Gennaro Nicola Bifulco

Human-Like Adaptive Cruise Control Systems through a Learning Machine Approach

In this work an Adaptive Cruise Control (ACC) model, with human-like driving capabilities,based on a learning machine approach, is proposed. The system is based on a neural network approach and is intended to assist the drivers in safe car-following conditions. The proposed approach allows for an extreme flexibility of the ACC that can be continuously trained by drivers in order to accommodate their actual driving preferences as these changes among drivers and over time. The model has been calibrated against accurate experimental data consisting in trajectories of vehicle platoons gathered on urban roads. Its performances have been compared with those of a conventional car-following model.

Experiments toward an human-like Adaptive Cruise Control

In this work some experiments are made in order to assess the feasibility of a human-like ACC (adaptive cruise control) system. The proposed system is able to understand driverpsilas attitudes and driving-styles by means of a self-calibration process that can be (re)initialized on request. Three different speed-control logics have been tested: one tries to learn from actual driverspsila behaviors by using an artificial neural network (ANN) approach, the second is based on the calibration of a linear function aimed to be mimic of the driver response to stimuli, the third is based on the calibration of a polynomial function instead of a linear one. A microscopic traffic model, accurately calibrated and validated for different aims and in a previous work, has been adapted and used in order to generate a long car-following trajectory on which the speed control logics have been calibrated and compared. This has allowed for a sufficient amount of accurate laboratory data at a relatively low cost. Comparison of the tested speed-control logics show that a fully adaptive human-like ACC system is feasible and worth further more costly developments.

A Linear Dynamic Model for Driving Behavior in Car Following

In this paper a car-following model is formulated as a time-continuous dynamic process, depending on two parameters and two inputs. One of these inputs is the followers desired equilibrium spacing, assumed to exist and to be known. Another input is the speed of the lead vehicle. Given the formulation of the model, the contribution of these two inputs is separable from an analytical point of view. The proposed model is simple enough whereas not being simplistic to support real-time applications in the field of advanced driving assistance systems. Starting from the equilibrium spacing, it is possible to estimate the parameters of the model, allowing for a full identification procedure. The modeling framework was prevalidated against observed data from two different data sets, collected by means of two instrumented vehicles in independent experiments, carried out in Italy and the United Kingdom. The validation proved that the proposed car-following model gives good results not only around the desired equilibrium spacing but also in general car-following conditions. The experimental data sets are discussed in terms of parameter values as well as performance of the dynamic process against observed data.

The Role of the Uncertainty in ATIS Applications

In recent years the interest toward ATIS (Advanced Traveller Information Systems) is constantly increasing, probably because of the intent of solving over-congestion with minimal expenditure. Great efforts have been devoted to both technological and modeling aspects; however, a unified theory does not yet exist, as well as a general agreement on the objectives that can be achieved. It is not widely recognised what can be expected from ATIS, how the information should be designed and how to assess/forecast the network level effects. Here the authors will present a theoretical framework and some practical analyses, aimed to deal with the additional uncertainties sometimes introduced in the route choice problem by the presence of ATIS.

Design of Signal Setting and Advanced Traveler Information Systems

This article analyzes the role of advanced traveler information systems (ATIS) in conjunction with signal setting (SS) design. ATIS and SS are considered as planning options for network optimization under recurrent traffic conditions. The traffic network is considered in within-day static, as is usual for planning-oriented models. Both day-to-day static (equilibrium) and dynamic states are investigated. Notably, equilibrium and stability can influence the feasibility of SS solutions. In addition, the role of ATIS is assessed with regard to its suitability in equilibrating SS optima and/or stabilizing SS equilibria. Travelers’ compliance with information, which plays a crucial role in both optimization and stabilization, is explicitly modeled. A formal modeling framework is introduced, allowing SS and ATIS to be represented, and several benefits and drawbacks of SS and ATIS options are explored. The model is then used for simulations on a hypothetical network. The results suggest the potential of the modeling framework and lead to nontrivial findings about the role of ATIS.

