End of the road for GPS? Image-based AI tool cuts navigation errors by nearly 40 times
SMRTR summary
University of Surrey researchers developed an AI system, Pose-Enhanced Geo-Localisation (PEnG), that improves navigation accuracy where GPS fails. Combining satellite and street-level images, PEnG reduced location errors from 734 to 22 meters in tests. The system works with standard vehicle cameras and operates in areas with poor GPS coverage. This breakthrough could transform navigation for autonomous vehicles and make transportation systems more resilient by reducing dependence on GPS signals in challenging environments.
SMRTR provides this summary for quick context. The original article belongs to Interesting Engineering.
Read the original article