REVIEW 5 cited by
Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Vision-and-language navigation (VLN) enables the agent to navigate to a remote location in 3D environments following the natural language instruction. In this field, the agent is usually trained and evaluated in the navigation simulators, lacking effective approaches for sim-to-real transfer. The VLN agents with only a monocular camera exhibit extremely limited performance, while the mainstream VLN models trained with panoramic observation, perform better but are difficult to deploy on most monocular robots. For this case, we propose a sim-to-real transfer approach to endow the monocular robots with panoramic traversability perception and panoramic semantic understanding, thus smoothly transferring the high-performance panoramic VLN models to the common monocular robots. In this work, the semantic traversable map is proposed to predict agent-centric navigable waypoints, and the novel view representations of these navigable waypoints are predicted through the 3D feature fields. These methods broaden the limited field of view of the monocular robots and significantly improve navigation performance in the real world. Our VLN system outperforms previous SOTA monocular VLN methods in R2R-CE and RxR-CE benchmarks within the simulation environments and is also validated in real-world environments, providing a practical and high-performance solution for real-world VLN.
Forward citations
Cited by 5 Pith papers
-
Joint On-and-Off Policy Learning for Vision-and-Language Navigation
JOP-VLN combines DAgger imitation learning with GRPO reinforcement learning, using high-entropy trajectory filtering and error-correction prioritization, achieving 69.9% SR on R2R Val-Unseen.
-
Structured Observation Language for Efficient and Generalizable Vision-Language Navigation
SOL-Nav encodes RGB-D observations as grid-organized text and uses a 0.6B text-embedding model with four classification heads to predict navigation action blocks, reporting SOTA/comparable R2R-CE/RxR-CE results with 1...
-
Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigation
The submitted abstract, the paper body, and the conclusion report incompatible headline results (73.2/75.6, 64.2/67.0, and 62.3/64.5 SR on R2R-CE/RxR-CE), so the claimed state of the art is not internally consistent.
-
StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling
A streaming navigation framework combining a sliding-window KV cache with depth-based token pruning achieves state-of-the-art results on VLN-CE benchmarks with bounded context and low latency.
-
MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation
Pyramidal multi-resolution visual memory plus single-token mid-level actions let a 4B–8B VLM navigate continuous indoor environments at 14 FPS with SOTA R2R/RxR success rates.
Discussion (0). Continue with ORCID to comment.