Representational image. Getty Images
Driving without GPS seems unthinkable, but a new Surrey AI system could spell its end.
Researchers at the University of Surrey have developed an artificial intelligence tool that pinpoints a device’s location even in dense urban areas where satellite signals often fail.
The system, called Pose-Enhanced Geo-Localisation (PEnG), narrowed down localisation errors from 734 metres to just 22 metres in tests.
Instead of relying on GPS satellites, PEnG combines satellite and street-level images to determine where a device is and which way it is facing.
This two-step process first narrows down the position at street level and then refines it through relative pose estimation, a technique that calculates the camera’s orientation.
The researchers explained that this approach works even with a simple monocular camera, the kind commonly found in vehicles, making it both accessible and practical for future deployment.
They stressed that GPS coverage is often unreliable in tunnels, high-rise cities such as New York, or regions with poor connectivity, and their system was designed precisely to fill this gap.
“Many navigation systems depend on GPS, but coverage isn’t always guaranteed,” said Tav Shore, postgraduate research student in AI and computer vision.
“Our goal was to develop a solution that works reliably using only visual information. By combining satellite and ground-level imagery, PEnG achieves a level of accuracy previously thought unachievable without GPS – and could help unlock new possibilities for autonomous vehicles and smart navigation tools.”
The team believes the system’s flexibility could transform how machines navigate when conditions are unpredictable.
“One of the most exciting aspects of this system is how it turns a simple monocular camera into a powerful navigation tool,” said Dr Simon Hadfield, associate professor in robot vision and autonomous systems.
“PEnG is designed to operate without GPS, making it ideal for fast-moving, unpredictable scenarios. That kind of flexibility is exactly what’s needed for the next generation of autonomous vehicles and robotics operating in challenging environments.”
Beyond GPS dependence
Global reliance on GPS has grown to the point where outages or signal interference can have serious consequences. From logistics and delivery fleets to aviation and defense, industries depend on precise navigation.
Yet GPS signals are vulnerable. Tall buildings, tunnels, jamming devices, or even atmospheric conditions can cause disruptions. By providing a GPS-free alternative, PEnG could make navigation more resilient and reliable.
The Surrey researchers argue that their work is as much about everyday convenience as it is about safety.
Professor Adrian Hilton, director of the Surrey Institute for People-Centred AI, noted: “Our team’s work demonstrates the people-centred approach to AI we champion here at Surrey, developing a system that addresses the challenges behind navigation technology, something we’ve all come to rely on.
The ability to accurately pinpoint a location without GPS lays the foundation for smarter, more resilient autonomous systems that can operate in even the most remote environments.”
The project has been supported by the University of Surrey’s PhD Foundership Award, which funds early-stage development of promising technologies. The team is now focused on creating a working prototype that could be tested in real-world conditions.
To accelerate progress in the field, they have also released their research as open source, inviting developers and engineers worldwide to build on their results.
The findings have been published in IEEE Robotics and Automation Letters.