DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation
Classification
View four quadrants- Major category
- WAMs
- Quadrant
- Outside quadrants
- Architecture
- Pending verification
- Prediction paradigm
- Other mechanisms
- Subcategories
- Latent prediction & JEPA3D multiview modeling
- Source review status
- Not assigned
Category review. Cross-view latent dynamics predict candidate-action consequences; CEM searches and executes robot controls against paired image goals. Its use of frozen DINO features does not make the complete planning method a visual encoder component. The described action mechanism is external planning, model-assisted policy optimization, geometric tracking, or video-conditioned control; the source does not establish joint future/action generation or an IDM action decoder. Reading evidence
Contribution
DUET-DINO couples side- and wrist-camera latent predictors through cross-attention, then searches seven-dimensional robot actions against paired goal images. Its clearest evidence is improved simulated spatial and orientation planning; hardware success remains limited under a smaller planning budget and safety terminations (e-architecture, e-planning, e-angled, e-hardware).
Abstract
An abstract has not been added yet.
Affiliations
Artificial Intelligence and Robotics Lab, University of Technology Nuremberg (UTN), Germany; Learning Systems and Robotics Lab, Technical University of Munich (TUM), Germany; Intuitive Robots Lab, Karlsruhe Institute of Technology (KIT), Germany; NVIDIA; Robotics Institute Germany