[2C4] [General Session] 12. HI / Education Aid

[2C4-01] Performance Evaluation of Automatic Gesture Generation System Using Bi-Directional LSTM on Humanoid Robot

〇Kodai Hiyori¹, Kenji Araki¹, Dai Hasegawa², Satoshi Yoshio¹ (1. Graduate School of Information Science and Technology, Hokkaido University, 2. Tokyo University of Technology (Currently: Hokkai Gakuen University))

Keywords:Lecture Robot, Gesture, Deep Learning, Bi-Directional Long short-term memory

Conventional lecture substitution systems with humanoid robots use pre-defined gestures created by hand. Automatically generating these gestures makes it possible to create gestures without requiring expert knowledge and work, which is expected to lead to further progress in research on lecture substitution systems. This paper proposes an automatic gesture generation method which is expected to consider the semantic context of an utterance. Our proposed method is implemented by using a deep neural network with Bi-Directional LSTM units, applying filters for data correction, and axis conversion.