José G. Zato

Environment perception based on lidar sensors for real road applications

The recent developments in applications that have been designed to increase road safety require reliable and trustworthy sensors. Keeping this in mind, the most up-to-date research in the field of automotive technologies has shown that LIDARs are a very reliable sensor family. In this paper, a new approach to road obstacle classification is proposed and tested. Two different LIDAR sensors are compared by focusing on their main characteristics with respect to road applications. The viability of these sensors in real applications has been tested, where the results of this analysis are presented.

GPS and Inertial Systems for High Precision Positioning on Motorways

The accurate location of a vehicle in the road is one of the most important challenges in the automotive field. The need for accurate positioning affects several in-vehicle systems like navigators, lane departure warning systems, collision warning and other related sectors such as digital cartography suppliers. The aim of this paper is to evaluate high precision positioning systems that are able to supply an on-the-centimetre accuracy source to develop on-the-lane positioning systems and to be used in future applications as an information source for autonomous vehicles that circulate at high speeds on public roads. In this paper we have performed some on-road experiments, testing several GPS-based systems: Autonomous GPS; RTK Differential GPS with a proprietary GPS base station; RTK Differential GPS connected to the public GPS base station network of the National Geographic Institute of Spain via vehicle-to-infrastructure GPRS communications; and GPS combination with inertial measurement systems (INS) for position accuracy maintenance in degraded satellite signal reception areas. In these tests we show the validity and the comparison of these positioning systems, allowing us to navigate, in some cases, on public roads at speeds near 120 km/h and up to 100 km from the start position without any significant accuracy reduction.

Floating Car Data Augmentation Based on Infrastructure Sensors and Neural Networks

The development of new-generation intelligent vehicle technologies will lead to a better level of road safety and CO2 emission reductions. However, the weak point of all these systems is their need for comprehensive and reliable data. For traffic data acquisition, two sources are currently available: (1) infrastructure sensors and (2) floating vehicles. The former consists of a set of fixed point detectors installed in the roads, and the latter consists of the use of mobile probe vehicles as mobile sensors. However, both systems still have some deficiencies. The infrastructure sensors retrieve information from static points of the road, which are spaced, in some cases, kilometers apart. This means that the picture of the actual traffic situation is not a real one. This deficiency is corrected by floating cars, which retrieve dynamic information on the traffic situation. Unfortunately, the number of floating data vehicles currently available is too small and insufficient to give a complete picture of the road traffic. In this paper, we present a floating car data (FCD) augmentation system that combines information from floating data vehicles and infrastructure sensors, and that, by using neural networks, is capable of incrementing the amount of FCD with virtual information. This system has been implemented and tested on actual roads, and the results show little difference between the data supplied by the floating vehicles and the virtual vehicles.

Low Level Control Layer Definition for Autonomous Vehicles Based on Fuzzy Logic

Abstract The intelligent control of autonomous vehicles is one of the most important challenges that intelligent transport systems face today. The application of artificial intelligence techniques to the automatic management of vehicle actuators enables the different Advanced Driver Assistance Systems (ADAS) or even autonomous driving systems, to perform a low level management in a very similar way to that of human drivers by improving safety and comfort. In this paper, we present a control schema to manage these low level vehicle actuators (steering throttle and brake) based on fuzzy logic, an artificial intelligence technique that is able to mimic human procedural behavior, in this case, when performing the driving task. This automatic low level control system has been defined, implemented and tested in a Citroen C3 testbed vehicle, whose actuators have been automated and can receive control signals from an onboard computer where the soft computing-based control system is running.

Evaluation of V2V and V2I mesh prototypes based on a wireless sensor network

Wireless vehicular communications have been identified as one of the most important Intelligent Transportation System technologies to be developed in the coming years, from a safety as well as an energy efficiency point of view. Several standards definitions, hardware developments, research projects, use cases definitions and field operational tests are currently under deployment in order to accelerate the market availability of this technology. Nevertheless, though the possible applications of vehicular communications are defined, there is a lack of availability of completely functional communication technology to support these applications. Issues like the adaptation of communication technologies to run in a massive high speed mobile environment, the behaviour of Vehicle Ad-hoc Networks (VANET) in multihop mesh mode or routing algorithms for reliable V2V and V2I data transmission are currently open research areas. In this paper we present an evaluation of V2V and V2I prototypes based on wireless sensor mesh networks, tested in real vehicles with real communication hardware. This paper opens up a frame to solve some of the present deficiencies of vehicular communications and enable the possibility of testing safety applications in real VANET situations.

Laser Scanner Como Sistema de Detección de Entornos Viales

Road security applications are getting more complex thanks to the latest advances. These applications require sensors able to provide information to perform complex and demanding tasks. Laser Scanners sensors have proved to be a trustable sensor family. This reliability has lead to increase the research activities related to laser scanners usability in road applications. Every day is more frequent to find Advance Driver Assistant Systems (ADAS) that takes advantage of the characteristics of these devices. These systems performs different task, some of them related to detection and prediction of movements of obstacles in the surroundings of a vehicle. Present work studies the possibility of using two different sensors in road applications. The second part of the work focuses on the presentation of a new algorithm able to detect moving obstacles in the surrounding of a vehicle using scanner laser.

