Detail of the student project

Topic:Transformace pohybových dat dítěte na humanoidního robota
Department:Katedra kybernetiky
Supervisor:doc. Mgr. Matěj Hoffmann, Ph.D.
Announce as:Diplomová práce, Bakalářská práce, Semestrální projekt
Description:Motion retargeting deals with the transformation of movements from one body to another. In this case, the inputs are 3D coordinates of keypoints on the bodies of infants and the outputs are movements of a simulated baby robot. This will make it possible to replay the movements of real babies in a humanoid robot and complement the kinematic data with sensory feedback - proprioception (joint angles), vision (from the eyes of the robot), and eventually touch (using artificial skin on the robot body). Such a tool will be key to understanding the mechanisms of early infant development.
Bibliography:N. S. Pollard, J. K. Hodgins, M. J. Riley and C. G. Atkeson, "Adapting human motion for the control of a humanoid robot," Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292), 2002, pp. 1390-1397 vol.2, doi: 10.1109/ROBOT.2002.1014737.

M. Gleicher, “Retargeting motion to new characters,” in Proc. of the 25th Annual Conference on Computer Graphics and Interactive Techniques, 1998, pp. 33–42

S. Mukherjee, D. Paramkusam and S. K. Dwivedy, "Inverse kinematics of a NAO humanoid robot using kinect to track and imitate human motion," 2015 International Conference on Robotics, Automation, Control and Embedded Systems (RACE), 2015, pp. 1-7, doi: 10.1109/RACE.2015.7097245

K. Ayusawa, M. Morisawa and E. Yoshida, "Motion retargeting for humanoid robots based on identification to preserve and reproduce human motion features," 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015, pp. 2774-2779, doi: 10.1109/IROS.2015.7353758.
Responsible person: Petr Pošík