An Adjustable Autonomy Agent for Intelligent Environments

There are many arguments for and against the use of autonomous-agents in ambient intelligence and intelligent environments. Some researchers maintain that it is vital to restrict autonomy of agents so that users have complete control over the system; whereas, many others maintain that there is a greater benefit to be gained by employing autonomous-agents to take some of the work load off the user and increase user convenience. Both of these approaches have their distinct advantages but they are not suitable for all since people’s opinions and concerns regarding autonomy are highly individual and can differ greatly from person to person. This work explores how it is possible to make intelligent environments more dynamic and personalisable by equipping them with adjustable autonomy, which allows the user to increase or decrease agent autonomy in order to find a comfortable sweet-spot between relinquishing/maintaining control and gaining/losing convenience. This chapter discusses how adjustable autonomy can be achieved in intelligent environments, reports on a recent online survey conducted to gauge people’s opinions of different levels of in intelligent environments, and discusses a user study for which an experimental adjustable autonomy enabled intelligent environment was developed. This work aims to raise awareness of the issues with using static (and extreme) levels of autonomy amongst researchers of intelligent environments and ambient intelligent environments.

2013

Agent-based systems have long been recognized as a candidate technology for delivering autonomous and autonomic behaviors; however it is only recently that their usage has been explored in a new, emerging generation of systems that involve embedding agents on computationally challenged devices. The prudent harnessing of such agents can offer software engineers additional tools in their efforts to construct and deploy innovative mobile services or to realize practical smart environments. However, documented results of comprehensive evaluations of mobile services conducted in real world environments are rare; evaluations of systems that harness the agent paradigm are almost non-existent. This paper seeks to remedy this deficiency. It is hoped that the results of this study will encourage researchers to reflect further on the potential and implications of harnessing the intelligent agent paradigm in the broad Ambient Intelligence domain, from a software engineering perspective, and as an enabler of intelligent interaction.

IEEE Expert / IEEE Intelligent Systems, 2004

The Essex intelligent dormitory, iDorm, uses embedded agents to create an ambient-intelligence environment. In a five-and-a-half-day experiment, a user occupied the iDorm, testing its ability to learn user behavior and adapt to user needs. The embedded agent discreetly controls the iDorm according to user preferences. Our work focuses on developing learning and adaptation techniques for embedded agents. We seek to provide online, lifelong, personalized learning of anticipatory adaptive control to realize the ambient-intelligence vision in ubiquitous-computing environments. We developed the Essex intelligent dormitory, or iDorm, as a test bed for this work and an exemplar of this approach.

Intelligent …

Various approaches to the configuration and control of intelligent environments have been researched in the past. The majority of these however, make use of either exclusively autonomous or exclusively end-user driven techniques which, in certain situations, may be an issue. A number of users may be reluctant to allow an autonomous system to monitor and interpret every action they take while, on the other hand, some users may be unable or unwilling to program and configure such a complex (end-user driven) system alone. This work-inprogress paper outlines our preliminary work aimed at exploring a solution to this issue by investigating the possibility of creating a hybrid autonomous-agent/enduser driven system that enables the user to set the level of autonomy for any given part of an intelligent environment. The principle contributions of this paper are to expose the issues regarding intelligent environment management systems, to give a comprehensive review of related work on adjustable autonomy and to present a conceptual model and an autonomy metric that can be used as a foundation of future research into developing hybrid autonomous-agent/end-user driven systems. This work forms part of an ongoing three year research project, funded by BT, that seeks to understand and address user concerns with the aim of equipping intelligent environments with better management systems and, furthermore, making intelligent environments more commercially deployable. Given the ongoing nature of this work, we propose to report any significant progress of this research at subsequent IE conferences until this work is complete.

2011

There is a long-standing debate over the role that intelligent agents should play and how much autonomy they should be given in user-centric systems such as intelligent environments and other pervasive computing technologies. A recent online survey has been conducted to assess people's opinions of the use of autonomy in intelligent environments. In order to conduct this survey, an animated video was created to explain the necessary concepts of intelligent environments to the survey participants. This short paper gives an overview of the online survey and discusses the explanation video.

2012

There are many arguments for and against the use of autonomous-agents in intelligent environments. Some researchers maintain that it is of utmost importance to give complete control to users, and hence greatly restrict autonomy of agents; whereas, others believe that is it preferable to increase user convenience by allowing agents to operate autonomously on the user's behalf. While both of these approaches have their distinct merits, they are not suitable for all users. As people's opinions and concerns regarding agent autonomy are highly individual, depending on a wide range of factors and often changing over time, a much more dynamic approach to agent autonomy is needed. This work explores how it is possible to equip intelligent environments with an adjustable autonomy mechanism, which allows an individual user to increase or decrease agent autonomy in order to find their own comfortable sweet-spot between maintaining/relinquishing control and gaining/losing convenience. This paper presents the Adjustable Autonomy Intelligent Environment (AAIE) model, discusses how adjustable autonomy can be achieved in intelligent environments, and discusses the major findings from a recent online survey and user study, which highlight the major factors and concerns of users that determine their personal preferences towards different levels of autonomy.

