PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps

Hugging Face Daily Papers Papers

Summary

PlatonicNav introduces a training-free framework for embodied navigation that uses vision-only semantic maps and blind matching to ground language goals, achieving generalization across tasks and embodiments without explicit cross-modal training.

Embodied visual navigation, where an agent perceives a complex environment and acts to reach a goal from raw sensory input, underpins a wide range of applications such as household service robotics, assistive robotics, and large-scale autonomous exploration. However, recent attempts to unify vision-and-language navigation (VLN) and object goal navigation (ObjNav) remain at the level of architectural fusion, mixed-task training, and large vision-language pretraining, without examining whether independently trained vision and language encoders may already share a common semantic structure. Moreover, even object-centric topological maps still ground language goals through explicit cross-modal supervision such as CLIP or large vision-language models, leaving open whether such grounding is possible from a purely vision-built map. To address these challenges, we extend the Platonic Representation Hypothesis to embodied navigation and recast vision-only ObjNav, cross-modal ObjNav, and VLN as three different interfaces to the same object-centric semantic manifold. We further introduce PlatonicNav, a training-free framework whose Platonic Topological Map fuses geometric and semantic node distances from a self-supervised visual encoder, and grounds language goals via blind matching without any paired vision-language data. Extensive experiments on simulation benchmarks including HM3D-IIN, OVON, and R2R-CE on MP3D, together with deployment on Unitree Go2, demonstrate that PlatonicNav generalizes across tasks, modalities, and embodiments without explicit cross-modal training. Code: https://github.com/AIGeeksGroup/PlatonicNav. Website: https://aigeeksgroup.github.io/PlatonicNav.
Original Article
View Cached Full Text

Cached at: 06/03/26, 03:35 AM

Paper page - PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps

Source: https://huggingface.co/papers/2606.01788

Abstract

A training-free framework for embodied navigation that uses a vision-only approach to create semantic maps and ground language goals through blind matching without paired vision-language data.

Embodied visual navigation, where an agent perceives a complex environment and acts to reach a goal from raw sensory input, underpins a wide range of applications such as household service robotics, assistive robotics, and large-scale autonomous exploration. However, recent attempts to unifyvision-and-language navigation(VLN) andobject goal navigation(ObjNav) remain at the level of architectural fusion, mixed-task training, and large vision-language pretraining, without examining whether independently trained vision and language encoders may already share a common semantic structure. Moreover, even object-centric topological maps still ground language goals through explicitcross-modal supervisionsuch asCLIPorlarge vision-language models, leaving open whether such grounding is possible from a purely vision-built map. To address these challenges, we extend thePlatonic Representation Hypothesisto embodied navigation and recastvision-only ObjNav,cross-modal ObjNav, andVLNas three different interfaces to the same object-centricsemantic manifold. We further introduce PlatonicNav, a training-free framework whosePlatonic Topological Mapfuses geometric and semantic node distances from aself-supervised visual encoder, and grounds language goals viablind matchingwithout any paired vision-language data. Extensive experiments on simulation benchmarks including HM3D-IIN, OVON, and R2R-CE on MP3D, together with deployment on Unitree Go2, demonstrate that PlatonicNav generalizes across tasks, modalities, and embodiments without explicit cross-modal training. Code: https://github.com/AIGeeksGroup/PlatonicNav. Website: https://aigeeksgroup.github.io/PlatonicNav.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2606\.01788

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.01788 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.01788 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.01788 in a Space README.md to link it from this page.

Collections including this paper1

Similar Articles