Skip to main content
Search

# Language-Conditioned Visual Navigation

1 related articles

Subscribe to updates
  1. openbiox Bizard

    LCVN turns visual navigation into open-loop trajectory prediction: one first frame and one instruction, a whole route

    LCVN recasts language-conditioned visual navigation as open-loop trajectory prediction: an embodied agent receives only an initial egocentric observation and a natural-language instruction, with no goal image and no intermediate environmental feedback, and must generate the future navigation trajectory. The accompanying LCVN dataset holds 39,016 trajectories and 117,048 human-verified instructions in concise, intricate and landmark-grounded styles. Two complementary model families are released: a diffusion-based world model, LCVN-WM, paired with a latent-space actor-critic agent, LCVN-AC, trained on intrinsic rewards, and LCVN-Uni, an autoregressive multimodal architecture that predicts actions and future observations in a single forward pass.

You’re all caught up