The trajectories are optimized to additional performance indicators such as travel time, traffic rules, consumption, and comfort. The output of this module is a trajectory in the vehicle frame that represents the recommended vehicle state (position, heading, speed, and acceleration) for the following seconds.

This paper presents the problematic of outdoor vehicle localization under the IMM (Interacting Multiple Model) approach. The IMM is now a well known modular approach, which is based on the discretization of the vehicle evolution space into simple maneuvers, represented each by a simple dynamic model such as constant velocity or constant turning etc. This allows the method to be optimized for highly dynamic vehicles. Unfortunately classical IMM shows some drawbacks concerning some real time multi sensors applications. In this work, we focus on outdoor vehicle localization with asynchronous sensors in order to report these drawbacks and then propose a new solution. Many tests carried out with simulated and real data confirm the interest for using such a solution in our applications.

This paper presents a new method for the detection and 3D reconstruction of the road lane using onboard stereovision. The proposed algorithm makes it possible to overcome the assumptions commonly used in most of the detection systems using monocular vision such as: flat road, constant pitch angle or absence of roll angle. The proposed method of detection and 3D reconstruction is based on two modules. The first one is aimed at detecting the road markings of the lane in each image of the stereoscopic pair. It is based on a recognition algorithm driven by a statistical model of the road lane: the initial state of the model is obtained after a learning stage; it is updated using the results of a feature extraction stage. Our model takes into account the intrinsic links between the projections of the road in the two images of the stereoscopic pair, so that its update from a feature extracted in one of two images drives the detection of the features in the other image. No disparity map is required since the matching of the road features is directly obtained as the result of the model update. The second module is aimed at 3D reconstruction and relative localization of the vehicle with respect to its lane. The parameters of a 3D surface including the horizontal and vertical profiles of the road lane are estimated from the road borders previously detected. The robustness of the algorithm is evaluated from synthetic and real images.

Nowadays, more and more driving assistances are available to help the driver and to improve the vehicle handling. With increasing sensing capacities, it also becomes possible to have a local view of the vehicle surrounding. Hence, the next steps are to provide the driving assistances a supervisor that schedules all the possible actions and plane trajectories. In this article, we propose a decision method that fits the driver decision and action schemes. The system is at three levels, for action, decision and long range planning. the article is focused on the second layer and the interaction with other layer. The second layer algorithm, based on risk assumption, evaluates, in the vehicle vicinity, the risk related to each detected object. It then computes possible actions for lower level layer. The developed method is constrained by the future implementation on a vehicle : low computation time available and small memory size.

Driving safety enhancement could be achieved by better understanding of risk situations from the knowledge of vehicle dynamic states as well as road geometry. Among the parameters of the road that have an impact on vehicle dynamics, one can find the bank and the slope angles, which can not however be measured by mean of low cost onboard sensors. This work of this paper is aimed to improve the controllability of the vehicle and the development of a low cost mapping system of the roadway. Two observers are developed firstly to estimate these two variables and secondly to localize the vehicle. The road attributes are estimated using an extended Kalman filter (EKF) and a Proportional Integral (PI) observer with unknown inputs based vehicle models and the measurements obtained from inertial (INS) and ABS sensors. The vehicle localization is performed at each time sample using an algorithm based on the IMM technique (Interacting Multiple Models), it allows to reconstruct the road shape in 3 dimensions. Testing on measurements obtained with a prototype vehicle show the good behavior of the proposed estimation scheme.

More and more research fields, in particular in the road safety area, need to establish a vehicle-to-vehicle (V2V) communication step in order to deploy applications (for instance warning messages in case of emergency situations and string and platoon stability). Generally, these applications are experimented with only few vehicles with a local ad hoc or centralized network. The aim of this paper is to determine the behavior of a such network in a traffic flow. We want to know which conditions are necessary and which quality of service (QoS) we can expect. We base our approach on probabilistic formal expression. This approach can be complementary to the solutions brought by network simulators as ns2.

The main goal of this paper is to develop a distance to line crossing (DLC) based computation of time to line crossing (TLC). Different computation methods with increasing complexity are provided. A discussion develops the influence of assumptions generally assumed for approximation. A sensitivity analysis with respect to vehicle parameters and positioning is performed. For TLC computation, both straight and curved vehicle paths are considered. The road curvature being another important variable considered in the proposed computations, an observer for its estimation is then proposed. An evaluation over a digitalized test track is first performed. Real data are then collected through an experiment carried out in test tracks with the equipped prototype vehicle. Based on these real data, TLC is then computed with the theoretically proposed methods. The obtained results outlined the necessity to take into consideration vehicle dynamics to use the TLC as a lane departure indicator.

The aim of this paper is to perform a comparison among several different Kalman filters algorithms designed for nonlinear systems. After presenting the most popular of them and showing its limitations, we introduce some new Kalman filters in order to compare them in the vehicle localization context. This comparison is based on the sole use of their predictive steps that corresponds to the worst case that it can occur in vehicle localization (corrective data are unavailable).