Environment-Adaptive Gait Planning through Reinforcement Learning for Lower-Limb Exoskeletons

Powered lower limb exoskeletons (LLEs) have demonstrated significant potential in augmenting mobility and providing rehabilitative support for individuals with gait impairments. However, most assistive exoskeletons rely on predetermined gait trajectories, limiting their effectiveness in unstructured environments. To address this limitation, Environment Adaptive Gait Planning (EAGP) strategies have emerged, focusing on real-time trajectory adaptation based on environmental perception. This work introduces a novel approach to EAGP using Deep Reinforcement Learning (DRL) for generating adaptive foot trajectories, specifically targeting obstacle avoidance during ground walking. The proposed method optimizes trajectory smoothness, environmental interaction, and compliance with exoskeleton kinematic constraints, as validated by simulations. This study advances the state-of-the-art of adaptive gait planning by leveraging the generalization capabilities of DRL, paving the way for enhanced mobility in real-world applications.