<ul><li>Researchers have introduced a Navigation World Model (NWM), a controllable video generation model for predicting future visual observations based on past observations and navigation actions.</li><li>NWM employs a Conditional Diffusion Transformer (CDiT) with 1 billion parameters, trained on a diverse collection of egocentric videos of human and robotic agents.</li><li>In familiar environments, NWM can plan navigation trajectories by simulating and evaluating them for achieving the desired goal, incorporating constraints dynamically during planning.</li><li>NWM can also imagine trajectories in unfamiliar environments using learned visual priors from a single input image, making it a versatile tool for next-generation navigation systems.</li></ul>

Navigation World Models

Discover more