Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization
It addresses the need for precise force control in generalist robotic agents, particularly in contact-rich scenarios, representing an incremental advance by integrating tactile sensing into existing frameworks.
The paper tackles the problem of grounding Vision-Language-Action models in physical interactions for contact-rich robotic tasks, achieving zero-shot generalization by connecting the model's prior knowledge to tactile sensors with few demonstrations.
Vision-Language-Action (VLA) models have shown remarkable achievements, driven by the rich implicit knowledge of their vision-language components. However, achieving generalist robotic agents demands precise grounding into physical interactions, especially in contact-rich scenarios where fine-grained force control is essential. We advance VLAs' implicit knowledge beyond identifying what to do, towards guiding how to physically interact with real world. This paper introduces Tactile-VLA, a novel framework that deeply fuses vision, language, action, and tactile sensing. This framework incorporates a hybrid position-force controller to translate the model's intentions into precise physical actions and a reasoning module that allows the robot to adapt its strategy based on tactile feedback. Experiments demonstrate Tactile-VLA's effectiveness and generalizability in three key aspects: (1) enabling tactile-aware instruction following, (2) utilizing tactile-relevant commonsense, and (3) facilitating adaptive tactile-involved reasoning. A key finding is that the VLM's prior knowledge already contains semantic understanding of physical interaction; by connecting it to the robot's tactile sensors with only a few demonstrations, we can activate this prior knowledge to achieve zero-shot generalization in contact-rich tasks.