Stability and Balance Enhancing Control

Falls during daily locomotion are a leading cause of injury among older adults, often resulting from delayed physiological responses to balance disturbances. While robotic exoskeletons hold promise for fall prevention, most current approaches focus on assisting movement to reduce energy rather than actively enhancing stability, and often depend on predefined heuristics instead of adaptive, real-time responses. Moreover, robust and generalizable perturbation detection models remain scarce.

Our group seeks to close these gaps by developing machine learning-driven models for perturbation detection and control architectures optimized for stability, balance recovery, and energy efficiency. By integrating deep learning, wearable sensing, and biomechanical modeling, we aim to create adaptive stabilization strategies that improve exoskeleton-assisted locomotion, with an emphasis on real-world applicability across diverse environments and user populations.

Team Members

• Maria Tagliaferri