Ambient Intelligence Environments (Artificial Intelligence)

INTRODUCTION

The trend in the direction of hardware cost reduction and miniaturization allows including computing devices in several objects and environments (embedded systems). Ambient Intelligence (AmI) deals with a new world where computing devices are spread everywhere (ubiquity), allowing the human being to interact in physical world environments in an intelligent and unobtrusive way. These environments should be aware of the needs of people, customizing requirements and forecasting behaviours.

AmI environments may be so diverse, such as homes, offices, meeting rooms, schools, hospitals, control centers, transports, touristic attractions, stores, sport installations, and music devices.

Ambient Intelligence involves many different disciplines, like automation (sensors, control, and actuators), human-machine interaction and computer graphics, communication, ubiquitous computing, embedded systems, and, obviously, Artificial Intelligence. In the aims of Artificial Intelligence, research envisages to include more intelligence in the AmI environments, allowing a better support to the human being and the access to the essential knowledge to make better decisions when interacting with these environments.

BACKGROUND

Ambient Intelligence (AmI) is a concept developed by the European Commission’s IST Advisory Group ISTAG (ISTAG, 2001) (ISTAG, 2002). ISTAG believes that it is necessary to take a holistic view of Ambient Intelligence, considering not just the technology, but the whole of the innovation supply-chain from science to end-user, and also the various features of the academic, industrial and administrative environment that facilitate or hinder realisation of the AmI vision (ISTAG, 2003). Due to the great amount of technologies involved in the Ambient Intelligence concept we may find several works that appeared even before the ISTAG vision pointing in the direction of Ambient Intelligence trends.


In what concerns Artificial Intelligence (AI), Ambient Intelligence is a new meaningful step in the evolution ofAI (Ramos, 2007).AI has closely walked side-by-side with the evolution of Computer Science and Engineering . The building ofthe first artificial neural models and hardware, with the Walter Pitts and Warren McCullock work (Pitts & McCullock, 1943) and Marvin Minsky and Dean Edmonds SNARC system correspond to the first step. Computer-based Intelligent Systems, like the MYCIN Expert System (Shortliffe, 1976) or network-based Intelligent Systems, like AUTHORIZER’s ASSISTANT (Rothi, 1990) used by American Express for authorizing transactions consulting several Data Bases are the kind of systems of the second step of AI. From the 80′s Intelligent Agents and Multi-Agent Systems have established the third step, leading more recently to Ontologies and Semantic Web. From hardware to the computer, from the computer to the local network, from the local network to the Internet, and from the Internet to the Web, Artificial Intelligence was on the state of the art of computing, most of times a little bit ahead of the technology limits.

Now the centre is no more in the hardware, or in the computer, or even in the network. Intelligence must be provided to our daily-used environments. We are aware of the push in the direction of Intelligent Homes, Intelligent Vehicles, Intelligent Transportation Systems, Intelligent Manufacturing Systems, even Intelligent Cities. This is the reason why Ambient Intelligence concept is so important nowadays (Ramos, 2007).

Ambient Intelligence is not possible without Artificial Intelligence. On the other hand, AI researchers must be aware of the need to integrate their techniques with other scientific communities’ techniques (e.g. Automation, Computer Graphics, Communications). Ambient Intelligence is a tremendous challenge, needing the better effort of different scientific communities.

There is a miscellaneous of concepts and technologies related withAmbient Intelligence. Ubiquitous Computing, Pervasive Computing, Embedded Systems, and Context Awareness are the most common. However these concepts are different from Ambient Intelligence.

The concept of Ubiquitous Computing (UbiComp) was introduced by Mark Weiser during his tenure as Chief Technologist of the Palo Alto Research Center (PARC) (Weiser, 1991). Ubiquitous Computing means that we have access to computing devices anywhere in an integrated and coherent way. Ubiquitous Computing was mainly driven by Communications and Computing devices scientific communities but now is involving other research areas. Ambient Intelligence differs from Ubiquitous Computing because sometimes the environment whereAmbient Intelligence is considered is simply local. Another difference is that Ambient Intelligence makes more emphasis on intelligence than Ubiquitous Computing. However, ubiquity is a real need today and Ambient Intelligence systems are considering this feature.

