arXiv cs.RO·2026-11-09 13:00· 2 days agoAI score62

VLD: Visual Learned Distance as an Interface for Reinforcement Learning Navigation

Summary

The authors propose the Visual Learned Distance (VLD) framework, which decouples perception learning from policy learning for image-goal navigation: first, a distance-to-goal predictor is trained self-supervised on about 3,000 hours of internet and simulated video; then, in simulation, a reinforcement learning policy is trained using privileged geometric distances perturbed by GeoNoise; at deployment, VLD predictions are used zero-shot.

This page provides a summary and source link only. Read the full article at the source.

Source: arXiv cs.RO · arxiv.org

Planning and decision making Robot models and learning Data and simulation Research papers #Research #Robot models and learning #Planning and decision-making #Data and simulation

Part of the event: VLD: Visually Learned Distance as an Interface for Reinforcement Learning Navigation