Hermes: Designing Flexible and Robust Agent Interactions

Hermes: Designing Flexible and Robust Agent Interactions

Christopher Cheong (RMIT University, Melbourne, Australia) and Michael Winikoff (RMIT University, Melbourne, Australia and University of Otago, Dunedin, New Zealand)
DOI: 10.4018/978-1-60566-256-5.ch005
OnDemand PDF Download:
$37.50

Abstract

Although intelligent agents individually exhibit a number of characteristics, including social ability, flexibility, and robustness, which make them suitable to operate in complex, dynamic, and error-prone environments, these characteristics are not exhibited in multi-agent interactions. For instance, agent interactions are often not flexible or robust. This is due to the traditional message-centric design processes, notations, and methodologies currently used. To address this issue, we have developed Hermes, a goaloriented design methodology for agent interactions which is aimed at being pragmatic for practicing software engineers. Hermes focuses on interaction goals, i.e., goals of the interaction which the agents are attempting to achieve, and results in interactions that are more flexible and robust than messagecentric approaches. In this chapter, we present the design and implementation aspects of Hermes. This includes an explanation of the Hermes design processes, notations, and design artifacts, along with a detailed description of the implementation process which provides a mapping of design artifacts to goal-plan agent platforms, such as Jadex.
Chapter Preview
Top

Introduction

Our ever-evolving and technologically advanced world is a place that is complex, dynamic, and failure-prone. Intelligent agents are steadily accruing purchase as a technology which is intrinsically able to address the aforementioned real world issues (Jennings, 2001). Currently, intelligent agents are used in a range of real world applications spanning a number of different domains. These include telecommunication systems (Chaib-draa, 1995; Jennings 2001), process control (Sycara 1998; Jennings et al. 1998), air traffic control (Sycara, 1998), business process management (Jennings, 2001), logistics (Benfield et al., 2006), production scheduling (Munroe et al., 2006), and many more.

A key issue in developing and using agents is how to systematically analyse and design multi-agent systems. This issue has resulted in the development of the field of Agent Oriented Software Engineering. This field has seen the development of a number of methodologies which provide the developer with guidance, processes, and notations for the analysis and design of agent systems.

The systems in the previous examples all employ multiple agents as “there is no such thing as a single agent system” (Wooldridge, 2002). In such multi-agent systems, agent interactions are the crux of the matter, as the agents will need to interact in various ways in order to achieve their goals. Consequently, the design of agent interactions is a crucial part of a design methodology.

Current approaches to interaction design are message-centric as the design process is driven by messages that are exchanged during the interaction and is focused on the information passed within the messages. For example, in the Prometheus methodology (Padgham and Winikoff, 2004), as part of its interaction design process, the designers are advised to think about messages and alternatives. This is not restricted to Prometheus, but is also the norm in other methodologies such as Gaia (Zambonelli et al., 2004), MaSE (DeLoach et al., 2001) and Tropos (Bresciani et al., 2004).

Using current message-centric approaches to create interactions results in a number of problems. The main problem is that designs resulting from message-centric approaches tend to be overly, and sometimes unnecessarily, constrained. For example, using the interaction protocol of Figure 1, the interaction must begin with the Customer agent enquiring about the price of a laptop. It cannot, for example, enquire about the availability of a laptop first. Similarly, if a laptop is out of stock, the Vendor cannot proactively send a “Laptop Out of Stock” message to the Customer agent before or after replying with the price.

Figure 1.

Message-centric protocol example

This lack of flexibility and robustness in interactions is problematic for intelligent agents. By following such limited designs, key intelligent agent characteristics, such as autonomy and proactivity, are greatly subdued and the fundamental concept of goal-orientation is ignored. Thus, current approaches to interaction design are not congruent with the agent paradigm.

More abstractly, the problem with message-centric approaches results from the general design process where the designer begins by creating a desirable but rigid message sequence and then “loosens it”, i.e. improves flexibility and robustness by adding alternatives. The problem with this is that the “default” result is an interaction that has not been sufficiently “loosened”, and is more constrained than it needs to be. A number of alternative approaches for specifying agent interactions have been explored. These alternative approaches avoid overly restricting interactions by starting with completely unconstrained interactions and then adding constraints so that the protocols are restricted and lead only to desirable interactions.

Complete Chapter List

Search this Book:
Reset
Editorial Advisory Board
Table of Contents
Foreword
Liz Sonenberg
Preface
Virginia Dignum
Acknowledgment
Virginia Dignum
Chapter 1
Virgina Dignum
Agent Organization can be understood from two perspectives: organization as a process and organization as an entity. That is, organization is... Sample PDF
The Role of Organization in Agent Systems
$37.50
Chapter 2
Luciano R. Coutinho, Jaime S. Sichman, Olivier Boissier
In this chapter, we discuss the concepts of agent organization, organizational model, and review some existing organizational models. Before the... Sample PDF
Modelling Dimensions for Agent Organizations
$37.50
Chapter 3
Jacques Ferber, Tiberiu Stratulat, John Tranier
In this chapter, we stress the importance of thinking a MAS in all its aspects (agents, environment, interactions, organizations, and institutions)... Sample PDF
Towards an Integral Approach of Organizations in Multi-Agent Systems
$37.50
Chapter 4
Scott A. DeLoach
This chapter introduces a suite of technologies for building complex, adaptive systems. It is based in the multi-agent systems paradigm and uses the... Sample PDF
OMACS: A Framework for Adaptive, Complex Systems
$37.50
Chapter 5
Christopher Cheong, Michael Winikoff
Although intelligent agents individually exhibit a number of characteristics, including social ability, flexibility, and robustness, which make them... Sample PDF
Hermes: Designing Flexible and Robust Agent Interactions
$37.50
Chapter 6
Viara Popova, Alexei Sharpanskykh
This chapter introduces a formal framework for modeling and analysis of organizations. It allows representing and reasoning about all important... Sample PDF
A Formal Framework for Organization Modeling and Analysis
$37.50
Chapter 7
Maksim Tsvetovat
Agent-based approaches provide an invaluable tool for building decentralized, distributed architectures and tying together sets of disparate... Sample PDF
Describing Agent Societies: A Declarative Semantics
$37.50
Chapter 8
Davide Grossi, Frank Dignum
In this chapter we investigate how organizations can be represented as graphs endowed with formal semantics. We distinguish different dimensions of... Sample PDF
Structural Aspects of Organizations
$37.50
Chapter 9
Virgina Dignum, Frank Dignum
Organization concepts and models are increasingly being adopted for the design and specification of multi-agent systems. Agent organizations can be... Sample PDF
A Logic for Agent Organizations
$37.50
Chapter 10
Cristiano Castelfranchi
This chapter presents organizations as a macro-micro notion and device; they presuppose autonomous proactive entities (agents) playing the... Sample PDF
Grounding Organizations in the Minds of the Agents
$37.50
Chapter 11
Paolo Torroni, Pinar Yolum, Munindar P. Singh, Marco Alberti, Federico Chesani, Marco Gavanelli, Evelina Lamma, Paola Mello
Organizational models often rely on two assumptions: openness and heterogeneity. This is, for instance, the case with organizations consisting of... Sample PDF
Modelling Interactions via Commitments and Expectations
$37.50
Chapter 12
Gita Sukthankar, Katia Sycara, Joseph A. Giampapa, Christopher Burnett
This chapter discusses the problem of agent aiding of ad-hoc, decentralized human teams so as to improve team performance on time-stressed group... Sample PDF
Communications for Agent-Based Human Team Support
$37.50
Chapter 13
Bob van der Vecht, Frank Dignum, John-Jules Ch. Meyer
This chapter discusses how autonomous agents can adopt organizational rules into their reasoning process. Agents in an organization need to... Sample PDF
Autonomous Agents Adopting Organizational Rules
$37.50
Chapter 14
Nicoletta Fornara, Marco Colombetti
The specification of open interaction systems is widely recognized to be a crucial issue, which involves the problem of finding a standard way of... Sample PDF
Specifying Artificial Institutions in the Event Calculus
$37.50
Chapter 15
Francesco Viganò, Marco Colombetti
Institutions have been proposed to explicitly represent norms in open multi-agent systems, where agents may not follow them and which therefore... Sample PDF
Verifying Organizations Regulated by Institutions
$37.50
Chapter 16
Mehdi Dastani, Nick A.M. Tinnemeier, John-Jules Ch. Meyer
Multi-agent systems are viewed as consisting of individual agents whose behaviors are regulated by an organizational artifact. This chapter presents... Sample PDF
A Programming Language for Normative Multi-Agent Systems
$37.50
Chapter 17
Antônio Carlos da Rocha Costa, Graçaliz Pereira Dimuro
This chapter presents the Population-Organization model, a formal tool for studying the organization of open multi-agent systems and its functional... Sample PDF
A Minimal Dynamical MAS Organization Model
$37.50
Chapter 18
Shaheen Fatima, Michael Wooldridge
This chapter presents an adaptive organizational policy for multi-agent systems called TRACE. TRACE allows a collection of multi-agent organizations... Sample PDF
A Framework for Dynamic Agent Organizations
$37.50
Chapter 19
Alexander Artikis, Dimosthenis Kaponis, Jeremy Pitt
We have been developing a framework for executable specification of norm-governed multi-agent systems. In this framework, specification is a... Sample PDF
Dynamic Specifications for Norm-Governed Systems
$37.50
Chapter 20
Marco Lamieri, Diana Mangalagiu
In this chapter we present a model of organization aimed to understand the effect of formal and informal structures on the organization’s... Sample PDF
Interactions Between Formal and Informal Organizational Networks
$37.50
Chapter 21
Steven Okamoto, Katia Sycara, Paul Scerri
Intelligent software personal assistants are an active research area with the potential to revolutionize the way that human organizations operate... Sample PDF
Personal Assistants for Human Organizations
$37.50
Chapter 22
Sachin Kamboj, Keith S. Decker
This chapter presents an approach to organizational-self design (OSD), a method of designing organizations at run-time in which the agents are... Sample PDF
Organizational Self-Design in Worth-Oriented Domains
$37.50
Chapter 23
Olivier Bonnet-Torrès, Catherine Tessier
This chapter focuses on a Petri Net-based model for team organization and monitoring. The applications considered are missions performed by several... Sample PDF
A Formal Petri Net Based Model for Team Monitoring
$37.50
About the Contributors