A simple and fast geometric kinematic solution for imitation of human arms by a NAO humanoid robot

This paper addresses the imitation procedure of the human arms by a NAO humanoid robot. The exact position of the user arms are obtained based on the position of him/her shoulders, elbows and wrists, which are obtained by using the Microsoft Kinect as a 3-dimensional optical motion capture sensor. Communication between the kinect and computer server is done by using Robot Operating System (ROS) framework. Due to the differences between human and humanoid robot dimensions, captured motion should be mapped on the robot's dimensions. Mapped data is used for kinematic operation. In this paper, the inverse kinematic problem is solved by proposing an approach based on a novel simplified geometric method. In this approach, the distal form of the Denavit-Hartenberg convention of both arms is studied and a simple and fast geometric inverse kinematic solution is proposed. Finally, the proposed method is verified experimentally in Webots simulator and on a real NAO-H25 humanoid robot. Experiments are resulting in a coherent imitation between human arm and NAO with respect to time response.

[1]  Kerstin Dautenhahn,et al.  Getting to know each other - Artificial social intelligence for autonomous robots , 1995, Robotics Auton. Syst..

[2]  Zhaoqin Peng,et al.  Kinematics mapping and similarity evaluation of humanoid motion based on human motion capture , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[3]  Masayuki Inaba,et al.  Learning by watching: extracting reusable task knowledge from visual observation of human performance , 1994, IEEE Trans. Robotics Autom..

[4]  Behzad Dariush,et al.  Online Transfer of Human Motion to Humanoids , 2009, Int. J. Humanoid Robotics.

[5]  Zhengyou Zhang,et al.  Microsoft Kinect Sensor and Its Effect , 2012, IEEE Multim..

[6]  Maren Bennewitz,et al.  Whole-body imitation of human motions with a Nao humanoid , 2012, 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[7]  Yoshihiko Nakamura,et al.  Motion capture based human motion recognition and imitation by direct marker control , 2008, Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots.

[8]  Xinyu Wu,et al.  A Real-Time Human Imitation System Using Kinect , 2015, Int. J. Soc. Robotics.

[9]  Ales Ude,et al.  Enabling real-time full-body imitation: a natural way of transferring human movement to humanoids , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[10]  Jean-Paul Laumond,et al.  On Real-time Whole-body Human to Humanoid Motion Transfer , 2010, ICINCO.

[11]  Christine Chevallereau,et al.  Offline Imitation of a Human Motion by a Humanoid Robot Under Balance Constraint , 2014 .

[12]  Sophie Sakka,et al.  Tasks prioritization for whole-body realtime imitation of human motion by humanoid robots , 2014 .

[13]  Sophie Sakka,et al.  Support changes during online human motion imitation by a humanoid robot using task specification , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Gillian M. Hayes,et al.  A Robot Controller Using Learning by Imitation , 1994 .

[15]  Peter Bakker,et al.  Robot see, robot do: An overview of robot imitation , 1996 .

[16]  Jorge Angeles,et al.  Fundamentals of Robotic Mechanical Systems , 2008 .

[17]  Maren Bennewitz,et al.  Real-time imitation of human whole-body motions by humanoids , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).