VacuumVLA: Boosting VLA Capabilities via a Unified Suction and Gripping Tool for Complex Robotic Manipulation

2025-11-26

AI Summary

Existing vision-language-action (VLA) systems predominantly employ parallel two-finger grippers, limiting their capability in tasks requiring large-area contact or strong adhesion—e.g., glass wiping or opening handleless drawers. To address this, we propose a low-cost, compact hybrid end-effector that innovatively integrates a mechanical gripper with a vacuum suction cup, enabling independent or synergistic switching between grasping and suction modalities. This design overcomes the inherent limitations of single-mode actuators in contact area and adhesive force. The end-effector is seamlessly embedded into mainstream VLA frameworks—including DexVLA and Pi0—to support vision-language-instruction-driven, adaptive grasp-mode selection and execution. Experimental evaluation demonstrates substantial improvements in success rates across diverse, realistic manipulation tasks, significantly enhancing operational feasibility. All hardware schematics and control software are publicly released under an open-source license.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Multi-modal Vision
• Humans and AI: Interaction Techniques and Devices

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Vision Language Action models have significantly advanced general purpose robotic manipulation by harnessing large scale pretrained vision and language representations. Among existing approaches, a majority of current VLA systems employ parallel two finger grippers as their default end effectors. However, such grippers face inherent limitations in handling certain real world tasks such as wiping glass surfaces or opening drawers without handles due to insufficient contact area or lack of adhesion. To overcome these challenges, we present a low cost, integrated hardware design that combines a mechanical two finger gripper with a vacuum suction unit, enabling dual mode manipulation within a single end effector. Our system supports flexible switching or synergistic use of both modalities, expanding the range of feasible tasks. We validate the efficiency and practicality of our design within two state of the art VLA frameworks: DexVLA and Pi0. Experimental results demonstrate that with the proposed hybrid end effector, robots can successfully perform multiple complex tasks that are infeasible for conventional two finger grippers alone. All hardware designs and controlling systems will be released.

Problem

• Addresses limitations of two-finger grippers in complex manipulation tasks
• Combines mechanical gripper with vacuum suction for dual-mode manipulation
• Enables flexible task execution in Vision Language Action robot systems

Innovation

• Combines mechanical gripper with vacuum suction unit
• Enables dual mode manipulation in single end effector
• Supports flexible switching between gripping and suction