CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
Vision-Language Navigation has increasingly emphasized high-level instruction reasoning, memory, global map construction, and instruction decomposition, while the low-level action representation remains comparatively underexplored. We propose CoFL-S, a low-level vision-language-action framework that predicts a language-conditioned flow field over the robot's local visible sector and generates continuous trajectories by rolling out the predicted field. To train this low-level representation, we convert each VLN-CE episode, originally a whole-episode instruction paired with an action sequence, i
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorHaokun Liu →
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
- Linked via arxiv authorZhaoqi Ma →
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
- Linked via arxiv authorYicheng Chen →
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
- Linked via arxiv authorWentao Zhang →
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
- Linked via arxiv authorMasaki Kitagawa →
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
- Linked via arxiv authorZicen Xiong →
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
- Linked via arxiv authorJinjie Li →
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
- Linked via arxiv authorMoju Zhao →
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation