论文/arXiv 2610.19753·14 天前

Coordi-pi：面向双手灵巧操作的协调感知双手动作表示

针对双手灵巧操作的高维结构化动作空间，提出 Coordi-π 动作表示，并在 DexJoCo 与真实双手任务上验证。

AI 整理

• 本体 SDK 与控制
• 数据与采集
• 具身模型

原文链接：Coordi-pi: Coordination-Aware Dual-Hand Action Representation for Bimanual Dexterous Manipulation（arXiv 2610.19753 · 发布日期：2026-10-14）

Coordi-pi: Coordination-Aware Dual-Hand Action Representation for Bimanual Dexterous Manipulation

针对双手灵巧操作的高维结构化动作空间，提出 Coordi-π 动作表示，并在 DexJoCo 与真实双手任务上验证。

核心要点

• 现有双手 VLA 策略常拼接左右臂手动作，跨手交互隐含在单一动作向量中。
• Coordi-π 将左右臂手动作表示为独立动作 token，并组织成交错序列以显式暴露两侧。
• 方法加入可学习手身份嵌入，并用因子化 RoPE 区分序列位置与控制时间步。
• 在 DexJoCo 五个任务及四个真实双手任务中，Coordi-π 均优于 π0.5。

验证范围与局限：验证范围包括 DexJoCo 中五个双手灵巧操作任务的 rand-obj 与 rand-full 设置，以及四个真实双手灵巧操作任务。

英文摘要 (Abstract)

Vision-language-action (VLA) models have shown strong potential for general-purpose robotic manipulation, but extending them to bimanual dexterous manipulation introduces a high-dimensional and structured action space. Existing bimanual VLA policies commonly concatenate right- and left-side arm--hand actions at each control timestep, leaving cross-hand interactions implicit within a single action vector. We introduce Coordi-$π$, a structured action representation for bimanual dexterous manipulation. Coordi-$π$ represents the right- and left-side arm--hand actions as individual action tokens and organizes them into an interleaved sequence, explicitly exposing the two sides within the action sequence. To explicitly encode hand identity and temporal synchronization in this interleaved representation, a learnable hand-identity embedding distinguishes the two sides, while sequence--control-timestep factorized rotary positional encoding (RoPE) separates sequence position from control timestep, allowing actions at the same control timestep to share a temporal coordinate while retaining distinct sequence positions. Across all five bimanual dexterous manipulation tasks in DexJoCo, Coordi-$π$ achieves state-of-the-art performance under both \textit{rand-obj} and \textit{rand-full}, improving the average success rate over $π_{0.5}$ from 31.9% to 51.3% and from 18.3% to 32.3%, respectively. Coordi-$π$ also consistently outperforms $π_{0.5}$ across four real-world bimanual dexterous manipulation tasks.

作者：Yiming Meng, Yanming Shao, Weijie Shen, Kunyang Lin, Jiayu Sun, Ping Luo, Yao Mu

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.19753：Coordi-pi: Coordination-Aware Dual-Hand Action Representation for Bimanual Dexterous Manipulation访问 2026-10-21