Hybrid filters and feedback mechanism for wearable-based human-manipulator interface

Abstract

Purpose – This paper aims to develop a wearable-based human-manipulator interface which integrates the interval Kalman filter (IKF), unscented Kalman filter (UKF), over damping method (ODM) and adaptive multispace transformation (AMT) to perform immersive human-manipulator interaction by interacting the natural and continuous motion of the human operator’s hand with the robot manipulator. Design/methodology/approach – The interface requires that a wearable watch is tightly worn on the operator’s hand to track the continuous movements of the operator’s hand. Nevertheless, the measurement errors generated by the sensor error and tracking failure signicantly occur several times, which means that the measurement is not determined with sufficient accuracy. Due to this fact, IKF and UKF are used to compensate for the noisy and incomplete measurements, and ODM is established to eliminate the influence of the error signals like data jitter. Furthermore, to be subject to the inherent perceptive limitations of the human operator and the motor, AMT that focuses on a secondary treatment is also introduced. Findings – Experimental studies on the GOOGOL GRB3016 robot show that such a wearable-based interface that incorporates the feedback mechanism and hybrid filters can operate the robot manipulator more flexibly and advantageously even if the operator is nonprofessional; the feedback mechanism introduced here can successfully assist in improving the performance of the interface. Originality/value – The interface uses one wearable watch to simultaneously track the orientation and position of the operator’s hand; it is not only avoids problems of occlusion, identification and limited operating space, but also realizes a kind of two-way human-manipulator interaction, a feedback mechanism can be triggered in the watch to reflect the system states in real time. Furthermore, the interface gets rid of the synchronization question in posture estimation, as hybrid filters work independently to compensate the noisy measurements respectively.

User-friendly task level programming based on an online walk-through teaching approach

“…Yepes et al (2013) presented an Android operating system-based application that communicates with an industrial robot, Kuka KR-6, through universal serial bus to serial connection, to control it with the on-board accelerometers and gyroscopes of a tablet or smartphone, intended for use in telemedicine procedures. Zhang et al (2015) used an Android-based tablet PC as a human-manipulator interface. Finally, Neira et al (2013) presented a flexible solution that can be incorporated in most of the Android devices on the market, implemented and tested in a manufacturing scenario by creating adaptive interfaces for different types of users based on user roles, tasks, the state of the system and the context.…”