Endogenous Driver Compliance and Network Performances under ATIS

In recent years a great effort has been made in studying many aspects related to modeling and design of ATIS, but a unified theory does not yet exist and there is no consensus on the objectives that can be achieved. This paper aims to show that the explicit modeling of the compliance as an endogenous variable depending on the information accuracy leads to the conclusion that the only objective worth pursuing (at least under recurrent conditions) is the provision of correct information, while the formulation of ATIS in the perspective of a system optimum is suitable only in cases where there is a not negligible incidence of non familiar travelers.

Coupling instrumented vehicles and driving simulators: Opportunities from the DRIVE IN2 project

DRIVE IN2 is an automotive research project within the field of Intelligent Transportation Systems, especially Advanced Driving Assistance Systems (ADAS). The project originates from the idea that the development of new ADAS and evaluation of their effect have to take drivers into account, as well as their behavior while driving: the benefits of adopting new in-vehicle technologies depend also on their adoption and usage by drivers. To this aim, the project develops a Driver-In-the-Loop framework to position observation of the drivers at the center of the research activities. Observations are carried out by coupling different research tools, namely instrumented vehicle and driving simulators. The premise and methodological framework of the research project are presented and discussed. Some preliminary activities with particular reference to validating the driving simulation environment are also described.

Identification of Driving Behaviors with Computer-Aided Tools

Identification of driving behavior is a crucial task in several Intelligent Transportation Systems applications, both to increase safety and assist drivers. Here we identify driving behaviors by means of an analytical model. In order to estimate the model parameters, data are collected with an instrumented vehicle. The paper presents the model, the procedure for the estimation of the parameters and the results of the proposed framework with respect to a pilot experiment to assess the feasibility and potential of the approach. Some practical implementations of the proposed model are presented. In particular, road safety assessment is introduced in greater depth to show the potential of the approach. For this purpose, a modified (and original) version of some surrogate measures of safety is introduced.

Validity of Mental Workload Measures in a Driving Simulation Environment

Automated in-vehicle systems and related human-machine interfaces can contribute to alleviating the workload of drivers. However, each new functionality can also introduce a new source of workload, due to the need to attend to new tasks and thus requires careful testing before being implemented in vehicles. Driving simulators have become a viable alternative to on-the-road tests, since they allow optimal experimental control and high safety. However, for each driving simulator to be a useful research tool, for each specific task an adequate correspondence must be established between the behavior in the simulator and the behavior on the road, namely, the simulator absolute and relative validity. In this study we investigated the validity of a driving-simulator-based experimental environment for research on mental workload measures by comparing behavioral and subjective measures of workload of the same large group of participants in a simulated and on-road driving task on the same route. Consistent with previous studies, mixed support was found for both types of validity, although results suggest that allowing more and/or longer familiarization sessions with the simulator may be needed to increase its validity. Simulator sickness also emerged as a critical issue for the generalizability of the results.

Validation of driving behaviour as a step towards the investigation of Connected and Automated Vehicles by means of driving simulators

Connected and Automated Vehicles (CAVs) are likely to become an integral part of the traffic stream within the next few years. Their presence is expected to greatly modify mobility behaviours, travel demands and habits, traffic flow characteristics, traffic safety and related external impacts. Tools and methodologies are needed to evaluate the effects of CAVs on traffic streams, as well as the impact on traffic externalities. This is particularly relevant under mixed traffic conditions, where human-driven vehicles and CAVs will interact. Understanding technological aspects (e.g. communication protocols, control algorithms, etc.) is crucial for analysing the impact of CAVs, but the modification induced in human driving behaviours by the presence of CAVs is also of paramount importance. For this reason, the definition of appropriate CAV investigations methods and tools represents a key (and open) issue. One of the most promising approaches for assessing the impact of CAVs is operator in the loop simulators, since having a real driver involved in the simulation represents an advantageous approach. However, the behaviour of the driver in the simulator must be validated and this paper discusses the results of some experiments concerning car-following behaviour. These experiments have included both driving simulators and an instrumented vehicle, and have observed the behaviours of a large sample of drivers, in similar conditions, in different experimental environments. Similarities and differences in driver behaviour will be presented and discussed with respect to the observation of one important quantity of car-following, the maintained spacing.