Learning to Recognize Novel Objects in One Shot through Human-Robot Interactions in Natural Language Dialogues

Authors

  • Evan Krause Tufts University
  • Michael Zillich Technical University Vienna
  • Thomas Williams Tufts University
  • Matthias Scheutz Tufts University

DOI:

https://doi.org/10.1609/aaai.v28i1.9143

Keywords:

one shot learning, vision, natural language, robotics

Abstract

Being able to quickly and naturally teach robots new knowledge is critical for many future open-world human-robot interaction scenarios. In this paper we present a novel approach to using natural language context for one-shot learning of visual objects, where the robot is immediately able to recognize the described object. We describe the architectural components and demonstrate the proposed approach on a robotic platform in a proof-of-concept evaluation.

Downloads

Published

2014-06-21

How to Cite

Krause, E., Zillich, M., Williams, T., & Scheutz, M. (2014). Learning to Recognize Novel Objects in One Shot through Human-Robot Interactions in Natural Language Dialogues. Proceedings of the AAAI Conference on Artificial Intelligence, 28(1). https://doi.org/10.1609/aaai.v28i1.9143