Towards the grounding of abstract words: A Neural Network model for cognitive robots

Stramandinoli, Francesca; Cangelosi, Angelo; Marocco, Davide

doi:10.1109/ijcnn.2011.6033258

Cited by 15 publications

(15 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grounding symbolic knowledge about actions and objects to a perceived model of the physical world has been addressed in many works over the past decades (for a review of symbol grounding and symbol grounding in relation to perceptual anchoring, in particular, see the report by Coradeschi et al (2013)). Nonetheless, a few notable contributions in grounding of actions are the works presented by Lemaignan et al (2012) and Stramandinoli et al (2011Stramandinoli et al ( , 2012. In the study by Lemaignan et al (2012), the authors presented a grounded shared model of the world that is used for both human-robot verbal and non-verbal interactions.…”

Section: Related Workmentioning

confidence: 99%

“…The model is realistic in the sense that 3D models of objects are created and maintained in such a way that spatial relations between objects can be used to reasoning upon various concepts, relations, and actions in human-robot interaction scenarios. In the study by Stramandinoli et al (2011Stramandinoli et al ( , 2012, the authors presented a cognitive model of high-order concepts that are grounded by using basic concepts and actions that are directly grounded in robot sensorimotor experiences. The suggested model is learned using a recurrent neural network (RNN), which is trained using the temporal sequences of robot action primitives to learn higher-order concepts.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning Actions to Improve the Perceptual Anchoring of Objects

2017

View full text Add to dashboard Cite

In this paper, we examine how to ground symbols referring to objects in perceptual data from a robot system by examining object entities and their changes over time. In particular, we approach the challenge by (1) tracking and maintaining object entities over time; and (2) utilizing an artificial neural network to learn the coupling between words referring to actions and movement patterns of tracked object entities. For this purpose, we propose a framework that relies on the notations presented in perceptual anchoring. We further present a practical extension of the notation such that our framework can track and maintain the history of detected object entities. Our approach is evaluated using everyday objects typically found in a home environment. Our object classification module has the possibility to detect and classify over several 100 object categories. We demonstrate how the framework creates and maintains, both in space and time, representations of objects such as "spoon" and "coffee mug." These representations are later used for training of different sequential learning algorithms to learn movement actions such as "pour" and "stir." We finally exemplify how learned movements actions, combined with commonsense knowledge, further can be used to improve the anchoring process per se.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Learning Actions to Improve the Perceptual Anchoring of Objects

2017

View full text Add to dashboard Cite

show abstract

“…Since the method used here is symmetric in the sense that if X is a co‐occurrent of Y, then Y is one of X, extensive circular relations are readily apparent (for instance, morals → promote → virtue → teach → morals → change in → custom → understand → virtue → promote → morals etc). This is not seen as a problem in computational linguistics, but grounded cognition researchers (e.g., Cangelosi & Riga, ; Roy, ; Stramandinoli et al., ) might argue that no true understanding can occur unless at least some terms are grounded in sensorimotor experience.…”

Section: Using Approaches From Computational Linguistics To Investigamentioning

confidence: 99%

On the Importance of a Rich Embodiment in the Grounding of Concepts: Perspectives From Embodied Cognitive Science and Computational Linguistics

Thill

Padó

Ziemke

2014

Topics in Cognitive Science

View full text Add to dashboard Cite

The recent trend in cognitive robotics experiments on language learning, symbol grounding, and related issues necessarily entails a reduction of sensorimotor aspects from those provided by a human body to those that can be realized in machines, limiting robotic models of symbol grounding in this respect. Here, we argue that there is a need for modeling work in this domain to explicitly take into account the richer human embodiment even for concrete concepts that prima facie relate merely to simple actions, and illustrate this using distributional methods from computational linguistics which allow us to investigate grounding of concepts based on their actual usage. We also argue that these techniques have applications in theories and models of grounding, particularly in machine implementations thereof. Similarly, considering the grounding of concepts in human terms may be of benefit to future work in computational linguistics, in particular in going beyond "grounding" concepts in the textual modality alone. Overall, we highlight the overall potential for a mutually beneficial relationship between the two fields.

show abstract

“…In [66,67] a cognitive robotics model is described in which the linguistic input provided by the experimenter guides the autonomous organization of the knowledge of the iCub. A hierarchical organization of concepts is used for the acquisition of abstract words.…”

Section: Grounding Words In Actionmentioning

confidence: 99%

A Short Review of Symbol Grounding in Robotic and Intelligent Systems

2013

View full text Add to dashboard Cite

This paper gives an overview of the research papers published in Symbol Grounding in the period from the beginning of the 21st century up 2012. The focus is in the use of symbol grounding for robotics and intelligent system. The review covers a number of subtopics, that include, physical symbol grounding, social symbol grounding, symbol grounding for vision systems, anchoring in robotic systems, and learning symbol grounding in software systems and robotics. This review is published in conjunction with a special issue on Symbol Grounding in the Künstliche Intelligenz Journal.

show abstract

Towards the grounding of abstract words: A Neural Network model for cognitive robots

Cited by 15 publications

References 28 publications

Learning Actions to Improve the Perceptual Anchoring of Objects

Learning Actions to Improve the Perceptual Anchoring of Objects

On the Importance of a Rich Embodiment in the Grounding of Concepts: Perspectives From Embodied Cognitive Science and Computational Linguistics

A Short Review of Symbol Grounding in Robotic and Intelligent Systems

Contact Info

Product

Resources

About