Learning nonlinear muscle-joint state mapping toward geometric model-free tendon driven musculoskeletal robots

To control a musculoskeletal tendon-driven robot we propose a novel method to learn musculoskeletal nonlinear bidirectional mapping between muscle length and posture (joint angle) from a real musculoskeletal robot. We show the nonlinear musculoskeletal mapping from joint angle to muscle length can be learned as a linear combination of simple nonlinear functions. This formulation can be extended to posture estimation (mapping from muscle length to joint angle) by EKF (Extened Kalman Filter) and torque estimation by differentiation in a musculoskeletal robot. In this paper, we applied the method to tendon driven musculoskeletal robots and verified the validity.

[1]  Junichi Urata,et al.  Design of upper limb by adhesion of muscles and bones — Detail human mimetic musculoskeletal humanoid kenshiro , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Alois Knoll,et al.  A scalable joint-space controller for musculoskeletal robots with spherical joints , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[3]  Alois Knoll,et al.  Computed muscle control for an anthropomimetic elbow joint , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Masayuki Inaba,et al.  Design of humanoid body trunk with “multiple spine structure” and “planar-muscle-driven” system for achievement of humanlike powerful and lithe motion , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[5]  Masayuki Inaba,et al.  Joint proprioception acquisition strategy based on joints-muscles topological maps for musculoskeletal humanoids , 2010, 2010 IEEE International Conference on Robotics and Automation.

[6]  Junichi Urata,et al.  Achievement of twist squat by musculoskeletal humanoid with screw-home mechanism , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Jianjun Meng,et al.  Dynamic modeling and adaptive neural network control of a class of 3-dof tendon-driven minimally invasive instruments , 2010, 2010 IEEE International Conference on Mechatronics and Automation.

[8]  Mohamed Laaraiedh,et al.  Implementation of Kalman Filter with Python Language , 2012, ArXiv.

[9]  Masayuki Inaba,et al.  Motion generation of redundant musculoskeletal humanoid based on robot-model error compensation by muscle load sharing and interactive control device , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[10]  Giulio Sandini,et al.  Machine-learning based control of a human-like tendon-driven neck , 2010, 2010 IEEE International Conference on Robotics and Automation.

[11]  Y. Nakamura,et al.  Somatosensory computation for man-machine interface from motion-capture data and musculoskeletal human model , 2005, IEEE Transactions on Robotics.

[12]  Robert Platt,et al.  Applied joint-space torque and stiffness control of tendon-driven fingers , 2010, 2010 10th IEEE-RAS International Conference on Humanoid Robots.