FLOWER：透過高效的視覺-語言-動作流程策略，實現通用機器人策略的民主化

摘要

開發高效的視覺-語言-動作（VLA）策略對於實際機器人部署至關重要，然而當前方法面臨著高昂的計算成本和資源需求。現有的基於擴散的VLA策略需要數十億參數的模型和龐大的數據集才能實現強勁性能。我們通過兩項貢獻來應對這一效率挑戰：中間模態融合，通過修剪高達50%的大型語言模型層來重新分配容量至擴散頭部；以及針對動作的全局自適應層歸一化（Global-AdaLN）條件化，通過模塊化適應將參數減少20%。我們將這些進展整合到一個名為FLOWER的新型950M參數VLA中。僅在200個H100 GPU小時內進行預訓練，FLOWER在涵蓋十個模擬和現實世界基準的190項任務中展現出與更大VLA相媲美的性能，並展示了對多樣化機器人實體的魯棒性。此外，FLOWER在CALVIN ABC基準上達到了4.53的新SoTA成績。演示、代碼及預訓練權重可於https://intuitive-robots.github.io/flower_vla/獲取。

English

Developing efficient Vision-Language-Action (VLA) policies is crucial for practical robotics deployment, yet current approaches face prohibitive computational costs and resource requirements. Existing diffusion-based VLA policies require multi-billion-parameter models and massive datasets to achieve strong performance. We tackle this efficiency challenge with two contributions: intermediate-modality fusion, which reallocates capacity to the diffusion head by pruning up to 50% of LLM layers, and action-specific Global-AdaLN conditioning, which cuts parameters by 20% through modular adaptation. We integrate these advances into a novel 950 M-parameter VLA called FLOWER. Pretrained in just 200 H100 GPU hours, FLOWER delivers competitive performance with bigger VLAs across 190 tasks spanning ten simulation and real-world benchmarks and demonstrates robustness across diverse robotic embodiments. In addition, FLOWER achieves a new SoTA of 4.53 on the CALVIN ABC benchmark. Demos, code and pretrained weights are available at https://intuitive-robots.github.io/flower_vla/.

FLOWER：透過高效的視覺-語言-動作流程策略，實現通用機器人策略的民主化

FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

摘要

Support