Biofeedback speeds adaptation to exoskeleton gait assistance
Ava Lakmazaheri, Steven H. Collins
- Year
- 2025
- Citations
- 2
- Access
- Open access
Abstract
Abstract Exoskeletons may enhance mobility, but users require extensive training to receive their full benefit. While augmented feedback can accelerate motor learning, its application to exoskeleton-assisted gait is limited by the complexity of locomotor function and human-robot interaction. We developed a visual biofeedback system to guide novice users of an ankle exoskeleton to modify their ankle joint kinematics and foot placement toward patterns associated with improved energy economy. Biofeedback-based training doubled the energy savings from exoskeleton use, enabling people to achieve benefits comparable to fully adapted users in one-quarter of the time. Notably, participants in this study had not fully adapted after the hour-long training session, underscoring the task’s difficulty and suggesting that greater benefit from exoskeletons may be unlocked with continued use of this approach. Energy savings were associated with increased exploration and progression toward lower-cost gait parameters in task-relevant dimensions. Our findings demonstrate that biofeedback can accelerate motor adaptation to exoskeletons, potentially enhancing their effectiveness and promoting broader device adoption.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002