A Multimodal Data Collection Framework for Dialogue-Driven Assistive Robotics to Clarify Ambiguities: A Wizard-of-Oz Pilot Study

TL;DR

This paper introduces a multimodal data collection framework using a Wizard-of-Oz setup to gather natural human-robot interaction data for assistive wheelchairs, aiming to improve dialogue-based control and ambiguity resolution.

Contribution

It presents a novel multimodal data collection framework that captures natural dialogue and ambiguity in assistive robotics, facilitating future AI development and benchmarking.

Findings

Collected 53 pilot trials demonstrating framework effectiveness.

Validated data quality through motion analysis and user feedback.

Showed the framework captures diverse ambiguity types for assistive control.

Abstract

Integrated control of wheelchairs and wheelchair-mounted robotic arms (WMRAs) has strong potential to increase independence for users with severe motor limitations, yet existing interfaces often lack the flexibility needed for intuitive assistive interaction. Although data-driven AI methods show promise, progress is limited by the lack of multimodal datasets that capture natural Human-Robot Interaction (HRI), particularly conversational ambiguity in dialogue-driven control. To address this gap, we propose a multimodal data collection framework that employs a dialogue-based interaction protocol and a two-room Wizard-of-Oz (WoZ) setup to simulate robot autonomy while eliciting natural user behavior. The framework records five synchronized modalities: RGB-D video, conversational audio, inertial measurement unit (IMU) signals, end-effector Cartesian pose, and whole-body joint states across five assistive tasks. Using this framework, we collected a pilot dataset of 53 trials from five participants and validated its quality through motion smoothness analysis and user feedback. The results show that the framework effectively captures diverse ambiguity types and supports natural dialogue-driven interaction, demonstrating its suitability for scaling to a larger dataset for learning, benchmarking, and evaluation of ambiguity-aware assistive control.