Research Analyzer
← Back ICRA 2026

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

PDF

AI summary

Key figure (auto-extracted from paper)
Combining symmetry-aware trajectory learning with energy-tank passivity control safely reduces peak interaction forces by 40 N while improving tracking accuracy and whole-body smoothness in ankle exoskeletons.
Rehabilitation robotics Ankle exoskeletons Symmetry-aware skill transfer Passivity-based control Wearable sensing Gait analysis

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.

Index terms

Control Architectures and Programming Rehabilitation Robotics Prosthetics and Exoskeletons

Related papers