Design of soft smart shoes for joint angle estimation in human gait

Abstract

Abstract Human gait involves activities in nervous and biomechanics of the musculoskeletal system. Thus, approaching the dynamics may be challenging. This paper aims to present the design of soft smart shoes for joint angle estimation in human gait. There are three pneumatic chambers at the heel, arch, and forefoot of the soft sole. Barometers embedded in every chambers are used to measure the ground reaction forces (GRFs). The inertial sensors are installed on the outsole of shoes to detect the foot attitudes. The soft soles are made of silicone rubber to provide good compliance and ensure the comfort of human. Gaussian process regression (GPR) is established and serves as the mathematics foundation to explore the deep layer correlation between the joint angle and GRFs and foot attitudes which are regarded as the inputs of the model. The statistic nature of the proposed model offers superior flexibility and encouraging estimation results of joint angles. One potential use of the novel designed shoes and the proposed joint estimation method is the high-level control of exoskeletons and prosthetic legs. Finally, experiments were conducted to verify the superiority of the proposed algorithms.