applied sciences Article Real-Time Whole-Body Imitation by Humanoid Robots and Task-Oriented Teleoperation Using an Analytical Mapping Method and Quantitative Evaluation Zhijun Zhang 1,2, * ,† , Yaru Niu 1,2, * ,† , Ziyi Yan 1,2 and Shuyang Lin 1 1 School of Automation Science & Engineering, South China University of Technology, Guangzhou 510641, China; auzyyan@mail.scut.edu.cn (Z.Y.); aulinshuyang@mail.scut.edu.cn (S.L.) 2 Center for Brain Computer Interfaces & Brain Information Processing, South China University of Technology, Guangzhou 510641, China * Correspondence: auzjzhang@scut.edu.cn (Z.Z.); auchrisniu@mail.scut.edu.cn (Y.N.) † These authors contributed equally to this work. Received: 23 August 2018; Accepted: 18 October 2018; Published: 22 October 2018   Abstract: Due to the limitations on the capabilities of current robots regarding task learning and performance, imitation is an efficient social learning approach that endows a robot with the ability to transmit and reproduce human postures, actions, behaviors, etc., as a human does. Stable whole-body imitation and task-oriented teleoperation via imitation are challenging issues. In this paper, a novel comprehensive and unrestricted real-time whole-body imitation system for humanoid robots is designed and developed. To map human motions to a robot, an analytical method called geometrical analysis based on link vectors and virtual joints (GA-LVVJ) is proposed. In addition, a real-time locomotion method is employed to realize a natural mode of operation. To achieve safe mode switching, a filter strategy is proposed. Then, two quantitative vector-set-based methods of similarity evaluation focusing on the whole body and local links, called the Whole-Body-Focused (WBF) method and the Local-Link-Focused (LLF) method, respectively, are proposed and compared. Two experiments conducted to verify the effectiveness of the proposed methods and system are reported. Specifically, the first experiment validates the good stability and similarity features of our system, and the second experiment verifies the effectiveness with which complicated tasks can be executed. At last, an imitation learning mechanism in which the joint angles of demonstrators are mapped by GA-LVVJ is presented and developed to extend the proposed system. Keywords: humanoid robot; whole-body imitation; social learning; motion mapping; teleoperation for tasks; similarity evaluation 1. Introduction Robots can be used in place of humans to perform remote tasks such as remote meetings/ interactions [1,2], telesurgery [3–6], rehabilitation [7], and search and rescue [8]. However, the ability to control a humanoid robot with a high degree of freedom using a traditional controller or through preprogramming based on human experience strongly depends on the operation skills of the users, the programming skills of the developers, and the availability of extensive experience. As an alternative, imitation is an efficient social learning approach that endows a robot with the ability to transmit and reproduce human postures, actions, behaviors, etc., as a human does. The questions of how to achieve accurate, stable, and complete whole-body imitation and how to evaluate the imitation similarity are two basic issues facing this approach. Appl. Sci. 2018, 8, 2005; doi:10.3390/app8102005 www.mdpi.com/journal/applsci