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

다국어 초록 (Multilingual 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.

참고문헌 (Reference)

1 Xsens, "Xsens MVN motion capture system"

2 J. Koenemann, "Whole-body imitation of human motions with a Nao humanoid" 425-425, 2012

3 S. Kim, "Stable whole-body motion generation for humanoid robots to imitate human motions" 2518-2524, 2009

4 S. R. Buss, "Selectively damped least squares for inverse kinematics" 10 (10): 37-49, 2005

5 F. Zuher, "Recognition of human motions for imitation and control of a humanoid Robot" 190-195, 2012

6 I. Almetwally, "Real-time tele-operation and telewalking of humanoid Robot Nao using Kinect Depth Camera" 463-466, 2013

7 J. Koenemann, "Real-time imitation of human whole-body motions by humanoids" 2806-2812, 2014

8 W. Suleiman, "On human motion imitation by humanoid robot" 2697-2704, 2008

9 Aldebaran, "NAO-H25 Joints information"

10 Aldebaran, "NAO qi related to self-collision avoidance"

11 Microsoft, "Microsoft Kinect V1.0 information"

12 K. Madsen, "Methods for non-linear least squares problems" 487-490, 2004

13 J. Chen, "Lower-body control of humanoid robot NAO via Kinect" 77 (77): 10883-10898, 2017

14 R. Chalodhorn, "Learning to walk through imitation" 2084-2090, 2007

15 S. Mukherjee, "Inverse kinematics of a NAO humanoid robot using Kinect to track and imitate human motion" 1-7, 2015

16 M. Alibeigi, "Inverse kinematics based human mimicking system using skeletal tracking technology" 85 (85): 27-45, 2017

17 J. Angeles, "Fundamentals of robotic mechanical systems" Springer 139-179, 2007

18 L. Zhang, "Fast human whole body motion imitation algorithm for humanoid robots" 1430-1435, 2016

19 J. K. T. Tang, "Emulating human perception of motion similarity" 19 (19): 211-221, 2008

20 N. Kofinas, "Complete analytical inverse kinematics for NAO" 1-6, 2013

21 T. F. Chan et al., "A weighted least-norm solution based scheme for avoiding joints limits for redundant manipulators" 11 (11): 286-292, 1995

22 B. Kruger, "A study on perceptual similarity of human motions" 65-72, 2011

23 N. Yang, "A study of the human-robot synchronous control system based on skeletal tracking technology" 2191-2196, 2013

24 F. Wang, "A real-time human imitation system" 3692-3697, 2012