DeCoNav achieves a 69.2% improvement in both-success rate on 1,213 tasks across 176 scenes by coupling event-triggered dialogue with dynamic task allocation and replanning in a decentralized multi-robot VLN setup.
Topv-nav: Unlocking the top-view spatial reasoning potential of mllm for zero-shot object navigation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DeCoNav: Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation
DeCoNav achieves a 69.2% improvement in both-success rate on 1,213 tasks across 176 scenes by coupling event-triggered dialogue with dynamic task allocation and replanning in a decentralized multi-robot VLN setup.