BridgeVLA++：一种数据高效、可泛化且记忆增强的视觉-语言-动作框架，用于三维操作

摘要

利用预训练的视觉-语言模型（VLM）构建视觉-语言-动作（VLA）模型，已成为三维机器人操作的一种颇具前景的范式。然而，现有的三维VLA方法仍依赖大量数据，在分布偏移下泛化能力有限，且缺乏对历史观测的显式记忆。这些局限性阻碍了其应用于数据稀缺、开放世界及依赖记忆的操作场景。我们此前的BridgeVLA工作通过在三维动作学习过程中保持预训练VLM的输入-输出对齐，提升了数据效率与泛化能力：原始点云被投影为多视角图像，并在生成机器人动作之前预测中间热图。在本工作中，我们通过为BridgeVLA配备统一的时空记忆架构，对持久的空间上下文与时序交互历史进行建模，从而发展了BridgeVLA++。由此产生的记忆增强框架能够在推理观测历史的同时，保持BridgeVLA的数据效率与泛化能力。大量实验表明，我们的框架在空间操作任务上取得了强劲性能，并展现出稳健的泛化能力。BridgeVLA++还在两个具有挑战性的依赖记忆的操作基准上取得了最先进的性能，且未牺牲原始BridgeVLA的数据效率与泛化能力。此外，BridgeVLA++在双臂操作设置中表现有效，并已在额外的真实机器人平台上得到验证，展示了其跨任务、跨环境及跨机器人平台的可扩展性。上述结果使BridgeVLA++成为一个统一的三维视觉-语言-动作框架，同时支持数据高效学习、稳健泛化及有效的记忆感知机器人操作。项目网站：https://bridgevla-plus.github.io/。

English

Leveraging pre-trained vision-language models (VLMs) to construct vision-language-action (VLA) models has emerged as a promising paradigm for 3D robot manipulation. However, existing 3D VLA methods remain data-hungry, exhibit limited generalization under distribution shifts, and lack explicit memory of past observations. These limitations hinder their application to data-scarce, open-world, and memory-dependent manipulation scenarios. Our previous work, BridgeVLA, improves data efficiency and generalization by preserving the input--output alignment of a pre-trained VLM during 3D action learning: raw point clouds are projected into multi-view images, and intermediate heatmaps are predicted before generating robot actions. In this work, we develop BridgeVLA++ by equipping BridgeVLA with a unified spatio-temporal memory architecture that models persistent spatial context and temporal interaction history. The resulting memory-augmented framework can reason over observation histories while preserving BridgeVLA's data efficiency and generalization capabilities. Extensive experiments show that our framework achieves strong performance on spatial manipulation tasks while exhibiting robust generalization. BridgeVLA++ further achieves state-of-the-art performance on two challenging memory-dependent manipulation benchmarks without sacrificing the data efficiency and generalization of the original BridgeVLA. In addition, BridgeVLA++ performs effectively in bimanual manipulation settings and is validated on an additional real-world robotic platform, demonstrating its scalability across tasks, environments, and robotic platforms. These results establish BridgeVLA++ as a unified 3D vision-language-action framework that simultaneously supports data-efficient learning, robust generalization, and effective memory-aware robot manipulation. Project website: https://bridgevla-plus.github.io/.