Reflective Dialogues with a Humanoid Robot Integrated with an LLM and a Curated NLU System for Positive Behavioral Change in Older Adults
We developed an innovative system that combines Natural Language Understanding (NLU), a curated knowledge base, and the efficient management of a Large Language Model (LLM) to support motivational health coaching. Using Rasa as the core framework, we enhanced it by integrating the GPT-3.5-turbo model. Users opt into reflective dialogues during conversations. When they respond to open-ended questions, their input goes directly to the GPT-3.5-turbo model, allowing for more flexible responses. To provide curated trustworthy content, we integrated a knowledge provision component that searches a PDF-based knowledge base and generates user-friendly responses using Retrieval-Augmented Generation. We tested the system in a real-world scenario by deploying it on a Nao robot in seven older adults’ homes for 1–2 weeks, encouraging positive behavioral changes in some users. Our system serves as a valuable foundation for building an even more integrated, personalized system that can connect with other Application Programing Interfaces (APIs) and integrate with home sensors and edge devices.
Authors
- Qasid Saleem
- Ryan Browne (ORCID: https://orcid.org/0000-0002-4537-241X)
- Kristiina Jokinen (ORCID: https://orcid.org/0000-0003-1229-239X)
- Keiko Homma (ORCID: https://orcid.org/0000-0002-2837-4341)
- Yasuyuki Taki (ORCID: https://orcid.org/0000-0003-3691-1159)
- Michael McTear (ORCID: https://orcid.org/0000-0001-9883-7500)
- Giulio Napolitano (ORCID: https://orcid.org/0000-0002-6842-7575)
- Toshimi Ogawa (ORCID: https://orcid.org/0000-0002-7852-2787)
- Andrew Hyder
- Mirza Mohtashim Alam (ORCID: https://orcid.org/0000-0002-7047-0791)
- Kyoung‐Sook Kim (ORCID: https://orcid.org/0000-0003-0670-8053)
- Martino Maggio (ORCID: https://orcid.org/0000-0001-5889-6477)
- Rainer Wieching (ORCID: https://orcid.org/0000-0002-4040-2544)
- Francesca D’Agresti (ORCID: https://orcid.org/0009-0009-1712-0563)
- Jun’ichi Tsujii
- T Kudo
- Naoko Kounosu
- Eerik-Juhanna Siitonen
Institutions
- University of Ulster (GB)
- Tohoku University (JP)
- University of Siegen (DE)
- Informa (Italy) (IT)
- Institut für Angewandte Trainingswissenschaft (DE)
- Engineering (Italy) (IT)
- National Institute of Advanced Industrial Science and Technology (JP)
Publication Details
- Journal
- Electronics
- Published
- 2024-11-07
- DOI
- https://doi.org/10.3390/electronics13224364
- Citations
- 5
- Primary Topic
- Social Robot Interaction and HRI
- Type
- article
- Field-Weighted Citation Impact
- 3.22
Funders
- European Commission