Minori Toyoda — accepted AI-conference papers

2022

Learning Bidirectional Translation Between Descriptions and Actions With Small Paired Data

Minori Toyoda, Kanata Suzuki, Yoshihiko Hayashi, Tetsuya Ogata

RA-L 2022

This study achieved bidirectional translation between descriptions and actions using small paired data from different modalities. The ability to mutually generate descriptions and actions is essential for robots to collaborate with humans in their daily lives, which generally requires a large datase

Cited by 5 Source ↗Scholar ↗

2021

Embodying Pre-Trained Word Embeddings Through Robot Actions

Minori Toyoda, Kanata Suzuki, Hiroki Mori, Yoshihiko Hayashi, Tetsuya Ogata

RA-L 2021

We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various linguistic expressions, including polysemous words, is an important ability for robots that interact with people via li

Cited by 14 Source ↗Scholar ↗