SuckTac: Camera-based Tactile Sucker for Unstructured Surface Perception and Interaction

2025-11-04

AI Summary

Existing suction grippers generally lack high-fidelity tactile and visual sensing capabilities, limiting their ability to resolve fine-grained surface geometry and real-time interaction states—resulting in insufficient adhesion robustness on unstructured, soft, or irregular surfaces. To address this, we propose SuckTac, a bioinspired intelligent suction cup inspired by cephalopods. SuckTac uniquely embeds a miniature camera and an annular light source within the suction chamber to enable in-situ, high-density visuo-tactile fusion sensing. Its multi-material monolithic casting process integrates a compliant lip and surface microstructures to enhance conformability and sealing performance. Experiments demonstrate that SuckTac achieves sub-50 μm surface topography resolution and improves adhesion stability by 3.2× under external disturbances. It significantly enhances performance in challenging tasks such as fabric manipulation and soft-robot inspection, validating its generality and superiority in unstructured environments.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Motion & Tracking
• Machine Learning: Bio-inspired Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Suckers are significant for robots in picking, transferring, manipulation and locomotion on diverse surfaces. However, most of the existing suckers lack high-fidelity perceptual and tactile sensing, 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, in this paper, we propose a novel, intelligent sucker, named SuckTac, that integrates a camera-based tactile sensor directly within its optimized structure to provide high-density perception and robust suction. Specifically, through joint structure design and optimization and based on 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 like 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 compliant 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.

Problem

• Developing camera-based tactile suckers for robotic surface perception and interaction
• Enhancing fine-grained geometric feature detection on unstructured surfaces
• Improving robotic adaptability to irregular objects in complex environments

Innovation

• Camera-based tactile sensor integrated in sucker
• Multi-material casting embeds camera and light
• Mechanical design optimized with compliant lip