Spatial Language for Mobile Robots: The Formation and Generative Grounding of Toponyms

Abstract

For robots to interact with each other and humans in a human environment, it is important for themto be able to use language meaningfully in practical applications. Grounding connects words andsentences with their meanings and is a necessary foundation for the meaningful usage of language.Combining simple concepts provides a way to label other simple concepts. The process of forminga simple concept from a combination of concepts is termed generative grounding in this thesis.To understand how language may be used meaningfully in practical applications, the nature oflanguage and the concepts on which language is built must be understood. Concepts of space andtime are among those that are directly experienced and directly grounded. In particular, space isused to form other concepts with spatial metaphors used to describe mood, energy, emotion,personal attributes, and time.This thesis addresses the question of how robots can form spatial languages. The literaturereview in Chapters 2 and 3 covers the diverse fields that this thesis builds on, from linguistics,computer science, psychology, neurology, and robotics. The literature review explores the languagefeatures that need to be addressed if language evolution and acquisition are to be understood, andthe features of space and spatial language that make the domain appropriate for investigating thegrounding and generative grounding of concepts.The studies presented investigated grounding spatial language in mobile robots that hadconstructed maps to represent their world. The pilot studies investigated the underlying spatialrepresentations and methods to produce and comprehend language. The experience map, arepresentation similar to a cognitive map of the world, provided the most appropriate representationfor forming a spatial language.A key question is what impact interactions between agents have on the languages. For the twomajor studies described in this thesis, agents interacted through language games and the experiencemap provided the base representation for concepts formation. A new way to associate conceptelements and words was developed: the distributed lexicon table. Each study had three sections: aninvestigation into the experimental design of the language games in a simulation world based on agrid, the implementation of the language games in simulated robots, and the implementation oflanguage games in the richer and less predictable real world.The first study investigated spatial concept formation through collective experience and agentinteractions as they explored their environment and played ‘where are we’ games. Games wereplayed when the agents were within hearing distance, with the shared attention defined by beingnear each other. After playing many language games, the agents successfully formed a toponymiclanguage that labelled all visited locations.The second study addressed the question of whether robots can form concepts for spatialrelationships. Agents played ‘where is there’ language games in addition to ‘where are we’language games. In ‘where is there’ games, they referred to locations other than the current location.Shared attention was being near each other and the same perspective was achieved when anorientation location was named. A third target location was specified by name, direction, anddistance. Agents formed a comprehensive spatial language of directions and distances that werecombined to specify other locations in their world.In summary, a computational language model for mobile robots was successfully developed, inwhich the robots formed spatial concepts that were associated with words through interactions withother agents. The features that made spatial concept formation easy included an appropriate conceptrepresentation, the distributed lexicon table with methods to produce and comprehend words, andsimple interactions from which the language emerged. With the addition of generative interactions,the agents extended languages in which known locations