Event
Daxiao Robotics and NTU S-Lab Release World Model Mundo
2 reports · 2 sources
Daxiao Robotics, in collaboration with Nanyang Technological University's S-Lab, released Mundo, an interactive world model built for specific environments that integrates 3D scene reconstruction, physics simulation, and video generation. The system uses scene code to record object weight, center of mass, and friction coefficients; a 960Hz MuJoCo physics engine computes object motion and collisions under gravity and contact constraints, and the imagery is then rendered in combination with on-site photographs. According to the team, users can capture 1 to 12 photos with a mobile phone to reconstruct a 3D space that can be pushed, pulled, and collided with; the model can also support long-path generation ranging from tens of seconds to the minute level via dozens of context images, and can be used for training-data generation and policy testing for tasks such as navigation and grasping and placement. The team says it has brought Mundo into a real commercial hotel for actual testing, reconstructing a floor and a laundry area, and says the technology system has entered commercial scenarios and will soon be deployed in leading domestic hotel chains.
Report timeline
- Daxiao Robotics and NTU S-Lab Release Interactive World Model Mundo
Daxiao Robotics, in collaboration with Nanyang Technological University's S-Lab, has released Mundo, an interactive world model built for specific environments that integrates 3D scene reconstruction, physics simulation, and video generation. The system uses scene code to record object weight, center of mass, and friction coefficients, computes motion and collisions with a 960Hz MuJoCo physics engine, and then renders visuals combined with on-site photos; inputting 1 to 12 phone photos is enough to reconstruct a 3D space that supports pushing, pulling, and collisions.
新智元 · 微信公众号 ·
- Daxiao Robotics and NTU Release Mundo World Model
Daxiao Robotics, in collaboration with Nanyang Technological University's S-Lab, has released Mundo, a world model that reconstructs 1 to 12 real-scene images into an explorable, physically interactive 3D simulation environment. The model has built-in physical properties, with MuJoCo computing object motion under gravity and contact constraints, and it supports training-data generation and policy testing for tasks such as navigation and pick-and-place. The team has reconstructed a hotel floor and laundry area for training service robots on navigation and interaction tasks.
未来机器人网 · 微信公众号 ·