ML Anthology

Diana's World: A Situated Multimodal Interactive Agent

Nikhil Krishnaswamy, Pradyumna Narayana, Rahul Bangar, Kyeongmin Rim, Dhruva Patil, David G. McNeely-White, Jaime Ruiz, Bruce A. Draper, J. Ross Beveridge, James Pustejovsky
AAAI 2020 pp. 13618-13619
doi:10.1609/AAAI.V34I09.7096 /aaai/2020/krishnaswamy2020aaai-diana/

Abstract

State of the art unimodal dialogue agents lack some core aspects of peer-to-peer communication—the nonverbal and visual cues that are a fundamental aspect of human interaction. To facilitate true peer-to-peer communication with a computer, we present Diana, a situated multimodal agent who exists in a mixed-reality environment with a human interlocutor, is situation- and context-aware, and responds to the human's language, gesture, and affect to complete collaborative tasks.

PDF AAAI Semantic Scholar

Cite

Text

Krishnaswamy et al. "Diana's World: A Situated Multimodal Interactive Agent." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I09.7096

Markdown

[Krishnaswamy et al. "Diana's World: A Situated Multimodal Interactive Agent." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/krishnaswamy2020aaai-diana/) doi:10.1609/AAAI.V34I09.7096

BibTeX

@inproceedings{krishnaswamy2020aaai-diana,
  title     = {{Diana's World: A Situated Multimodal Interactive Agent}},
  author    = {Krishnaswamy, Nikhil and Narayana, Pradyumna and Bangar, Rahul and Rim, Kyeongmin and Patil, Dhruva and McNeely-White, David G. and Ruiz, Jaime and Draper, Bruce A. and Beveridge, J. Ross and Pustejovsky, James},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13618-13619},
  doi       = {10.1609/AAAI.V34I09.7096},
  url       = {https://mlanthology.org/aaai/2020/krishnaswamy2020aaai-diana/}
}