Abstract

International audience; This chapter describes the emerging robotics application field of intelligent vehicles – motor vehicles that have autonomous functions and capabilities. The chapter is organized as follows:- Section 62.1 provides a motivation for why the development of intelligent vehicles is important, a brief history of the field, and the potential benefits of the technology.- Section 62.2 describes the technologies that enable intelligent vehicles to sense vehicle, environment, and driver state, work with digital maps and satellite navigation, and communicate with intelligent transportation infrastructure.- Section 62.3 describes the challenges and solutions associated with road scene understanding – a key capability for all intelligent vehicles.- Section 62.4 describes advanced driver assistance systems, which use the robotics and sensing technologies described earlier to create new safety and convenience systems for motor vehicles, such as collision avoidance, lane keeping, and parking assistance.- Section 62.5 describes driver monitoring technologies that are being developed to mitigate driver fatigue, inattention, and impairment.- Section 62.6 describes fully autonomous intelligent vehicles systems that have been developed and deployed.- Sections 62.7 and 62.8 conclude the chapter with a discussion of future prospects, and provide references to further reading and additional resources.

Abstract

Mención Internacional en el título de doctor The technological advances in the Intelligent Transportation Systems (ITS) are exponentially improving over the last century. The objective is to provide intelligent and innovative services for the different modes of transportation, towards a better, safer, coordinated and smarter transport networks. The Intelligent Transportation Systems (ITS) focus is divided into two main categories; the first is to improve existing components of the transport networks, while the second is to develop intelligent vehicles which facilitate the transportation process. Different research efforts have been exerted to tackle various aspects in the fields of the automated vehicles. Accordingly, this thesis is addressing the problem of multiple automated vehicles cooperation and coordination. At first, 3DCoAutoSim driving simulator was developed in Unity game engine and connected to Robot Operating System (ROS) framework and Simulation of Urban Mobility (SUMO). 3DCoAutoSim is an abbreviation for "3D Simulator for Cooperative Advanced Driver Assistance Systems (ADAS) and Automated Vehicles Simulator". 3DCoAutoSim was tested under different circumstances and conditions, afterward, it was validated through carrying-out several controlled experiments and compare the results against their counter reality experiments. The obtained results showed the efficiency of the simulator to handle different situations, emulating real world vehicles. Next is the development of the iCab platforms, which is an abbreviation for "Intelligent Campus Automobile". The platforms are two electric golf-carts that were modified mechanically, electronically and electrically towards the goal of automated driving. Each iCab was equipped with several on-board embedded computers, perception sensors and auxiliary devices, in order to execute the necessary actions for self-driving. Moreover, the platforms are capable of several Vehicle-to-Everything (V2X) communication schemes, applying three layers of control, utilizing cooperation architecture for platooning, executing localization systems, mapping systems, perception systems, and finally several planning systems. Hundreds of experiments were carried-out for the validation of each system in the iCab platform. Results proved the functionality of the platform to self-drive from one point to another with minimal human intervention. Los avances tecnológicos en Sistemas Inteligentes de Transporte (ITS) han crecido de forma exponencial durante el último siglo. El objetivo de estos avances es el de proveer de sistemas innovadores e inteligentes para ser aplicados a los diferentes medios de transporte, con el fin de conseguir un transporte mas eficiente, seguro, coordinado e inteligente. El foco de los ITS se divide principalmente en dos categorías; la primera es la mejora de los componentes ya existentes en las redes de transporte, mientras que la segunda es la de desarrollar vehículos inteligentes que hagan más fácil y eficiente el transporte. Diferentes esfuerzos de investigación se han llevado a cabo con el fin de solucionar los numerosos aspectos asociados con la conducción autónoma. Esta tesis propone una solución para la cooperación y coordinación de múltiples vehículos. Para ello, en primer lugar se desarrolló un simulador (3DCoAutoSim) de conducción basado en el motor de juegos Unity, conectado al framework Robot Operating System (ROS) y al simulador Simulation of Urban Mobility (SUMO). 3DCoAutoSim ha sido probado en diferentes condiciones y circunstancias, para posteriormente validarlo con resultados a través de varios experimentos reales controlados. Los resultados obtenidos mostraron la eficiencia del simulador para manejar diferentes situaciones, emulando los vehículos en el mundo real. En segundo lugar, se desarrolló la plataforma de investigación Intelligent Campus Automobile (iCab), que consiste en dos carritos eléctricos de golf, que fueron modificados eléctrica, mecánica y electrónicamente para darle capacidades autónomas. Cada iCab se equipó con diferentes computadoras embebidas, sensores de percepción y unidades auxiliares, con la finalidad de transformarlos en vehículos autónomos. Además, se les han dado capacidad de comunicación multimodal (V2X), se les han aplicado tres capas de control, incorporando una arquitectura de cooperación para operación en modo tren, diferentes esquemas de localización, mapeado, percepción y planificación de rutas. Innumerables experimentos han sido realizados para validar cada uno de los diferentes sistemas incorporados. Los resultados prueban la funcionalidad de esta plataforma para realizar conducción autónoma y cooperativa con mínima intervención humana. Programa Oficial de Doctorado en Ingeniería Eléctrica, Electrónica y Automática Presidente: Francisco Javier Otamendi Fernández de la Puebla.- Secretario: Hanno Hildmann.- Vocal: Pietro Cerri

Abstract

To enhance the efficiency and safety of today's road transport, the application of driver support systems and fully automated, intelligent transport systems becomes increasingly important. The safety and reliability requirements of these systems and their complexity are high, which results in a costly, time consuming development and testing process. This paper presents an intelligent vehicle hardware in the loop simulator for faster and more efficient development and testing of full-scale intelligent vehicle and transport systems. Its technical feasibility and added value are illustrated by applying the concept to a passenger car platooning experiment.

