Abstract
With requirements to improve life quality, smart homes, and healthcare have gradually become a future lifestyle. In particular, service robots with human behavioral sensing for private or personal use in the home have attracted a lot of research attention thanks to their advantages in relieving high labor costs and the fatigue of human assistance. In this paper, a novel force-sensing- and robotic learning algorithm-based teaching interface for robot massaging has been proposed. For the teaching purposes, a human operator physically holds the end-effector of the robot to perform the demonstration. At this stage, the end position data are outputted and sent to be segmented via the Finite Difference (FD) method. A Dynamic Movement Primitive (DMP) is utilized to model and generalize the human-like movements. In order to learn from multiple demonstrations, Dynamic Time Warping (DTW) is used for the preprocessing of the data recorded on the robot platform, and a Gaussian Mixture Model (GMM) is employed for the evaluation of DMP to generate multiple patterns after the completion of the teaching process. After that, a Gaussian Mixture Regression (GMR) algorithm is applied to generate a synthesized trajectory to minimize position errors. Then a hybrid position/force controller is integrated to track the desired trajectory in the task space while considering the safety of human-robot interaction. The validation of our proposed method has been performed and proved by conducting massage tasks on a KUKA LBR iiwa robot platform.
Highlights
With the continuous development of technology, many traditional industries have been gradually replaced by high-tech products
To overcome the abovementioned issues, this paper develops a teaching-by-demonstration-based interface using a hybrid position/force control strategy with adjustable stiffness, which can be implemented onto a general robot manipulator with high accuracy, taught by a human operator
The motion planning is performed in 3D task space, where the Gaussian Mixture Model (GMM) is employed to evaluate the Dynamic Movement Primitive (DMP) to learn from multiple demonstrations, and Gaussian Mixture Regression (GMR)
Summary
With the continuous development of technology, many traditional industries have been gradually replaced by high-tech products. To overcome the abovementioned issues, this paper develops a teaching-by-demonstration-based interface using a hybrid position/force control strategy with adjustable stiffness, which can be implemented onto a general robot manipulator with high accuracy, taught by a human operator. This paper mainly presents two aspects of research: the theory of hybrid force/position control with direct human–robot interaction and the experimental studies on a real robotic platform. The motion planning is performed in 3D task space, where the GMM is employed to evaluate the DMP to learn from multiple demonstrations, and GMR is used for the reproduction of the generalized trajectory with a smaller error. 1. This paper employs a teaching interface to perform the robot massaging under the demonstrations of the human operator, and the experimental studies show that, after the teaching process, the robot can generate an even smoother trajectory that strictly adheres to what is requested to be followed. The generalization functions of our proposed method supplies a more flexible and convenient option with only once teaching for multiple tasks to the carers and patients, which promotes the user experiences
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
