綠色視覺語言行動模型：面向通用機器人的分階段視覺語言行動整合架構

摘要

我們推出Green-VLA——一個分階段的視覺-語言-動作框架，專為Green人形機器人的實際部署設計，同時保持跨多樣化具身系統的泛化能力。該框架遵循五階段課程體系：（L0）基礎視覺語言模型、（L1）多模態接地、（R0）多具身預訓練、（R1）具身專用適配、（R2）強化學習策略對齊。我們將可擴展的數據處理流程（含3,000小時示範數據）與時序對齊及質量篩選相結合，並採用統一的具身感知動作接口，使單一策略能同時控制人形機器人、移動機械臂及固定基座機械臂。在推理階段，通過引入任務進度預測、分佈外檢測和基於關節預測的引導機制，增強VLA控制器的安全性與精準目標選擇能力。在Simpler BRIDGE WidowX與CALVIN ABC-D模擬環境的實驗及真實機器人評估中，該框架展現出強大的泛化性能，並通過強化學習對齊在成功率、魯棒性和長時序任務效率方面實現顯著提升。

English

We introduce Green-VLA, a staged Vision-Language-Action (VLA) framework for real-world deployment on the Green humanoid robot while maintaining generalization across diverse embodiments. Green-VLA follows a five stage curriculum: (L0) foundational VLMs, (L1) multimodal grounding, (R0) multi-embodiment pretraining, (R1) embodiment-specific adaptation, and (R2) reinforcement-learning (RL) policy alignment. We couple a scalable data-processing pipeline (3,000 hours of demonstrations) with temporal alignment and quality filtering, and use a unified, embodiment-aware action interface enabling a single policy to control humanoids, mobile manipulators, and fixed-base arms. At inference, the VLA controller is enhanced with episode-progress prediction, out-of-distribution detection, and joint-prediction-based guidance to improve safety and precise target selection. Experiments on Simpler BRIDGE WidowX and CALVIN ABC-D, as well as real-robot evaluations, show strong generalization and performance gains from RL alignment in success rate, robustness, and long-horizon efficiency.

綠色視覺語言行動模型：面向通用機器人的分階段視覺語言行動整合架構

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

摘要

Support