Computación Y Sistemas, 2006

The idea of ubiquitous computing (ubicomp) is an environment dominated by computing and communication devices of different scales which are seamlessly integrated to the users activities. The features of ubiquitous computing environments require developers to face important challenges in dealing with the complexities associated to the development of ubiquitous computing systems. This thesis describes a middleware to facilitate developers to manage some of the complexities associated with the development of ubiquitous computing systems by means of the use of autonomous agents, which enable ubiquitous computing technology to respond to users' particular conditions and demands. Autonomous agents were used to implement the desirable features of ubiquitous computing systems and for enhancing the interactions of the users with the environment. The contributions of this thesis focus on presenting the functional requirements of autonomous agents for implementing ubiquitous computing systems and the agent SALSA middleware, which was created with the aim of facilitating the implementation and evolution of ubicomp systems. Finally, this thesis provides evidence of the SALSA flexibility for enabling the progressive development of ubicomp systems.

Atlantis Ambient and Pervasive Intelligence, 2010

Ubiquitous computing names the third wave in computing, where the personal computing era appears when technology recedes into the background of our lives. The widespread use of new mobile technology implementing wireless communications such as personal digital assistants (PDAs) and smart phones enables a new type of advanced applications. In the past years, the main focus of research in mobile services has aimed at the anytime-anywhere principle (ubiquitous computing). However, there is more to it. The increasing demand for distributed problem solving led to the development of multi-agent systems. The latter are formed from a collection of independent software entities whose collective skills can be applied in complex and real-time domains. The target of such systems is to demonstrate how goal directed, robust and optimal behavior can arise from interactions between individual autonomous intelligent software agents. These software entities exhibit characteristics like autonomy, responsiveness, pro-activeness and social ability. Their functionality and effectiveness has proven to be highly depended on the design and development and the application domain. In fact, in several cases, the design and development of effective services should take into account the characteristics of the context from which a service is requested. Context is the set of suitable environmental states and settings concerning a user, which are relevant for a situation sensitive application in the process of adapting the services and information offered to the user. Agent technology seems to be the right technology to offer the possibility of exploring the dynamic context of the user in order to provide added-value services or to execute more and complex tasks. In this respect, agent-based ubiquitous computing can benefit from marrying the agent-based technology for the extensive usage of distributed functionality, to be deployed for lightweight devices and enable to combine ubiquity and intelligence in different application areas and challenge with questions the research communities in computer science, artificial intelligence and engineering. We noticed during the AAMAS workshop we organized about this issue in 2007 that, although a number of other books on ubiquitous computing have been published in the last years, none of these has focused on the agent-based perspective. So we opened a call for chapters to gather input and feedback concerning the above challenges, through the collection of the high-quality contributions that reflect and advance the state-of-the art in agent-based ubiquitous application systems. It brought together researchers, agent-based vii viii Agent-Based Ubiquitous Computing software developers, users and practitioners involved in the area of agent-based ubiquitous systems, coming from many disciplines, with the target to discuss the different fundamental principles for construction and design of agents for specific applications, how they cooperate and communicate, what tasks can be set and how different properties like coordination and communication have been implemented, and which are the different problems they had to cope with. Existing perspectives of ubiquitous agents within different application domains have been welcome, as well as the different mechanisms for design and cooperation that can be used within different agent building environments. Specifically, the book focused on the different disciplines contributing to the design, cooperation, coordination and implementation problems of ubiquitous computing applications and how these can be solved through the utilization of agents. Thanks are due to all contributors and referees for their kind cooperation and enthusiasm, and to Zeger Karssen (Editorial Atlantis Press) for his kind advice and help to publish this volume.

2015 International Conference on Pervasive and Embedded Computing and Communication Systems (PECCS), 2015

This paper describes the architecture and functionality of a generic agent that is in charge of handling a given environment in an Ambient Intelligence context, ensuring suitable contextualized and personalized support to the user's actions, adaptivity to the user's peculiarities and to changes over time, and automated management of the environment itself. The architecture is implemented in a multi-agent system, where different types of agents are endowed with different levels of reasoning and learning capabilities. In addition to controlling normal operations of the environment, the system may identify user's needs and goals and activate suitable workflows to satisfy them. Some actions in these workflow involve the execution of semantic services. When a single service is not available for fulfilling a given need, an automatic service composer is used to obtain a suitable combination of services. The architecture has been implemented in a prototypical agent-based system ...

2008

Abstract The pervasive computing scenario provides a diffused presence of technological appliances distributed in the environment and interacting by means of wired or wireless networks. These computational units should be able to fruitfully exploit interactions with other components (eg information sources) in order to supply context aware services and support advanced forms of interaction among users.