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

2026-09-21

AI Summary

本文提出CableVLA框架，通过模拟特权监督学习电缆拓扑和触觉表示，以解决电缆布线中全局与局部协调控制问题。

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.

Problem

• Cable Routing
• Global-Local Representation Learning
• Simulation-Privileged Supervision
• Tactile Representations
• Topology Control

Innovation

• simulation-privileged supervision
• global-local representation learning
• multimodal vision-language-action framework
• cable routing