Pith. sign in

REVIEW 18 cited by

InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment

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

arxiv 2406.04882 v1 pith:372IEFS5 submitted 2024-06-07 cs.RO cs.AIcs.CLcs.CV

classification cs.ROcs.AIcs.CLcs.CV
keywords navigationinstructioninstructnavdifferentgoalzero-shotdcondiverse
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Enabling robots to navigate following diverse language instructions in unexplored environments is an attractive goal for human-robot interaction. However, this goal is challenging because different navigation tasks require different strategies. The scarcity of instruction navigation data hinders training an instruction navigation model with varied strategies. Therefore, previous methods are all constrained to one specific type of navigation instruction. In this work, we propose InstructNav, a generic instruction navigation system. InstructNav makes the first endeavor to handle various instruction navigation tasks without any navigation training or pre-built maps. To reach this goal, we introduce Dynamic Chain-of-Navigation (DCoN) to unify the planning process for different types of navigation instructions. Furthermore, we propose Multi-sourced Value Maps to model key elements in instruction navigation so that linguistic DCoN planning can be converted into robot actionable trajectories. With InstructNav, we complete the R2R-CE task in a zero-shot way for the first time and outperform many task-training methods. Besides, InstructNav also surpasses the previous SOTA method by 10.48% on the zero-shot Habitat ObjNav and by 86.34% on demand-driven navigation DDN. Real robot experiments on diverse indoor scenes further demonstrate our method's robustness in coping with the environment and instruction variations.

Discussion (0). Sign in to comment.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. BioVLN: A Simulation Platform for Visual Language Navigation in Biomedical Laboratories

    cs.RO 2026-07 conditional novelty 6.0 of 10

    BioVLN introduces a three-zone operational envelope for biomedical lab navigation, with 47 scenes and benchmarks showing multi-point operation-area goals raise success to 83–92% while cutting unsafe proximity.

  2. Joint On-and-Off Policy Learning for Vision-and-Language Navigation

    cs.RO 2026-07 conditional novelty 6.0 of 10

    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.

  3. ABot-N1: Toward a General Visual Language Navigation Foundation Model

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    A slow–fast VLN model that routes five navigation tasks through CoT plus image-space pixel goals reaches SOTA on established and new urban benchmarks, including 77.3% POI arrival.

  4. DRIVE-Nav: Directional Reasoning, Inspection, and Verification for Efficient Open-Vocabulary Navigation

    cs.RO 2026-03 conditional novelty 6.0 of 10

    Organizing zero-shot object navigation around tracked directional exits with 240° inspection and VLM verification yields 50.2% SR / 32.6% SPL on HM3D-OVON and best SPL on HM3Dv2 and MP3D.

  5. Structured Observation Language for Efficient and Generalizable Vision-Language Navigation

    cs.CV 2026-03 reject novelty 6.0 of 10

    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...

  6. HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System

    cs.CV 2026-03 conditional novelty 6.0 of 10

    A hierarchical memory system—visual graph memory for re-visit detection plus a global instruction tracker—raises open-source zero-shot VLN success rate to 30% from 14% on R2R-CE.

  7. Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigation

    cs.CV 2025-12 reject novelty 6.0 of 10

    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.

  8. PIGEON: VLM-Driven Object Navigation via Points of Interest Selection

    cs.RO 2025-11 conditional novelty 6.0 of 10

    PIGEON selects sparse Points of Interest for VLM-driven object navigation, achieving state-of-the-art zero-shot ObjectNav results in Habitat and improving a local 7B VLM via distance-based RLVR.

  9. MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning

    cs.RO 2025-10 conditional novelty 6.0 of 10

    A four-camera VLA navigation model trained by distilling multiple RL experts achieves strong simulation performance and qualitative real-world transfer.

  10. DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigation

    cs.RO 2025-09 conditional novelty 6.0 of 10

    DreamNav achieves new zero-shot SOTA on VLN-CE with an egocentric-only pipeline that generates candidate trajectories, imagines their futures, and selects the best by language alignment.

  11. CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model

    cs.RO 2025-08 unverdicted novelty 6.0 of 10

    By iteratively retraining on automatically generated corrective examples derived from its own wrong paths, CorrectNav reports new state-of-the-art success rates of 65.1% (R2R-CE) and 69.3% (RxR-CE).

  12. Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation

    cs.RO 2025-08 conditional novelty 6.0 of 10

    SGImagineNav uses an imagined hierarchical scene graph, filled in by an LLM, that guides a robot to unseen objects and achieves 65.4% and 66.8% success on HM3D and HSSD.

  13. StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

    cs.RO 2025-07 conditional novelty 6.0 of 10

    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.

  14. CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A first benchmark that tests whether robots can read multi-page appliance manuals and then plan and execute manipulation tasks on appliances in simulation.

  15. MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation

    cs.CV 2026-07 conditional novelty 5.0 of 10

    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.

  16. HRO: Hierarchical Room-to-Object Framework for Zero-Shot Object Goal Navigation with Large Language Models

    cs.RO 2026-07 conditional novelty 5.0 of 10

    Hierarchical LLM room-type inference plus object-room affinity scoring yields 84.0% Gibson and 53.0% HM3D success for zero-shot object-goal navigation.

  17. CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process Thinking

    cs.AI 2025-07 conditional novelty 5.0 of 10

    CogDDN uses a fast heuristic VLM paired with a slow analytic reflection process and a growing knowledge base to navigate to objects that implicitly satisfy a user's demand, with large reported gains on AI2Thor DDN benchmarks.

  18. Nav-R1: Reasoning and Navigation in Embodied Scenes

    cs.RO 2025-09 reject novelty 4.0 of 10

    Nav-R1 uses a 110K synthetic CoT dataset, GRPO with three rewards, and a fast-in-slow system to set new SOTA on R2R-CE, RxR-CE, and HM3D-OVON.

Pith tools