RABBIT: A Robot-Assisted Bed Bathing System with Multimodal Perception and Integrated Compliance

2024-01-26

IEEE/ACM International Conference on Human-Robot Interaction

AI Summary

This study addresses the clinical challenge of providing safe, comfortable, and protocol-compliant bed baths for bedridden patients. Methodologically, it introduces a novel robotic assistance system featuring RGB-thermal multimodal perception coupled with semantic skin-state segmentation, human-like motion primitive planning, hybrid soft–hard two-layer compliant control, and a custom-designed flexible end-effector (“Scrubby”) enabling fully autonomous washing, rinsing, and drying. Its core contribution is a multimodal physiological-state-aware adaptive human–robot interaction mechanism. In a user study involving 12 participants—including one with severe mobility impairment—the system achieved 100% task completion without adverse events or reported discomfort; average comfort scores were significantly higher than baseline (p < 0.01). These results demonstrate the system’s efficacy, safety, and clinical feasibility.

Technology Category

Intelligent Robots: Human-Robot InteractionHumans and AI: Interaction Techniques and DevicesNatural Language Processing: Safety and Robustness

Application Category

Responsible Web: Machine-in-the-loop, human agency and autonomyUser Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systemsSystems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

This paper introduces RABBIT, a novel robot-assisted bed bathing system designed to address the growing need for assistive technologies in personal hygiene tasks. It combines multimodal perception and dual (software and hardware) compliance to perform safe and comfortable physical human-robot interaction. Using RGB and thermal imaging to segment dry, soapy, and wet skin regions accurately, RABBIT can effectively execute washing, rinsing, and drying tasks in line with expert caregiving practices. Our system includes custom-designed motion primitives inspired by human caregiving techniques, and a novel compliant end-effector called Scrubby, optimized for gentle and effective interactions. We conducted a user study with 12 participants, including one participant with severe mobility limitations, demonstrating the system’s effectiveness and perceived comfort. Supplementary material and videos can be found on our website emprise.cs.cornell.edu/rabbit.CCS CONCEPTS• Human-centered computing → Accessibility technologies;• Computer systems organization → Robotics; • Social and professional topics → People with disabilities.

Problem

• Develop robot system for safe bed bathing assistance
• Integrate multimodal perception for accurate skin condition detection
• Design compliant hardware for gentle human-robot interaction

Innovation

• Multimodal perception with RGB and thermal imaging
• Dual compliance in software and hardware
• Compliant end-effector Scrubby for gentle interaction