Whole-Body Motion Blending Under Physical Constraints Using Functional PCA

This paper presents a method for motion synthesis using Functional Principal Component Analysis (Functional PCA) to generate complex humanoid robot motions in a low-dimensional space while considering physical consistency. Since each motion can be expressed by a point in a space called FPC space, this method allows blending different motions. For more complex motion synthesis, we introduce a novel framework to synthesize blended motions by configuring a local FPC space and a global FPC space. This method enables to merge data while considering data features. However, physical consistency was not ensured in our previous work, we here apply optimization under constraints after synthesis. We show the dynamic feasibility and the feature of the synthesized blended motions and also an interesting observation opening to the possibility to generate a variety of motions from a few motion data in a local space at low cost and time.

[1]  Shuuji Kajita,et al.  Robot motion remix based on motion capture data towards human-like locomotion of humanoid robots , 2009, 2009 9th IEEE-RAS International Conference on Humanoid Robots.

[2]  Bruno Maisonnier,et al.  Choregraphe: a graphical tool for humanoid robot programming , 2009, RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication.

[3]  Stefano Caselli,et al.  Functional Principal Component Analysis for Recognition of arm Gestures and humanoid Imitation , 2013, Int. J. Humanoid Robotics.

[4]  S. Nakaoka,et al.  Choreonoid: Extensible virtual robot environment built on an integrated GUI framework , 2012, 2012 IEEE/SICE International Symposium on System Integration (SII).

[5]  Kazuhito Yokoi,et al.  Human-like walking with toe supporting for humanoids , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Eiichi Yoshida,et al.  Whole-body motion retargeting using constrained smoothing and functional principle component analysis , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[7]  Hideki Hirakawa,et al.  Functional Principal Component Analysis via Regularized Basis Expansion and Its Application , 2006 .

[8]  Masayuki Inaba,et al.  Motion planning for humanoid robots under obstacle and dynamic balance constraints , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[9]  Eiichi Yoshida,et al.  Optimization-based motion retargeting integrating spatial and dynamic constraints for humanoid , 2013, IEEE ISR 2013.

[10]  Eiichi Yoshida,et al.  Motion Retargeting for Humanoid Robots Based on Simultaneous Morphing Parameter Identification and Motion Optimization , 2017, IEEE Transactions on Robotics.

[11]  Eiichi Yoshida,et al.  Humanoid robot as an evaluator of assistive devices , 2013, 2013 IEEE International Conference on Robotics and Automation.

[12]  Eiichi Yoshida,et al.  Task-driven Support Polygon Reshaping for Humanoids , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[13]  Eiichi Yoshida,et al.  On human motion imitation by humanoid robot , 2008, 2008 IEEE International Conference on Robotics and Automation.

[14]  Mitsuharu Morisawa,et al.  Humanoid robot HRP-4 - Humanoid robotics platform with lightweight and slim body , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Eiichi Yoshida,et al.  New evaluation framework for human-assistive devices based on humanoid robotics , 2016, Adv. Robotics.

[16]  J. Ramsay,et al.  Principal components analysis of sampled functions , 1986 .

[17]  Shin’ichiro Nakaoka.  Choreonoid as a Software Framework for Implementing Graphical Robotics Applications , .

[18]  Katsu Yamane,et al.  Natural Motion Animation through Constraining and Deconstraining at Will , 2003, IEEE Trans. Vis. Comput. Graph..

[19]  Yoshihiko Nakamura,et al.  Fast inverse kinematics algorithm for large DOF system with decomposed gradient computation based on recursive formulation of equilibrium , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.