🤖 AI Summary
This work addresses the limitations of current human-robot voice interaction systems, which often feel rigid and lack robust error-correction capabilities, compounded by the absence of a Wizard-of-Oz (WoZ) development platform that supports fluid dialogue. To overcome these challenges, the authors propose and implement a virtual reality–based human-robot interaction (HRI) simulation system integrating four core mechanisms: interruptibility and correctability, real-time polling, low-latency response, and high-fidelity motion replay. The resulting system substantially enhances interaction naturalness and development efficiency, successfully establishing a VR WoZ platform that meets fluid-interaction standards. This platform provides a highly effective and reproducible experimental foundation for research on voice-based interaction with mobile manipulation robots.
📝 Abstract
Achieving truly fluid interaction with robots with speech interfaces remains a hard problem, and the experience of current Human-Robot Interaction (HRI) remains laboured and frustrating. Some of the barriers to fluid interaction stem from a lack of a suitable development platform for HRI for improving interaction, even in robotic Wizard-of-Oz (WoZ) modes of operation used for data collection and prototyping. Based on previous systems, we propose the properties of interruptibility and correction (IaC), pollability, latency measurement and optimisation and time-accurate reproducibility of actions from logging data as key criteria for a fluid WoZ system to support fluid error correction. We finish by presenting a Virtual Reality (VR) HRI simulation environment for mobile manipulators which meets these criteria.