Fabio Tango

Bio: Fabio Tango is an academic researcher from Fiat Automobiles. The author has contributed to research in topics: Automation & Driving simulator. The author has an hindex of 11, co-authored 45 publications receiving 526 citations. Previous affiliations of Fabio Tango include University of Modena and Reggio Emilia & Infineon Technologies.

Real-Time Detection System of Driver Distraction Using Machine Learning

Abstract: There is accumulating evidence that driver distraction is a leading cause of vehicle crashes and incidents. In particular, increased use of so-called in-vehicle information systems (IVIS) and partially autonomous driving assistance systems (PADAS) have raised important and growing safety concerns. Thus, detecting the driver's state is of paramount importance, to adapt IVIS and PADAS accordingly, therefore avoiding or mitigating their possible negative effects. The purpose of this paper is to show a method for the nonintrusive and real-time detection of visual distraction, using vehicle dynamics data and without using the eye-tracker data as inputs to classifiers. Specifically, we present and compare different models that are based on well-known machine learning (ML) methods. Data for training the models were collected using a static driving simulator, with real human subjects performing a specific secondary task [i.e., a surrogate visual research task (SURT)] while driving. Different training methods, model characteristics, and feature selection criteria have been compared. Based on our results, using a support vector machine (SVM) has outperformed all the other ML methods, providing the highest classification rate for most of the subjects. Potential applications of this paper include the design of an adaptive IVIS and of a “smarter” PADAS.

Supporting Drivers in Keeping Safe Speed and Safe Distance: The SASPENCE Subproject Within the European Framework Programme 6 Integrating Project PReVENT

Abstract: This paper describes a novel driver-support system that helps to maintain the correct speed and headway (distance) with respect to lane curvature and other vehicles ahead. The system has been developed as part of the Integrating Project PReVENT under the European Framework Programme 6, which is named SAfe SPEed and safe distaNCE (SASPENCE). The application uses a detailed description of the situation ahead of the vehicle. Many sensors [radar, video camera, Global Positioning System (GPS) and accelerometers, digital maps, and vehicle-to-vehicle wireless local area network (WLAN) connections] are used, and state-of-the-art data fusion provides a model of the environment. The system then computes a feasible maneuver and compares it with the driver's behavior to detect possible mistakes. The warning strategies are based on this comparison. The system “talks” to the driver mainly via a haptic pedal or seat belt and “listens” to the driver mainly via the vehicle acceleration. This kind of operation, i.e., the comparison between what the system thinks is possible and what the driver appears to be doing, and the consequent dialog can be regarded as simple implementations of the rider-horse metaphor (H-metaphor). The system has been tested in several situations (driving simulator, hardware in the loop, and real road tests). Objective and subjective data have been collected, revealing good acceptance and effectiveness, particularly in awakening distracted drivers. The system intervenes only when a problem is actually detected in the headway and/or speed (approaching curves or objects) and has been shown to cause prompt reactions and significant speed correction before getting into really dangerous situations.

Dynamic situation and threat assessment for collision warning systems: the EUCLIDE approach

Abstract: Situation and threat assessment is considered as the highest level of abstraction in the vehicle tracking processes. In this paper, a broad discussion is introduced on algorithms for active safety functions, whilst a new dynamic algorithm is proposed. This approach handles all objects' states as dynamic stochastic variables and based on a Kalman approach calculates in real time all trajectories respectively. Thus, a reconstruction of the traffic scene can be achieved in order to assess a level of threat for all moving and stationary obstacles in the longitudinal area of the subject vehicle. This approach is adopted in the European co-funded project "EUCLIDE", which develops a vision enhancement and collision warning system merging the functionality of an infrared camera and mmw radar sensor. Results are presented using simulated and real data sets from dedicated sessions.

Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behavior

Abstract: Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized high-streets. Unlike static obstacles, pedestrians are active agents with complex, interactive motions. Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behavior as well as detecting and tracking them. This narrative review article is Part II of a pair, together surveying the current technology stack involved in this process, organising recent research into a hierarchical taxonomy ranging from low-level image detection to high-level psychological models, from the perspective of an AV designer. This self-contained Part II covers the higher levels of this stack, consisting of models of pedestrian behavior, from prediction of individual pedestrians’ likely destinations and paths, to game-theoretic models of interactions between pedestrians and autonomous vehicles. This survey clearly shows that, although there are good models for optimal walking behavior, high-level psychological and social modelling of pedestrian behavior still remains an open research question that requires many conceptual issues to be clarified. Early work has been done on descriptive and qualitative models of behavior, but much work is still needed to translate them into quantitative algorithms for practical AV control.

