Normative Coordination for Embodied AI —A Noumostásian Framework
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Abstract Current embodied AI systems excel at task execution but lack protocols for normative coordination: detecting whether a human has accepted, modified, or rejected an interaction, not merely whether a task is completed. This gap produces friction, distrust, and inefficient re-engagement. We introduce Noumostásia, a framework for embodied accountability that specifies (1) the Ratification Loop—a state machine for detecting multi-modal uptake signals; (2) tactile-to-deontic translation (NTDTT), mapping sensor data to normative meaning; and (3) Sol Maintenance, a protocol for preserving the phatic ground between actions. We demonstrate the framework's applicability to humanoid robots, teleoperated systems, and collaborative agents. A reference implementation is available upon reqquest. This work establishes normative coordination as a foundational layer for trustworthy human-robot interaction.
Fields of Study & Subjects
Social Robot Interaction and HRI
Speech and dialogue systems
Robot Manipulation and Learning
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 12 February 2026
- Language
- EN
- Document type
- Preprint