让机器人在用户输入完成前就开始预执行，提升响应速度。
Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are Complete
- 在用户输入时提前计算动作，利用等待时间做预处理
- 平均耗时从34秒降到29.4秒，成功率保持95%以上
- 适合对实时性要求高的机器人交互场景
视觉-语言-动作（VLA）策略通常假设用户在机器人开始行动前已完成指令输入。但在实际部署中，用户输入需数秒，导致策略长时间处于空闲状态。本文提出Premover，一种轻量级模块，将这段空闲期转化为有效预计算。Premover保持VLA主干网络冻结，添加两个小型投影头，分别对图像块和语言标记进行映射，生成共享空间中的注意力图。该图由仿真器渲染的目标物体分割掩码监督，并用于重加权下一步的图像标记。一个单一标量就绪阈值，通过流式前缀联合训练，决定何时启动动作。在LIBERO基准测试中，Premover将平均墙钟时间从34.0秒降至29.4秒，降低13.6%，同时成功率与完整指令基线持平（95.1% vs. 95.0%）；而简单预执行则骤降至66.4%。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) policies are typically evaluated as if the user had finished typing or speaking before the robot begins acting. In real deployment, however, users take several seconds to enter a request, leaving the policy idle for a substantial fraction of the interaction. We introduce Premover, a lightweight module that converts this idle window into useful precomputation. Premover keeps the VLA backbone frozen and attaches two small projection heads, one for image patches, one for language tokens, that map an intermediate layer of the backbone into a shared space. The resulting focus map is supervised by simulator-rendered target-object segmentation masks and applied as a per-patch reweighting of the next step's image tokens. A single scalar readiness threshold, trained jointly from streaming prefixes, decides when the policy should begin acting. On the LIBERO benchmark suite, Premover reduces mean wall-clock time from 34.0 to 29.4 seconds, a 13.6% reduction, while matching the full-prompt baseline's success rate (95.1% vs. 95.0%); naive premoving, by contrast, collapses to 66.4%.
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。