Mirror Skin: In Situ Visualization of Robot Touch Intent on Robotic Skin

2025-12-12

AI Summary

Current robot touch-intent communication methods lack spatial precision and semantic depth, undermining safety and predictability in physical human–robot interaction (pHRI). To address this, we propose an octopus-inspired mirrored robotic skin that employs an in-situ mirror visualization paradigm: real-time human pose estimation is spatially mapped onto the robot’s intended contact region, enabling simultaneous spatial alignment, semantic concretization, and temporal predictability of “who, where, and when” touch intent. The system integrates high-resolution flexible displays, real-time human pose estimation, VR-enabled co-design, and controlled human-subject experiments. User studies demonstrate significantly improved touch-intent recognition accuracy and substantially reduced response latency. This work presents the first empirical validation of spatially aligned visual feedback as an effective and superior modality for conveying touch intent in pHRI.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Interaction Techniques and Devices
• Computer Vision: Vision for Robotics & Autonomous Driving

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Effective communication of robotic touch intent is a key factor in promoting safe and predictable physical human-robot interaction (pHRI). While intent communication has been widely studied, existing approaches lack the spatial specificity and semantic depth necessary to convey robot touch actions. We present Mirror Skin, a cephalopod-inspired concept that utilizes high-resolution, mirror-like visual feedback on robotic skin. By mapping in-situ visual representations of a human's body parts onto the corresponding robot's touch region, Mirror Skin communicates who shall initiate touch, where it will occur, and when it is imminent. To inform the design of Mirror Skin, we conducted a structured design exploration with experts in virtual reality (VR), iteratively refining six key dimensions. A subsequent controlled user study demonstrated that Mirror Skin significantly enhances accuracy and reduces response times for interpreting touch intent. These findings highlight the potential of visual feedback on robotic skin to communicate human-robot touch interactions.

Problem

• Communicates robot touch intent for safe human-robot interaction
• Provides spatial and semantic details on who, where, and when of touch
• Enhances accuracy and reduces response time in interpreting touch intent

Innovation

• High-resolution mirror-like visual feedback on robotic skin
• In-situ visual mapping of human body parts onto robot touch regions
• Iterative design refinement through virtual reality expert exploration