CoSMO: Conformal Semantic Mapping for Open-World Safe Robot Navigation
CoSMO: Conformal Semantic Mapping for Open-World Safe Robot Navigation
This research presents CoSMO, a framework that transforms vision-language model embeddings into online-calibrated coverage sets and safety-aware obstacle dilations to ensure safe navigation in open-world environments. By calibrating directly in the embedding space, CoSMO avoids score rescaling issues as vocabulary expands. Experiments on the Matterport3D dataset show a 61.6% reduction in semantic collisions compared to geometry-only baselines while maintaining formal coverage guarantees. Real-world tests on a quadruped robot achieved an empirical coverage of 90.73% against a 90% target, demonstrating generalization under distribution shift and delayed expert feedback.
The paper introduces CoSMO, a framework that uses conformal prediction to calibrate vision-language model embeddings for safe navigation in open-world environments, demonstrating reduced semantic collisions on Matterport3D and empirical coverage guarantees on a quadruped robot.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S2
- code: not_reported
- weights: not_reported
- dataset: not_reported
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2610.18321v2 Announce Type: replace Abstract: Safe autonomous navigation requires not only geometric obstacle avoidance but also semantic awareness. Different object categories demand different safety clearances, and the set of relevant categories may expand as the robot explores novel environments. Vision-language models (VLMs) offer rich semantic representations for building maps of unknown scenes, yet their
Open source S2
ings into online-calibrated coverage sets and safety-aware obstacle dilations under distribution shift. By calibrating directly in the embedding space, CoSMO avoids the score rescaling that arises in confidence calibration as the vocabulary expands. Experiments on the Matterport3D (MP3D) dataset show that CoSMO reduces semantic collisions by 61.6% relative to a geometry-only baseline, while maintaining formal coverag
Open source S4
e guarantees even under delayed expert feedback. Real-world experiments on a quadruped robot further demonstrate generalization by achieving long-run empirical coverage of 90.73% against the 90% target. Project website: https://yangming911.github.io/cosmo-page/.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org