A concept that sometimes is seen as a synonymous of Ubiquitous Computing is Pervasive Computing. According to Teresa Dillon, Ubiquitous Computing is best considered as the underlying framework, the embedded systems, networks and displays which are invisible and everywhere, allowing us to ‘plug-and-play’ devices and tools, On the other hand, Pervasive Computing, is related with all the physical parts of our lives; mobile phone, hand-held computer or smart jacket (Dillon, 2006).

Embedded Systems mean that electronic and computing devices are embedded in current objects or goods. Today goods like cars are equipped with microprocessors; the same is true for washing machines, refrigerators, and toys. Embedded Systems community is more driven by electronics and automation scientific communities. Current efforts go in the direction to include electronic and computing devices in the most usual and simple objects we use, like furniture or mirrors. Ambient Intelligence differs from Embedded Systems since computing devices may be clearly visible in AmI scenarios. However, there is a clear trend to involve more embedded systems in Ambient Intelligence.

Context Awareness means that the system is aware of the current situation we are dealing with. An example is the automatic detection of the current situation in a Control Centre. Are we in presence of a normal situation or are we dealing with a critical situation, or even an emergency? In this Control Centre the intelligent alarm processor will exhibit different outputs according to the identified situation (Vale, Moura, Fernandes, Marques, Rosado, Ramos, 1997). Automobile Industry is also investing in Context Aware systems, like near-accident detection. Human-Computer Interaction scientific community is paying lots of attention to ContextAwareness. Context Awareness is one of the most desired concepts to include in Ambient Intelligence, the identification of the context is important for deciding to act in an intelligent way.

There are different views of the importance of other concepts and technologies in the Ambient Intelligence field. Usually these differences are derived from the basic scientific community of the authors. ISTAG see the technology research requirements from different points of view (Components, Integration, System, and User/Person). In (ISTAG, 2003) the following ambient components are mentioned: smart materials; MEMS and sensor technologies; embedded systems; ubiquitous communications; I/O device technology; adaptive software. In the same document ISTAG refers the following intelligence components: media management and handling; natural interaction; computational intelligence; context awareness; and emotional computing.

Recently Ambient Intelligence is receiving a significant attention from Artificial Intelligence Community. We may refer the Ambient Intelligence Workshops organized by Juan Augusto and Daniel Shapiro at ECAI’2006 (European Conference on Artificial Intelligence) and IJCAI’2007 (International Joint Conference on Artificial Intelligence) and the Special Issue on Ambient Intelligence, coordinated by Carlos Ramos, Juan Augusto and Daniel Shapiro to appear in the March/April’2008 issue of the IEEE Intelligent Systems magazine.

AMBIENT INTELLIGENT PROTOTYPES AND SYSTEMS

Here we will analyse some examples of Ambient Intelligence prototypes and systems, divided by the area of application.

AmI at Home

Domotics is a consolidated area of activity. After the first experiences using Domotics at homes there was a trend to refer the Intelligent Home concept. However, Domotics is too centred in the automation, giving to the user the capability to control the house devices from everywhere. We are still far from the real Ambient Intelligence in homes, at least at the commercial level. In (Wichert, Hellschimidt, 2006) there is an interesting example in the aims of EMBASSI project, by gesture a woman is commanding the TV to be brighter, however the TV is already at the brightest level, so the lights reduce the level and the windows close, showing an example of context awareness in the environment.

Several organizations are doing experiments to achieve the Intelligent Home concept. Some examples are HomeLab from Philips, MIT House_n, Georgia Tech Aware Home, Microsoft Concept Home, and e2 Home from Electrolux and Ericsson.

AmI in Vehicles and Transports

Since the first experiences with NAVLAB 1 (Thorpe, Herbert, Kanade, Shafer, 1988) Carnegie Mellon University has developed several prototypes for Autonomous Vehicle Driving and Assistance. The last one, NAVLAB 11, is an autonomous Jeep. Most of the car industry companies are doing research in the area of Intelligent Vehicles for several tasks like car parking assistance or pre-collision detection.

Another example of AmI application is related with Transports, namely in connection with Intelligent Transportation Systems (ITS). The ITS Joint Program of the US Department ofTransportation identified several areas of applications, namely: arterial management; freeway management; transit management; incident management; emergence management; electronic payment; traveller information; information management; crash prevention and safety; roadway operations and management; road weather management; commercial vehicle operations; and intermodal freight. In all these application areas Ambient Intelligence can be used.

