Diden Robotics and Movin Team Up to Develop Human-Like Humanoid Robots
Diden Robotics, an industrial physical AI company, and Movin, a human motion AI company, have signed a Memorandum of Understanding (MOU) to build and utilize datasets required for humanoid learning.
Press
Original Article: Maeil Business Newspaper https://www.mk.co.kr/news/it/12099077
Diden Robotics, an industrial physical AI company, and Movin, a human motion AI company, announced on the 15th that they have signed a memorandum of understanding (MOU) to build and utilize datasets required for humanoid learning.
Through this agreement, the two companies plan to jointly improve the motion learning performance of robots. They will combine Movin's LiDAR-based motion capture technology and multimodal data collection capabilities with Diden Robotics' humanoid development capabilities.
Improving humanoid performance requires precise data on how actual humans move, maintain balance, and interact with surrounding objects in complex environments. Existing motion data was often built for content creation or animation, which has limitations as it is difficult to apply directly to a robot's joint structure, motion range, and physical constraints.
The two companies will collect diverse human movements occurring in real-world environments as high-precision 3D motion data and multimodal sensor data. Together, they will build a data pipeline to convert this into a format suitable for humanoid robot learning.
Movin will collect LiDAR and camera data from various viewpoints and provide it in a retargeted format that fits the robot structure of Diden Robotics. Diden Robotics plans to utilize this dataset to enhance the learning efficiency and precision of core behavior models, such as humanoid walking, balancing, whole-body control, and interaction with objects and environments. Starting with this MOU, the two companies plan to expand the scope of cooperation to joint research and potential commercialization.
Jun-ha Kim, CEO of Diden Robotics, said, "To improve humanoid performance, high-quality multimodal data containing both human movement and surrounding spatial information is required. Through cooperation with Movin, we will secure data optimized for robot hardware and strengthen a learning system that can be directly applied to actual robot development."
Byul-yi Choi, CEO of Movin, said, "The technology to precisely collect human movements and convert them to fit a robot's physical structure is an important foundation for humanoid robot learning. Through this collaboration, we expect Movin's motion data technology to expand beyond the content industry to become a core data infrastructure in the robotics field."
