Efficient Jacobian-Based Inverse Kinematics with Sim-to-Real Transfer of Soft Robots by Learning
This work addresses the challenge of efficiently computing inverse kinematics for soft robots, which is a problem for researchers and engineers working with these complex systems.
This paper tackles the inverse kinematic (IK) problem for soft robots, which lack analytical formulations due to their highly non-linear deformation. The authors use neural networks to learn forward kinematics and its Jacobian, enabling Jacobian-based iterative IK solutions, and employ a sim-to-real transfer strategy for practical application.
This paper presents an efficient learning-based method to solve the inverse kinematic (IK) problem on soft robots with highly non-linear 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. The effectiveness of our approach has been verified on pneumatic-driven soft robots for path following and interactive positioning.