arXiv:2605.06100v2 Announce Type: replace-cross Abstract: Global navigation satellite system (GNSS) positioning is widely used for urban navigation, but the covariance reported by the GNSS solver is often unreliable in urban canyons. Existing differentiable factor graph optimization (DFGO) methods learn measurement weighting through the solver, but they still use position-only objectives. As a result, the position estimate may improve while the reported covariance remains too small, too large, or incorrectly oriented. We propose CredibleDFGO (CDFGO), a differentiable GNSS factor graph framewor
The increasing reliance on autonomous systems and AI in urban environments drives the need for more robust and trustworthy navigation, pushing research in areas like better GNSS covariance reporting.
Reliable positioning and uncertainty quantification are critical for the safe and effective deployment of AI agents and robotics, especially in complex urban settings where GNSS is often unreliable.
This research introduces a method to improve both the accuracy and the credibility of uncertainty estimates in GNSS, which is a foundational component for advanced autonomous systems.
- · Autonomous vehicle developers
- · Robotics companies
- · Logistics and delivery services
- · Urban planning and smart city initiatives
Improved positional accuracy and uncertainty reporting for AI agents and robots operating in urban environments.
Faster and safer deployment of autonomous systems in complex scenarios due to enhanced navigational reliability.
Reduced operational costs and increased public trust in autonomous services as a result of fewer navigation-related failures.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG