# Vision-and-Language Navigation

MemoryVLN compresses long-horizon vision-language navigation history into pose-grounded spatial memories and reuses them across episodes within the same environment, raising success rate by about 2% on R2R-CE and 6.5% on RxR-CE.

MemoryVLN compresses long-horizon vision-language navigation history into pose-grounded spatial memories and reuses them across episodes within the same environment, raising success rate by about 2% on R2R-CE and 6.5% on RxR-CE.

Vision-language navigation agents previously matched a whole instruction against candidate trajectories, so already executed content kept interfering with later decisions. VLN-AIEP couples instruction-execution progress estimation with navigation decision-making: it uses the visited trajectory to suppress embeddings of executed content, then matches candidate locations only against pending content, so progress can be learned directly from navigation decision labels without explicit progress annotations. Across R2R, RxR, CVDN and R2R-CE, the method reaches competitive results on multiple metrics, including 77% success on R2R val-unseen, 3 points above PRET.

Vision-language navigation agents previously matched a whole instruction against candidate trajectories, so already executed content kept interfering with later decisions. VLN-AIEP couples instruction-execution progress estimation with navigation decision-making: it uses the visited trajectory to suppress embeddings of executed content, then matches candidate locations only against pending content, so progress can be learned directly from navigation decision labels without explicit progress annotations. Across R2R, RxR, CVDN and R2R-CE, the method reaches competitive results on multiple metrics, including 77% success on R2R val-unseen, 3 points above PRET.

NavGPT-3 connects a language-model Planner and the 8B navigation policy NavGPT VLA through a harness with an OS-like runtime: reasoning, execution, and monitoring run as threads with their own context, tools, and permissions, and the runtime assigns motion authority by event priority so the robot can be interrupted and switched between threads; the complete system reaches 81.51 SR on R2R-CE and matches human followers on RxR-CE at 90.43 SR and 78.47 nDTW, lowering the system's minimum reaction time from 3–19 s per language-model decision to 0.5–1 s per action-policy step.

NavGPT-3 connects a language-model Planner and the 8B navigation policy NavGPT VLA through a harness with an OS-like runtime: reasoning, execution, and monitoring run as threads with their own context, tools, and permissions, and the runtime assigns motion authority by event priority so the robot can be interrupted and switched between threads; the complete system reaches 81.51 SR on R2R-CE and matches human followers on RxR-CE at 90.43 SR and 78.47 nDTW, lowering the system's minimum reaction time from 3–19 s per language-model decision to 0.5–1 s per action-policy step.

The work proposes GeoScaffold, a geometric supervision framework that first learns a compact depth tokenizer on depth maps from training trajectories and freezes it, then fine-tunes the policy with a handful of learnable geometry query tokens whose hidden states reconstruct navigation-critical geometry such as depth, connectivity, and traversability, thereby internalizing geometry into the policy itself; after training the tokenizer, target generators, and reconstruction heads are discarded, leaving the backbone and action interface unchanged, and experiments show it consistently outperforms leading vision-only navigators on continuous VLN benchmarks, offering a practical paradigm for lightweight edge deployment of spatially aware embodied navigation models.

The work proposes GeoScaffold, a geometric supervision framework that first learns a compact depth tokenizer on depth maps from training trajectories and freezes it, then fine-tunes the policy with a handful of learnable geometry query tokens whose hidden states reconstruct navigation-critical geometry such as depth, connectivity, and traversability, thereby internalizing geometry into the policy itself; after training the tokenizer, target generators, and reconstruction heads are discarded, leaving the backbone and action interface unchanged, and experiments show it consistently outperforms leading vision-only navigators on continuous VLN benchmarks, offering a practical paradigm for lightweight edge deployment of spatially aware embodied navigation models.

This work introduces AdaGeoVLN, a streaming vision-language navigation framework that couples VGGT geometry-foundation-model representations at depths 11, 17, and 23 to the first three Qwen3.5-4B decoder layers and retains historical VGGT global-attention KV states under a fixed budget according to instruction relevance, geometric confidence, and transition novelty, achieving 55.7%/51.4% and 54.1%/44.7% SR/SPL on R2R-CE and RxR-CE Val-Unseen with a single RGB stream and no additional navigation-specific external data, with ablations showing that multi-depth coupling substantially outperforms repeated terminal-feature injection at matched fusion locations and that bounded navigation-aware retention preserves navigation performance while reducing GFM-KV memory.

This work introduces AdaGeoVLN, a streaming vision-language navigation framework that couples VGGT geometry-foundation-model representations at depths 11, 17, and 23 to the first three Qwen3.5-4B decoder layers and retains historical VGGT global-attention KV states under a fixed budget according to instruction relevance, geometric confidence, and transition novelty, achieving 55.7%/51.4% and 54.1%/44.7% SR/SPL on R2R-CE and RxR-CE Val-Unseen with a single RGB stream and no additional navigation-specific external data, with ablations showing that multi-depth coupling substantially outperforms repeated terminal-feature injection at matched fusion locations and that bounded navigation-aware retention preserves navigation performance while reducing GFM-KV memory.