ExTraCT – Explainable trajectory corrections for language-based human-robot interaction using textual feature descriptions
ExTraCT offers a more explainable approach to understanding language corrections, which could facilitate learning human preferences. We also demonstrated the adaptability and effectiveness of ExTraCT in a complex scenarios like assistive feeding, presenting it as a versatile solution across various HRI applications.
Authors
- J-Anne Yow (ORCID: https://orcid.org/0000-0003-2502-4183)
- Manoj Ramanathan (ORCID: https://orcid.org/0000-0001-5860-5342)
- Neha Priyadarshini Garg (ORCID: https://orcid.org/0000-0001-7374-659X)
- Wei Tech Ang
Institutions
- Agency for Science, Technology and Research (SG)
- Singapore Institute for Clinical Sciences (SG)
Publication Details
- Journal
- Frontiers in Robotics and AI
- Published
- 2024-09-23
- DOI
- https://doi.org/10.3389/frobt.2024.1345693
- Citations
- 6
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 2.08