A Grammar-Based Communication Model for Conveying Design Intent in Human-Robot Teams

IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp. 872–877

Abstract

This paper investigates how to represent and communicate evolving design intent driven by dynamic conditions in human-robot teams engaged in unstructured design tasks. We introduce a grammar-based communication model that computationally encodes design intent and translates it into machine-readable language. The model uses rule-based formalisms to computationally encode contextual, transformational, and conditional relationships between sensing and actions, enabling purposeful interactions between human and robot agents. Robotic clay and sand forming studies validated the grammar-based communication model and demonstrated how the rules organised HRI-enabled robotic fabrication, where the iterations of design intent were communicated through the relationships between sensing and action parameters captured in real time. This study may ultimately contribute to more fluid teamwork in unstructured and dynamic environments while improving the transparency of data collection and interpretation in autonomous systems.

Authors 1

1. İremnur Tokaç corresponding Aachen Chair of Individualized Production (IP)

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Chair of Individualized Production,Aachen,Germany,52074