PALO ALTO – October 31, 2026 -- KRAFTON subsidiary Ludo Robotics presented Ludi 0.2, the second iteration of its robotic intelligence system, at the 2026 Bay Area Robotics Symposium (BARS) at UC Berkeley, and confirmed that a next-generation foundation model, Ludi 1.0, is in development.
Ludi 0.2 adds five capabilities to August's Ludi 0.1 release
Ludi 0.1, introduced in August 2026, combined a vision-language model for reasoning and dialogue with specialized navigation and manipulation functions. It was built to interpret spoken instructions, maintain conversational context, ask clarifying questions and adapt to changing tasks in supported environments.
Ludi 0.2 extends that base in five areas:
- Social intelligence, covering human intent, feedback and social cues
- Memory and reasoning across changing tasks
- Tool coordination across navigation, manipulation and interaction
- Gesture interpretation
- Smoother, more adaptable physical movement
Kangwook Lee, KRAFTON's Chief AI Officer and Ludo Robotics CTO, said understanding and responding to people "remains a major challenge" even as robots grow more capable at physical tasks.
Ludi 1.0 targets a unified model for perception, dialogue and action
Ludi 1.0 aims to integrate perception, dialogue and physical action in one system. The goal is for robots to hold a shared understanding of tasks with people while communicating and acting in real time. The source gives no release date for the model.
KRAFTON applies game-AI work with NVIDIA to physical robots
KRAFTON says its game-development experience feeds the robotics effort. The company has invested in machine learning, reinforcement learning, large language models and multimodal AI. It has also developed proprietary AI foundation models and Co-Playable Characters (CPCs), AI teammates built with NVIDIA that respond to players in real time. CH Kim, CEO of KRAFTON and Ludo Robotics, said Ludo Robotics carries that experience into the physical world.
Palo Alto headquarters and Seoul lab anchor the research team
Ludo Robotics is headquartered in Palo Alto and runs an additional R&D lab in Seoul. Lee is a former tenured associate professor at the University of Wisconsin-Madison. Chief Scientist Rob Nowak is an IEEE Fellow and UW-Madison professor specializing in machine learning, embodied AI and robot learning. Human-Robot Interaction Lead Yea-Seul Kim is a former UW-Madison assistant professor of Computer Sciences.
Training combines simulation, AI-generated interactions and real-world data
Ludo Robotics trains its systems on simulated environments, AI-generated social interactions and real-world human behavior data. It is also developing benchmarks that test how robots handle social situations involving different personalities, preferences and relationships, as well as gesture-driven physical manipulation. The company's stated long-term ambition is robots that collaborate with people in homes, workplaces and other real-world settings.