# CableVLA：面向线缆布线的仿真特权全局-局部表征学习

> 原文链接：https://robotics.hellobike.com/papers/2026-09-22-2609-25606
> 频道：papers | 更新日期：2026-09-22 | 标签：arxiv, cs.RO
> 核心摘要：针对线缆布线的全局拓扑与局部接触协同控制，CableVLA用仿真特权监督学习拓扑和触觉表征，并在MuJoCo等评估中验证。

# CableVLA：面向线缆布线的仿真特权全局-局部表征学习

::: v-pre
> 原文链接：[CableVLA: Simulation-Privileged Global-Local Representation Learning for Cable Routing](https://arxiv.org/abs/2609.25606)（arXiv 2609.25606 · 发布日期：2026-09-22）

**CableVLA: Simulation-Privileged Global-Local Representation Learning for Cable Routing**

针对线缆布线的全局拓扑与局部接触协同控制，CableVLA用仿真特权监督学习拓扑和触觉表征，并在MuJoCo等评估中验证。

## 核心要点

- 线缆布线需要同时协调全局线缆拓扑和不断变化的局部接触。
- TopoHead蒸馏节点级物理及当前/未来拓扑，TacSense从电阻阵列学习接触动态。
- 接触门控启用力-触觉残差，细化冻结的拓扑条件策略的下一组8个臂和夹爪动作。
- 345次MuJoCo评估中成功率由62.6%提升至84.9%，触觉与拓扑评估检验表征质量。

**验证范围与局限**：验证包括MuJoCo评估、拓扑预测、57任务触觉评估，以及跨仿真器和真机比较。

## 英文摘要 (Abstract)

Cable routing requires coordinated control of global cable topology and changing local contacts. We present CableVLA, an end-to-end multimodal vision-language-action framework that converts simulation-privileged supervision into deployable cable-topology and tactile representations. TopoHead distills node-level physics and current and future cable-topology information into causal visual context for the action expert. TacSense uses complementary frame and taxel branches to learn contact dynamics from resistive arrays, with simulator-derived kinematics and contact events providing supervision beyond the measured force map. A contact gate activates force-tactile residuals that refine the next 8 arm-and-gripper actions of a frozen topology-conditioned policy. Across 345 MuJoCo evaluations, CableVLA improves success from 62.6% for the $π_{0.5}$-V visual baseline to 84.9%. TacSense achieves pronounced gains in slip-transition recognition over a CNN-LSTM baseline with a similar parameter count, and this advantage persists under frozen-encoder probes. Topology prediction and 57-task tactile evaluations assess representation quality, while policy adaptation studies evaluate downstream control performance. Cross-simulator and real-robot comparisons further examine zero-shot policy transfer under changes in dynamics and sensing.

作者：Zhifei Teng, Bo Feng, Xiang Zou, Jinpeng Xiao, Min Li, Zhouping Yin, Yiqun Li
:::

## 原始参考来源 (Sources)

- [arXiv 2609.25606：CableVLA: Simulation-Privileged Global-Local Representation Learning for Cable Routing](https://arxiv.org/abs/2609.25606)