The Role of Embodiment in Intuitive Whole-Body Teleoperation for Mobile Manipulation

2025-09-03

AI Summary

This study addresses the dual challenges of low-quality demonstration data and high operator cognitive load in teleoperation of mobile manipulation robots. We propose an embodied teleoperation framework featuring coupled control of the robotic arm and mobile base. Through systematic comparison of coupled versus decoupled control paradigms under two visual feedback modalities—virtual reality (VR) and conventional screen-based interfaces—we find that while VR enhances immersion, it significantly increases task completion time and subjective cognitive workload. In contrast, coupled control substantially improves both the quality of imitation-learning demonstrations and downstream policy performance—without elevating operator burden. To our knowledge, this work is the first to empirically quantify the long-term cognitive cost of VR feedback in whole-body coordinated teleoperation tasks and to demonstrate the human-factor advantages of coupled control for acquiring high-dimensional, kinematically coherent demonstration data. Our findings provide a validated interaction paradigm and empirical foundation for learning-oriented teleoperation interface design.

Technology Category

• Intelligent Robots: Manipulation
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience

Abstract

Intuitive Teleoperation interfaces are essential for mobile manipulation robots to ensure high quality data collection while reducing operator workload. A strong sense of embodiment combined with minimal physical and cognitive demands not only enhances the user experience during large-scale data collection, but also helps maintain data quality over extended periods. This becomes especially crucial for challenging long-horizon mobile manipulation tasks that require whole-body coordination. We compare two distinct robot control paradigms: a coupled embodiment integrating arm manipulation and base navigation functions, and a decoupled embodiment treating these systems as separate control entities. Additionally, we evaluate two visual feedback mechanisms: immersive virtual reality and conventional screen-based visualization of the robot's field of view. These configurations were systematically assessed across a complex, multi-stage task sequence requiring integrated planning and execution. Our results show that the use of VR as a feedback modality increases task completion time, cognitive workload, and perceived effort of the teleoperator. Coupling manipulation and navigation leads to a comparable workload on the user as decoupling the embodiments, while preliminary experiments suggest that data acquired by coupled teleoperation leads to better imitation learning performance. Our holistic view on intuitive teleoperation interfaces provides valuable insight into collecting high-quality, high-dimensional mobile manipulation data at scale with the human operator in mind. Project website:https://sophiamoyen.github.io/role-embodiment-wbc-moma-teleop/

Problem

• Evaluating intuitive teleoperation interfaces for mobile manipulation robots
• Comparing coupled versus decoupled control paradigms for whole-body coordination
• Assessing VR versus screen-based visual feedback for operator performance

Innovation

• VR feedback modality increases task time
• Coupled manipulation navigation comparable user workload
• Coupled teleoperation improves imitation learning performance