New AI system could change how autonomous vehicles navigate without GPS

August 20, 2025

The GIST New AI system could change how autonomous vehicles navigate without GPS

Lisa Lock

scientific editor

Alexander Pol

deputy editor

Editors' notes

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

peer-reviewed publication

trusted source

proofread

An AI system capable of pinpointing a device's location in dense urban areas without relying on GPS has been developed by researchers at the University of Surrey. Narrowing down localization errors from 734 meters to within 22 meters, the innovation could be a significant step forward for technologies such as self-driving cars and aid delivery vehicles.

In their paper published in IEEE Robotics and Automation Letters, researchers describe PEnG (Pose-Enhanced Geo-Localization), a technology that combines satellite and street-level imagery to determine location using only visual data. In environments where GPS signals are weak or obstructed, such as tunnels, cities like New York, or regions with poor connectivity, PEnG offers a reliable and precise alternative for navigation.

Tavis Shore, Postgraduate Researcher in AI and Computer Vision at the University of Surrey, said, "Many navigation systems depend on GPS, but coverage isn't always guaranteed. 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."

Unlike previous methods, which are limited by how often satellite images are sampled, PEnG uses a two-step process—first narrowing down the location at street-level, then refining it using relative pose estimation, a technique that analyzes exactly where a camera is and which way it is facing. The system delivers high accuracy even when using standard monocular cameras found in most vehicles.

Dr. Simon Hadfield, associate professor (reader) in robot vision and autonomous systems at the University of Surrey and primary supervisor on the project, 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, 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."

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

Professor Adrian Hilton, director of Surrey's Center for Vision, Speech and Signal Processing, and the Surrey Institute for People-Centered AI, said, "Our team's work demonstrates the people-centered 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 research has been released as open source to support future innovation in navigation technologies.

More information: Tavis Shore et al, PEnG: Pose-Enhanced Geo-Localisation, IEEE Robotics and Automation Letters (2025). DOI: 10.1109/LRA.2025.3546513

Journal information: IEEE Robotics and Automation Letters Provided by University of Surrey Citation: New AI system could change how autonomous vehicles navigate without GPS (2025, August 20) retrieved 20 August 2025 from https://techxplore.com/news/2025-08-ai-autonomous-vehicles-gps.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further

Novel motion forecasting framework can deliver safer and smarter self-driving cars shares