PUMA
Istituto di Scienza e Tecnologie dell'Informazione     
Mambrini R., Cordiviola E., Magrini M., Martinelli M., Moroni D., Pieri G., Salvetti O. [Web and Automotive] shift into high gear on the Web - Intecs and ISTI-CNR position paper. In: W3C Web and Automotive Workshop (Rome, 1-15 November 2012). Abstract, article n. 28. W3C, 2012.
 
 
Abstract
(English)
Intecs is an italian large enterprise privately held that operates in the following domains: aerospace, defense, transportation, telecommunications. One of the most relevant activity for Intecs is the design and development of smart systems, based on the M2M paradigm, from the sensors to the application software passing through the communication middleware, applied to the automotive and mobility markets. Intecs is active both in industrial partnerships and in national and international R&D projects. Intecs is an ETSI (European Telecommunications Standards Institute) member, active in the ITS (Intelligent Transportation Systems) and M2M technical committes, is an AUTOSAR (AUTomotive Open Systems Architecture) premium member, a GENIVI member and also operates within the OneM2M.org. The Signals & Images Lab is a Research Laboratory of ISTI-CNR working in the fields of signal processing, image understanding and artificial vision. The Lab was born on the consideration that sensorial information is increasing its importance in both our daily life and the most advanced technological and scientific contexts. In particular, visual and audio information is becoming the most significant part of the global information to be processed, understood and manipulated. Nowadays, more than 35 people actively participate to the Lab, bringing together expertise ranging from computer science to mathematics, from physics to engineering. The general goal of the Lab is to increase the knowledge in the fields of signal processing, image understanding and artificial vision, in both theoretical and applicative contexts. This is achieved by studying and developing models, computer-based methods and machines for the formation, elaboration, analysis and recognition of images and signals, and by applying these methods and techniques to several sectors of the public and private society having strategic, scientific and technological interests. Carrying out these activities, the Lab has paid great attention to the development of semantic web technologies with the strong conviction that the web is the ideal platform for offering a rich range of benefits and smart services connected to the understanding of multimedia information. The Lab has participated to W3C activities including the Multimedia Semantics (MMSEM) Incubator Group. The Lab is currently involved in both Italian and European projects for infomobility and smart traffic management. The main focus is the design and development of innovative algorithms for real-time image understanding for the analysis of traffic flows and parking lot availability. The lab is interested in the possibility to integrate --thanks to the web-- real-time information derived from pervasive sensor nodes inside the car and scattered along roads and cities with traffic models for personalized services. Viewpoint: Transportation systems are evolving towards Intelligent Transportation Systems (ITS), where there is closed loop interaction between vehicles/drivers and the transportation infrastructure, as enabled by cooperative V2X communications and cellular networks. While some of the enabling technologies are entering their mature phase, e.g., traffic flow sensors and IEEE 802.11p, there is still the need of a complete integrated solution that can take the most benefits from a real-time analysis of the data gathered and appropriate reaction on the transportation system. This requires a higher level of intelligence to be integrated into the sensing and communication infrastructures, with decentralized aggregation and decision for robust and timely decisions to be taken. Finally, an additional and significant improvement can be brought by using tools that enable a pro-active decision making process, with the integration of predictive models running in real-time (even on board a car) alongside the reaction schemes. In this context, the web and HTML5 may be the most appropriate (and ready to be exploited) ingredients to perform such integration. The dependence on road transport in our daily lives has grown massively in recent years, in line with the problems arising from its use: permanent congestion on highways and urban centres, energy waste, CO2 emissions mass with consequent impact public health and high rates of accidents on the road networks. These challenges are even more pressing if we take into account the forecast growth in transport, as estimated by the Transport White Paper (March 2011) congestion costs will increase by about 50% by 2050. Therefore, the main objective derived from them is to ensure that the mobility and transport are: more efficient, safer and energetically sustainable. Given the magnitude of these challenges conventional approaches such as new road construction or expansion of existing ones, will not bring the desired results in due time. It is clear that innovative solutions are needed to achieve rapid advances imposed by the urgency of the needs identified. And that is where Intelligent Transportation Systems (ITS) should play the role in contributing to tangible results quickly and efficiently. Taking into account these considerations, we aim to address simultaneously the challenges raised and thus give a qualitative leap towards the future mobility. This raises the implementation of a platform to merge and integrate heterogeneous data sources into a common system and provide a set of advanced tools for control, monitoring, simulation and prediction of traffic, that achieves a more safe, sustainable and uncongested road. Today ITSs are very complex systems, made of several subsystems working in isolation to provide dedicated functions. Such subsystems are often closed, i.e. they do not provide interfaces for direct access to third parties, and vertical, i.e. they provide an end-to-end system from sensors/actuators to the human-machine interface (HMI) of the system. Therefore, the fusion of data provided by different sub-systems operating in the same area is very difficult in practice and is bound to become worse in the future as the ICT infrastructure in transportation systems become bigger and more complex. In this context, we believe that semantic web technologies may become an essential framework to foster interoperability and information sharing across different ITSs. Suggestions: Our vision is to make such interaction between heterogeneous data sources as seamless as possible, by providing a common layer for data distribution, and to leverage such opportunity to shift the intelligence for decision making from humans in control centres to machines distributed within the ICT infrastructure itself. This machine-to-machine (M2M) interaction between sensors (e.g., traffic flow) and actuators will be enabled with local scope, so as to keep it effective while being efficient and highly scalable. In such vision, the mobile phone may act as the hub connecting the world to the car and thus it might be able to: - Convey real time information from the outside to the car for personalized services, including better, safer and more efficient driving experience. For example, real-time traffic conditions gathered by external wireless sensor network (e.g. smart camera networks) may be exploited for context-aware driving - Share the context in which the car is moving with the environment, e.g. reporting actual travel time - Connect with the sensors on the car (eg fuel consumption) to provide personalized smart services (e.g. suggesting driving styles) by using an on-board decision support system Existing and emerging web technologies can give a strong push to the development of the above-mentioned functionalities.
URL: http://www.w3.org/2012/11/web-and-automotive/submissions/webautomotive1_submission_28.txt
Subject Intelligent transport systems
Traffic flow sensors
Cooperative sensing
M2M communications
I.4.7 Feature Measurement
I.4.8 Scene Analysis
J.m Computer Applications. MISCELLANEOUS


Icona documento 1) Download Document PDF


Icona documento Open access Icona documento Restricted Icona documento Private

 


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional