Several high level methodological debates among AI researchers, linguists, psychologists and philosophers, appear to be endless, e.g. about the need for and nature of representations, about the role of symbolic processes, about embodiment, about situatedness, about whether symbol-grounding is needed, and about whether a robot needs any knowledge at birth or can start simply with a powerful learning mechanism. Consideration of the variety of capabilities and development patterns on the precocial-altricial spectrum in biological organisms will help us to see these debates in a new light. 1

Recognizing and responding to human affect is important in collaborative tasks in joint human-robot teams. In this paper we present an integrated architecture for HRI and report results from an experiment with this architecture that shows that expressing affect and responding to human affect with affect expressions improves performance in a joint human-robot task. 1.

Animals and robots perceiving and acting in a world require an ontology that accommodates entities, processes, states of a#airs, etc., in their environment. If the perceived environment includes information-processing systems, the ontology should reflect that. Scientists studying such systems need an ontology that includes the first-order ontology characterising physical phenomena, the second-order ontology characterising perceivers of physical phenomena, and a (recursive) third order ontology characterising perceivers of perceivers, including introspectors. We argue that second- and third-order ontologies refer to contents of virtual machines and examine requirements for scientific investigation of combined virtual and physical machines, such as animals and robots. We show how the CogA# architecture schema, combining reactive, deliberative, and meta-management categories, provides a first draft schematic third-order ontology for describing a wide range of natural and artificial agents. Many previously proposed architectures use only a subset of CogA#, including subsumption architectures, contention-scheduling systems, architectures with `executive functions' and a variety of types of `Omega' architectures.

This paper complements McCarthy’s “The well designed child”, in part by putting it in a broader context, the space of possible well designed progeny, and in part by relating design features to development of mathematical competence. I first moved into AI in an attempt to understand myself, especially hoping to understand how I could do mathematics. Over the ensuing four decades, my interactions with AI and other disciplines led to: design-based, cross-disciplinary investigations of requirements, especially those arising from interactions with a complex environment; a draft partial ontology for describing spaces of possible architectures, especially virtual machine architectures, for behaving systems (including our precursors); investigations of varied forms of representation and how they are suited to different functions; analysis of biological nature/nurture tradeoffs and their relevance to future machines; studies of control issues in a complex architecture; and showing how the states and processes possible in such an architecture relate to our (simplified) intuitive concepts of motivation, feeling, preferences, emotions, attitudes, values, moods, consciousness, etc. In 1971 I thought working models of human vision could lead to models of visual/spatial reasoning that would help to support Kant’s view of mathematics, against Hume’s. This has not yet happened, but I am still exploring

Research on algorithms and representations once dominated AI. Recently the importance of architectures has been acknowledged, but researchers have different objectives, presuppositions and conceptual frameworks, and this can lead to confused terminology, argumentation at cross purposes, re-invention of wheels and fragmentation of the research. We propose a methodological framework: develop a general representation of a wide class of architectures within which different architectures can be compared and contrasted. This should facilitate communication and integration across sub-fields of and approaches to AI, as well as providing a framework for evaluating alternative architectures. As a first-draft example we present the CogAff architecture schema, and show how it provides a useful framework for comparing and contrasting a wide range of architectures, including H-Cogaff, a proposed architecture for human-like systems. All of these concern virtual machine architectures whose natural implementations use biological mechanisms but some of which may use products of human engineering. Besides attempting to understand what sorts of virtual machine architectures are possible

This paper extends three decades of work arguing that instead of focusing only on (adult) human minds, we should study many kinds of minds, natural and artificial, and try to understand the space containing all of them, by studying what they do, how they do it, and how the natural ones can be emulated in synthetic minds. That requires: (a) understanding sets of requirements that are met by different sorts of minds, i.e. the niches that they occupy, (b) understanding the space of possible designs, and (c) understanding the complex and varied relationships between requirements and designs. Attempts to model or explain any particular phenomenon, such as vision, emotion, learning, language use, or consciousness lead to muddle and confusion unless they are placed in that broader context. in part because current ontologies for specifying

Some AI researchers aim to make useful machines, including robots. Others aim to understand general principles of information-processing machines with various kinds of intelligence, whether natural or artificial, including humans and human-like systems. They primarily address scientific and philosophical questions rather than practical goals. However, the tasks required to pursue scientific and engineering goals overlap, since both involve building working systems to test ideas and demonstrate results, and the conceptual frameworks and development tools needed for both overlap. This paper, partly based on philosophical analysis of requirements for robots in complex 3-D environments, surveys varieties of meta-cognition, drawing attention to requirements that drove biological evolution and which are also relevant to ambitious engineering goals.

The ability to achieve one’s goals is a defining characteristic of intelligent behaviour. A great many existing theories, systems and research programmes address the problems associated with generating behaviour to achieve a goal; much fewer address the related problems of how and why goals should be generated in an intelligent artifact, and how a subset of all possible goals are selected as the focus of behaviour. It is research into these problems of motivation, which this article aims to stimulate. Building from the analysis of scenario involving a futuristic household robot, we extend an existing account of motivation in intelligent systems to provide a framework for surveying relevant literature in AI and robotics. This framework guides us to look at the problems of encoding drives (how the needs of the system are represented), goal generation (how particular instances of goals are generated from the drives with reference to the current state), and goal selection (how the system determines which goal instances to act on). After surveying a variety of existing approaches in these terms, we build on the results of the survey to sketch a design for a new motive management framework which goes beyond the current state of the art. Key words: motivation, planning, goal-directed behaviour, agent architecture 1.

Traditional studies of cognitive ability have examined the component processes and factor structure of ability tests. Theoretical and empirical studies of non-cognitive dimensions of personality have examined how individual differences in personality interact with situational stressors to affect efficient cognitive performance. Previously reported results have emphasized motivational direction and intensity effects upon cognitive performance. Using a new technique of “Synthetic Aperture Personality Assessment ” (SAPA) which takes advantage of the large subject populations available on the internet, it is possible to study how basic personality dimensions relate to dimensions of cognitive ability. The SAPA procedure presents to participants small subsets of items sampled from large pools of publicly available personality and ability items. Although each participant is given only a small subset of items, with the recognition that subjects (> 65, 000) are randomly sampled and items are missing at random, it is possible to synthesize large (> 350x350) interitem correlation matrices. Individual differences in complex pattern recognition, spatial reasoning, and (self reported) standardized ability tests are moderately associated with Big 5 measures. We present the SAPA procedure in some detail and review findings relating dimensions of personality, ability, and interest. Based on a talk presented as part of a conference on “Individual differences in cognition ” A symposium

Clearly we can solve problems by thinking about them. Sometimes we have the impression that in doing so we use words, at other times diagrams or images. Often it feels as if we use both. Sometimes we have no idea what we are doing. What is going on when we use mental diagrams or images? This question is addressed in relation to the more general multi-pronged question: what are representations, what are they for, how many different types are there, in how many different ways can they be used, and what difference does it make whether they are in the mind or on paper? The question is related to deep problems about how vision and spatial manipulation work. We are far from understanding what is going on. In consequence of our not understanding this we cannot design user interfaces that understand their displays in the same way as human users do. In particular we need to explain how people (and some other animals) understand spatial structure and motion, and how we can think about objects in terms of a basic