FlexiCup: Wireless Multimodal Suction Cup with Dual-Zone Vision-Tactile Sensing

2025-11-17

AI Summary

Traditional suction cups lack contact-aware perception and struggle with perception-driven manipulation in unstructured environments. To address this, we propose FlexiCup—a soft, multimodal suction cup. Our approach integrates (1) a novel dual-zone vision–tactile fusion architecture: a central zone enables dynamic modality switching between vision and tactile sensing via adaptive illumination control, while an annular zone delivers continuous spatial tactile feedback; (2) hybrid vacuum and Bernoulli suction mechanisms, coupled with a diffusion-model-based end-to-end control paradigm; and (3) a multi-head attention mechanism for fusing heterogeneous sensory inputs, improving operational performance by 13%. Experiments demonstrate success rates of 90.0% in diverse-surface grasping, 73.3% in inclined transport, and 66.7% in orange harvesting—significantly enhancing adaptive manipulation capability in unstructured settings.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Conventional suction cups lack sensing capabilities for contact-aware manipulation in unstructured environments. This paper presents FlexiCup, a fully wireless multimodal suction cup that integrates dual-zone vision-tactile sensing. The central zone dynamically switches between vision and tactile modalities via illumination control for contact detection, while the peripheral zone provides continuous spatial awareness for approach planning. FlexiCup supports both vacuum and Bernoulli suction modes through modular mechanical configurations, achieving complete wireless autonomy with onboard computation and power. We validate hardware versatility through dual control paradigms. Modular perception-driven grasping across structured surfaces with varying obstacle densities demonstrates comparable performance between vacuum (90.0% mean success) and Bernoulli (86.7% mean success) modes. Diffusion-based end-to-end learning achieves 73.3% success on inclined transport and 66.7% on orange extraction tasks. Ablation studies confirm that multi-head attention coordinating dual-zone observations provides 13% improvements for contact-aware manipulation. Hardware designs and firmware are available at https://anonymous.4open.science/api/repo/FlexiCup-DA7D/file/index.html?v=8f531b44.

Problem

• Lack of sensing capabilities in conventional suction cups
• Need for contact-aware manipulation in unstructured environments
• Requirement for wireless multimodal perception in robotic grasping

Innovation

• Wireless multimodal suction cup with dual-zone sensing
• Dynamic vision-tactile switching via illumination control
• Modular suction modes with onboard computation and power