In this paper, we develop a proof procedure for multi-agent autoepistemic logic (MAEL) by translating it into a logic program with stable model semantics. We introduce a method that translates a MAEL theory in normal form into a logic program which includes integrity constrains, and prove some theorems that guarantee soundness and completeness of the translation. In fact, there is a one-to-one correspondence between MAEL extensions of a theory and stable models of a logic program which is translated from the theory. Our approach has the following advantages compared with the former ones whose decision procedures are based on tableaux and resolution technique: (1) We can get all extensions (all inference results) of a MAEL theory if we compute all stable models of the logic program. (2) We can fully use efficient techniques or systems for computing stable models of a logic program on the process of MAEL theorem proving. Furthermore, we investigate properties of inference on MAEL through this translation. The fact that the extension computing problem of MAEL can be reduced to a stable model computing problem of logic programs implies that there are close relationships between MAEL and other formalizations of nonmonotonic reasoning.
In this paper, we propose a framework for searching information through both the WWW and a human group. Though information retrieval using a searc engine in the WWW is very useful, we can not acquire local information owned by persons and not explicitly described in text. A user knows neither where target information is in the WWW nor who knows in a human group. Thus we integrate the information retrieval in the WWW with that in a human group, develop a heterogeneous information search system HERIS as a multi-agent system. We develop this framework as multi-agent system consisting of user agents and search engine agents, and use contract net protocol to communication among the agents. A user agent and a search engine agent are assigned to a user and a search engine. Each of the agents maintains a user profile and a search engine profile. When a user gives a query to a system, it selectively searches information resources consisting the WWW and user group. Finally a user acquires integrated results of a hit list from the WWW and a audio/video connection to a user who can answer the query. It was found through experimental evaluation that information retrieval using a human group as an information resource is valid and a search with HERIS has a different character from conventional search engines.
Conventional reinforcement learning has focused on learning in a stable environment. However, an agent may be given another environment which differs from the old environment. Thus, an autonomous agent needs a method to learn efficiently a new policy suited for the new environment. In this paper, we propose a method to adapt to a new environment for an agent which has a task to reach goals. When an agent is provided with a new environment, our method learns a new partial policy using the precondition of agent’s old policy. The precondition of a policy is a condition that says what must be satisfied in order to reach goals by using the policy. Similarly to learning the precondition of an action from the instances of action’s success or failure by using concept learning, our method learns the precondition of a policy from the instances of policy’s success or failure by using concept learning. We describe a method using inductive logic programming (ILP) as a concept learning method. Since ILP provides methods for learning relational knowledge that is not expressible in attribute-value learning, our method can use relational representation for the precondition. We applied our method to a blocks-world problem for evaluation. We have come to conclusion that our method is effective when the cost to carry out the task is high.
This paper addresses the problem of selecting a route to a given destination that traverses several non-specific sites (e.g. a bank, a gas station) as requested by a driver. The proposed solution uses a genetic algorithm that includes viral infection. The method is to generate two populations of viruses as domain specific knowledge in addition to a population of routes. A part of an arterial road is regarded as a main virus, and a road that includes a site is regarded as a site virus. An infection occurs between two points common to a candidate route and the virus, and involves the substitution of the intersections carried by the virus for those on the existing candidate route. Crossover and infection determine the easiest-to-drive and quasi-shortest route through the objective landmarks. Experiments using actual road maps show that this infection-based mechanism is an effective way of solving the problem. Our strategy is general, and can be effectively used in other optimization problems.
In this paper, we discuss a method to dynamically determine the generality of the target concept in a class hierarchy, when learning default rules, i.e., rules including exceptions with Inductive Logic Programming (ILP). The ILP system for default rules has to learn both the target concept and its opposite, if it is based on a three valued setting, in which we clearly discriminate among the three values: what is true, what is false, and what is unknown. Thus in order to learn rules which holds as generally as possible in a class hierarchy implicitly existing in given examples, we should give a higher priority to the concept which is more general, or covers more examples than does the other in the hierarchy. For this purpose, our method first finds out the general rule from a set of candidate rules independently of the concept it defines. Then the body of the rule can be viewed as the description defining the most general class in the hierarchy. Therefore, according to the ratio of positive examples it covers, we can determine which of the concepts, the target one or its opposite, is more general, and dynamically change the head of the rule to the negative literal if the latter concept is more general. In this paper, we formalize this method as a new ILP system, GREX, and discuss it with some examples.
This paper describes availability of personal Web-pages and a prototype development for Decision Support for Internet Users, called DSIU, which is an area of research for decision support by using information on the Internet. The availability of Web-pages concerns usage of formal pages, which are provided by companies and so on, and personal pages, which are provided by private persons. Web-pages are gathered by using an Internet search engine to determine destinations for travel and personal pages are confirmed to provide much subjective information than formal pages. The prototype development concerns a travel recommendation system, which is a kind of decision support systems. The prototype uses subjective and objective information on the Internet to select several destinations for users and to provide explanations the reason why the destinations are recommended. This paper also describes our perspective of DSIU researches.
We started working on Q, an interaction design language, which is to describe and experiment interaction among autonomous agents and humans. Unlike previous agent communication languages, Q is intended to design various interaction patterns without depending any internal models of agents. Unlike previous protocol description languages, Q cannot guarantee the correctness of protocols. We rather combine execution and planning layers to create robust behaviors of agents.
We have been developing Robotic Communication Terminals (RCT) as a mobility support system for the elderly and disabled people, which assists for their impaired elements of mobility— recognition, actuation, and information access. The RCT consist of three types of terminals: “environment-embedded terminal”“user-carried mobile terminal”, and “user-carrying mobile terminal”. These terminals communicate with one another to provide the users with a comfortable means of mobility. In this paper, we introduce the overview of our research. The recent progress is also presented as well as the future plan.
We address the problem of information flow in disaster relief scenarios by presenting an architecture for generating natural language dialogue between large numbers of agents. This architecture is the first step towards real-time support systems for relief workers and their controllers. Our work demonstrates how natural generation techniques from the MIKE commentary system for RoboCup soccer can be carried over to that of RoboCup Rescue. Thanks to this background, the initial product of our research is a system that explains a RoboCup Rescue simulation not to the agents in the domain themselves but to a watching audience. This ”commentary” is produced by recreating the actual dialogues most likely be occurring in the domain: walkie-talkie-conversations.
The aim of this study is to provide all people, from small children to aged persons, with a computational environment for everyday language communication. In order to achieve this, we propose a framework for a language-based operating system. In this paper, we explain our approach to dealing with the meaning of language, the architecture of the language operating system and its components. In particular, we describe the notion of language protocol and its resource representation (i.e., semiotic base), compared to the other protocols and their resource representations. We argue that by processing meaning of language rather than processing information, we attempt to provide a more human-like computer system and an intelligent computational environment to all people.