ワークショップ (国際) Tourist Guidance Robot Based on HyperCLOVA

Takato Yamazaki, Katsumasa Yoshikawa, Toshiki Kawamoto (LINE/Tokyo Institute of Technology), Masaya Ohagi, Tomoya Mizumoto, Shuta Ichimura, Yusuke Kida, Toshinori Sato

The 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems - Dialogue Robot Competition 2022 (IROS 2022 - DRC2022)


This paper describes our system submitted to Dialogue Robot Competition 2022. Our proposed system is a combined model of rule-based and generation-based dialog systems. The system utilizes HyperCLOVA, a Japanese foundation model, not only to generate responses but also summarization, search information, etc. We also used our original speech recognition system, which was fine-tuned for this dialog task. As a result, our system ranked second in the preliminary round and moved on to the finals.

Paper : Tourist Guidance Robot Based on HyperCLOVA新しいタブまたはウィンドウで開く (外部サイト)