🤔 Got your attention? If you are at #HRI2026 next week make sure to join the Foundational Concepts session on Thursday, or to catch us at any time during the conference. We will be super happy to chat with you 😊
You can also download and read the paper here: https://jrenoux.github.io/uploads/papers/alt-hri-2026.pdf
📜 In short, ToM is an outdated and harmful concept, not properly backed up, that should be abandonned entirely. This does not mean that all the research done in Social Robotics is to be abandonned or redone, but that we need to rethink how we justify our work and what we actually do.
🥳 I am extremely proud to bring you a wonderful paper in collaboration with Cansu Elmadağlı, which we will present at @hri, track alt.HRI!
This paper looks at the concept of Theory of Mind (ToM), a core concept in Social Robotics. However, this concept is very strongly criticized in social sciences, though these critics had not crossed the border to robotics yet. We are doing just that with this paper.
MIT engineers aim to give robots a bit of common sense when faced with situations that push them off their trained path, so they can self-correct after missteps and carry on with their chores. The team’s method connects robot motion data with the common sense knowledge of large language models, or LLMs.
Jennifer
Hacker News
amir