Human level walking gait modeling and analysis based on semi-Markov process

Evaluation of individual gait pattern is important for both abnormal gait diagnosis and gait rehabilitation in mobility impaired people. In this paper, semi-Markov process (SMP) is applied to model and analyze human gait in level walking. Gait states are detected from ground reaction forces (GRFs), and gait cycles are described as state transitions in a gait Markov chain (GMC) with sojourn times. Several gait features are defined and online estimated based on the SMP model. With this model, abnormal gait patterns are further analyzed and indexes for gait abnormality assessment are proposed. Experiments of gait analyses with proposed method are conducted on subjects with different health conditions. Results show that individual gait pattern can be successfully obtained and evaluated. Potential applications in gait diagnosis and powered lower limb orthosis (PLLO) control for gait assistance are also discussed.