# PolyMorphWBC实现四足移动操作跨臂型全身控制与延伸抓取

> 原文链接：https://robotics.hellobike.com/papers/2026-11-13-2611-15117-75ce4e2e
> 频道：papers | 更新日期：2026-11-13 | 标签：auto, arxiv
> 核心摘要：提出PolyMorphWBC分层控制器，仅凭末端轨迹即可协调四足底盘与机械臂。在IsaacLab中任务完成率93.95%，MuJoCo测试位置误差较UMI-on-Legs降低69-72%，并在Go2-ARX5实机验证了无需VLA底盘指令的语义延伸抓取。

# PolyMorphWBC实现四足移动操作跨臂型全身控制与延伸抓取

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[PolyMorphWBC: Whole-Body Control from End-Effector Trajectories for Quadrupedal Mobile Manipulation across Arm Morphologies with Extended Reach](https://arxiv.org/abs/2611.15117)（arXiv 2611.15117）

## 核心内容

针对四足移动操作中基座与机械臂协同难、依赖特定构型的问题，研究提出PolyMorphWBC分层控制器。该方法以末端执行器轨迹为唯一任务指令，通过轨迹条件协调器规划底盘运动，结合臂型特定IK与冻结步态后端，支持四类6-DoF机械臂的跨形态复用及超固定基座范围的延伸操作。

系统利用URDF衍生形态条件化与在线残差力反馈实现跨臂泛化，在程序化生成的机械臂与结构化轨迹上训练。IsaacLab测试显示保留集任务完成率达93.95%，位置误差2.30cm；MuJoCo对比UMI-on-Legs位置误差降低69-72%、姿态误差降低91-97%。物理端在unitree-go2搭载ARX5平台上，结合pi_0模型成功实现无视觉语言动作模型底盘指令的语言条件延伸抓取。

## 关键看点

- **跨形态控制架构**：采用URDF形态条件化与在线残差力反馈，支持四类6-DoF机械臂复用，仅需末端轨迹输入即可自动生成臂-基协同运动
- **仿真高精度验证**：IsaacLab保留集测试任务完成率93.95%，位置误差2.30cm、姿态误差4.81°；MuJoCo中EE位置误差较UMI-on-Legs降低69-72%
- **实机延伸抓取落地**：在unitree-go2与ARX5组合平台上，直接利用pi_0生成的末端轨迹完成语言条件延伸抓取，无需VLA输出底盘控制指令
- **分层解耦设计**：将任务级轨迹规划与底层步态执行解耦，通过预览目标点驱动底盘协调器，使单一控制器适配多种臂型并扩展操作空间

## 工程与产业观察

该工作解决了移动操作中基座-手臂协同对特定硬件的强耦合痛点，通过形态条件化WBC实现了控制策略跨构型迁移。其验证了通用VLA模型可专注于高层末端轨迹生成，而将复杂的全身协调下沉至标准化控制器，为具身智能在非标准硬件上的快速部署提供了可复用的工程范式。

## 英文摘要 (Abstract)

Quadrupedal mobile manipulators can extend their manipulation workspace by coordinating the mounted arm with the mobile base. At the task level, short-horizon end-effector (EE) trajectories provide an interface for specifying the desired manipulation motion without prescribing how it should be realized by the arm and base. However, executing such trajectories remains challenging because the controller must determine when and how the base should move, and this decision depends on the mounted-arm morphology. We therefore present PolyMorphWBC, a hierarchical controller that takes an EE trajectory as the sole task-level motion command and generates coordinated arm--base motions across four families of 6-DoF mounted arms, with extended-reach trajectories beyond the initial fixed-base reach. Within PolyMorphWBC, a trajectory-conditioned coordinator determines the base motion from previewed EE targets, while arm-specific Inverse Kinematics (IK) tracks the current target, and a frozen locomotion backend executes the resulting motion. Cross-arm reuse is enabled by a Unified Robot Description Format (URDF)-derived morphology conditioning, together with online residual-wrench feedback. We train PolyMorphWBC on procedurally generated arms and structured trajectories within and beyond fixed-base reach. In IsaacLab, it achieves 93.95% completion with 2.30cm position error and 4.81{\deg} orientation error on held-out trajectories and arm morphologies. In MuJoCo evaluation against UMI-on-Legs, PolyMorphWBC reduces EE position error by 69--72% and orientation error by 91--97% across four within- and extended-reach trajectories. On a physical Go2--ARX5 system, we demonstrate language-conditioned extended-reach pick-and-place using EE trajectories from pi_0 without vision-language-action (VLA)-generated base commands.

作者：Heng Li, Yang Li, Yifan Duan, Ren Fang, Matao Duan, Wenhao Yu, Lu Zhang, Jianmin Ji, Yanyong Zhang
:::

## 原始参考来源 (Sources)

- [arXiv 2611.15117：PolyMorphWBC: Whole-Body Control from End-Effector Trajectories for Quadrupedal Mobile Manipulation across Arm Morphologies with Extended Reach](https://arxiv.org/abs/2611.15117)