The authors present TWIG, a visually grounded wordlearning system that uses its existing knowledge of vocabulary, grammar, and action schemas to help it learn the meanings of new ...
Plan recognition has traditionally been developed for logically encoded application domains with a focus on logical reasoning. In this paper, we present an integrated plan-recogni...
We outline elements of the Abstract Contract Calculator, a prototype language implemented in Haskell (a declarative programming language) in which we simulate agents executing abst...
In this paper we explore the idea of using high-level semantic concepts, also called attributes, to represent human actions from videos and argue that attributes enable the constr...
This paper offers a logical formalisation of an argument-based account of reasoning about action, taking seriously the abductive nature of this form of reasoning. The particular qu...