Lower-body control of humanoid robot NAO via Kinect. Issue 9 (May 2018)

• Record Type: Journal Article
• Authors: Chen, Jianxin; Wang, Guanwen; Hu, Xiao; Shen, Jiayun
• Is Part Of: Multimedia tools and applications. Volume 77:Issue 9(2018)
• Page Start: 10883
• Page End: 10898
• Publication Date: 2018-05
• Subjects: Humanoid robot -- Kinect -- Lower-body -- Joint angle
• DOI: 10.1007/s11042-017-5332-3
• Languages: English
• ISSNs: 1380-7501

Abstract

Abstract Humanoid robot has been concerned as it can perform some movements as human, especially imitating human motion in real time with motion tracking equipments. To imitate the human motion, there are still some challenges for the lower-body control of robot due to the physical difference between human and robot. In this paper, we propose a joint angle-based control (JAC) scheme for the lower-body control of humanoid robot to imitate human motion via Kinect sensor. Due to factors such as noise, tracking error and robot joint constrains, the motion information captured from the Kinect sensor applied to the robot directly will arise the problem of balance control. To overcome it, we optimize the joint angles in the lower-body of NAO, and define a gain factor to compensate the difference between the human motion and the robot so as to keep the balance of humanoid robot during imitation. Experimental results show that the proposed control scheme works efficiently even when the humanoid robot performs some complex movements such as standing on single foot.