analiza aiqbench
This research introduces an analytical, training-free pipeline for zero-shot semantic navigation by leveraging room-mediated object co-occurrence derived from CLIP vectors rather than relying solely on direct latent space similarity. By projecting these relationships onto value maps using geodesic flood-fill propagation, the method achieves measurable improvements in success rates and path efficiency while maintaining open-vocabulary flexibility. The approach represents a significant step toward more interpretable and robust autonomous navigation systems that can generalize to unseen objects without additional training data.
Room-Mediated Co-occurrence for Zero-Shot Object-Centric Semantic Navigation via Frontier Scoring
arXiv:2607.25448v1 Announce Type: new Abstract: Zero-shot ObjectNav methods increasingly use vision-language priors, but direct object-object similarity in the latent space is often a weak proxy for spatial co-occurrence. We present an analytical, training-free semantic navigation pipeline that mediates object relationships through a compact room lexicon. Each object label is mapped to a CLIP-derived Room Probability Vector (RPV), and object-target co-occurrence is computed from RPV distribution overlap. These scores are projected onto a value map using geodesic flood-fill propagation (Fast Marching Method), with adaptive signal decay, and are used to rank frontiers by semantic score for navigation. Together, these components form an integrated, training-free, object-centric pipeline for open-vocabulary zero-shot navigation. Results show that our object-centric approach improves Success Rate (SR) and Success by weighted inverse Path Length (SPL) by a relative 3% and 1.3%, respectively, compared to image-holistic baselines on the HM3D dataset validation split, while preserving interpretability and open-vocabulary flexibility. Code is available at: uts-ri.github.io/RPV-SemNav.
Abstract:Zero-shot ObjectNav methods increasingly use vision-language priors, but direct object-object similarity in the latent space is often a weak proxy for spatial co-occurrence. We present an analytical, training-free semantic navigation pipeline that mediates object relationships through a compact room lexicon. Each object label is mapped to a CLIP-derived Room Probability Vector (RPV), and object-target co-occurrence is computed from RPV distribution overlap. These scores are projected onto a value map using geodesic flood-fill propagation (Fast Marching Method), with adaptive signal decay, and are used to rank frontiers by semantic score for navigation. Together, these components form an integrated, training-free, object-centric pipeline for open-vocabulary zero-shot navigation. Results show that our object-centric approach improves Success Rate (SR) and Success by weighted inverse Path Length (SPL) by a relative 3% and 1.3%, respectively, compared to image-holistic baselines on the HM3D dataset validation split, while preserving interpretability and open-vocabulary flexibility. Code is available at: this http URL.
8 pages. Accepted to IROS 2026
Robotics (cs.RO)
arXiv:2607.25448 [cs.RO]
(or arXiv:2607.25448v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.25448 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 251 cuvinte
Subiecte conexe
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · 8 oct. 2026
MatterDoor: Sampling Zero-shot Spatio-semantic Priors using Generative Models
arXiv · 8 iun. 2026
SemAnCorr: Semantic Anchored Correspondence for Zero-Shot Manipulation Skill Transfer
arXiv · 31 iul. 2026
SkillNav: Score-Level Skill Intervention for Zero-Shot Object Goal Navigation
arXiv · 20 iul. 2026