FORTE: Tactile Force and Slip Sensing on Compliant Fingers for Delicate Manipulation
Siqi Shang, Mingyo Seo, Yuke Zhu, Lillian Chin
AI summary
Problem
Current robotic grippers lack human-like tactile feedback, making it difficult to apply the exact force needed for delicate manipulation without damaging fragile objects or losing grip. Existing solutions suffer from high integration complexity, slow response times, or durability issues.
Approach
FORTE integrates internal air channels into 3D-printed fin-ray compliant fingers, using off-the-shelf pressure transducers to measure deformation-induced pressure changes for real-time force estimation and frequency-based slip detection.
Key results
- Accurate force estimation across 0–8 N range with RMSE below 0.2 N
- Real-time slip detection within 100 ms (0.91 F1 score)
- 91.9% success rate on 31 fragile and deformable objects
- Open-source hardware and algorithm implementations
Why it matters
Provides a simple, low-cost, and robust tactile sensing solution for soft robotics, enabling safer and more precise manipulation of delicate items in manufacturing, agriculture, and household tasks.
Abstract
Handling fragile objects remains a major challenge for robotic manipulation. Tactile sensing and soft robotics can im- prove delicate object handling, but typically involve high integra- tion complexity or slow response times. We address these issues through FORTE, an easy-to-fabricate tactile sensing system com- prised of 3D-printed fin-ray grippers with internal air channels. FORTE provides low-latency force and slip feedback, enabling us to apply just enough force to grasp objects without damaging them. We accurately estimate grasping forces from 0–8 N ± 0.2 N, and detect slip events within 100 ms of occurring. FORTE can grasp a wide range of slippery, fragile, and deformable objects, including raspberries and potato chips with 92% success and achieves 93% accuracy in detecting slip events. These results highlight FORTE’s potential as a robust solution for delicate manipulation. https://merge-lab.github.io/FORTE/