The nervous system that human beings use to control balance is remarkably adaptable to a wide variety of environments and conditions. This neural system is likely a combination of many inputs and feedback control loops working together. The ability to emulate this system of balance could be of great value in understanding and developing solutions to proprioceptive disorders and other diseases that affect the human balance control system. Additionally, the process of emulating the human balance system may also have widespread applications to the locomotion capabilities of many types of robots, in both bipedal and non-bipedal configurations.
The goal of this project is to simulate a proprioceptive system controlled by a simulated neural network. The system uses an inverted pendulum model with an actuator simulating the ankle joint in human beings and an inertial measurement unit (IMU) to approximate the vestibular system (inner ear). A desired angle is calculated in MATLAB and the error between the desired angle and the angle of the actuator is then sent as input to the neural network. The neural network responds to this input and sends commands back to the actuator to bring the inverted pendulum back to an upright position.
Future work on the project aims to integrate the data collected by the IMU with the data from the actuator as an additional input to the neural network.
Caneer, Joshua E., "Simulation of Human Balance Control Using an Inverted Pedulum Model" (2019). Undergraduate Research & Mentoring Program. 39.