High DOF Tendon-Driven Soft Hand: A Modular System for Versatile and Dexterous Manipulation

Ulsan National Institute of Science and Technology, Korea1
Korea University, Korea2
Center for Multidimensional Programmable Matter, Korea3
University of California, Berkeley, United States4
† Corresponding author: Jiyun Kim. Email: jiyunkim@unist.ac.kr
* The authors contributed equally to this study

Accepted to 2025 IEEE/RJS International Conference on Intelligent Robots and Systems (IROS)

Abstract

The soft robotic hand exhibits a wide range of manipulation capabilities, which are attributed to the dexterity of its soft fingers and their coordinated movements. the dexterity of its soft fingers and their coordinated movements. Therefore, designing a versatile soft hand requires careful consideration of both the characteristics of the individual fingers, such as degree of freedom (DOF), and their strategic arrangements to optimize performance for specific target tasks. This work presents a modularized high DOF tendon-driven soft finger and a customized design of a soft robotic hand for diverse dexterous manipulation tasks. Furthermore, an all-in-one module is developed that integrates both the 4-way tendon-driven soft finger body and drive parts. Its high DOF enables multi-directional actuations with a wide actuation range, thereby expanding possible manipulation modes. The modularity of the system expands the design space for finger arrangements, which enables the diverse configuration of robotic hands and facilitates the customization of task-oriented platforms. The performance of a single finger is validated, including dexterity and payload, and several real-world manipulation tasks are demonstrated, including writing, grasping, rotating, and spreading, using motion primitives of diverse soft hands with distinctive finger arrangements. These demonstrations showcase the system's versatility and precision in various tasks. We expect that our system will contribute to the expansion of possibilities in the field of soft robotic manipulation.

DEMO