SELF-VLA: 一种增强技能的代理视觉-语言-动作框架用于接触丰富的拆解
SELF-VLA: A Skill Enhanced Agentic Vision-Language-Action Framework for Contact-Rich Disassembly
AI总结：
SELF-VLA是一种整合显式拆解技能的代理视觉-语言-动作框架，通过实验在接触丰富的拆解任务中优于现有端到端VLA模型。
摘要：
拆解自动化长期以来一直被追求，以应对对高效且正确回收有价值组件的需求增长。现有方法通过将拆解过程分解为不同子任务，展示了有希望且有规律的性能。然而，每个子任务通常需要大量数据准备、模型训练和系统管理。此外，这些方法通常是任务和组件特定的，使其难以处理EoL产品的变异性与不确定性，限制了其泛化能力。所有这些因素限制了当前机器人拆解系统的实际部署，使它们高度依赖人工劳动。随着机器人领域基础模型的发展，视觉-语言-动作（VLA）模型在标准机器人操作任务上表现出色，但其在复杂、接触丰富且长周期的工业实践中如拆解中的适用性仍有限。为解决这一挑战，我们提出SELF-VLA，一种整合显式拆解技能的代理VLA框架。实验研究显示，我们的框架在两个接触丰富的拆解任务上显著优于当前最先进的端到端VLA模型。视频演示可通过https://zh.engr.tamu.edu/wp-content/uploads/sites/310/2026/03/IROS-VLA-Video.mp4获取。
英文摘要：
Disassembly automation has long been pursued to address the growing demand for efficient and proper recovery of valuable components from the end-of-life (EoL) electronic products. Existing approaches have demonstrated promising and regimented performance by decomposing the disassembly process into different subtasks. However, each subtask typically requires extensive data preparation, model training, and system management. Moreover, these approaches are often task- and component-specific, making them poorly suited to handle the variability and uncertainty of EoL products and limiting their generalization capabilities. All these factors restrict the practical deployment of current robotic disassembly systems and leave them highly reliant on human labor. With the recent development of foundation models in robotics, vision-language-action (VLA) models have shown impressive performance on standard robotic manipulation tasks, but their applicability to complex, contact-rich, and long-horizon industrial practices like disassembly, which requires sequential and precise manipulation, remains limited. To address this challenge, we propose SELF-VLA, an agentic VLA framework that integrates explicit disassembly skills. Experimental studies demonstrate that our framework significantly outperforms current state-of-the-art end-to-end VLA models on two contact-rich disassembly tasks. The video illustration can be found via https://zh.engr.tamu.edu/wp-content/uploads/sites/310/2026/03/IROS-VLA-Video.mp4.
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。
