Researchers at the University of Surrey have developed an artificial intelligence system that can precisely locate devices in densely populated urban areas without relying on GPS. The system reduces positioning error from 734 meters to within 22 meters, which is of great significance for the development of technologies such as autonomous vehicles and emergency response vehicles.

In a paper published in IEEE Robotics and Automation Letters, the researchers describe PEnG (Pose-Enhanced Geolocation) technology, which combines satellite and street images to determine location using only visual data. In environments where GPS signals are weak or blocked, such as tunnels, cities like New York, or areas with poor network connectivity, PEnG provides a reliable and accurate navigation alternative.

Tavis Shore, a graduate researcher in artificial intelligence and computer vision at the University of Surrey, said: "Many navigation systems rely on GPS, but its coverage is not always guaranteed. Our goal is to develop a solution that can operate reliably using only visual information. By combining satellite and ground images, PEnG achieves a level of accuracy previously thought impossible without GPS, and is expected to open new possibilities for autonomous vehicles and smart navigation tools."

Unlike previous methods limited by satellite image sampling frequency, PEnG uses a two-step process: first narrowing down the location to the street level, then refining it using relative pose estimation technology. Relative pose estimation can accurately analyze the camera's position and orientation. Even with standard monocular cameras commonly found in most vehicles, the system can deliver high precision.

Dr. Simon Hadfield, Associate Professor (Reader) in Robotic Vision and Autonomous Systems at the University of Surrey and the project's principal supervisor, said: "One of the most exciting aspects of this system is how it turns a simple monocular camera into a powerful navigation tool."

PEnG is designed to operate without GPS and is well-suited for fast-moving, unpredictable scenarios. This flexibility is exactly what the next generation of autonomous vehicles and robots need to operate in challenging environments.

Tavis and his team are currently focused on building a working prototype, supported by the University of Surrey's Doctoral Founder Award, which funds the early development of the proposed GPS-free navigation device.

Professor Adrian Hilton, Director of the Centre for Vision, Speech and Signal Processing and Director of the Surrey Institute for People-Centred Artificial Intelligence at the University of Surrey, said: "Our team's work embodies the University of Surrey's people-centred AI approach, developing a system that addresses the challenges behind navigation technology—a technology we all rely on."

"The ability to accurately locate without GPS lays the foundation for smarter, more resilient autonomous systems that can even operate in the most remote environments."

The research has been released in open source to support future innovation in navigation technology.