It is difficult for a human operator to find roll, pitch, yaw (RPY) that indicates the desired direction of unmanned aerial vehicle (UAV) in a three-dimensional space. Herein, a controller for UAV was developed allowing the human operator controlling the direction of UAV without finding RPY information. The algorithm implemented in the controller automatically calculated RPY information of UAV from the normal vector of the end effector. The developed controller was designed using a parallel mechanism. The joint angles of the controller were measured using potentiometers to estimate the normal vector of the end effector. Five subjects participated in an experiment to control a vector in three-dimensional space to follow a randomly generated target vector using the developed controller and the thumb sticks. The performance of the two controllers was evaluated by two methods: measuring the required time to reduce the error between the controlled vector and the target vector to be less than 0.1 cm and calculating a normalized error between the controlled vector and the target vector after manipulating the controlled vector for 10 seconds. When using the developed controller, the difference in control ability between subjects was reduced, and both required time and normalized error were generally reduced.

Knee contact forces and knee stiffness are biomechanical factors worth considering for walking in knee osteoarthritis patients. However, it is challenging to acquire these factors in real time; thus, making it difficult to use them in robotic rehabilitation and assistive systems. This study investigated whether trained deep neural networks (DNNs) can capture the biomechanical factors only using kinematics during gait, which is possible to measure via sensors in real time. A public dataset of walking on the ground was analyzed through biomechanical analysis to train and test DNNs. Using the training dataset, several DNN topologies were explored via Bayesian optimization to tune the hyperparameters. After optimization, DNNs were trained to estimate the biomechanical factors in a supervised manner. The trained DNNs were then evaluated using two new datasets, which were not used in the training process. The trained DNNs estimated the biomechanical factors with a high level of accuracy in both types of test datasets. Results confirmed that DNNs can estimate the biomechanical factors based on only kinematics during gait.