Browse > Article
http://dx.doi.org/10.4218/etrij.2018-0057

Work chain-based inverse kinematics of robot to imitate human motion with Kinect  

Zhang, Ming (Key Lab of Broadband Wireless Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Ministry of Education)
Chen, Jianxin (Key Lab of Broadband Wireless Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Ministry of Education)
Wei, Xin (Key Lab of Broadband Wireless Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Ministry of Education)
Zhang, Dezhou (Key Lab of Broadband Wireless Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Ministry of Education)
Publication Information
ETRI Journal / v.40, no.4, 2018 , pp. 511-521 More about this Journal
Abstract
The ability to realize human-motion imitation using robots is closely related to developments in the field of artificial intelligence. However, it is not easy to imitate human motions entirely owing to the physical differences between the human body and robots. In this paper, we propose a work chain-based inverse kinematics to enable a robot to imitate the human motion of upper limbs in real time. Two work chains are built on each arm to ensure that there is motion similarity, such as the end effector trajectory and the joint-angle configuration. In addition, a two-phase filter is used to remove the interference and noise, together with a self-collision avoidance scheme to maintain the stability of the robot during the imitation. Experimental results verify the effectiveness of our solution on the humanoid robot Nao-H25 in terms of accuracy and real-time performance.
Keywords
humanoid robot; imitation; inverse kinematics; motion tracking; work-chains;
Citations & Related Records
연도 인용수 순위
  • Reference
1 M. Alibeigi et al., Inverse kinematics based human mimicking system using skeletal tracking technology, J. Intell. Robot. Syst.: Theory Applicat. J. 85 (2017), no. 1, 27-45.   DOI
2 Microsoft, Microsoft Kinect V1.0 information, Accessed Aug. 14, 2017, available at www.kinectforwindows.com.
3 Xsens, Xsens MVN motion capture system, Accessed Aug. 15, 2017, available at www.xsens.com/products/xsens-mvn-animate.
4 B. Kruger et al., A study on perceptual similarity of human motions, Workshop Virtual Reality Interaction Phys. Simulation, Lyon, France, Dec. 5-6, 2011, pp. 65-72.
5 J. K. T. Tang et al., Emulating human perception of motion similarity, Comput. Animat. Virtual Worlds J. 19 (2008) no. 3-4, 211-221.   DOI
6 S. R. Buss and J. S. Kim, Selectively damped least squares for inverse kinematics, J. Graph. GPU Game Tools, 10 (2005), no. 3, 37-49.   DOI
7 T. F. Chan et al., A weighted least-norm solution based scheme for avoiding joints limits for redundant manipulators, IEEE Trans. Robot. Autom. 11 (1995), no. 2, 286-292.   DOI
8 K. Madsen, H. B. Nielsen, and O. Tingleff, Methods for non-linear least squares problems, Informatics and Mathematical Modelling, Technical University of Denmark; Denmark, Apr. 2004, pp. 487-490.
9 N. Kofinas, E. Orfanoudakis, and M. G. Lagoudakis, Complete analytical inverse kinematics for NAO, Proc. IEEE Int. Conf. Auton. Robot. Syst. (Robotica), Lisbon, Portugal, Apr. 24, 2013, pp. 1-6.
10 Aldebaran, NAO-H25 Joints information, Accessed Aug. 16, 2017a, available at http://doc.aldebaran.com/21/family/nao_h25/joints_h25.html#h25-joints 2015.
11 J. Angeles, Fundamentals of robotic mechanical systems, Springer, USA, 2007, pp. 139-179.
12 J. Chen et al., Lower-body control of humanoid robot NAO via Kinect, Multimed. Tools Applicat. 77 (2017), no. 9, 10883-10898.
13 Aldebaran, NAO qi related to self-collision avoidance, Accessed Aug. 16, 2017b, available at http://doc.aldebaran.com/2-1/naoqi/motion/reflexes-collision-avoidance.html 2015.
14 S. Kim et al., Stable whole-body motion generation for humanoid robots to imitate human motions, Proc. IEEE/RSJ Int. Conf. Intell. Robot. Syst. (IROS), St. Louis, MO, USA, Oct. 10-15, 2009, pp. 2518-2524.
15 W. Suleiman et al., On human motion imitation by humanoid robot, Proc. IEEE Int. Conf. Robot. Autom. (ICRA), Pasadena, CA, USA, May 19-23, 2008, pp. 2697-2704.
16 R. Chalodhorn et al., Learning to walk through imitation, Int. Conf. Artif. Intell. (IJCAI), Hyderabad, India, Jan. 2007, pp. 2084-2090.
17 N. Yang et al., A study of the human-robot synchronous control system based on skeletal tracking technology, Proc. IEEE Int. Conf. Robot. Biomimetics (ROBIO), Shenzhen, China, Dec. 12-1, 2013, pp. 2191-2196.
18 I. Almetwally and M. Mallem, Real-time tele-operation and telewalking of humanoid Robot Nao using Kinect Depth Camera, Proc. IEEE Int. Conf. Netw., Sens. Contr. (ICNSC), Evry, France, Apr. 10-12, 2013, pp. 463-466.
19 F. Zuher and R. Romero, Recognition of human motions for imitation and control of a humanoid Robot, Conf. Braz. Robot. Symp. Lat. Am. Robot. Symp. (SBR-LARS), Fortaleza, Brazil, Nov.29, 2012, pp. 190-195.
20 J. Koenemann and M. Bennewitz, Whole-body imitation of human motions with a Nao humanoid, Conf. IEEE Human-Robot Interact. (HRI), Boston, MA, USA, Mar. 5-8, 2012, pp. 425-425.
21 J. Koenemann, F. Burget, and M. Bennewitz, Real-time imitation of human whole-body motions by humanoids, Proc. IEEE Conf. Robot. Autom. (ICRA), Hong Kong, China, May 31-June 7, 2014, pp. 2806-2812.
22 F. Wang et al., A real-time human imitation system, Proc. Intell. Contr. Autom., Beijing, China, July 6-8, 2012, pp. 3692-3697.
23 L. Zhang, Z. Cheng, and Y. Gan, Fast human whole body motion imitation algorithm for humanoid robots, Conf. IEEE Robot. Biomimetics, Qingdao, China, Dec. 3-7, 2016, pp 1430-1435.
24 S. Mukherjee, D. Paramkusam, and S. K. Dwivedy, Inverse kinematics of a NAO humanoid robot using Kinect to track and imitate human motion, Conf. RACE, Chennai, India, Feb. 18-20, 2015, pp. 1-7.