AmI in Elderly and Health Care

Several studies point to the aging of population during the next decades. While being a good result of increasing of life expectation, this also implies some problems. The percentage of population with health problems will increase and it will be very difficult to Hospitals to maintain all patients. Our society is faced with the responsibility to care for these people in the best possible social and economical ways. So, there is a clear interest to create Ambient Intelligence devices and environments allowing the patients to be followed in their own homes or during their day-by-day life.

The medical control support devices may be embedded in clothes, like T-shirts, collecting vital-sign information from sensors (e. g. blood pressure, temperature). Patients will be monitored at long distance. The surrounding environment, for example the patient home, may be aware of the results from the clinical data and even perform emergency calls to order an ambulance service.

For instance, we may refer the IST Vivago® system (IST International Security Technology Oy, Helsinki, Finland), an active social alarm system, which combines intelligent social alarms with continuous remote monitoring of the user’s activity profile (Sarela, Korhonen, Lotjonen, Sola, Myllymaki, 2003).

AmI in Tourism and Cultural Heritage

Tourism and Cultural Heritage are good application areas for Ambient Intelligence. Tourism is a growing industry. In the past tourists were satisfied with pre-defined tours, equal for all the people. However there is a trend in the customization and the same tour can be conceived to adapt to tourists according their preferences.

Immersive tour post is an example of such experience (Park, Nam, Shi, Golub, Van Loan, 2006). MEGA is an user-friend virtual-guide to assist visitors in the ParcoArcheologico della Valle del Temple inAgrigento, an archaeological area with ancient Greek temples in Agrigento, located in Sicily, Italy (Pilato, Augello, Santangelo, Gentile, Gaglio, 2006). DALICA has been used for constructing and updating the user profile of visitors of Villa Adriana in Tivoli, near Rome, Italy (Constantini, Inverardi, Mostarda, Tocchio, Tsintza, 2007).

AmI at Work

The human being spends considerable time in working places like offices, meeting rooms, manufacturing plants, control centres.

SPARSE is a project initially created for helping Power Systems Control Centre Operators in the diagnosis and restoration of incidents (Vale, Moura, Fernandes, Marques, Rosado, Ramos, 1997). It is a good example of context awareness since the developed system is aware of the on-going situation, acting in different ways according the normal or critical situation of the power system. This system is evolving for an Ambient Intelligence framework applied to Control Centres.

Decision Making is one of the most important activities of the human being. Nowadays decisions imply to consider many different points of view, so decisions are commonly taken by formal or informal groups of persons. Groups exchange ideas or engage in a process of argumentation and counter-argumentation, negotiate, cooperate, collaborate or even discuss techniques and/or methodologies for problem solving. Group Decision Making is a social activity in which the discussion and results consider a combination of rational and emotional aspects. ArgEmotionAgents is a project in the area of the application of Ambient Intelligence in the group argumentation and decision support considering emotional aspects and running in the Laboratory of Ambient Intelligence for Decision Support (LAID), seen in Figure 1 (Marreiros, Santos, Ramos, Neves, Novais, Machado, Bulas-Cruz, 2007), a kind of an Intelligent Decision Room. This work has also a part involving ubiquity support.

AmI in Sports

Sports involve high-level athletes and many more practitioners. Many sports are done without any help of the associated devices, opening here a clear opportunity for Ambient Intelligence to create sports assistance devices and environments.

FlyMaster NAV+ is a free-flight on-board pilot Assistant (e.g. gliding, paragliding), using the FlyMaster F1 module with access to GPS and sensorial information. FlyMaster Avionics S.A., a spin-off, was created to commercialize these products (see figure 2).

AMBIENT INTELLIGENCE PLATFORMS

Some companies and academic institutions are investing in the creation of Ambient Intelligence generation platforms.

The Endeavour proj ect is developed by the California University in Berkeley (http://endeavour.cs.berkeley.edu/). The project aims to specify, design, and implement prototypes at a planet scale, self organized and involving an adaptive “Information Utility”.

