MA-VLA：面向協作與組合泛化的多機械臂視覺-語言-動作模型

摘要

多臂協作正成為具身操作中的核心能力。近期的視覺-語言-動作（VLA）模型整合了感知、語言與控制，但多數模型將語言表示為單一全局指令，且未提供明確機制來分配與組合各機械臂的特定行為。此設計限制了模型遷移至與訓練期間所觀察到的不同的協作模式。我們提出 MA-VLA，一個透過原子動作分配實現多臂協作的統一框架。MA-VLA 將協作行為分解為中層原子提示，並將其分配至各機械臂，從而實現顯式的子目標指定以及跨任務的組合式重用。為減少對固定執行角色的依賴，我們引入了 Arm Shuffle，這是一種在訓練時對每個機械臂的觀測、狀態與所分配的原子提示進行置換的方法。此置換強制模型遵循與角色無關的指令，並支持重組為未見過的協調模式，我們稱之為多臂組合式泛化。我們亦構建了一個基準測試，其中測試時的協作模式並未出現在訓練集中。在模擬與真實世界的評估中，先前的最先進VLA模型在這些未見過的協作場景下大多失敗，而 MA-VLA 則始終成功。這些結果表明，結構化的、按臂的原子動作分配為多臂具身系統中的可擴展泛化提供了實用途徑。程式碼、模型與資料可於 https://github.com/zhangzaibin/future-robots 取得。

English

Multi-arm collaboration is becoming a core capability in embodied manipulation. Recent vision-language-action (VLA) models integrate perception, language, and control, but most represent language as a single global instruction and do not provide an explicit mechanism for assigning and composing arm-specific behaviors. This design limits transfer to collaboration patterns that differ from those observed during training. We present MA-VLA, a unified framework for multi-arm collaboration via atomic action assignment. MA-VLA decomposes cooperative behavior into mid-level atomic prompts and allocates them to individual arms, enabling explicit subgoal specification and compositional reuse across tasks. To reduce reliance on fixed execution roles, we introduce Arm Shuffle, a training-time permutation of the observation, state, and assigned atomic prompts for each arm. This permutation enforces role-agnostic instruction following and supports recomposition into unseen coordination patterns, which we term multi-arm compositional generalization. We also construct a benchmark in which test-time collaboration patterns are absent in training set. Across simulation and real-world evaluations, prior state-of-the-art VLAs largely fail under these unseen collaborations, while MA-VLA consistently succeeds. These results indicate that structured, per-arm atomic action assignment offers a practical route to scalable generalization in multi-arm embodied systems. Code, models, and data are available at https://github.com/zhangzaibin/future-robots