ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control

• URL: http://arxiv.org/abs/2605.09869v2
• Date: Fri, 15 May 2026 04:14:32 GMT
• Title: ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control
• Abstract summary: ConsistNav is a training-free zero-shot ObjectNav framework built around a semantic executive composed of three coordinated modules.<n>We conduct experiments on HM3D and MP3D, where ConsistNav achieves results and improves SR by 11.4% and SPL by 7.9% over the controlled baseline on MP3D.
• Score: 20.155796585668607
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Zero-shot object navigation has advanced rapidly with open-vocabulary detectors, image--text models, and language-guided exploration. However, even after current methods detect a plausible target hypothesis, the agent may still oscillate between exploration and pursuit, or abandon the object near success. We identify this failure mode as an action consistency gap: semantic evidence is repeatedly reinterpreted at each step without persistent commitment across the episode. We introduce ConsistNav, a training-free zero-shot ObjectNav framework built around a semantic executive composed of three coordinated modules: Finite-State Executive Controller stages target pursuit through guarded semantic phases; Persistent Candidate Memory accumulates cross-frame target evidence into stable object hypotheses; and Stability-Aware Action Control suppresses rotational stagnation, ineffective pursuit, and unverified stopping. This design changes neither the detector nor the low-level planner; instead, it controls when semantic evidence should influence navigation and when it should be suppressed or revisited. We conduct extensive experiments on HM3D and MP3D, where ConsistNav achieves state-of-the-art results among compared zero-shot ObjectNav methods and improves SR by 11.4% and SPL by 7.9% over the controlled baseline on MP3D. Ablation studies and real-world deployment experiments further demonstrate the effectiveness and robustness of the proposed executive mechanism.