Oxygen enables pervasive human centred computing through a combination of specific user and system technologies (http://www.oxygen.lcs.mit.edu/). This project provides speech and vision technologies enabling us to communicate with Oxygen as if we were interacting with another person, saving much time and effort (Rudolph, 2001).

The Portolano project was developed in the University of Washington and seeks to create a testbed for research into the emerging field of invisible computing (http://portolano.cs.washington.edu/). The invisible computing is possible with devices so highly optimized to particular tasks that they bend into the world and require little technical knowledge from the users (Esler, Hightower, Anderson, Borrielo, 1999).

The EasyLiving project of Microsoft Research Vision Group corresponds to a prototype architecture and associated technologies for building intelligent environments (Brumitt, Meyers, Krumm, Kern, Shafer, 2000). EasyLiving goal is to facilitate the interaction of people with other people, with computer, and with devices (http://research.microsoft.com/easyliving/).

Figure 1. Ambient Intelligence for decision support, LAID Laboratory

Ambient Intelligence for decision support, LAID Laboratory

Figure 2. FlyMaster Pilot Assistant device, from FlyMaster Avionics S.A.

FlyMaster Pilot Assistant device, from FlyMaster Avionics S.A.

FUTURE TRENDS

Ambient Intelligence deals with a futuristic notion for our lives. Most of the practical experiences concerning Ambient Intelligence are still in a very incipient phase, due to the recent existence of this concept. Today, it is not clear the separation between the computer and the environments. However, for new generations things will be more transparent, and environments with Ambient Intelligence will be more widely accepted.

In the area of transport, AmI will cover several aspects. The first will be related with the vehicle itself. Several performances start to be available, like the automatic identification ofthe situation (e.g. pre-collision identification, identification of the driver conditions). Other aspects will be related with the traffic information. Today, GPS devices are generalized, but they deal with static information. Joining on-line traffic conditions will enable the driver to avoid roads with accidents. Technology is giving good steps in the direction of automatic vehicle driving. But in the near future the developed systems will be seen more like driver assistants in spite of autonomous driving systems.

Another area where AmI will experience a strong development will be the area of Health Care, especially in the Elderly Care. Patients will receive this support to allow a more autonomous life in their homes. However automatic acquisition of vital signals (e.g. blood pressure, temperature) will allow to do automatic emergency calls when the patient health is in significant trouble. The person monitoring will also be done in his/her home, trying to detect differences in expected situations and habits.

The home support will achieve the normal personal and family life. Intelligent Homes will be a reality. The home residents will pay less attention to normal home management aspects, for example, how many bottles of red wine are available for the week meals or if the specific ingredients for a cake are all available.

AmI for job support are also expected. Decision Support Systems will be oriented to on-the-job environments. This will be clear in offices, meeting rooms, call centres, control centres, and plants.

CONCLUSION

This article presents the state of the art in which concerns Ambient Intelligence field. After the history of the concept, we established some related concepts definitions and illustrated with some examples. There is a long way to follow in order to achieve the Ambient Intelligence concept, however in the future, this concept will be referred as one of the landmarks in the Artificial Intelligence development.

TERMS AND DEFINITIONS

Ambient Intelligence: Ambient Intelligence (AmI) deals with a new world where computing devices are spread everywhere, allowing the human being to interact in physical world environments in an intelligent and unobtrusive way. These environments should be aware of the needs of people, customizing requirements and forecasting behaviours.

Context Awareness: Context Awareness means that the system is aware of the current situation we are dealing with.

Embedded Systems: Embedded Systems means that electronic and computing devices are embedded in current objects or goods.

Intelligent Decision Room: A decision-making space, eg a meeting room or a control center, equipped with intelligent devices and/or systems to support decision-making processes.

Intelligent Home: A home equipped with several electronic and interactive devices to help residents to manage conventional home decisions.

Intelligent Transportation Systems: Intelligent Systems applied to the area of Transports, namely to traffic and travelling issues.

Intelligent Vehicles: A vehicle equipped with sensors and decision support components.

Pervasive Computing: Pervasive Computing is related with all the physical parts of our lives, the user may have not notion of the computing devices and details related with these physical parts.

Ubiquitous Computing: Ubiquitous Computing means that we have access to computing devices anywhere in an integrated and coherent way.

Next post:

Previous post: