A model for integrating dialogue and the execution of joint plans (original) (raw)
Towards the implementation of multiagent planning dialogues
Abstract—To support coalition teams, we are investigating the use of software agents that can help in planning team activities, thus reducing the cognitive burden on team members. Since the timely delivery of information can be crucial to team performance, we are especially interested in creating plans than explicitly include communications between team members. In previous work we developed a formal model of planning and communication that can support the creation of such plans.
Integrating Multiagent Dialogues, Planning and Plan Execution
2010
Abstract Coming up with a plan for a team that operates in a nondeterministic environment is a complex process, and the problem is further complicated by the need for team members to communicate during the process of planning and the execution of plans. Dialogues can be used to coordinate both the planning process and the plan execution.
Agent-based dialogues to support plan execution by human teams
2008
Abstract—Analysis of communications in human teams sug-gests that an important form of communication between team members is an “information providing” dialogue, in which team members update their fellows with information that they regard as important to the task at hand. In this paper we introduce and analyse a formal model of such a form of dialogue, seeing this as a necessary first step in providing software support for this kind of communication.
A Planner for Plan Construction Dialogues for Multi Agent Plans
2004
A natural language dialogue planner is described that chooses dialogue moves to revise the beliefs of an agent. In particular those beliefs that refer to the mental state of another agent are revised. In a planning problem of repeated decisions, the future decision of the other agent is better predicted, and therefore the immediate plan decision of the first agent is a better one.
Deliberation Dialogues during Multi-agent Planning
Lecture Notes in Computer Science, 2011
Cooperation in multi-agent systems essentially hinges on appropriate communication. This paper shows how to model communication in teamwork within TeamLog, the first multi-modal framework wholly capturing a methodology for working together. Starting from the dialogue theory of Walton and Krabbe, the paper focuses on deliberation, the main type of dialogue during team planning. We provide a schema of deliberation dialogue along with semantics of adequate speech acts, this way filling the gap in logical modeling of communication during planning.
An efficient algorithm for multiagent plan coordination
2005
The multiagent plan coordination problem arises whenever multiple agents plan to achieve their individual goals independently, but might mutually benefit by coordinating their plans to avoid working at cross purposes or duplicating effort. Although variations of this problem have been studied in the literature, there is as yet no agreement over a general characterization of the problem. In this paper, we describe a general framework that extends the partialorder, causal-link plan representation to the multiagent case, and that treats coordination as a form of iterative repair of plan flaws that cross agents. We show, analytically and empirically, that this algorithmic formulation can scale to the multiagent case better than can a straightforward application of the most advanced single-agent plan coordination technique, highlighting fundamental differences between single-agent and multiagent planning.
An initial assessment of plan-recognition-based coordination for multi-agent teams
… of the Second International Conference on Multi- …, 1996
Plan recognition remains a largely unexplored paradigm for facilitating coordination. In this paper, we begin to explore domain, task, and agent characteristics which impact upon the utility of using plan recognition for coordinating multiple agents and, in particular, collections of agents organized into competing teams. Agents in our research are supplied plan-recognition capabilities in the form of specially instantiated belief networks called Plan Recognition Networks (PRNs). Our initial experiments test several hypotheses concerning coordination performance as a factor of plan-recognition model expressiveness compared to coordination based upon using communication protocols of varying expressiveness. The initial results demonstrate that plan-recognition capabilities permit agents to realize better coordination performance in many situations due to increased knowledge provided through observation and inference compared to that supplied by communication protocols.
A framework for multi-agent planning
Proceedings of the AgentLink Workshop on Practical Reasoning Agents (FAPR-00)}, 2000
We introduce a computational framework, consisting of resources, skills, goals and services to represent the plans of individual agents and to develop models and algorithms for cooperation processes between a collection of agents. Keywords: Teamwork and cooperation, multiagent planning, distributed resource allocation.
2000
The process of cooperative problem solving can be divided into four stages. First, finding potential team members, then forming a team followed by constructing a plan for that team. Finally, the plan is executed by the team. Traditionally, very simple protocols like the Contract Net protocol are used for performing the first two stages of the process. And often the team is already taken for granted. In an open environment (like in e.g. electronic commerce) however, there can be discussion among the agents in order to form a team that can achieve the collective goal of solving the problem. For these cases fixed protocols like contract net do not suffice. In this paper we present an alternative solution, using structured dialogues that can be shown to lead to the required team formation. The dialogues are described formally (using some modal logics), thus making it possible to actually prove that a certain dialogue has a specific outcome.