Symmetry-Aware Skill Transfer with Energy-Tank Passive Control for Ankle Exoskeletons
Etienne Largeteau, loqmane bencharif, Bangaly CONTE, Abderahim Ibset, Hang Su, Olivier BRUNEAU, Samer Alfayad
AI summary
Problem
Ankle exoskeletons struggle to generate stable, subject-specific gait references that adapt to timing variability, and enforcing interaction safety to prevent unbounded energy injection into the human–robot system remains a persistent challenge.
Approach
The framework uses Dynamic Time Warping and Gaussian Mixture Regression to extract and reconstruct phase-consistent ankle trajectories from wearable IMU data, then tracks them with a PID controller wrapped in an energy-tank layer that adaptively gates torque to guarantee passivity.
Key results
- DTW-GMR pipeline learns subject-specific templates and reconstructs contralateral references from unilateral sensing
- Energy-tank passivity layer bounds power exchange and guarantees safety under timing errors
- Simulation reduces ankle-angle tracking RMSE by 52% and improves center-of-mass smoothness
- Benchtop experiments cut peak interaction force by 40 N, reducing mechanical strain on users
Why it matters
Provides a safe, adaptive, and clinically viable control framework for next-generation wearable ankle exoskeletons in rehabilitation and mobility assistance.
Abstract
This paper presents a unified framework that combines symmetry-aware skill transfer with energy-tank pas- sive control to achieve safe and adaptive ankle exoskeleton assistance. Subject-specific ankle references are first extracted from wearable IMU data : Dynamic Time Warping (DTW) aligns gait cycles onto a normalized phase axis , and Gaussian Mixture Regression (GMR) synthesizes smooth probabilistic templates suitable for online modulation. When only unilateral sensing is available, contralateral trajectories are reconstructed through either a half-period phase shift or a DTW-informed nonlinear mapping, enabling robust bilateral assistance. These references are then tracked by a joint-space PID controller wrapped with an energy tank, which bounds power exchange and prevents unintended energy injection. In simulation ex- periments, the proposed controller improved center-of-mass smoothness relative to plain PID. Benchtop validation confirms the efficacy of both GMR-generated and symmetric-generated trajectories. Furthermore, experimental results show a reduc- tion of 40 N in peak interaction force (from 120 N to 80 N), resulting in less mechanical strain on the user. By unifying phase-consistent gait synthesis with passivity shaping, this work advances ankle exoskeleton assistance that is individualized, robust, and inherently safe.