Static Is Not Enough: A Comparative Study of VR and SpaceMouse in Static and Dynamic Teleoperation Tasks

2026-01-19

AI Summary

This study addresses the limitation of existing teleoperation interface evaluations, which predominantly focus on static tasks and thus offer limited guidance for collecting high-quality demonstration data in dynamic scenarios. The work presents the first systematic comparison of interaction performance between VR controllers and SpaceMouse across both static and dynamic teleoperation tasks. Through a within-subjects experiment, quantitative and qualitative analyses were conducted across four task types, incorporating metrics such as task success rate, completion time, NASA-TLX workload, System Usability Scale (SUS) scores, and subjective feedback. Results demonstrate that in dynamic tasks, VR significantly outperforms SpaceMouse—achieving higher success rates, shorter execution times, steeper learning curves, lower perceived workload, and greater usability—highlighting that findings from static-task evaluations do not generalize to dynamic contexts. The project also open-sources a VR interface tailored for dynamic teleoperation.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Interaction Techniques and Devices
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Imitation learning relies on high-quality demonstrations, and teleoperation is a primary way to collect them, making teleoperation interface choice crucial for the data. Prior work mainly focused on static tasks, i.e., discrete, segmented motions, yet demonstrations also include dynamic tasks requiring reactive control. As dynamic tasks impose fundamentally different interface demands, insights from static-task evaluations cannot generalize. To address this gap, we conduct a within-subjects study comparing a VR controller and a SpaceMouse across two static and two dynamic tasks ($N=25$). We assess success rate, task duration, cumulative success, alongside NASA-TLX, SUS, and open-ended feedback. Results show statistically significant advantages for VR: higher success rates, particularly on dynamic tasks, shorter successful execution times across tasks, and earlier successes across attempts, with significantly lower workload and higher usability. As existing VR teleoperation systems are rarely open-source or suited for dynamic tasks, we release our VR interface to fill this gap.

Problem

• teleoperation
• static tasks
• dynamic tasks
• interface evaluation
• imitation learning

Innovation

• teleoperation
• virtual reality
• dynamic tasks
• imitation learning
• human-robot interaction