Aiming to Implement Universal Driving Intelligence
Advancing Control with an Integrated AI Model

On March 17, KGM announced that it had signed a Letter of Intent (LOI) with the Electronics and Telecommunications Research Institute (ETRI) and Sodis to develop next-generation end-to-end (E2E) autonomous driving AI technology. The signing ceremony, held the previous day at the ETRI headquarters in Daejeon, was attended by Kwon Yongil, Head of Development and Production at KGM; Choi Jeongdan, Head of Division at ETRI; and Kang Chanho, CEO of Sodis, among others, who pledged mutual cooperation.

KGM has signed a Letter of Intent (LOI) with the Electronics and Telecommunications Research Institute (ETRI) and Sodis Co., Ltd. to develop next-generation end-to-end (E2E) autonomous driving AI technology. From the left, Sodis CEO Chanho Kang, KGM Head of Development and Production Yongil Kwon, and ETRI Director Jungdan Choi. KGM

KGM has signed a Letter of Intent (LOI) with the Electronics and Telecommunications Research Institute (ETRI) and Sodis Co., Ltd. to develop next-generation end-to-end (E2E) autonomous driving AI technology. From the left, Sodis CEO Chanho Kang, KGM Head of Development and Production Yongil Kwon, and ETRI Director Jungdan Choi. KGM

View original image

Through this collaboration, KGM will provide driving data collected from real roads and test infrastructure, while ETRI and Sodis will use this to implement a universal driving intelligence in which AI perceives the environment and directly controls the vehicle. Unlike traditional autonomous driving, which handled perception, judgment, and control in separate steps, the new E2E approach features a single integrated AI model that understands road conditions and simultaneously makes steering and acceleration or deceleration decisions.


In particular, multimodal technology will be applied to enable not only visual information but also linguistic concepts and situational context to be understood together. The partners plan to jointly develop reinforcement learning-based AI software that can predict dangerous situations in congested road environments, as well as core technologies for perception and decision-making in uncertain conditions such as inclement weather.


KGM expects that by combining ETRI's foundational technologies from national projects with its own real-world driving data, it will be able to derive the optimal autonomous driving model. Through this, the company aims to efficiently equip vehicles with advanced autonomous driving functions from the development stage, thereby enhancing product competitiveness.



A KGM official stated, "Through technological cooperation with research institutes, we will be able to overcome the limitations of existing autonomous driving technology," adding, "By advancing technology and completing our lineup of eco-friendly vehicles, we will secure future growth engines and establish a foundation for sustainable growth."


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

© The Asia Business Daily. All rights reserved. Unauthorized AI training and use prohibited.

Today’s Briefing