VLA-Touch：通过双层触觉反馈增强视觉-语言-动作模型
VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedback
AI总结：
针对现有VLA模型缺乏触觉感知能力、接触密集任务效能受限的问题，研究提出无需微调基础模型的VLA-Touch方法，通过语义触觉规划与扩散动作优化双层集成触觉反馈，提升了机器人任务规划效率与执行精度。
摘要：
触觉反馈被普遍认为对与物理世界的有效交互至关重要。然而，当前最先进的视觉-语言-动作（Vision-Language-Action，VLA）模型缺乏解读和利用触觉信号的能力，限制了其在接触密集型任务中的效能。由于缺乏大型多模态数据集，将触觉反馈融入这类系统颇具挑战。我们提出VLA-Touch方法，可在不对基础VLA进行微调的情况下，通过触觉感知增强通用机器人策略。该方法包含两项核心创新：（1）利用预训练触觉-语言模型的流水线，为高层任务规划提供语义级触觉反馈；（2）基于扩散的控制器，借助触觉信号优化VLA生成的动作，以实现接触密集型操作。通过真实世界实验，我们证明这种双层触觉反馈集成方式提升了任务规划效率，同时增强了执行精度。代码已在该URL开源：https://github.com/jxbi1010/VLA-Touch。
英文摘要：
Tactile feedback is generally recognized to be crucial for effective interaction with the physical world. However, state-of-the-art Vision-Language-Action (VLA) models lack the ability to interpret and use tactile signals, limiting their effectiveness in contact-rich tasks. Incorporating tactile feedback into these systems is challenging due to the absence of large multi-modal datasets. We present VLA-Touch, an approach that enhances generalist robot policies with tactile sensing \emph{without fine-tuning} the base VLA. Our method introduces two key innovations: (1) a pipeline that leverages a pretrained tactile-language model that provides semantic tactile feedback for high-level task planning, and (2) a diffusion-based controller that refines VLA-generated actions with tactile signals for contact-rich manipulation. Through real-world experiments, we demonstrate that our dual-level integration of tactile feedback improves task planning efficiency while enhancing execution precision. Code is open-sourced at \href{https://github.com/jxbi1010/VLA-Touch}{this URL}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
