analiza aiqbench
VGP-Nav addresses the deployment overhead of multi-sensor robotic systems by enabling metric-consistent localization and obstacle perception using only monocular RGB input. The framework resolves scale ambiguity online by anchoring visual geometry to ground-plane constraints, offering a scalable path for low-cost autonomous navigation without LiDAR. This approach is particularly relevant for applications requiring cost-effective, robust perception in diverse environments.
VGP-Nav: Metric-Aware Visual Geometric Perception for Robot Navigation
arXiv:2606.09268v1 Announce Type: new Abstract: Reliable robotic navigation necessitates the seamless integration of accurate global localization and dense, metric-consistent obstacle perception. A common strategy to achieve these capabilities involves integrating diverse sensing modalities: cameras offer rich visual features for localization, while active sensors like LiDAR provide direct metric measurements. However, such multi-sensor configurations necessitate complex spatial-temporal calibration and increase deployment overhead. Although vision-only approaches offer a low-cost and scalable alternative, existing monocular visual systems typically struggle to simultaneously achieve efficient, globally consistent localization and dense, metric-consistent geometric perception. To bridge this gap, we propose \textbf{VGP-Nav}, a unified framework for \textit{Metric-Aware Visual Geometric Perception} that relies solely on monocular RGB input to jointly support metric localization and obstacle perception. Our key insight is to anchor localization-grounded visual geometry to physically meaningful scale constraints derived from ground-plane geometry, thereby providing a reliable metric reference for monocular perception. VGP-Nav resolves monocular scale ambiguity online and produces localization-grounded, metric obstacle representations that are directly applicable to downstream planning. Extensive experiments demonstrate strong generalization across diverse environments and successful deployment on real mobile robots, highlighting the practicality of our approach for scalable, low-cost, and safe autonomous navigation.
Abstract:Reliable robotic navigation necessitates the seamless integration of accurate global localization and dense, metric-consistent obstacle perception. A common strategy to achieve these capabilities involves integrating diverse sensing modalities: cameras offer rich visual features for localization, while active sensors like LiDAR provide direct metric measurements. However, such multi-sensor configurations necessitate complex spatial-temporal calibration and increase deployment overhead. Although vision-only approaches offer a low-cost and scalable alternative, existing monocular visual systems typically struggle to simultaneously achieve efficient, globally consistent localization and dense, metric-consistent geometric perception. To bridge this gap, we propose \textbf{VGP-Nav}, a unified framework for \textit{Metric-Aware Visual Geometric Perception} that relies solely on monocular RGB input to jointly support metric localization and obstacle perception. Our key insight is to anchor localization-grounded visual geometry to physically meaningful scale constraints derived from ground-plane geometry, thereby providing a reliable metric reference for monocular perception. VGP-Nav resolves monocular scale ambiguity online and produces localization-grounded, metric obstacle representations that are directly applicable to downstream planning. Extensive experiments demonstrate strong generalization across diverse environments and successful deployment on real mobile robots, highlighting the practicality of our approach for scalable, low-cost, and safe autonomous navigation.
Robotics (cs.RO)
arXiv:2606.09268 [cs.RO]
(or arXiv:2606.09268v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.09268 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 · 280 cuvinte
Subiecte conexe
Safe Multi-Robot Coordination via VLM-LLM Reasoning and Reachability Analysis
arXiv · 24 sept. 2026
CollisionSplatting: Collision-Aware Motion Planning in 3DGS Scenes with Image-Conditioned Objectives and Adjustable Conservatism
arXiv · 29 sept. 2026
DROID-ANCHOR: Odometry-Anchored Recurrent Metric Depth Estimation
arXiv · 21 iul. 2026
Onboard Lightweight LLM Reasoning for Human-Aware Safe UAV Navigation
arXiv · 16 oct. 2026