Visual Instruction as an Intuitive Interface for Robotic Sorting

Adam T. Müller, Nicolaj C. Stache

Abstract: Human-Robot Interaction (HRI) is a rapidly evolving field that seeks to bridge the gap between human users and increasingly capable robotic systems. While robotic technology has advanced significantly, designing intuitive and accessible interaction methods remains a key challenge. Traditional paradigms, such as programming-based interfaces or text-based commands, often impose steep learning curves and hinder broader adoption. While recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have enabled natural language interaction, these approaches are prone to ambiguity, particularly when specifying spatial relationships.

External IDs:dblp:conf/hci/MullerS25