After more than 20 years of research, ADAS are common in modern vehicles available in the market. Automated Driving systems, still in research phase and limited in their capabilities, are starting early commercial tests in public roads. These systems rely on the information provided by on-board sensors, which allow to describe the state of the vehicle, its environment and other actors. Selection and arrangement of sensors represent a key factor in the design of the system. This survey reviews existing, novel and upcoming sensor technologies, applied to common perception tasks for ADAS and Automated Driving. They are put in context making a historical review of the most relevant demonstrations on Automated Driving, focused on their sensing setup. Finally, the article presents a snapshot of the future challenges for sensing technologies and perception, finishing with an overview of the commercial initiatives and manufacturers alliances that will show the intention of the market in sensors technologies for Automated Vehicles.

The deployment of Intelligent Vehicles in urban environments requires reliable estimation of positioning for urban navigation. The inherent complexity of this kind of environments fosters the development of novel systems which should provide reliable and precise solutions to the vehicle. This article details an advanced GNSS/IMU fusion system based on a context-aided Unscented Kalman filter for navigation in urban conditions. The constrained non-linear filter is here conditioned by a contextual knowledge module which reasons about sensor quality and driving context in order to adapt it to the situation, while at the same time it carries out a continuous estimation and correction of INS drift errors. An exhaustive analysis has been carried out with available data in order to characterize the behavior of available sensors and take it into account in the developed solution. The performance is then analyzed with an extensive dataset containing representative situations. The proposed solution suits the use of fusion algorithms for deploying Intelligent Transport Systems in urban environments.

Advanced Driver Assistance Systems (ADAS) acting over throttle and brake are already available in level 2 automated vehicles. In order to increase the level of automation new systems need to be tested in an extensive set of complex scenarios, ensuring safety under all circumstances. Validation of these systems using real vehicles presents important drawbacks: the time needed to drive millions of kilometers, the risk associated with some situations, and the high cost involved. Simulation platforms emerge as a feasible solution. Therefore, robust and reliable virtual environments to test automated driving maneuvers and control techniques are needed. In that sense, this paper presents a use case where three longitudinal low speed control techniques are designed, tuned, and validated using an in-house simulation framework and later applied in a real vehicle. Control algorithms include a classical PID, an adaptive network fuzzy inference system (ANFIS), and a Model Predictive Control (MPC). The simulated dynamics are calculated using a multibody vehicle model. In addition, longitudinal actuators of a Renault Twizy are characterized through empirical tests. A comparative analysis of results between simulated and real platform shows the effectiveness of the proposed framework for designing and validating longitudinal controllers for real automated vehicles.

In last decades, great technology advances have been done related to the automotive sector, especially in Advanced Driver Assistance Systems (ADAS) developed to improve mobility in terms of comfort and safety during driving process; hence, automated driving is presented as an evolution of those systems in the present and upcoming years. The aim of this work is to present a complete framework of motion planning for automated vehicles, considering different constraints with parametric curves for lateral and longitudinal planners. Parametric Bézier curves are used as the core approach for trajectory design in intersections, roundabouts, and lane change maneuvers. Additionally, a speed planner algorithm is presented using the same parametric curve approach, considering comfort and safety. A simulation environment is used for testing the planning method in urban conditions. Finally, tests with the real platform in automated mode have been performed showing goods results.

This paper presents a speed profile generation approach for longitudinal control of automated vehicles, based on quintic Bézier curves. The described method aims to increase comfort level of passengers based on the ISO2631-1 specification, while taking into account vehicle dynamics and traffic rules to keep high safety levels. The algorithm has been tested in an in-house tool for high accuracy vehicle dynamics simulations, called Dynacar. The considered scenario is a closed circuit inside Tecnalia facilities. The resulting profile has better properties (for example, rate of change) than a raw input based on traffic speed limits. When used as reference for the speed controller, it improves both comfort and safety.

As vehicles get increasingly automated, they need to properly evaluate different situations and assess threats at run-time. In this scenario automated vehicles should be able to evaluate risks regarding a dynamic environment in order to take proper decisions and modulate their driving behavior accordingly. In order to avoid collisions, in this work we propose a risk estimator based on fuzzy logic which accounts for risk indicators regarding (1) the state of the driver, (2) the behavior of other vehicles and (3) the weather conditions. A scenario with two vehicles in a car-following situation was analyzed, where the main concern is to avoid rear-end collisions. The goal of the presented approach is to effectively estimate critical states and properly assess risk, based on the indicators chosen.

No abstract

Face recognition is a problem that arises on many real world applications, such as those related with Ambient Intelligence (AmI). The specific nature and goals of AmI applications, however, requires minimizing the invasiveness of data collection methods, often resulting in a drastic reduction of data quality and a plague of unforeseen effects which can put standard face recognition systems out of action. In order to deal with this, a face recognition system for AmI applications must not only be carefully designed but also subject to an exhaustive configuration plan to ensure it offers the required accuracy, robustness and real-time performance. This document covers the design and tuning of a holistic face recognition system targeting an Ambient Intelligence scenario. It has to work under partially uncontrolled capturing conditions: frontal images with pose variation up to 40 degrees, changing illumination, variable image size and degraded quality. The proposed system is based on Support Vector Machine (SVM) classifiers and applies Gabor Filters intensively. A complete sensitivity analysis shows how the recognition accuracy can be boosted through careful configuration and proper parameter setting, although the most adequate setting depends on the requirements for the final system.