Backend
Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
arXiv cs.RO0 views
arXiv:2604.24661v5 Announce Type: replace Abstract: 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.
Source:https://arxiv.org/abs/2604.24661PreviousRoboForge: Cross-space Motion Refinement for Physically Executable Humanoid Whole-body TrackingNextSixthSense: Proprioception-Only Whole-Body Wrench Estimation for Humanoids
Related posts
Shipping an LLM feature to production: a 6-step checklist from real client projects
0dev.to
Why I Built an Ad-Free, 4K Video Downloader in Next.js 14 & Python (And Killed Popups Forever)
0dev.to
Three Hundred of Our Trade Accounts Belonged to Companies That No Longer Existed
0dev.to
Title40-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
0dev.to
Title50-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
0dev.to

Practical: a webcam physiology lab that grades itself against a wrist count
0dev.to