The nature of cognition is being re-considered. Instead of emphasizing formal operations on abstract symbols, the new approach foregrounds the fact that cognition is, rather, a situated activity, and suggests that thinking beings ought therefore be considered first and foremost as acting beings. The essay reviews recent work in Embodied Cognition, provides a concise guide to its principles, attitudes and goals, and identifies the physical grounding project as its central research focus.

This essay describes a general approach to building perturbation-tolerant autonomous systems, based on the conviction that artificial agents should be able to notice when something is amiss, assess the anomaly, and guide a solution into place. This basic strategy of self-guided learning is termed the metacognitive loop; it involves the system monitoring, reasoning about, and, when necessary, altering its own decision-making components. This paper (a) argues that equipping agents with a metacognitive loop can help to overcome the brittleness problem, (b) details the metacognitive loop and its relation to our ongoing work on time-sensitive commonsense reasoning, (c) describes specific, implemented systems whose perturbation tolerance was improved by adding a metacognitive loop, and (d) outlines both short-term and long-term research agendas.

this paper to elaborate on that claim; the format consists of an initial primer on uncertainty in active logic, then its current implementation (Alma/Carne), existing applications, and finally a discussion of potential future applications

In recentyears, embodied cognitiveagents have become a central research focus in Cognitive Science. We suggest that there are at least three aspects of embodiment--- physical, social and temporal---whichmust be treated simultaneously to make possible a realistic implementation of agency. In this paper we detail the ways in whichattention to the temporal embodiment of a cognitiveagent (perhaps the most neglected aspect of embodiment) can enhance the abilityofanagenttoactintheworld, both in itself, and also by supporting more robust integrations with the physical and social worlds.

As more information becomes available on the World Wide Web (there are currently over 4 billion pages covering most areas of human endeavor), it becomes more difficult to provide effective search tools for information access. Today, people access web information through two main kinds of search interfaces: Browsers (clicking and following hyperlinks) and Query Engines (queries in the form of a set of keywords showing the topic of interest). The first process is tentative and time consuming and the second may not satisfy the user because of many inaccurate and irrelevant results. Better support is needed for expressing one's information need and returning high quality search results by web search tools. There appears to be a need for systems that do reasoning under uncertainty and are flexible enough to recover from the contradictions, inconsistencies, and irregularities that such reasoning involves.

This paper presents an investigation of rational agents that have limited computational resources and intentionally interact with their environments. We present an example logical formalism, based on Active Logic and Situation Calculus, that can be employed in order to satisfy the requirements arising due to being situated in a dynamic universe. We analyse how such agents can combine, in a time-aware fashion, inductive learning from experience and deductive reasoning using domain knowledge. In particular, we consider how partial plans are created and reasoned about, focusing on what new information can be provided as a result of action execution. 1

There is growing interest in accessing, relating, and combining data from multiple sources on the Web. Enormous amounts of heterogeneous information have been accumulated within corporations, government organization and universities. Such information continues to grow at an ever-increasing rate. This information comes from different subject areas, and comes in different formats: bitmap, plain text, binary, etc.

In this paper I propose a flexible method of characterizing a test environment such that its environmental complexity, information density, variability and volatility can be easily measured.

The problem of nding a suitable formal approach to describe on-going reasoning process has been open since the very beginning of AI. In this paper we argue that active logic might be a formalism useful in this context. Active logic is rst introduced, then we analyse resource limitations that constrain the space of possible practical realisations of such reasoners. Finally some steps towards creating a practical active logic reasoner are presented. 1

Abstract. We study agents situated in partially observable environments, who do not have sufficient resources to create conformant (complete) plans. Instead, they create plans which are conditional and partial, execute or simulate them, and learn from experience to evaluate their quality. Our agents employ an incomplete symbolic deduction system based on Active Logic and Situation Calculus for reasoning about actions and their consequences. An Inductive Logic Programming algorithm generalises observations and deduced knowledge so that the agents can choose the best plan for execution. We describe an architecture which allows ideas and solutions from several subfields of Artificial Intelligence to be joined together in a controlled and manageable way. In our opinion, no situated agent can achieve true rationality without using at least logical reasoning and learning. In practice, it is clear that pure logic is not able to cope with all the requirements put on reasoning, thus more domainspecific solutions, like planners, are also necessary. Finally, any realistic agent needs a reactive module to meet demands of dynamic environments. Our architecture is designed in such a way that those three elements interact in order to complement each other’s weaknesses and reinforce each other’s strengths. 1