ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913131758878720 |
|---|---|
| author | Wang, Haosen Li, Zhenyang Zhang, Yinqiang He, Zongqi Jiang, Lutao Li, Kai Zhao, Yizhou Fan, Liaoyuan Hou, Wenjian Liang, Tingbang Wen, Yibin Gu, Defeng |
| author_facet | Wang, Haosen Li, Zhenyang Zhang, Yinqiang He, Zongqi Jiang, Lutao Li, Kai Zhao, Yizhou Fan, Liaoyuan Hou, Wenjian Liang, Tingbang Wen, Yibin Gu, Defeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09869 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control Wang, Haosen Li, Zhenyang Zhang, Yinqiang He, Zongqi Jiang, Lutao Li, Kai Zhao, Yizhou Fan, Liaoyuan Hou, Wenjian Liang, Tingbang Wen, Yibin Gu, Defeng Robotics Computer Vision and Pattern Recognition 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. |
| title | ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.09869 |