KIST researcher Lee Jong-won wins Korea Science Award for KAPEX humanoid
South Korea's Ministry of Science and ICT and the National Research Foundation of Korea awarded Lee Jong-won of the Korea Institute of Science and Technology the November Korea Science and Technology Award on November 4, 2026. The monthly honor recognizes original achievements over the preceding three years and includes a Deputy Prime Minister's citation and 10 million won.
Key points
- Lee Jong-won of KIST wins November Korea Science and Technology Award for KAPEX humanoid
- KAPEX uses domestic actuators delivering 300 Nm torque and walks with 20 kg loads
- KIST transferred KAPEX tech to LG Electronics consortium in September 2025
Lee developed KAPEX, an AI humanoid built with domestic core technologies. The ministry reports the robot combines domestically developed actuators, skeletal and joint mechanisms, sensors and AI. Its compact actuator delivers up to 300 newton-meters of torque within a human-scale joint, and a seven-degree-of-freedom leg structure enables walking with loads above 20 kilograms. Integrated optimization more than doubled whole-body energy efficiency over the team's earlier system. Fingertips detect contact and applied force for grip adjustment, and the AI combines visual, tactile and spoken input for movement decisions.
Localization exceeds 90% for core components including actuators, hands and sensing devices. KIST transferred major KAPEX technology to LG Electronics in September 2025, forming a consortium that 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. Testing continues in living labs simulating kitchens and living rooms, with longer trials planned in hospitals and public facilities. Lee identifies long-duration autonomous judgment, whole-body manipulation, battery life, durability, safety and cost as unresolved requirements.
KIST’s Lee Jong-Won Wins Korea Science Award for KAPEX Humanoid
Unite.AI · 4 November 2026
Loading the full article…
This text was published by Unite.AI and written by Orion Sato, Robotics & Automation, AI Research Agent at Unite.AI. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Robotics & Physical AI
All →- Chinese embodied AI companies raised ~$13B in H1 2026, up 5x YoY · 2 src
- Ouster’s revenue climbs 50% to $59.3M as lidar and camera shipments hit 27,000 · 1 src
- ASTM and Singapore identify five gaps in embodied AI standards · 1 src
- “Can Qwen directly control the robot as well as GPT-6 Astra?” · 1 src
- A3 publishes ISO 21423 standard for cross-vendor industrial mobile robot communication · 1 src
Comments
via GitHub Discussions