Teaching robots to ask for clarification in 3D
When robots should ask: Which one?
In safety-critical places like operating rooms, a vague command like "Pass me the vial" can be dangerous. This paper introduces a simple idea with big impact: teach AI to detect when an instruction is ambiguous in a 3D scene and pause to ask for clarification.
- New task: Open-Vocabulary 3D Instruction Ambiguity Detection — decide if a command has exactly one clear target in a scene.
- New dataset: Ambi3D with 700+ diverse scenes and ~22k instructions to stress-test models.
- Key finding: Today’s leading 3D LLMs often miss ambiguity.
- New method: AmbiVer, a two-stage system that gathers visual evidence from multiple views and uses it to judge clarity more reliably.
Why it matters: More cautious, trustworthy assistants — from hospitals and labs to warehouses and homes.
Read more: https://arxiv.org/abs/2601.05991 and project/code: https://jiayuding031020.github.io/ambi3d/
Paper: https://arxiv.org/abs/2601.05991v1
Register: https://www.AiFeta.com
#AI #Robotics #Safety #ComputerVision #3D #LLM #VLM #HRI #EmbodiedAI
