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

Evan A. Krause, Michael Zillich, Thomas Emrys Williams, Matthias Scheutz

AAAI 2014 pp. 2796-2802

doi:10.1609/AAAI.V28I1.9143 /aaai/2014/krause2014aaai-learning/

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.

PDF AAAI Semantic Scholar

Cite

Text

Krause et al. "Learning to Recognize Novel Objects in One Shot Through Human-Robot Interactions in Natural Language Dialogues." AAAI Conference on Artificial Intelligence, 2014. doi:10.1609/AAAI.V28I1.9143

Markdown

[Krause et al. "Learning to Recognize Novel Objects in One Shot Through Human-Robot Interactions in Natural Language Dialogues." AAAI Conference on Artificial Intelligence, 2014.](https://mlanthology.org/aaai/2014/krause2014aaai-learning/) doi:10.1609/AAAI.V28I1.9143

BibTeX

@inproceedings{krause2014aaai-learning,
  title     = {{Learning to Recognize Novel Objects in One Shot Through Human-Robot Interactions in Natural Language Dialogues}},
  author    = {Krause, Evan A. and Zillich, Michael and Williams, Thomas Emrys and Scheutz, Matthias},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2014},
  pages     = {2796-2802},
  doi       = {10.1609/AAAI.V28I1.9143},
  url       = {https://mlanthology.org/aaai/2014/krause2014aaai-learning/}
}