Creating Tendon-Driven Soft Dexterous Robot Hands for the Real World

Dexterous soft robot hands have the potential to transform how robots interact with the physical world by enabling safe and robust manipulation, even in unstructured environments. Due to their inherent compliance, soft hands could address many challenges ranging from caregiving and agriculture to precision manufacturing. However, despite this promise, dexterous soft hands have not seen widespread adoption in real-world applications. Key barriers to adoption include challenges in achieving consistent performance across manipulation tasks, ensuring the durability of soft materials, and addressing the technical complexity of designing and controlling such systems. The design space for soft hands is vast and poorly understood. The lack of efficient modeling further complicates the process of deter mining hand morphology and actuator placement. This typically requires significant technical expertise, intuition, and multiple design iterations. Moreover, controlling soft hands is complicated due to the effects of underactuation and a lack of precise forward and inverse kinematics. This thesis aims to improve real-world performance and facilitate a broader adoption of dexterous soft robot hands by addressing many of these challenges. To achieve this, I present novel design methodologies, an iterative prototyping framework, practical yet effective control approaches, and a strategic outlook on the development of soft robot hands. I demonstrate that through iterative prototyping and advances in multi-material 3D printing, it is possible to create highly customizable, low-cost dexterous soft hands for under $1000 and within days. Additionally, a novel contact transfer optimization framework is introduced for efficiently mapping human manipulation skills to robot hands with different morphologies. Control methods, including open-loop and teleoperation approaches for different types of soft hands, are explored. I further validate the prac ticality and robustness of the presented design, fabrication, and control approaches through real-world experiments in agricultural green pepper harvesting. Finally, I provide a strategic outlook on dexterous soft hands and offer practical insights on building them.

Institutions

Publication Details

Journal
Figshare
Published
2025-01-01
DOI
https://doi.org/10.1184/r1/29120411.v1
Primary Topic
Soft Robotics and Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Creating Tendon-Driven Soft Dexterous Robot Hands for the Real World

Figshare
Soft Robotics and Applications
article

Creating Tendon-Driven Soft Dexterous Robot Hands for the Real World

article en

Abstract

Dexterous soft robot hands have the potential to transform how robots interact with the physical world by enabling safe and robust manipulation, even in unstructured environments. Due to their inherent compliance, soft hands could address many challenges ranging from caregiving and agriculture to precision manufacturing. However, despite this promise, dexterous soft hands have not seen widespread adoption in real-world applications. Key barriers to adoption include challenges in achieving consistent performance across manipulation tasks, ensuring the durability of soft materials, and addressing the technical complexity of designing and controlling such systems. The design space for soft hands is vast and poorly understood. The lack of efficient modeling further complicates the process of deter mining hand morphology and actuator placement. This typically requires significant technical expertise, intuition, and multiple design iterations. Moreover, controlling soft hands is complicated due to the effects of underactuation and a lack of precise forward and inverse kinematics. This thesis aims to improve real-world performance and facilitate a broader adoption of dexterous soft robot hands by addressing many of these challenges. To achieve this, I present novel design methodologies, an iterative prototyping framework, practical yet effective control approaches, and a strategic outlook on the development of soft robot hands. I demonstrate that through iterative prototyping and advances in multi-material 3D printing, it is possible to create highly customizable, low-cost dexterous soft hands for under $1000 and within days. Additionally, a novel contact transfer optimization framework is introduced for efficiently mapping human manipulation skills to robot hands with different morphologies. Control methods, including open-loop and teleoperation approaches for different types of soft hands, are explored. I further validate the prac ticality and robustness of the presented design, fabrication, and control approaches through real-world experiments in agricultural green pepper harvesting. Finally, I provide a strategic outlook on dexterous soft hands and offer practical insights on building them.

Figshare
Carnegie Mellon University (US)
Zero hunger
Openalex Percentile: Top 59%
Soft Robotics and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.