Ludo Robotics
About
About Ludo Robotics
Ludo Robotics is developing general-purpose intelligence for social humanoid robots, joining machine perception, learning and human-robot interaction. Its research goal is to make robots interpret both physical surroundings and social behaviour, remain aware of people around them and respond in ways suited to shared environments. The company frames this as a software and learning problem rather than a finished robot product line.
Its technical programme uses large-scale, data-driven machine learning to pursue adaptable behaviour outside tightly scripted demonstrations. Work spans robotic perception and decision-making, control systems and models of human behaviour, with engineering in Palo Alto and Seoul. Ludo is backed by KRAFTON and has access to the game company's AI infrastructure and technical network. Public activity currently centres on research and team building; Ludo has not announced a commercially available humanoid platform or a deployed customer fleet.
Team
- Kim Chang-han / CH Kim - CEO - Alongside leading Krafton, he serves as chief executive of Ludo Robotics and brings large-scale AI, simulation and product-development experience to its robot-intelligence…
Research
- Ludo Robotics releases Prompt-to-Policy reinforcement-learning system
2026-04-03 - Research Publication - The system writes reward functions, trains policies with PPO and evaluates rollouts using code and vision-language judges. Its release includes a web dashboard and support for MuJoCo environments, with optional IsaacLab integration. The official technical report demonstrated 64 learned behaviors and published the full training and evaluation repository under an MIT license.
Source
Timeline
Events
- 2026-04-03 - Research Publication - Ludo Robotics releases Prompt-to-Policy reinforcement-learning system
The system writes reward functions, trains policies with PPO and evaluates rollouts using code and vision-language judges. Its release includes a web dashboard and support for MuJoCo environments, with optional IsaacLab integration. The official technical report demonstrated 64 learned behaviors and published the full training and evaluation repository under an MIT license.
Source - 2026-03-11 - Org Change - KRAFTON CEO Kim Chang-han takes CEO role at Ludo Robotics
The appointment aligned Ludo’s physical-AI programme directly with KRAFTON’s corporate leadership. Kangwook Lee continued as CTO and head of the Korean operation. The leadership structure separated corporate oversight from day-to-day technology management.
Source - 2026-02-23 - Org Change - Krafton launches Ludo Robotics for physical AI
The new unit focuses on physical AI and general-purpose robotic intelligence. Its research remit spans perception, learning and human-robot interaction. KRAFTON CEO Changhan Kim personally led the company’s robotics initiative.
Source
Relations
Relationships
- KRAFTON, Inc.
Krafton Robotics Subsidiary - Ludo Robotics is a KRAFTON subsidiary created for physical-AI and robotic-intelligence research.
Context
Comparable profiles
- Lightwheel
stack adjacency - Physical AI Data Infrastructure
- microagi
stack adjacency - Physical AI Data Infrastructure
- LabyrinthAI
stack adjacency - Physical AI Data Infrastructure
- peaq
stack adjacency - Physical AI Data Infrastructure
- Encord
stack adjacency - Physical AI Data Infrastructure
- Hyundai Motor Group
stack adjacency - Physical AI Data Infrastructure
- Picogrid
stack adjacency - Physical AI Data Infrastructure
- Mecka AI
stack adjacency - Physical AI Data Infrastructure
- Avea Robotics
stack adjacency - Physical AI Data Infrastructure
- FORMOVE GmbH
stack adjacency - Physical AI Data Infrastructure
- Vision Lab
stack adjacency - Physical AI Data Infrastructure
- YYForce
stack adjacency - Physical AI Data Infrastructure
Context tags
- Social humanoid intelligence - Capability - Ludo Robotics describes itself as building social humanoid intelligence for robots that understand the social world.
- Human-robot interaction - Capability - Ludo works across perception, learning, and human-robot interaction.
- Physical AI data infrastructure - Stack Layer - Ludo is adjacent to physical-AI model development, though its public copy emphasizes research rather than dataset services.