Efficient Jacobian-Based Inverse Kinematics With Sim-to-Real Transfer of Soft Robots by Learning
G. Fang (TU Delft - Materials and Manufacturing)
Yingjun Tian (The University of Manchester)
Zhi Xin Yang (University of Macau)
J.M.P. Geraedts (TU Delft - Mechatronic Design)
Charlie C.L. Wang (The University of Manchester)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
This article presents an efficient learning-based method to solve the <italic>inverse kinematic</italic> (IK) problem on soft robots with highly nonlinear deformation. The major challenge of efficiently computing IK for such robots is due to the lack of analytical formulation for either forward or inverse kinematics. To address this challenge, we employ neural networks to learn both the mapping function of forward kinematics and also the Jacobian of this function. As a result, Jacobian-based iteration can be applied to solve the IK problem. A sim-to-real training transfer strategy is conducted to make this approach more practical. We first generate a large number of samples in a simulation environment for learning both the kinematic and the Jacobian networks of a soft robot design. Thereafter, a sim-to-real layer of differentiable neurons is employed to map the results of simulation to the physical hardware, where this sim-to-real layer can be learned from a very limited number of training samples generated on the hardware.