In this paper, we outline a comprehensive approach to composed analogies based on the theory of conceptual spaces. Our algorithmic model understands analogy as a search procedure and builds upon the idea that analogical similarity depends on a conceptual phenomena called ‘dimensional salience.’ We distinguish between category-based, property-based, event-based, and part-whole analogies, and propose computationally-oriented methods for explicating them in terms of conceptual spaces.

Most semantic models employed in human-robot interactions concern how a robot can understand commands, but in this article the aim is to present a framework that allows dialogic interaction. The key idea is to use events as the fundamental structures for the semantic representations of a robot. Events are modeled in terms of conceptual spaces and mappings between spaces. It is shown how the semantics of major word classes can be described with the aid of conceptual spaces in a way that is amenable to computer implementations. An event is represented by two vectors, one force vector representing an action and one result vector representing the effect of the action. The two-vector model is then extended by the thematic roles so an event is built up from an agent, an action, a patient, and a result. It is shown how the components of an event can be put together to semantic structures that represent the meanings of sentences. It is argued that a semantic framework based on events can generate a general representational framework for human-robot communication. An implementation of the framework involving communication with an iCub will be described.

We present a novel action recognition system that is able to learn how to recognize and classify actions. Our system employs a three-layered hierarchy of Self-Organizing Maps together with a supervised neural network for labelling the actions. We have evaluated our system in an experiments consisting of ten different actions from a publicly available data set. The results are encouraging with 83% correctly classified actions based on the actor’s spatial trajectory.

Pointing is a typical means of directing a human's attention to a specific object or event. Robot pointing behaviours that direct the attention of humans are critical for human-robot interaction, communication and collaboration. In this paper, we describe an experiment undertaken to investigate human comprehension of a humanoid robot's pointing behaviour. We programmed a NAO robot to point to markers on a large screen and asked untrained human subjects to identify the target of the robots pointing gesture. We found that humans are able to identify robot pointing gestures. Human subjects achieved higher levels of comprehension when the robot pointed at objects closer to the gesturing arm and when they stood behind the robot. In addition, we found that subjects performance improved with each assessment task. These new results can be used to guide the design of effective robot pointing behaviours that enable more effective robot to human communication and improve human-robot collaborative performance.

Abstract This paper extends earlier work by its authors on formal aspects of the processes of contracting a theory to eliminate a proposition and revising a theory to introduce a proposition. In the course of the earlier work, Gärdenfors developed general postulates of a more or less equational nature for such processes, whilst Alchourrón and Makinson studied the particular case of contraction functions that are maximal, in the sense of yielding a maximal subset of the theory (or alternatively, of one of its axiomatic bases), that fails to imply the proposition being eliminated. In the present paper, the authors study a broader class, including contraction functions that may be less than maximal. Specifically, they investigate “partial meet contraction functions”, which are defined to yield the intersection of some nonempty family of maximal subsets of the theory that fail to imply the proposition being eliminated. Basic properties of these functions are established: it is shown in particular that they satisfy the Gärdenfors postulates, and moreover that they are sufficiently general to provide a representation theorem for those postulates. Some special classes of partial meet contraction functions, notably those that are “relational” and “transitively relational”, are studied in detail, and their connections with certain “supplementary postulates” of Gàrdenfors investigated, with a further representation theorem established.

In this article propositions will be identified with a certain kind of changes of belief. The intended interpretation is that a proposition is characterised by the change it would induce if added to a state of belief. Propositions will thus be defined as functions from states of belief to states of belief. A set of postulates concerning the properties and existence of propositions will be formulated. A proposition will be said to be a tautology iff it is the identity function on states of belief. The main result is that the logic determined by the set of postulates is intuitionistic propositional logic. The basic epistemic concept is that of a belief model, which is defined as a pair 〈 , 〉, where is a nonempty set and is a class of functions from to . The elements in will be called states of belief and they will be denoted K, K′,…. A discussion of the epistemological interpretation of the states of belief can be found in Gärdenfors [2]. Here, no assumptions about the structure of the elements in will be made. The elements in will be called propositions, and A, B, C, … will be used as variables over . Functions from states of belief to states of belief can be characterised as epistemic inputs. The intended interpretation of the functions in is that they correspond to changes of belief where the new evidence is accepted as “certain” or “known” in the resulting state of belief. This means that not all functions defined on can properly be called propositions.