Kakao Mobility Outlines Roadmap for Level 4 Autonomous Vehicles
68Kakao Mobility has announced its plans to develop Level 4 autonomous driving technology as part of its physical AI strategy. The company aims to build these advanced systems in-house to enhance its mobility services. The roadmap was shared by Kim Jin-kyu, vice president and head of Kakao Mobility’s Physical AI division, at the 2026 World IT Show in Seoul.
The event, held at COEX and attended by over 460 companies from 17 countries, focused on turning AI ideas into real-world applications. Under the theme “Beyond Idea, Into Action: AI moves Reality,” the conference highlighted Korea’s push toward integrating AI into physical industrial fields. Kakao Mobility emphasized its goal to combine autonomous driving with physical infrastructure to boost local competitiveness and foster an open autonomous driving ecosystem in Korea.
Kakao Mobility’s Level 4 Autonomous Driving Roadmap
The company’s plan for Level 4 autonomy centers on three main technology areas: machine learning models, vehicle redundancy, and validation systems. Kakao is developing sophisticated machine learning models that support perception, decision-making, and vehicle control without human intervention. These models enable autonomous vehicles to interpret their surroundings, decide on actions, and execute driving commands safely.
In addition, Kakao Mobility is designing vehicle architectures with redundant systems. This means critical functions have backup components, ensuring the vehicle can continue operating smoothly even if a part fails. To support ongoing development, the company is also creating a validation platform that combines virtual simulations with real-world driving data. This platform helps test, improve performance, and ensure quality as they develop autonomous services.
Safety and Control Systems Development
Kakao Mobility is also working on an integrated safety management system for autonomous vehicles. A key part of this is the Autonomous Vehicle Visualizer, a 3D tool that displays what the vehicle’s sensors detect in real time. Passengers can see the vehicle’s view during a ride, giving them confidence in the system’s awareness and decision-making.
The company plans to establish a 24-hour control center that will monitor autonomous vehicles after deployment. This center will oversee safety and performance, ready to intervene if necessary. Additionally, Kakao Mobility is developing an anomaly detection system using vision-language models. While details are scarce, this system is expected to analyze vehicle data in real time, identify issues, and support remote interventions during operations.
Overall, Kakao Mobility’s roadmap demonstrates a clear focus on safety, reliability, and integration. By combining advanced AI models, robust vehicle architecture, and real-time monitoring, the company aims to bring Level 4 autonomous driving closer to reality in Korea and beyond.
What do you think?
It is nice to know your opinion. Leave a comment.