T2-z: Test-Time Optimization of Environment Latents for Robotic World Models
[Robotyka] Autorzy: Chenyuan Zhou, Yining Hong, Huang Huang i 9 więcej
Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitly specified, from physical properties such as friction and mass to human-defined environmental rules. We introduce T2-Z for test-time optimization of environment latents, which augments a robotic world model with a learnable environment latent to condition world predictions. This compact latent captures underlying environmental variation without supervision of what environmental factors exist or what values they take. During training, T2-Z alternates between two stages: a world-model optimization stage that fixes the latents and learns general action-conditioned dynamics across environments; and an environment-latent optimization stage that freezes the world model and optimizes the conditioning latents, allowi…
- Kategoria arxiv
- cs.RO
- Kategoria
- Robotyka