Objective: In this article, we present the conceptual development of a robotics platform, called ALICE (Assistive Lower Limb Controlled Exoskeleton), for kinetic and kinematic gait characterization. The ALICE platform includes a robotics wearable exoskeleton and an on-board muscle driven simulator to estimate the user’s kinetic parameters. Background: Even when the kinematics patterns of the human gait are well studied and reported in the literature, there exists a considerable intra-subject variability in the kinetics of the movements. ALICE aims to be an advanced mechanical sensor that allows us to compute real-time information of both kinetic and kinematic data, opening up a new personalized rehabilitation concept. Methodology: We developed a full muscle driven simulator in an open source environment and validated it with real gait data obtained from patients diagnosed with multiple sclerosis. After that, we designed, modeled, and controlled a 6 DoF lower limb exoskeleton with inertial measurement units and a position/velocity sensor in each actuator. Significance: This novel concept aims to become a tool for improving the diagnosis of pathological gait and to design personalized robotics rehabilitation therapies. Conclusion: ALICE is the first robotics platform automatically adapted to the kinetic and kinematic gait parameters of each patient.
Learning a Predictive Model of Human Gait for the Control of a Lower-limb Exoskeleton
