Toward a human-like biped robot gait: Biomechanical analysis of human locomotion recorded by Kinect-based Motion Capture system
B.M. Gabbasov, Igor Danilov, Ilya Afanasyev, Evgeni Magid
- Year
- 2015
- Citations
- 12
Abstract
This paper presents biomechanical analysis of human locomotion recorded by Motion Capture (MoCap) system based on four Kinect 2 sensors and iPi Soft markerless tracking and visualization technology. To analyze multi-depth sensor video recordings we utilize iPi Mocap Studio software and iPi Biomech Add-on plug-in, which provide us visual and biomechanical human gait data: linear and angular joint coordinates, velocity, acceleration, center of mass (CoM) position, skeleton and 3D point cloud. The final analysis was performed in MATLAB environment, calculating zero moment point (ZMP) and ground projection of the CoM (GCoM) trajectories from human body dynamics by considering human body as a single weight point. These were followed by GCoM and ZMP error estimation. The further objective of our research is to reproduce the obtained with our MoCap system human-like gait with Russian biped robot AR-601M.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002