用视觉模型里的闲置参数提升机器人的空间推理能力。
RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models
- 把视觉模型中原本废弃的注册令牌重新用于存储全局空间信息
- 在不增加参数量的前提下，使机器人任务成功率提升17.1个百分点
- 适合需要高效且具备空间理解能力的轻量化机器人系统
视觉-语言-动作（VLA）模型在多种机器人任务中表现出色，但其高内存与计算需求常限制实时部署。现有压缩技术虽减少参数量，却常损害3D空间推理与场景布局理解能力。本文提出RetoVLA，通过重用注册令牌——一种原用于缓解视觉变压器注意力伪影的可学习参数——来构建全局空间上下文的密集表征。这些令牌本在使用后被丢弃，我们将其复用于空间感知。RetoVLA通过专用路径将这些复用令牌注入动作规划模块，实现无需增加参数总量的全局上下文恢复。真实世界实验使用7自由度机械臂验证，平均成功率较基线提升17.1个百分点。结果表明，利用内部注册令牌是构建高效且具备空间意识的机器人智能体的有效机制。视频演示见：https://youtu.be/2CseBR-snZg
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models have demonstrated robust performance across diverse robotic tasks. However, their high memory and computational demands often limit real-time deployment. While existing model compression techniques reduce the parameter footprint, they often drop in 3D spatial reasoning and scene layout understanding. This work introduces RetoVLA, an architecture designed to maintain spatial awareness in lightweight models by repurposing Register Tokens-learnable parameters originally introduced to mitigate attention artifacts in Vision Transformers. While these tokens are generally discarded once used, we repurpose them for their dense representation of global spatial context. RetoVLA integrates these recycled tokens directly into the action-planning module through a dedicated spatial context injection path. Our proposed design enables the recovery of global context without increasing the total parameter count. Real-world experiments using a 7-DOF manipulator show a 17.1%p improvement in average success rates over the baseline. Our results demonstrate that leveraging internal register tokens provides a highly effective mechanism for developing efficient, spatially-aware robotic agents. A video demonstration is available at: https://youtu.be/2CseBR-snZg
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。