This paper presents a new biomimetic soft finger joint with elastic ligaments for enhanced restoration capability. A hemisphere-shaped flexible finger joint is designed to secure omnidirectional restoration and guarantee a reliable recovery function. Joint design comparative studies for enhancing restoration are presented with joint mechanisms and potential energy formulation analyses. A ligament design that enables an efficient grasping mode switch from power to pinch grasping is also considered. By using the presented joint and ligament, a tendon-driven robot hand is assembled. For the finger’s biomimetic features, the hand provides a reasonably secure grasping operation for various complicated objects with minimum controls. The impact test and grasping experiments confirmed that the fabricated hand has the right amount of passive compliance in all directions as designed, and the restoration to the original state is also stably performed.

This paper proposes a simple tracking and synchronization control of a dual-drive system using inversion-based iterative learning control (IILC), which reformulates the model at each iteration based on input/output data. By the power of the IILC, this work simplifies the dual-actuator-driven dynamic system control problem that is normally addressed with a MIMO method. This work also shows the potential of the IILC for nonlinear system applications by reformulating the model at each iteration based on the input/output data. An analytical representation of the iteration-varying IILC followed by simulations is provided. A set of physical system testings with a dual-motor gantry and a semiconductor wafer inspection robotic system are carried out to verify the control method.