Related papers

• HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness [30.61739879302674]
  Embodied navigation requires agents to interpret visual observations, accumulate spatial knowledge, and execute actions to follow instructions or locate objects.<n>We present HarnessVLN, a zero-shot, training-free framework whose Agent Harness coordinates perception, retrieval, grounding, navigation, recovery, and termination through a unified tool interface.
  arXiv  Detail & Related papers  (2026-09-14T08:15:56Z)
• AECNav: Active Evidence Consolidation for Efficient Zero-Shot Open-Vocabulary Object Navigation [10.327375579404402]
  Zero-shot object-goal navigation (ZSON) in open-vocabulary scenarios is challenging.<n>Currently, the task still suffers from high latency and limited accuracy due to redundant perception pipelines.<n>We present AECNav, a training-free pipeline built on three components.
  arXiv  Detail & Related papers  (2026-08-11T11:40:05Z)
• Untangling Co-Drift: Proactive Multi-Intent Failure Prediction and Root-Cause Disambiguation for Self-Driving Networks [0.0]
  We introduce MILD, a framework that reformulates intent assurance from reactive drift detection to proactive failure prediction.<n> MILD achieves high failure detection rates and strong reliance on root-cause detection.<n>This MILD enabler is a practical enabler of closedloop assurance in next-generation autonomous networks.
  arXiv  Detail & Related papers  (2026-07-28T17:06:24Z)
• Rethinking Embodied Navigation via Relational Inductive Bias [53.72276435022479]
  We propose DB-Nav, a framework that reshapes the search space via dual relational biases.<n>It factorizes target-centric relations into an Activation Bias and an Inhibition Bias.<n>It significantly outperforms existing methods in success rate (SR) and Success weighted by Path Length (SPL)
  arXiv  Detail & Related papers  (2026-06-09T02:57:34Z)
• ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop [55.468404995694975]
  We develop a benchmark for embodied spatial intelligence spanning 10 task categories and 29 subcategories built on OmniGibson.<n>We conduct experiments on state-of-the-art MLLMs and find that active exploration substantially outperforms passive counterparts.<n>Unlike humans who seek falsifying viewpoints and revise beliefs under contradiction, models commit prematurely with high confidence regardless of evidence quality.
  arXiv  Detail & Related papers  (2026-05-18T17:59:02Z)
• ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation [35.416693138335354]
  Zero-shot object navigation requires agents to locate unseen target objects in unfamiliar environments.<n>Recent advancements in vision-language models provide promising commonsense reasoning capabilities for this task.<n>We propose a novel hierarchical navigation framework named ReMemNav, which seamlessly integrates panoramic semantic priors and episodic memory.
  arXiv  Detail & Related papers  (2026-03-25T09:07:32Z)
• Your Vision-Language-Action Model Already Has Attention Heads For Path Deviation Detection [14.088116748512428]
  Vision-Language-Action (VLA) models have demonstrated strong potential for predicting semantic actions in navigation tasks.<n>They are fundamentally hindered by visual-reasoning hallucinations that lead to trajectory deviations.<n>We show that monitoring a few attention heads within a frozen VLA model can accurately detect path deviations without incurring additional computational overhead.
  arXiv  Detail & Related papers  (2026-03-14T06:26:11Z)
• DSCD-Nav: Dual-Stance Cooperative Debate for Object Navigation [63.439158093945956]
  We propose Dual-Stance Cooperative Debate Navigation (DSCD-Nav) to replace one-shot scoring with stance-based cross-checking and evidence-aware arbitration.<n> Experiments on HM3Dv1, HM3Dv2, and MP3D demonstrate consistent improvements in success and path efficiency while reducing exploration redundancy.
  arXiv  Detail & Related papers  (2026-01-29T08:47:55Z)
• BiTAA: A Bi-Task Adversarial Attack for Object Detection and Depth Estimation via 3D Gaussian Splatting [14.918777539580978]
  We present BiTAA, a bi-task adversarial attack built on 3D Gaussian Splatting.<n>Specifically, we introduce a dual-model attack framework that supports both full-image and patch settings.<n>We also propose a unified evaluation protocol with cross-task transfer metrics and real-world evaluations.
  arXiv  Detail & Related papers  (2025-09-24T06:27:15Z)
• HUNT: High-Speed UAV Navigation and Tracking in Unstructured Environments via Instantaneous Relative Frames [50.83645076723809]
  HUNT (High-speed UAV Navigation and Tracking) is a real-time framework that unifies, acquisition, and tracking within a single relative formulation.<n>Trials in dense forests, container compounds, and search-and-rescue operations with vehicles and mannequins demonstrate robust autonomy where global methods fail.
  arXiv  Detail & Related papers  (2025-09-23T18:07:10Z)
• Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration [58.4036440289082]
  Hand-object motion-capture (MoCap) offer large-scale, contact-rich demonstrations and hold promise for dexterous robotic scopes.<n>We introduce Dexplore, a unified single-loop optimization that performs repositories and tracking to learn robot control policies directly from MoCap at scale.
  arXiv  Detail & Related papers  (2025-09-11T17:59:07Z)
• DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation [55.888688171010365]
  DORAEMON is a cognitive-inspired framework consisting of Ventral and Dorsal Streams that mimics human navigation capabilities.<n>We evaluate DORAEMON on the HM3D, MP3D and GOAT datasets, where it achieves state-of-the-art performance on both success rate (SR) and success weighted by path length (SPL) metrics.
  arXiv  Detail & Related papers  (2025-05-28T04:46:13Z)
• Seamless Detection: Unifying Salient Object Detection and Camouflaged Object Detection [73.85890512959861]
  We propose a task-agnostic framework to unify Salient Object Detection (SOD) and Camouflaged Object Detection (COD)<n>We design a simple yet effective contextual decoder involving the interval-layer and global context, which achieves an inference speed of 67 fps.<n> Experiments on public SOD and COD datasets demonstrate the superiority of our proposed framework in both supervised and unsupervised settings.
  arXiv  Detail & Related papers  (2024-12-22T03:25:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.