VLSA模型：搭载即插即用安全约束层的视觉-语言-行动模型

摘要

視覺-語言-動作模型在跨機器人操作任務的泛化能力方面展現出卓越性能。然而，在非結構化環境中部署這類模型仍面臨挑戰，關鍵在於需同時確保任務執行合規性與安全性，特別是在物理交互過程中防止潛在碰撞。本研究提出名為AEGIS的視覺-語言-安全動作架構，該架構通過控制屏障函數構建了即插即用的安全約束層。AEGIS可直接與現有VLA模型集成，在保持原有指令跟隨性能的同時，以理論保證提升安全性。為評估架構效能，我們構建了涵蓋不同空間複雜度與障礙物干預程度的安全關鍵基準測試SafeLIBERO。大量實驗證明本方法優於現有頂尖基準模型，其中AEGIS在障礙物規避率方面實現59.16%的提升，同時將任務執行成功率顯著提高17.25%。為促進可重現性與後續研究，我們已將代碼、模型及基準數據集公開於https://vlsa-aegis.github.io/。

English

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks. However, deploying these models in unstructured environments remains challenging due to the critical need for simultaneous task compliance and safety assurance, particularly in preventing potential collisions during physical interactions. In this work, we introduce a Vision-Language-Safe Action (VLSA) architecture, named AEGIS, which contains a plug-and-play safety constraint (SC) layer formulated via control barrier functions. AEGIS integrates directly with existing VLA models to improve safety with theoretical guarantees, while maintaining their original instruction-following performance. To evaluate the efficacy of our architecture, we construct a comprehensive safety-critical benchmark SafeLIBERO, spanning distinct manipulation scenarios characterized by varying degrees of spatial complexity and obstacle intervention. Extensive experiments demonstrate the superiority of our method over state-of-the-art baselines. Notably, AEGIS achieves a 59.16% improvement in obstacle avoidance rate while substantially increasing the task execution success rate by 17.25%. To facilitate reproducibility and future research, we make our code, models, and the benchmark datasets publicly available at https://vlsa-aegis.github.io/.

VLSA模型：搭载即插即用安全约束层的视觉-语言-行动模型

VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer

摘要

Support