让机器人学会跨任务复用操作经验，提升新任务成功率。
VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
- 训练时存下任务专属的操作记忆，推理时按需调用融合。
- 仿真环境任务成功率最高提升207%，真实世界成功率从5.8%升至65.0%。
- 适合需要快速适应新任务的通用机器人系统使用。
视觉-语言-动作（VLA）模型在通用机器人操作中展现出巨大潜力，但仍难以泛化到需要跨物体、场景和动作模式迁移经验的未见任务。本文提出VLA-Pro，一种即插即用的框架，通过在训练阶段存储任务相关的参数化过程记忆，并在推理时基于多模态上下文检索与动态融合这些记忆，增强跨任务泛化能力。具体而言，VLA-Pro在训练时将任务特定的LoRA适配器作为参数化过程记忆存储。推理时，根据当前多模态上下文检索相关记忆，并动态融合生成当前动作片段。在RoboTwin、RLBench及真实世界操作任务上的实验表明，VLA-Pro在多种骨干网络上均显著提升跨任务泛化性能，仿真环境下相对成功率最高提升207%，真实世界成功率为5.8%提升至65.0%。结果表明，过程记忆的检索与自适应是有效迁移操作经验至新任务的关键机制，同时保持模块化与执行稳定性。
原文摘要 · Abstract (English)
Vision-Language-Action~(VLA) models have shown strong potential for general-purpose robotic manipulation, yet they still struggle to generalize to unseen tasks that necessitate transferring relevant experience across objects, scenes, and action patterns. This paper proposes VLA-Pro, a plug-and-play framework designed to enhance cross-task generalization by storing task-relevant procedural memories at training time and transferring these memories during inference. Specifically, VLA-Pro stores task-specific LoRA adapters as parameterized procedural memories during training. At inference time, VLA-Pro retrieves relevant procedural memories based on the current multi-modal context and dynamically fuses these memories for generating the current action chunk. Experiments on RoboTwin, RLBench, and real-world manipulation tasks show that VLA-Pro consistently improves cross-task generalization across multiple backbones, achieving up to a 207% relative improvement in simulation and increasing real-world success rate from 5.8% to 65.0%. These results suggest that procedural memory retrieval and adaptation provide an effective mechanism for transferring manipulation experience to novel tasks while preserving modularity and execution stability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。