TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulation

TL;DR

TacVLA introduces a contact-aware tactile fusion mechanism in vision-language-action models, significantly improving robotic manipulation performance in contact-rich and occluded scenarios through adaptive multimodal integration.

Contribution

The paper presents a novel contact-aware gating mechanism for tactile integration in transformer-based VLA models, enhancing fine-grained manipulation capabilities.

Findings

20% success rate improvement in disassembly tasks

60% success rate increase in in-box picking

2.1x robustness gain under visual occlusion

Abstract

Vision-Language-Action (VLA) models have demonstrated significant advantages in robotic manipulation. However, their reliance on vision and language often leads to suboptimal performance in tasks involving visual occlusion, fine-grained manipulation, and physical contact. To address these challenges, we propose TacVLA, a fine-tuned VLA model by incorporating tactile modalities into the transformer-based policy to enhance fine-grained manipulation capabilities. Specifically, we introduce a contact-aware gating mechanism that selectively activates tactile tokens only when contact is detected, enabling adaptive multimodal fusion while avoiding irrelevant tactile interference. The fused visual, language, and tactile tokens are jointly processed within the transformer architecture to strengthen cross-modal grounding during contact-rich interaction. Extensive experiments on constraint-locked disassembly, in-box picking and robustness evaluations demonstrate that our model outperforms baselines, improving the performance by averaging 20% success rate in disassembly, 60% in in-box picking and 2.1x improvement in scenarios with visual occlusion. Videos are available at https://sites.google.com/view/tacvla and code will be released.