Ludo Robotics introduces Ludi 0.2

Ludo Robotics introduced Ludi 0.2 on October 30, 2026, as a new version of its robotic intelligence system.[1][2] The update adds social intelligence, with improvements in how the system interprets human intent, responds to feedback and accounts for social cues during interactions.[2] Krafton says robots running the model can read social cues and understand human intent.[2] The system also improves its ability to recognize and respond to human gestures during physical interaction.[2] These capabilities describe the update’s intended behavior; the evidence does not provide performance measurements or comparative test results.

Ludi 0.2 advances the system’s ability to maintain context and reason through changing tasks and situations.[2] It supports more coordinated use of capabilities involved in navigation, manipulation and interaction.[2] Ludo also says the update expands context memory, tool coordination, movement adaptability and gesture interpretation compared with the previous version.[1] The system advances smoother, more adaptable movement in supported environments.[2] The evidence does not specify which environments are supported, or give numeric measures for movement or task performance.

Ludo presented Ludi 0.2 at the Bay Area Robotics Symposium at UC Berkeley.[2] The company introduced Ludi 0.1 in August 2026; that version combined a vision-language model for reasoning and dialogue with specialized navigation and manipulation capabilities.[3] Ludo is working toward a final version that integrates perception, dialogue and physical action.[3] Its stated objective is to combine communication, reasoning and physical action in one system.[3] Ludo describes a goal in which robots interpret what they observe and hear alongside gestures and physical movements.[3]

Ludo Robotics spun out of Krafton, which is known for publishing video games and PUBG: Battlegrounds.[3] Krafton says it is drawing on its experience to explore how AI can understand people and interact naturally in the physical world through Ludo Robotics.[2] Ludo’s stated goal is for robots to coordinate actions in real time in response to human activity in a shared workspace.[1] The evidence presents that as a goal, not as a demonstrated deployment or guarantee. Ludi 0.2 is described as a step toward robots that understand intent, respond to feedback and adapt as situations change.[3]