跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2604.24661 · v4

Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations

首次提交 2026-04-28 00:24
版本更新 2026-11-17 16:05
雷达观测 2026-11-18 19:42
arXiv ↗PDF ↗

摘要

Visual control maps visual streams to actions in reinforcement learning and vision-language-action (VLA) policies. Changing weather, noise, blur, and compression can obscure different task cues within one episode. Existing control benchmarks mainly test scene distractions, while generic restorers optimize whole-image fidelity. We introduce the Visual Degraded Control Suite (VDCS) to evaluate seven degradations under Markov switching. We propose Agent-Centric Observations with Mixture-of-Experts (ACO-MoE), which routes each frame to a repair expert, restores RGB content, and composes task-relevant foregrounds. On eight VDCS tasks, corruption lowers DreamerV3's mean return from 769 to 562. ACO-MoE raises it to 730, recovering 81.2% of the lost return. It also improves returns on DMC-GB and RoboSuite and retains 70% to 97% of clean-input mean return under six unseen perturbation families. We train ACO-MoE on robot demonstrations and deploy it with a 3B-parameter VLA policy on a Piper arm for cube placement in blue and white boxes and cup placement on a coaster. On the blue-box and cup tasks, motion blur and physical low light with added noise reduce success from 100% to at most 10%. ACO-MoE raises success to 75% to 95% over 20 trials per task and condition.

作者备注:34 pages, including supplementary material. Zhengru Fang and Yu Guo contributed equally. Source code is available at https://github.com/fangzr/aco-moe-code

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v4,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v4 · 2026-11-17 16:05 · 最新观测版本

Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations

Visual control maps visual streams to actions in reinforcement learning and vision-language-action (VLA) policies. Changing weather, noise, blur, and compression can obscure different task cues within one episode. Existing control benchmarks mainly test scene distractions, while generic restorers optimize whole-image fidelity. We introduce the Visual Degraded Control Suite (VDCS) to evaluate seven degradations under Markov switching. We propose Agent-Centric Observations with Mixture-of-Experts (ACO-MoE), which routes each frame to a repair expert, restores RGB content, and composes task-relevant foregrounds. On eight VDCS tasks, corruption lowers DreamerV3's mean return from 769 to 562. ACO-MoE raises it to 730, recovering 81.2% of the lost return. It also improves returns on DMC-GB and RoboSuite and retains 70% to 97% of clean-input mean return under six unseen perturbation families. We train ACO-MoE on robot demonstrations and deploy it with a 3B-parameter VLA policy on a Piper arm for cube placement in blue and white boxes and cup placement on a coaster. On the blue-box and cup tasks, motion blur and physical low light with added noise reduce success from 100% to at most 10%. ACO-MoE raises success to 75% to 95% over 20 trials per task and condition.

查看此版本解读 →查看此版本原文 ↗