Guiding Exploratory Behaviors for Multi-Modal Grounding of Linguistic Descriptions

Authors

  • Jesse Thomason University of Texas at Austin
  • Jivko Sinapov Tufts University
  • Raymond Mooney University of Texas at Austin
  • Peter Stone University of Texas at Austin

Keywords:

Multi-modal grounding, NLP, Human-robot interaction

Abstract

A major goal of grounded language learning research is to enable robots to connect language predicates to a robot's physical interactive perception of the world. Coupling object exploratory behaviors such as grasping, lifting, and looking with multiple sensory modalities (e.g., audio, haptics, and vision) enables a robot to ground non-visual words like ``heavy'' as well as visual words like ``red''. A major limitation of existing approaches to multi-modal language grounding is that a robot has to exhaustively explore training objects with a variety of actions when learning a new such language predicate. This paper proposes a method for guiding a robot's behavioral exploration policy when learning a novel predicate based on known grounded predicates and the novel predicate's linguistic relationship to them. We demonstrate our approach on two datasets in which a robot explored large sets of objects and was tasked with learning to recognize whether novel words applied to those objects.

Downloads

Published

2018-04-27

How to Cite

Thomason, J., Sinapov, J., Mooney, R., & Stone, P. (2018). Guiding Exploratory Behaviors for Multi-Modal Grounding of Linguistic Descriptions. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11966