Adaptive Gait Assistance for Foot Drop Rehabilitation Based on Uncertainty Fusion of Contralateral Limb Information

Foot drop resulting from neurological injury severely compromises mobility and gait stability, yet existing assistive solutions often overlook physiological bilateral coordination and lack adaptability to individual gait variability. This study introduces a novel adaptive gait assistance framework for a soft exosuit that simultaneously aims to restore inter-limb coordination and generate personalized ankle joint assistance. First, we design a contralateral-guided adaptive phase synchronization engine that transforms healthy-limb information into an ideal phase reference for the impaired limb, enabling active correction of gait asymmetry. Second, to reconcile stability and personalization, we propose an uncertainty fusion-based adaptive gait assistance that estimates the real-time confidence of each model, arbitrates and fuses their predictions, and produces assistance trajectories that are both robust and individualized. After demonstrating high predictive accuracy and robustness in validation experiments with healthy subjects, a clinical evaluation involving five individuals with foot drop showed significant improvements in ankle kinematics, walking speed, and gait symmetry. Subjective feedback confirmed superior comfort, balance, and confidence over baseline and preset assistance. These preliminary results suggest that the proposed framework can improve gait kinematics, symmetry, and user-perceived walking performance, and support its potential as a personalized assistance strategy for foot-drop rehabilitation.