Learning Global Inverse Kinematics Solutions for a Continuum Robot

This paper presents a learning based approach for obtaining the inverse kinematics (IK) solution for continuum robots. The proposed model learns a particular global solution for IK problem by supervised learning without any prior knowledge about the system. We have developed an approach that solely relies on the sampling method and a unique IK formulation. The convergence of the solution, practically feasible sample data requirements and adaptability of the model is shown with simulations of a redundant continuum robot.

[1]  Cagdas D. Onal,et al.  Design and control of a soft and continuously deformable 2D robotic manipulation system , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[2]  Jochen J. Steil,et al.  Constant curvature continuum kinematics as fast approximate model for the Bionic Handling Assistant , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Susumu Tachi,et al.  Inverse kinematics learning by modular architecture neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[4]  Cecilia Laschi,et al.  Neural Network and Jacobian Method for Solving the Inverse Statics of a Cable-Driven Soft Arm With Nonconstant Curvature , 2015, IEEE Transactions on Robotics.

[5]  Rochdi Merzouki,et al.  Neural Networks based approach for inverse kinematic modeling of a Compact Bionic Handling Assistant trunk , 2014, 2014 IEEE 23rd International Symposium on Industrial Electronics (ISIE).

[6]  Paolo Dario,et al.  Integrating Feedback and Predictive Control in a Bio-Inspired Model of Visual Pursuit Implemented on a Humanoid Robot , 2015, Living Machines.

[7]  Matteo Cianchetti,et al.  Dynamic Model of a Multibending Soft Robot Arm Driven by Cables , 2014, IEEE Transactions on Robotics.

[8]  Stefan Schaal,et al.  Learning inverse kinematics , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[9]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[10]  Jochen J. Steil,et al.  Efficient Exploratory Learning of Inverse Kinematics on a Bionic Elephant Trunk , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Bernhard Schölkopf,et al.  Learning inverse kinematics with structured prediction , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[13]  Robert J. Webster,et al.  Design and Kinematic Modeling of Constant Curvature Continuum Robots: A Review , 2010, Int. J. Robotics Res..

[14]  Jochen J. Steil,et al.  Goal Babbling Permits Direct Learning of Inverse Kinematics , 2010, IEEE Transactions on Autonomous Mental Development.

[15]  Cecilia Laschi,et al.  Adaptive visual pursuit involving eye-head coordination and prediction of the target motion , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.