ProjecTA: A Semi-Humanoid Robotic Teaching Assistant with In-Situ Projection for Guided Tours

2026-01-16

AI Summary

This study addresses the limitation of traditional robotic teaching assistants, whose reliance on onboard screens often diverts learners’ attention from physical objects and increases extraneous cognitive load. To mitigate this issue, the authors propose ProjecTA, a semi-humanoid robotic tutor that innovatively integrates near-object projection, gestural guidance, and synchronized speech to anchor instructional content in specific spatiotemporal locations adjacent to physical artifacts, thereby enabling contextualized multimodal instruction. In the first empirical comparison between projection-based and screen-based robotic tutors, a user study (N=24) demonstrated that ProjecTA significantly reduces extraneous cognitive load and outperforms conventional screen-based designs in perceived usability, usefulness of visual display, and cross-modal complementarity.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Interaction Techniques and Devices
• Machine Learning: Multimodal 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

Robotic teaching assistants (TAs) often use body-mounted screens to deliver content. In nomadic, walk-and-talk learning, such as tours in makerspaces, these screens can distract learners from real-world objects, increasing extraneous cognitive load. HCI research lacks empirical comparisons of potential alternatives, such as robots with in-situ projection versus screen-based counterparts; little knowledge has been derived for designing such alternatives. We introduce ProjecTA, a semi-humanoid, gesture-capable TA that guides learners while projecting near-object overlays coordinated with speech and gestures. In a mixed-method study (N=24) in a university makerspace, ProjecTA significantly reduced extraneous load and outperformed its screen-based counterpart in perceived usability, usefulness of visual display, and cross-modal complementarity. Qualitative analyses revealed how ProjecTA's coordinated projections, gestures, and speech anchored explanations in place and time, enhancing understanding in ways a screen could not. We derive key design implications for future robotic TAs leveraging spatial projection to support mobile learning in physical environments.

Problem

• robotic teaching assistant
• extraneous cognitive load
• in-situ projection
• mobile learning
• human-robot interaction

Innovation

• in-situ projection
• robotic teaching assistant
• extraneous cognitive load
• multimodal interaction
• mobile learning