Motion Compensation and Adaptive Force Control Via iOCT�FBG Sensor Fusion for Robotic Subretinal Injection
Aoqi Long, Tianle Wu, Chongyang She, Mojtaba Esfandiari, Peter Gehlbach, Russell H. Taylor, Ioan Iulian Iordachita
AI summary
Problem
Current robotic subretinal injection systems struggle with physiological retinal motion and lack real-time tip force feedback, risking irreversible tissue damage during delicate therapeutic deliveries.
Approach
The framework integrates a finite-state machine with an LSTM-enhanced Kalman filter for motion prediction and an adaptive compliance estimator to dynamically blend low-rate vision data with high-rate force feedback for precise needle tracking.
Key results
- 40% reduction in tracking RMSE (to 18.5 µm) under simulated motion
- 96.7% of tip forces maintained within ±0.7 mN safety threshold
- Control latency minimized to 0.25 seconds for real-time corrections
- Unified FSM and adaptive force compensation framework for surgical phase coordination
Why it matters
Enhances precision and safety for robot-assisted retinal surgeries, advancing reliable therapeutic delivery for fragile ocular tissues.
Abstract
Subretinal injection is a highly delicate procedure that demands micron-level precision to avoid irreversible retinal damage. Current robotic systems achieve accurate positioning but remain limited by retinal motion and the lack of tip force feedback. We present the first adaptive tip force compensation framework for robotic subretinal injection, fusing intraoper- ative optical coherence tomography (iOCT) vision with fiber Bragg grating (FBG) force sensing. Our architecture integrates a finite-state machine (FSM) for surgical phase coordina- tion, a Long Short-Term Memory (LSTM) enhanced residual Kalman filter for real-time motion prediction, and an adaptive compliance estimator for safe force regulation. Compared to previous vision-only and force-only method, ex vivo experiments on porcine eyes demonstrate robust improvements: the root- mean-square tracking error reduced by 40% (to 18.5 μm), the maximum absolute error lowered by 2.5 times, and 96.7% of tip forces maintained within ± 0.7 mN. Control delays were minimized to 0.25 s, enabling low-latency corrections beyond freehand capabilities. Our system enhances precision and safety in fragile retinal tissues, advancing the potential for reliable robot-assisted surgeries for retinal diseases.