Toward Intuitive and Adaptive Robot Command Systems: A Comparative Study Using Generative AI and Bodystorming

Abstract

As robotic technologies become increasingly integrated into everyday life, there is a growing need for intuitive natural language command systems that allow general users to easily control robots without specialized knowledge. This study investigates how such commands are actually constructed through two comparative experiments: one using a generative AI-based simulation, and the other using a bodystorming-based participatory session with a human surrogate. In particular, in the bodystorming experiment, a human acted in place of a humanoid robot to observe real-time interactions and user expressions. Participants issued and refined commands using a generative AI model (ChatGPT-4o) in the generative AI-based simulation experiment, and employed both verbal and non-verbal expressions in the bodystorming session. Quantitative and qualitative analyses revealed that while the generative AI struggled to interpret context-dependent commands, requiring users to overly formalize their expressions, the human surrogate in the bodystorming method was able to understand even less structured commands and allowed participants to construct more concise, intuitive, and adaptive instructions, especially when non-verbal behaviors were included. This study provides empirical insights for developing user-friendly robot command interfaces and natural, adaptable command systems that better reflect users’ intentions in everyday contexts.