Robot Hand Performing Manipulation Tasks with Locked Wrist Joints on Arm

Vatsal V. Patel and Aaron M. Dollar
Nature Machine Intelligence 2025

Video snippet from paper: https://www.nature.com/articles/s4225...

Title:
Combining Grasping and Rotation with a Spherical Robot Hand Mechanism

Abstract:
Object reorientation is a key functionality in dexterous manipulation tasks, such as turning a doorknob. This is usually done on robot arms with a simple gripper and a 3-DOF wrist. But wrists are mechanically-complex, and the wrist axes are often far away from the grasped object, resulting in coupled translations that need to be compensated with awkward whole-arm motions. We present a robot hand mechanism based on a spherical parallel architecture that can both grasp and rotate a wide range of objects in all three axes, combining much of the function of traditional wrists and grippers. The hand mechanism allows for pure spherical rotations of the grasped object about a known fixed point close to the object, thus avoiding parasitic translations and inefficient arm motions. This point also stays fixed with respect to the hand, and is independent of object shape, pose, or initial grasp. We detail the spherical parallel design and workspace model of the wrist-like Sphinx hand, validate its performance for lower-DOF robot arms without traditional wrists, and show that it can accurately rotate grasped objects over large angles with basic open-loop control.

Sphinx Hand is available open-source through Yale OpenHand: https://www.eng.yale.edu/grablab/open...