Development of whole body motion imitation in humanoid robot

To be able to interact with humans, robot are made to perform similar motion to human movement. Imitation Learning or often called Motion Capture is one of the humanoid robot control techniques with human as an actor and the robot as an agent who will imitate the movement of the actor. This method offers flexibility and ease to modify robot system. This paper explores the method of designing whole body imitation in Humanoid Robot. Robot motion is controlled by Joint Space Control with reference motion captured by natural human motion through Microsoft Kinect. The motions are also preserved in database for later used on robot motion generation and teaching as well. Finally, the effectiveness of the proposed method is illustrated by the experiment of imitating Indonesia Traditional Dances motion using humanoid robot with 18 DOF.

[1]  Y. I. Al-Mashhadany,et al.  Analytical solution for anthropomorphic limbs model, (IK of human arm) , 2009, 2009 IEEE Symposium on Industrial Electronics & Applications.

[2]  John J. Craig Zhu,et al.  Introduction to robotics mechanics and control , 1991 .

[3]  Abdul Muis,et al.  Realistic Motion Preservation-Imitation Development Through Kinect and Humanoid Robot , 2012 .

[4]  Kazuhito Yokoi,et al.  Generating whole body motions for a biped humanoid robot from captured human dances , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[5]  Rosanes Siscart,et al.  Algorithms and graphic interface design to control and teach a humanoid robot through human imitation , 2011 .

[6]  Trevor Darrell,et al.  Practical 3-D Object detection using category and instance-level appearance models , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Parul Gupta,et al.  Futuristic Humanoid Robots: An Overview , 2006, First International Conference on Industrial and Information Systems.

[8]  Yanmin Wang,et al.  Research and implementation from point cloud to 3D model , 2010, 2010 Second International Conference on Computer Modeling and Simulation.