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Effects of adaptive cruise control and highly automated driving on workload and situation awareness: A review of the empirical evidence

Abstract: Adaptive cruise control (ACC), a driver assistance system that controls longitudinal motion, has been introduced in consumer cars in 1995. A next milestone is highly automated driving (HAD), a system that automates both longitudinal and lateral motion. We investigated the effects of ACC and HAD on drivers' workload and situation awareness through a meta-analysis and narrative review of simulator and on-road studies. Based on a total of 32 studies, the unweighted mean self-reported workload was 43.5% for manual driving, 38.6% for ACC driving, and 22.7% for HAD (0% = minimum, 100 = maximum on the NASA Task Load Index or Rating Scale Mental Effort). Based on 12 studies, the number of tasks completed on an in-vehicle display relative to manual driving (100%) was 112% for ACC and 261% for HAD. Drivers of a highly automated car, and to a lesser extent ACC drivers, are likely to pick up tasks that are unrelated to driving. Both ACC and HAD can result in improved situation awareness compared to manual driving if drivers are motivated or instructed to detect objects in the environment. However, if drivers are engaged in non-driving tasks, situation awareness deteriorates for ACC and HAD compared to manual driving. The results of this review are consistent with the hypothesis that, from a Human Factors perspective, HAD is markedly different from ACC driving, because the driver of a highly automated car has the possibility, for better or worse, to divert attention to secondary tasks, whereas an ACC driver still has to attend to the roadway.

The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems

Abstract: Scenario-based testing for the safety validation of highly automated vehicles is a promising approach that is being examined in research and industry. This approach heavily relies on data from real-world scenarios to derive the necessary scenario information for testing. Measurement data should be collected at a reasonable effort, contain naturalistic behavior of road users and include all data relevant for a description of the identified scenarios in sufficient quality. However, the current measurement methods fail to meet at least one of the requirements. Thus, we propose a novel method to measure data from an aerial perspective for scenario-based validation fulfilling the mentioned requirements. Furthermore, we provide a large-scale naturalistic vehicle trajectory dataset from German highways called highD. We evaluate the data in terms of quantity, variety and contained scenarios. Our dataset consists of 16.5 hours of measurements from six locations with 110 000 vehicles, a total driven distance of 45 000 km and 5600 recorded complete lane changes. The highD dataset is available online at: http://www.highD-dataset.com

Driver Inattention Monitoring System for Intelligent Vehicles: A Review

Abstract: In this paper, we review the state-of-the-art technologies for driver inattention monitoring, which can be classified into the following two main categories: 1) distraction and 2) fatigue. Driver inattention is a major factor in most traffic accidents. Research and development has actively been carried out for decades, with the goal of precisely determining the drivers' state of mind. In this paper, we summarize these approaches by dividing them into the following five different types of measures: 1) subjective report measures; 2) driver biological measures; 3) driver physical measures; 4) driving performance measures; and 5) hybrid measures. Among these approaches, subjective report measures and driver biological measures are not suitable under real driving conditions but could serve as some rough ground-truth indicators. The hybrid measures are believed to give more reliable solutions compared with single driver physical measures or driving performance measures, because the hybrid measures minimize the number of false alarms and maintain a high recognition rate, which promote the acceptance of the system. We also discuss some nonlinear modeling techniques commonly used in the literature.

Multiple Sensor Fusion and Classification for Moving Object Detection and Tracking

Abstract: The accurate detection and classification of moving objects is a critical aspect of advanced driver assistance systems. We believe that by including the object classification from multiple sensor detections as a key component of the object's representation and the perception process, we can improve the perceived model of the environment. First, we define a composite object representation to include class information in the core object's description. Second, we propose a complete perception fusion architecture based on the evidential framework to solve the detection and tracking of moving objects problem by integrating the composite representation and uncertainty management. Finally, we integrate our fusion approach in a real-time application inside a vehicle demonstrator from the interactIVe IP European project, which includes three main sensors: radar, lidar, and camera. We test our fusion approach using real data from different driving scenarios and focusing on four objects of interest: pedestrian, bike, car, and truck.