What Questions Should Robots Be Able to Answer? A Dataset of User Questions for Explainable Robotics
arXiv:2510.16435v2 Announce Type: replace-cross Abstract: With the growing use of large language models and conversational interfaces in human-robot interaction, robots' ability to answer user questions is more important than ever. We therefore introduce a dataset of 1,893 user questions for household robots, collected from 100 participants and organized into 12 categories and 70 subcategories. Most work in explainable robotics focuses on why-questions. In contrast, our dataset provides a wide variety of questions, from questions about simple execution details to questions about how the robot
The growing integration of large language models and conversational interfaces into human-robot interaction necessitates a deeper understanding of how robots can effectively communicate and explain their actions to users.
This development is crucial for the transparent and trustworthy deployment of advanced robotic systems, moving beyond simple task execution to complex human-robot collaboration.
The focus of explainable robotics is broadening from solely 'why-questions' to a wider array of user inquiries, indicating a more sophisticated expectation of robotic communicative abilities.
- · AI/robotics developers
- · Human-robot interaction researchers
- · Household robot manufacturers
- · Robotics companies ignoring explainability
- · Developers solely focused on basic task automation
Robots will become more intuitive and user-friendly through improved conversational interfaces and explanatory capabilities.
Enhanced explainability will accelerate the adoption of robots in sensitive environments, such as elder care or collaborative workplaces.
The development of sophisticated robot-user dialogue could lead to new ethical frameworks for AI culpability and accountability in complex scenarios.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL