FUNTOM AR: AR-Based Phantom Limb Pain Rehabilitation System

Phantom limb pain (PLP) is a debilitating neuropathic condition affecting amputees, characterized by painful sensations perceived in a missing limb. Traditional treatments, including medication, nerve blocks, and mirror therapy, often provide only partial relief and may be impractical for continuous, home-based use due to cost, side effects, or reliance on clinical settings. In recent years, augmented reality (AR) has emerged as a promising tool for PLP rehabilitation by providing immersive visual feedback to reduce sensorimotor conflict. However, existing AR systems remain limited by high cost, bulky hardware, lack of personalization, and insufficient progress tracking. This project proposes an AR-based therapeutic system designed to alleviate phantom limb pain through interactive, personalized rehabilitation exercises. The system consists of a wearable AR headset with a birdbath optical display, EMG sensors for capturing residual muscle activity, and a Raspberry Pi 5 processing unit to enable real-time control of a virtual limb. The solution incorporates two therapeutic modes: a therapist-guided animation sequence and an EMG-driven interactive system where users control the virtual limb through muscle activation. An AI-powered cloud backend personalizes the virtual arm’s appearance using unsupervised skin-tone analysis and adapts task difficulty based on user performance. By integrating accessible hardware, adaptive software, and cloud-based monitoring, the system aims to provide an engaging, portable, and clinically viable tool for phantom pain management. It is designed to complement existing therapies, support independent home use, and offer therapists actionable insights through a dedicated dashboard. This work outlines the engineering design, architecture, and implementation approach, addressing key challenges in real-time processing, sensor integration, and user-centered design for AR-mediated rehabilitation.

Project Details

[photo]