Related Experiment Video
Updated: Jun 12, 2025
11:53
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
Published on: October 14, 2017
11.6K
Unraveling the thread: understanding and addressing sequential failures in human-robot interaction
Lucien Tisserand1, Brooke Stephenson1,2, Heike Baldauf-Quilliatre1
1Interactions, Corpus, Apprentissages, Représentations (ICAR) UMR5191, Centre National de la Recherche Scientifique, ENS de Lyon and Université Lyon 2, Labex ASLAN, Lyon, France.
Frontiers in Robotics and AI
|September 27, 2024
Summary
Human robot interaction struggles with real-time conversation flow. Analyzing library interactions reveals issues in sequential understanding, guiding future dialogue system design for better context adaptation.
Area of Science:
- Human-Robot Interaction (HRI)
- Conversation Analysis
- Natural Language Processing (NLP)
Background:
- Interaction is a dynamic, real-time process.
- Participants use relevance and social norms to interpret speech turns.
- Adapting to changing conversational context is a key challenge in HRI.
Purpose of the Study:
- Identify issues in sequential flow handling within in-the-wild Human Robot Interactions (HRIs).
- Analyze HRIs in an open-world university library setting.
- Guide the design of improved HRI systems for complex situations.
Main Methods:
- Analysis of a corpus of in-the-wild HRIs.
- Identification of problems related to inadequate sequential flow handling.
- Survey of Natural Language Processing (NLP) and machine dialogue management approaches.
Main Results:
- Inadequate handling of sequential flow is a significant issue in current HRI systems.
- Real-world library interactions present complex contextual challenges.
- Specific problems arising from poor sequential understanding were identified.
Conclusions:
- Insights from analyzing in-the-wild HRIs can inform better system design.
- Improved handling of conversational context is crucial for effective HRI.
- Further research in NLP and dialogue management is needed to mitigate identified problems.