Abstract

Anticipating future situations from streaming sensor data is a key perception challenge for mobile robotics and automated vehicles. We address the problem of predicting the path of objects with multiple dynamic modes. The dynamics of such targets can be described by a Switching Linear Dynamical System (SLDS). However, predictions from this probabilistic model cannot anticipate when a change in dynamic mode will occur. We propose to extract various types of cues with computer vision to provide context on the target’s behavior, and incorporate these in a Dynamic Bayesian Network (DBN). The DBN extends the SLDS by conditioning the mode transition probabilities on additional context states. We describe efficient online inference in this DBN for probabilistic path prediction, accounting for uncertainty in both measurements and target behavior. Our approach is illustrated on two scenarios in the Intelligent Vehicles domain concerning pedestrians and cyclists, so-called Vulnerable Road Users (VRUs). Here, context cues include the static environment of the VRU, its dynamic environment, and its observed actions. Experiments using stereo vision data from a moving vehicle demonstrate that the proposed approach results in more accurate path prediction than SLDS at the relevant short time horizon (1 s). It slightly outperforms a computationally more demanding state-of-the-art method. Document type: Article

Abstract

International audience; Reliable obstacle detection and localization is a key issue for driver assistance systems, particularly in urban environments. In this study a multi-modal perception approach is investigated, the objective being to enhance vehicle localization and dynamic object tracking in a world-centric map. A 3D ego-localization is achieved by merging information from a stereo vision system and data obtained from vehicle sensors. Mobile objects are detected using a multi-layer lidar that is also used to identify a constrained search space within the multiple target tracking process. Object localization and tracking is then performed in the fixed frame, which facilitates analysis and understanding of the scene. Experimental results using real world data are performed to evaluate the performance of the multi-modal system, and these are presented to show the effectiveness of the approach.

Abstract

ording to the "i"United Nations"/i", 70% of the world’s population will live in cities by 2050. This growth will be reflected in the demand for better services that should be adjusted to the collective and individual needs of the population. Governments and organizations are working on defining and implementing strategies that will enable them to respond to these challenges. The main challenges are related to transport and its management, considering transportation as a core issue in the economy, sustainability, and development of the regions. In this way, the Intelligent Transportation Systems (ITS) play a key role in the response to these scenarios, being that they are the framework where the new hardware and software tools are integrated, allowing an efficient development of transportation systems management, attending to aspects such as: traffic management, communications between vehicles and infrastructures, and security, among others. Nevertheless, the concept of ITS evolves rapidly so it is necessary to understand its evolution. To do that, the current research develops a thematic analysis of ITS in literature, evaluating the intellectual structure and its evolution using "i"SciMAT"/i", quantifying the main bibliometric performance indicators, and identifying the main research areas, authors, journals, and countries. To this purpose, the publications related to ITS from 1993 to 2019 available in the "i"Web of Science (WoS) Core Collection"/i" were retrieved (7649 publications) and analyzed. Finally, one of the main results is the latest research themes map of ITS, considering its intellectual structure, evolution, and relationship. It assists in the definition and implementation of strategies, the identification of the scientific, academic, and business opportunities, and future research lines to consolidate the role of ITS in the new city models. Document type: Article

Abstract

Nowadays, intelligent systems applied to vehicles have grown very rapidly; their goal is not only the improvement of safety, but also making autonomous driving possible. Many of these intelligent systems are based on making use of computer vision in order to know the environment and act accordingly. It is of great importance to be able to estimate the pose of the vision system because the measurement matching between the perception system (pixels) and the vehicle environment (meters) depends on the relative position between the perception system and the environment. A new method of camera pose estimation for stereo systems is presented in this paper, whose main contribution regarding the state of the art on the subject is the estimation of the pitch angle without being affected by the roll angle. The validation of the self-calibration method is accomplished by comparing it with relevant methods of camera pose estimation, where a synthetic sequence is used in order to measure the continuous error with a ground truth. This validation is enriched by the experimental results of the method in real traffic environments. This work was supported by the Spanish Government through the CICYTprojects (TRA2013-48314-C3-1-R and TRA2015-63708-R) and Comunidad de Madrid through SEGVAUTO-TRIES (S2013/MIT-2713). Publicado Document type: Article

Abstract

This paper investigates the trajectory generation problem for an advanced driver assistance system that could sense the driving state of the vehicle, so that a collision free trajectory can be generated safely. Specifically, the problem of trajectory generation is solved for the safety assessment of the driving state and to manipulate the vehicle in order to avoid any possible collisions. The vehicle senses the environment so as to obtain information about other vehicles and static obstacles ahead. Vehicles may share the perception of the environment via an inter-vehicle communication system. The planning algorithm is based on a visibility graph. A lateral repulsive potential is applied to adaptively maintain a trade-off between the trajectory length and vehicle clearance, which is the greatest problem associated with visibility graphs. As opposed to adaptive roadmap approaches, the algorithm exploits the structured nature of the environment for construction of the roadmap. Furthermore, the mostly organized nature of traffic systems is exploited to obtain orientation invariance, which is another limitation of both visibility graphs and adaptive roadmaps. Simulation results show that the algorithm can successfully solve the problem for a variety of commonly found scenarios. Document type: Article