Development of an Intuitive GUI for Non-Expert Teleoperation of Humanoid Robots

TL;DR

The paper addresses the need for an intuitive, non-expert-friendly GUI to teleoperate humanoid robots in FIRA HuroCup obstacle courses. It proposes a camera-centric, web-based interface built on ROS1 via ROSBridge, leveraging iterative wireframes, minimal external libraries, and real-time WebSocket communication to simplify control and visualization. Key contributions include a two-page UI with on-the-fly motion tuning, improved layout, keyboard mappings, dynamic resizing, and collapsible menus, all designed to reduce cognitive load for novice operators. The work demonstrates qualitative improvements over a legacy interface and offers a scalable blueprint for applying similar UIs to other humanoid-robot teleoperation tasks, with plans for quantitative user testing in the future.

Abstract

The operation of humanoid robotics is an essential field of research with many practical and competitive applications. Many of these systems, however, do not invest heavily in developing a non-expert-centered graphical user interface (GUI) for operation. The focus of this research is to develop a scalable GUI that is tailored to be simple and intuitive so non-expert operators can control the robot through a FIRA-regulated obstacle course. Using common practices from user interface development (UI) and understanding concepts described in human-robot interaction (HRI) and other related concepts, we will develop a new interface with the goal of a non-expert teleoperation system.

Figures (9)

• Figure 1: Visual of kid-size humanoid robot navigating a replica of the FIRA obstacle run event.
• Figure 2: Wireframe depiction set before each draft
• Figure 3: Image of original screen with the map on the left side of the screen and operation buttons on the bottom
• Figure 4: Image of new map layout with map on left and operation buttons on the right
• Figure 5: Legacy teleoperation screen.