Learning Bidirectional Translation Between Descriptions and Actions With Small Paired Data

Minori Toyoda*, Kanata Suzuki, Yoshihiko Hayashi, Tetsuya Ogata


研究成果: Article査読


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 dataset that maintains comprehensive pairs of both modality data. However, a paired dataset is expensive to construct and difficult to collect. To address this issue, this study proposes a two-stage training method for bidirectional translation. In the proposed method, we train recurrent autoencoders (RAEs) for descriptions and actions with a large amount of non-paired data. Then, we fine-tune the entire model to bind their intermediate representations using small paired data. Because the data used for pre-training do not require pairing, behavior-only data or a large language corpus can be used. We experimentally evaluated our method using a paired dataset consisting of motion-captured actions and descriptions. The results showed that our method performed well, even when the amount of paired data to train was small. The visualization of the intermediate representations of each RAE showed that similar actions were encoded in a clustered position and the corresponding feature vectors were well aligned.

ジャーナルIEEE Robotics and Automation Letters
出版ステータスPublished - 2022 10月 1

ASJC Scopus subject areas

  • 制御およびシステム工学
  • 生体医工学
  • 人間とコンピュータの相互作用
  • 機械工学
  • コンピュータ ビジョンおよびパターン認識
  • コンピュータ サイエンスの応用
  • 制御と最適化
  • 人工知能


「Learning Bidirectional Translation Between Descriptions and Actions With Small Paired Data」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。