UniTacVLA：视觉语言动作模型中的统一触觉理解与预测
UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models
AI总结：
提出统一触觉学习框架，通过触觉链式推理和由粗到细的未来触觉预测构建状态与动力学感知先验，并设计触觉-动作混合控制器，在接触丰富操作任务中提升成功率、精度和鲁棒性。
摘要：
视觉-语言-动作（VLA）模型在许多机器人操作任务中取得了强大性能，但在接触丰富的灵巧操作中仍存在局限。为克服这一限制，最近的视觉-触觉-语言-动作（VTLA）方法将触觉感知融入VLA模型以提供直接接触信息。然而，它们通常将触觉信号视为被动辅助输入，难以建模触觉语义和未来的物理交互。为此，我们提出一个用于接触丰富操作的统一触觉学习框架，将触觉信号建模为用于接触理解和预测的动态交互线索。具体而言，我们构建一个统一的触觉潜在空间，并通过触觉链式推理和由粗到细的未来触觉预测，联合建模当前触觉状态和未来接触变化，从而形成状态感知和动力学感知的触觉先验。基于该先验，我们引入一个触觉-动作混合控制器，结合实时和预测的触觉反馈，用高频修正来细化低频动作块。在四类接触丰富任务（包括调整、插入、擦拭和组装）上的真实世界实验，在清洁和外部扰动设置下，表明我们的方法在成功率、操作精度和接触鲁棒性上优于现有方法，展示了其在灵巧物理交互中的有效性。
英文摘要：
Vision-language-action (VLA) models have achieved strong performance in many robotic manipulation tasks, yet remain limited in contact-rich dexterous manipulation. To overcome this limitation, recent vision-tactile-language-action (VTLA) methods incorporate tactile sensing into VLA models to provide direct contact information. However, they typically treat tactile signals as passive auxiliary inputs, making it difficult to model tactile semantics and future physical interactions. To this end, we propose a unified tactile learning framework for contact-rich manipulation that models tactile signals as dynamic interaction cues for both contact understanding and prediction. Specifically, we construct a unified tactile latent space and jointly model current tactile states and future contact changes through tactile chain-of-thought reasoning and coarse-to-fine future tactile prediction, thereby forming a state-aware and dynamics-aware tactile prior. Based on this prior, we introduce a tactile-action mixed controller that combines real-time and predicted tactile feedback to refine low-frequency action chunks with high-frequency corrections. Real-world experiments on four categories of contact-rich tasks, including adjustment, insertion, wiping, and assembly, under both clean and externally perturbed settings, show that our method improves success rate, manipulation accuracy, and contact robustness over existing methods, demonstrating its effectiveness in dexterous physical interaction.
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。
