![[2512.23482] Theory of Mind for Explainable Human-Robot Interaction](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2512.23482] Theory of Mind for Explainable Human-Robot Interaction
Summary
This article explores the integration of Theory of Mind (ToM) in human-robot interaction (HRI) to enhance robot interpretability and user experience, proposing a user-centered approach to Explainable AI (XAI).
Why It Matters
The integration of Theory of Mind into robotics is crucial for developing systems that can effectively understand and respond to human mental states. This research addresses a significant gap in current HRI methodologies, emphasizing the need for user-centered explanations in AI, which can improve trust and collaboration between humans and robots.
Key Takeaways
- Theory of Mind can enhance robot adaptability by inferring human mental states.
- Integrating ToM into Explainable AI frameworks prioritizes user needs.
- Current HRI methods often overlook the alignment between robot explanations and internal reasoning.
Computer Science > Robotics arXiv:2512.23482 (cs) [Submitted on 29 Dec 2025 (v1), last revised 19 Feb 2026 (this version, v3)] Title:Theory of Mind for Explainable Human-Robot Interaction Authors:Marie S. Bauer, Julia Gachot, Matthias Kerzel, Cornelius Weber, Stefan Wermter View a PDF of the paper titled Theory of Mind for Explainable Human-Robot Interaction, by Marie S. Bauer and 4 other authors View PDF HTML (experimental) Abstract:Within the context of human-robot interaction (HRI), Theory of Mind (ToM) is intended to serve as a user-friendly backend to the interface of robotic systems, enabling robots to infer and respond to human mental states. When integrated into robots, ToM allows them to adapt their internal models to users' behaviors, enhancing the interpretability and predictability of their actions. Similarly, Explainable Artificial Intelligence (XAI) aims to make AI systems transparent and interpretable, allowing humans to understand and interact with them effectively. Since ToM in HRI serves related purposes, we propose to consider ToM as a form of XAI and evaluate it through the eValuation XAI (VXAI) framework and its seven desiderata. This paper identifies a critical gap in the application of ToM within HRI, as existing methods rarely assess the extent to which explanations correspond to the robot's actual internal reasoning. To address this limitation, we propose to integrate ToM within XAI frameworks. By embedding ToM principles inside XAI, we argue for a...