Related papers: Language Bootstrapping: Learning Word Meanings Fro…
Human infants learn the names of objects and develop their own conceptual systems without explicit supervision. In this study, we propose methods for learning aligned vision-language conceptual systems inspired by infants' word learning…
Communication in both human-human and human-robot interac-tion (HRI) contexts consists of verbal (speech-based) and non-verbal(facial expressions, eye gaze, gesture, body pose, etc.) components.The verbal component contains semantic and…
The ability to connect language units to their referents in the physical world, referred to as grounding, is crucial to learning and understanding grounded meanings of words. While humans demonstrate fast mapping in new word learning, it…
The paper presents a neurorobotics cognitive model to explain the understanding and generalisation of nouns and verbs combinations when a vocal command consisting of a verb-noun sentence is provided to a humanoid robot. This generalisation…
Many functional elements of human homes and workplaces consist of rigid components which are connected through one or more sliding or rotating linkages. Examples include doors and drawers of cabinets and appliances; laptops; and swivel…
Spoken language interaction is at the heart of interpersonal communication, and people flexibly adapt their speech to different individuals and environments. It is surprising that robots, and by extension other digital devices, are not…
Robots which interact with the physical world will benefit from a fine-grained tactile understanding of objects and surfaces. Additionally, for certain tasks, robots may need to know the haptic properties of an object before touching it. To…
World models have demonstrated impressive performance on robotic learning tasks. Many such tasks inherently demand multimodal reasoning; for example, filling a bottle with water will lead to visual information alone being ambiguous or…
The problem of extracting important and meaningful parts of a sensory data stream, without prior training, is studied for symbolic sequences, by using textual narrative as a test case. This is part of a larger study concerning the…
Humans use semantic concepts such as spatial relations between objects to describe scenes and communicate tasks such as "Put the tea to the right of the cup" or "Move the plate between the fork and the spoon." Just as children, assistive…
We present an approach for acquiring grounded representations of words from mixed-initiative, situated interactions with a human instructor. The work focuses on the acquisition of diverse types of knowledge including perceptual, semantic,…
Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes.…
In recent years, robots are used in an increasing variety of tasks, especially by small- and medium- sized enterprises. These tasks are usually fast-changing, they have a collaborative scenario and happen in unpredictable environments with…
Service robots are expected to autonomously and efficiently work in human-centric environments. For this type of robots, object perception and manipulation are challenging tasks due to need for accurate and real-time response. This paper…
Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora. We present an exploration of active learning approaches applied to three grounded language problems of…
This document chronicles this author's attempt to explore how words come to mean what they do, with a particular focus on child language acquisition and what that means for models of language understanding.\footnote{I say \emph{historical}…
Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempts to decode the mappings between utterances and situations.…
We tackle the problem of learning complex, general behaviors directly in the real world. We propose an approach for robots to efficiently learn manipulation skills using only a handful of real-world interaction trajectories from many…
Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in turn be used to induce similarity measures among words,…
Developmental AI creates embodied AIs that develop human-like abilities. The AIs start with innate competences and learn more by interacting with the world including people. Developmental AIs have been demonstrated, but their abilities so…