Kakao Mobility Reveals Level 4 Autonomous Roadmap

At the 2026 World IT Show, Kakao Mobility announced a Level 4 autonomy plan with in-house ML models, redundant vehicle systems, a validation platform and shared datasets, HD maps and APIs for partners.

At the 2026 World IT Show at COEX in Seoul, Kim Jin-kyu, vice president and head of Kakao Mobility’s Physical AI division, presented the company’s Level 4 autonomous driving roadmap. The plan commits to building in-house machine learning models, redundant vehicle architectures and a validation platform while opening large-scale datasets, high-definition maps and platform APIs to industry partners. The project aligns with South Korea’s physical AI initiative led by the Ministry of Science and ICT.

The roadmap rests on three technical pillars. The first is machine learning models for perception, decision-making and vehicle control that operate without human input. The second is vehicle architectures with redundant systems to maintain core functions if primary components fail. The third is a validation platform that combines virtual simulation with recorded driving data for testing, performance tuning and quality checks.

For safety and operations, the company plans an integrated safety management platform. One tool under development, the Autonomous Vehicle Visualizer, will provide a three-dimensional view of a vehicle’s sensors in real time so passengers and operators can see what the car detects during a trip. The company intends to establish a 24-hour control center to monitor services and to deploy an anomaly detection system that uses vision-language models for real-time context analysis, remote intervention and emergency response.

Selected technology assets will be shared with automakers, startups and other companies working on autonomy. Those assets include large-scale driving datasets, HD maps for localization and decision-making, and platform APIs for ride-hailing and dispatch. The company plans to offer operational resources such as fleet management systems and on-site response capabilities to reduce setup needs for partners.

Kakao Mobility cited its late-night autonomous taxi service in Seoul’s Gangnam district as an operational example. The service, available through the Kakao T mobility app, launched on September 26, 2024. Seoul city data show 7,754 rides from launch through February 28, 2026, averaging about 24 trips per operating day, with no accidents attributed to the autonomous system. The pilot moved from free testing to paid operation in April 2026 and the operating fleet expanded from three to seven vehicles, excluding two reserve vehicles.

Level 4 autonomy, as defined by the U.S. National Highway Traffic Safety Administration, enables a vehicle to handle driving in limited service areas without requiring passengers to monitor the road or take control. These systems are typically deployed in defined zones such as autonomous taxi districts or fixed operating areas.

Kakao Mobility stated the roadmap and asset-sharing plan are intended to support a domestic ecosystem for autonomous driving and to integrate autonomy with existing mobility platforms and physical infrastructure for broader urban deployment.

Content on BlockPort is provided for informational purposes only and does not constitute financial guidance.
We strive to ensure the accuracy and relevance of the information we share, but we do not guarantee that all content is complete, error-free, or up to date. BlockPort disclaims any liability for losses, mistakes, or actions taken based on the material found on this site.
Always conduct your own research before making financial decisions and consider consulting with a licensed advisor.
For further details, please review our Terms of Use, Privacy Policy, and Disclaimer.

Articles by this author

This site is registered on wpml.org as a development site. Switch to a production site key to remove this banner.