ShapeForce: Low-Cost Soft Robotic Wrist for Contact-Rich Manipulation

📅 2025-11-25
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
High-cost, fragile, and cumbersome deployment of conventional six-axis force/torque (FT) sensors hinders contact-intensive robotic manipulation. Method: This paper proposes a low-cost, plug-and-play soft wrist device centered on a deformable soft core; marker-based visual pose tracking captures real-time deformation, enabling a calibration-free, electronics-free pseudo-force mapping mechanism inspired by human perception of relative force changes. The approach integrates soft structural design, vision-based feedback, and a lightweight mapping algorithm, ensuring compatibility with mainstream robot controllers. Contribution/Results: Experimental evaluation demonstrates performance comparable to commercial six-axis FT sensors across diverse high-contact-complexity tasks—including peg-in-hole, surface wiping, and compliant assembly—while reducing cost by over 90%. The method exhibits strong generalization across robots and tasks, establishing a cost-effective, easily deployable paradigm for contact sensing in robotics.

Technology Category

Application Category

📝 Abstract
Contact feedback is essential for contact-rich robotic manipulation, as it allows the robot to detect subtle interaction changes and adjust its actions accordingly. Six- axis force-torque sensors are commonly used to obtain contact feedback, but their high cost and fragility have discouraged many researchers from adopting them in contact-rich tasks. To offer a more cost-efficient and easy-accessible source of contact feedback, we present ShapeForce, a low-cost, plug-and-play soft wrist that provides force-like signals for contact-rich robotic manipulation. Inspired by how humans rely on relative force changes in contact rather than precise force magnitudes, ShapeForce converts external force and torque into measurable deformations of its compliant core, which are then estimated via marker-based pose tracking and converted into force-like signals. Our design eliminates the need for calibration or specialized electronics to obtain exact values, and instead focuses on capturing force and torque changes sufficient for enabling contact-rich manipulation. Extensive experiments across diverse contact-rich tasks and manipulation policies demonstrate that ShapeForce delivers performance comparable to six-axis force-torque sensors at an extremely low cost.
Problem

Research questions and friction points this paper is trying to address.

Providing low-cost contact feedback for robotic manipulation tasks
Replacing expensive force-torque sensors with affordable soft wrist
Enabling contact-rich manipulation through measurable deformation signals
Innovation

Methods, ideas, or system contributions that make the work stand out.

Soft robotic wrist with compliant core deformation
Marker-based pose tracking for force estimation
Plug-and-play design eliminating calibration requirements
🔎 Similar Papers
No similar papers found.
J
Jinxuan Zhu
School of Computing, National University of Singapore, Singapore
Zihao Yan
Zihao Yan
School of Computing, National University of Singapore, Singapore
Y
Yangyu Xiao
School of Computing, National University of Singapore, Singapore
Jingxiang Guo
Jingxiang Guo
National University of Singapore
Manipulation
Chenrui Tie
Chenrui Tie
National University of Singapore
roboticsreinforcement learning
X
Xinyi Cao
School of Computing, National University of Singapore, Singapore
Yuhang Zheng
Yuhang Zheng
NUS; TARS AI
Robotics3D Vision
L
Lin Shao
School of Computing, National University of Singapore, Singapore