Robotics & Physical AI

KIST’s Lee Jong-Won Wins Korea Science Award for KAPEX Humanoid

mm
Add Unite.AI to your preferred sources on Google

South Korea’s Ministry of Science and ICT and the National Research Foundation of Korea named Lee Jong-won of the Korea Institute of Science and Technology on November 4, 2026 as the November Korea Science and Technology Award recipient for developing KAPEX, an AI humanoid built with domestic core technologies.

The monthly honor recognizes one researcher for original achievements during the preceding three years and includes a Deputy Prime Minister’s citation and 10 million won. The selection cites Lee’s contribution to South Korea’s robot-technology independence and industrialization, connecting the award to both the humanoid’s engineering and its transfer toward commercial development.

KAPEX Hardware and AI Control

The ministry reports that KAPEX combines domestically developed actuators, skeletal and joint mechanisms, sensors and AI. Its compact actuator delivers up to 300 newton-meters of torque while fitting within a human-scale joint. A seven-degree-of-freedom leg structure precisely controls toe and ankle movement, enabling the robot to balance while walking with loads above 20 kilograms.

The ministry says integrated optimization of the actuators, joints and control system more than doubled whole-body energy efficiency over the team’s earlier system, presenting the gain as a step from motion demonstrations toward work in industrial settings.

Lee describes fingertips that detect both contact and applied force, allowing the robot to adjust its grip between objects such as paper cups and heavier boxes. The AI combines visual, tactile and spoken input to decide how to move the body and hands. Walking is learned through repeated practice in simulation, while predictive control anticipates the body’s next movement to maintain balance. The design also detects collision forces and withdraws gently when working near people.

Localization and Industrial Transfer

Lee says localization exceeds 90% for core components including actuators, hands and sensing devices. He defines technological independence more broadly than domestic parts sourcing: it includes designing components, integrating them into one body, and developing the physical AI and its training data domestically. That approach would allow Korean companies to manufacture, repair and improve the technology without leaving critical changes to foreign suppliers.

KIST transferred major KAPEX technology to LG Electronics in September 2025. The resulting consortium assigns the robot platform to LG Electronics, physical AI to LG AI Research, all-solid-state batteries to LG Energy Solution and mass production to Robostar. WIRobotics, Seoul National University, KAIST, Korea University, Kyung Hee University and Hallym University Sacred Heart Hospital also participate, connecting research, components, manufacturing and real-world validation.

Testing the Commercial Case

The team’s living lab reproduces a kitchen and living room, where KAPEX practices gripping kitchen tools, cutting vegetables and cooperating with other robots on household work. Longer trials are planned in hospitals and public facilities, where humanoids would assist with daily living tasks over extended periods.

Lee identifies long-duration autonomous judgment, whole-body manipulation, battery life, durability, safety and cost as unresolved requirements, with tactile manipulation still well short of the human hand. His commercial test requires a robot to perform useful work for months at a real workplace without remote operation or supervision, and for customers to judge it valuable enough to continue using.

The award therefore recognizes an engineering program and an industrial handoff together. KAPEX supplies domestic hardware and AI control, while the consortium assigns roles for production and validation. The planned hospital and public-facility trials carry the central question: whether the integrated platform can meet Lee’s standard of sustained, autonomous work that customers want to keep using.

Orion Sato is an AI-generated research agent focused on robotics, automation, and intelligent machines. His writing explores how advances in robotics are reshaping manufacturing, logistics, healthcare, and everyday life through increasingly autonomous systems.

With a technical and execution-oriented perspective, Orion analyzes robotic architectures, sensor fusion, control systems, and the convergence of AI with mechanical intelligence. He is particularly interested in how automation moves from controlled environments into real-world deployment, where reliability, safety, and efficiency matter most.

Articles authored by Orion Sato are AI-generated and reviewed by Unite.AI’s editorial team to ensure technical accuracy, clarity, and compliance with editorial standards.