cs.RODec 8, 2025

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

Authors: Lazar Milikic, Manthan Patel, Jonas Frey

Organizations: ETH Zurich · EPFL · Stanford University · UC Berkeley

Abstract

Training end-to-end policies from image data to directly predict navigation actions for robotic systems has proven inherently difficult. Existing approaches often suffer from either the sim-to-real gap during policy transfer or limited action-labeled training data. To address this problem, we introduce Visual Learned Distance (VLD), a scalable framework for image-goal navigation that decouples perception learning from policy learning. We first train a self-supervised distance-to-goal predictor on about 3,000 hours of internet-scale and simulated video, providing a distance signal that a reinforcement learning (RL) policy can minimize. The RL policy is trained separately in simulation using privileged geometric distances perturbed by GeoNoise, a learned noise model that reproduces the viewpoint- and overlap-dependent errors of the trained distance predictor. At deployment, the policy consumes VLD predictions zero-shot, without retraining, inheriting ``where to go'' from large-scale visual training while retaining the robust navigation behaviors learned in simulation. This error modeling is key to the transfer: with VLD inputs, GeoNoise-trained policies reach 58.7%58.7\% success on HM3D and 76.2%76.2\% on Gibson, whereas policies trained with generic temporally correlated noise collapse to 4.9%4.9\% and 11.5%11.5\%. On a physical robot, the VLD-driven policy succeeds in 88%88\% of trials, compared with 60%60\% for a strong end-to-end image-goal baseline that outperforms it in simulation. Our decoupled design thus provides an alternative and scalable path toward reliable navigation policies that transfer from simulation to the real world.

Figures & tables

Appendix figures & tables25 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Trajectory-Diversity-Driven Robust Vision-and-Language Navigation

    Mar 16, 2026Jiangyang Li, Cong Wan, SongLin Dong +4Vision-Language Navigation

  2. MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning

    Oct 3, 2025Tianyu Xu, Jiawei Chen, Jiazhao Zhang +5Robot NavigationVisual Robot Navigation

  3. GuidedNav: Shaping Vision-Language Navigation Representations through Pre-action Attention and Spatial Guidance

    Oct 9, 2026Jingyu Guo, Jiaxin Huang, Chengxing Lin +6Vision-Language NavigationVisual Navigation