Hybrid Model-Learning Decoupled Control for Tendon-Driven Multi-Segment Continuum Robotic Bronchoscope
Yawen Deng, Chao Guo, Wenhao He, Gui-Bin Bian
AI summary
Problem
Long, elastic tendon transmissions in multi-segment continuum bronchoscopes cause severe inter-segment coupling and nonlinear disturbances, degrading navigation accuracy and safety in narrow airways.
Approach
The method online-learns a pose-dependent coupling map using recursive least squares to cancel proximal drift, while adaptively compensating for tendon elasticity and backlash in real time.
Key results
- Reduced mean proximal coupling angle to 5.84° at 90° distal bend
- Achieved 86.47% reduction in coupling rate versus piecewise constant curvature baseline
- Enabled stable, independent control of proximal and distal segments in free and restricted environments
- Validated on a two-segment prototype with electromagnetic tracking and safety-constrained actuation
Why it matters
Improves precision and safety for minimally invasive lung interventions by enabling reliable navigation in tortuous bronchial trees.
Abstract
Flexible tendon-driven multi-segment robotic bronchoscopes can reach peripheral lung regions for min- imally invasive diagnosis and therapy. However, long ten- don transmissions introduce friction, elasticity, and backlash, which couple the motion of adjacent segments and reduce operational accuracy and safety. This paper proposes a hy- brid model-learning decoupled control framework for a two- segment bronchoscope that explicitly cancels distal-to-proximal coupling while compensating transmission disturbances. The method learns online a pose-dependent coupling map from synchronized encoder and electromagnetic measurements and uses it for feedforward cancellation in the proximal channel. In addition, an adaptive disturbance compensation module estimates per-tendon compliance and backlash to correct stretch and dead-zone effects. A two-segment tendon-driven robotic bronchoscope platform demonstrated a substantial reduction in proximal drift during distal actuation. At a 90° distal bend, the mean proximal coupling angle was 5.84°. Compared with the most commonly used piecewise constant curvature model baseline, the proposed controller achieved stronger motion decoupling, reducing the coupling rate by 86.47%, thereby enabling more precise bronchoscopic manipulation in anatom- ically constrained environments.