"Challenging Google for 'Location Sovereignty': KAIST Develops Core Technology for Building 'Radio Maps'"

A homegrown core technology has been independently developed in Korea to challenge the dominance of global platform companies such as Google and Apple in the field of location services. The key function is the precise identification of indoor locations by combining a smartphone's Wi-Fi signals with a radio map (signal fingerprint map). This technology is expected to help secure the golden hour for searching for missing persons, and is being recognized as a "location sovereignty" technology that could reshape the current location service structure centered on global big tech companies.

AI Generated Image. KAIST

On April 2, KAIST announced that the research team led by Professor Dongsoo Han from the School of Computing has developed a core technology to build a nationwide Wi-Fi radio map by integrating Wi-Fi signals with real address information, as well as key technology to implement a high-precision location infrastructure based on this foundation.

The core of this technology is the use of Wi-Fi signals collected by smartphones in daily life. Without the need for large-scale additional equipment or infrastructure, it can provide precise location information anywhere in the country. It also achieves high accuracy in locations where GPS is weak, such as indoors, underground, or in clusters of high-rise buildings. The research team has enhanced the technological completeness by filing more than 10 patents over the past eight years.

Currently, location data around the world is accumulated and managed by a handful of big tech companies like Google and Apple, and Korea also heavily relies on these platforms. In this context, the establishment of an independent foundation for building and managing a nationwide radio map tailored to domestic needs carries significant meaning.

A radio map is a database built by linking Wi-Fi signals collected in specific spaces with the corresponding location information, enabling the estimation of a location based on unique signal patterns for each place. While radio maps are typically constructed at the building level, expanding them to city or national scale enables the implementation of more precise and versatile location services.

Schematic diagram of address-based wireless signal collection automation and wireless signal collection location labeling AI technique. KAIST

In particular, recent controversies over the overseas export of the "1:5000 precision map" (a national core spatial dataset detailing buildings, roads, etc.) have heightened the importance of securing data sovereignty.

The technology developed by the research team is considered an alternative that can realize "location sovereignty" by reducing dependence on global big tech companies.

Most importantly, precision location services are usually based on building a nationwide radio map, and the team's technology enables this to be achieved quickly and at low cost. It works by automatically combining Wi-Fi signals collected during smartphone app usage with the actual address information of the location, thereby creating a unique "signal pattern map (signal fingerprint)" for each place.

The research team explained that as radio maps are accumulated in this way, precise location recognition becomes possible, and the more data is accumulated, the higher the completeness of the radio map, which continually improves location accuracy.

In fact, when verified using a gas meter reading app, an average of over 30 Wi-Fi signals were detected per household in apartments, confirming the possibility of rapidly constructing a city-scale radio map.

(From left) Professor Dongsoo Han, Dr. Kyooho Son, Dr. Byungcheol Moon, Dr. Sumin Ahn, PhD candidate Seungwoo Chae. KAIST

If the completed radio map is applied to emergency rescue situations such as searching for missing persons, it is expected to drastically reduce location errors, which had previously reached several hundred meters, thereby helping to secure the golden hour. In addition, if utilized as a "location-based authentication" technology that allows transactions only at specific locations, it could also help prevent financial incidents such as identity theft or remote payment fraud.

Considering that precise location data is regarded as core infrastructure in future artificial intelligence (AI) industries such as autonomous driving, robotics, and logistics, the research team's achievements are expected to serve as foundational technology to enhance the overall competitiveness of related industries.

Professor Han stated, "It is difficult for a single company to build a nationwide radio map alone, so it is necessary to establish a public-private joint infrastructure led by the government and supported by telecommunications companies, platform providers, and research institutes. Location infrastructure is not merely a convenience technology, but a core asset directly linked to national 'data sovereignty.' The government should collaborate with telecommunications and platform companies to independently establish a national location infrastructure."

This research was supported by the Ministry of Science and ICT, the National Research Foundation of Korea, the National Fire Agency, and the Korea Evaluation Institute of Industrial Technology (KEIT).

This content was produced with the assistance of AI translation services.