Prediction of Plantar Forces During Gait Using Wearable Sensors and Deep Neural Networks.

To enable on-time and high-fidelity lower-limb exoskeleton control, it is effective to predict the future human motion from the observed status. In this research, we propose a novel method to predict future plantar force during the gait using IMU and plantar sensors. Deep neural networks (DNN) are used to learn the non-linear relationship between the measured sensor data and the future plantar force data.

Estimation of the Operating Force From the Human Motion.

In this research, we propose a new method to estimate the operating force exerted when moving an object with the hands by observing the human motion only. The required force for moving the object can be estimated without equipping any sensors on the object or on the human body. From the measured joint angles, we calculate the center of mass and the hand's position using a human model.