GeoNetworking based V2V Mesh Communications over WSN

An intensive effort is presently carried out in order to research and develop vehicular communication systems. Several standards, prototypes and field operational tests are under deployment all around the world, involving multiple research centers and vehicle and electronics manufacturers. However, some research lines are open today, in which vehicular communication systems with guaranteed reliability and robustness are necessary. One of these challenges is the development of an effective GeoNetworking in vehicular communications. This concept means that the vehicle ad-hoc network (VANET) bases the data package transmission in the topographical location of the different nodes (vehicles) of the network, organizing the data flow in an optimal way that covers the surroundings of each vehicle. The core of this GeoNetworking system is the GeoRouting algorithm, that supports the optimal routing of the data packages and reorganizes the network structure in function of the positions of the nodes. In this paper we present a novel GeoRouting algorithm, based in the evolution of previous results of mesh vehicular networks. This algorithm has been designed, implemented and tested in real vehicles in real roads with free flow traffic. The results suggest that the features of the designed routing algorithm can be applied as core of any kind of vehicular network to support ADAS applications.

Highway test of V2V mesh communications over WSN

Wireless vehicular communications are one of the most important technologies in the ITS field to improve the transport safety as well efficiency impact. Several standards definitions, hardware developments, research projects, use cases definitions and field operational tests are currently under deployment in order to accelerate the market availability of this technology. Nevertheless, though the possible applications of vehicular communications are defined, there is a lack of availability of completely functional communication technology to support these applications. In this paper we present the results of a V2V communications field operational test using Wireless Sensor Networks (WSN) as nodes of the VANET and three vehicles that circulate on public highways in free flow traffic situations. These results show that this communications technology is able to support continuous mesh data transmission with enough features of efficiency and reliability to be used as main data source in a big set of advanced driver assistance systems (ADAS).

Vehicular GeoNetworking based communications to support cooperative safety systems

En la actualidad, se esta llevando a cabo una intensa labor con el fin de investigar y desarrollar sistemas de comunicaciones vehiculares, que serviran de soporte a los denominados sistemas de seguridad cooperativos. Varias normas, prototipos y pruebas operativas sobre el terreno estan en proceso de desarrollo en todo el mundo, implicando tanto a centros de investigacion como a fabricantes de vehiculos y de electronica. Sin embargo, algunas lineas de investigacion aun estan abiertas hoy en dia, fundamentalmente en el ambito de garantizar comunicaciones vehiculares con la suficiente calidad en cuanto a fiabilidad y robustez para dar ser vicio a aplicaciones de asistencia y seguridad en la conduccion. Uno de estos retos es el desarrollo de soporte de comunicaciones basadas en topologia fisica de los nodos o GeoNetworking. Este concepto significa que la red ad-hoc vehicular (VANET) basa la transmision de los paquetes de datos en la localizacion topografica de los diferentes nodos (vehiculos) de la red, organizando el flujo de datos de una manera optima que cubra los alrededores de cada vehiculo. El nucleo de este sistema GeoNetworking es el algoritmo GeoRouting, que soporta el encaminamiento optimo de los paquetes de datos y reorganiza la estructura de la red en funcion de las posiciones de los nodos. En esta ponencia se presenta un nuevo algoritmo GeoRouting, basado en la evolucion de los resultados anteriores de redes vehiculares malla. Este algoritmo se ha disenado, implementado y probado en vehiculos reales en carreteras reales con flujo de trafico libre. Los resultados sugieren que las caracteristicas del algoritmo de enrutamiento disenado se pueden aplicar como nucleo de cualquier tipo de red vehicular para soportar aplicaciones de asistencia a la conduccion basadas en sistemas de seguridad cooperativos.

Comunicaciones vehiculares georreferenciadas como soporte a sistemas de seguridad cooperativos

En la actualidad, se esta llevando a cabo una intensa labor con el fin de investigar y desarrollar sistemas de comunicaciones vehiculares, que serviran de soporte a los denominados sistemas de seguridad cooperativos. Varias normas, prototipos y pruebas operativas sobre el terreno estan en proceso de desarrollo en todo el mundo, implicando tanto a centros de investigacion como a fabricantes de vehiculos y de electronica. Sin embargo, algunas lineas de investigacion aun estan abiertas hoy en dia, fundamentalmente en el ambito de garantizar comunicaciones vehiculares con la suficiente calidad en cuanto a fiabilidad y robustez para dar ser vicio a aplicaciones de asistencia y seguridad en la conduccion. Uno de estos retos es el desarrollo de soporte de comunicaciones basadas en topologia fisica de los nodos o GeoNetworking. Este concepto significa que la red ad-hoc vehicular (VANET) basa la transmision de los paquetes de datos en la localizacion topografica de los diferentes nodos (vehiculos) de la red, organizando el flujo de datos de una manera optima que cubra los alrededores de cada vehiculo. El nucleo de este sistema GeoNetworking es el algoritmo GeoRouting, que soporta el encaminamiento optimo de los paquetes de datos y reorganiza la estructura de la red en funcion de las posiciones de los nodos. En esta ponencia se presenta un nuevo algoritmo GeoRouting, basado en la evolucion de los resultados anteriores de redes vehiculares malla. Este algoritmo se ha disenado, implementado y probado en vehiculos reales en carreteras reales con flujo de trafico libre. Los resultados sugieren que las caracteristicas del algoritmo de enrutamiento disenado se pueden aplicar como nucleo de cualquier tipo de red vehicular para soportar aplicaciones de asistencia a la conduccion basadas en sistemas de seguridad cooperativos.