SuckTac: Camera-Based Tactile Sucker for Unstructured Surface Perception and Interaction
Ruiyong Yuan, Jieji Ren, Zhanxuan Peng, Qianyu Guo, Feifei Chen, Guoying Gu
AI summary
Problem
Conventional robotic suckers lack high-fidelity tactile perception, making it difficult to adhere to and interact with irregular or rough surfaces. This limits their ability to resolve fine geometric details and adapt to complex, unstructured environments.
Approach
The authors developed SuckTac, a bionic sucker that embeds a camera and light source within a multi-material silicone structure. By optimizing the profile, adding a compliant corrugated lip, and incorporating micro-holes, the device captures high-density tactile images while maintaining adaptive, robust suction.
Key results
- Integrated a camera-based tactile sensor directly into a sucker using multi-material casting
- Optimized sucker geometry with a corrugated lip and micro-holes to enhance adhesion on rough surfaces
- Achieved over 90% accuracy in classifying 18 distinct surface textures via ResNet18
- Demonstrated robust grasping and locomotion in challenging robotic tasks like cloth manipulation
Why it matters
Provides a practical solution for robots to reliably interact with unstructured environments, advancing applications in dexterous manipulation and soft robotics.
Abstract
Suckers are significant for robots in picking, transferring, manipulation and locomotion on diverse surfaces. However, conventional suckers lack high-fidelity tactile per- ception, which impedes them from resolving the fine-grained geometric features and interaction status of the target surface. This limits their robust performance with irregular objects and in complex, unstructured environments. Inspired by the adaptive structure and high-performance sensory capabilities of cephalopod suckers, we propose a novel, intelligent sucker, named SuckTac, that integrates a camera-based tactile sen- sor directly within its optimized structure to provide high- density perception and robust suction. Specifically, through joint structural optimization and a multi-material integrated casting technique, a camera and light source are embedded into the sucker, which enables in-situ, high-density perception of fine details such as surface shape, texture, and roughness. To further enhance robustness and adaptability, the sucker’s mechanical design is also optimized by refining its profile, adding a com- pliant lip, and incorporating surface microstructure. Extensive experiments, including challenging tasks such as robotic cloth manipulation and soft mobile robot inspection, demonstrate the superior performance and broad applicability of the proposed system.