This paper presents a new contact and wearable sensing system for estimating the posture and joint angles of the human body using foot pressure distribution information from a sensor on the plantar region. The system differs from previous ones as it doesn’t require the sensor to be near the target joint or body. The estimation is done using a multivariate linear regression model. The results show that it is possible to estimate posture and joint angles from foot pressure distribution information. The method was validated by morphological computation, confirming that it is enabled by foot morphology. The method is also considered as physical reservoir computing, with the human foot used as a computational resource.
Publication date: 25 Jan 2024
Project Page: Not provided
Paper: https://arxiv.org/pdf/2401.12464
