智能体
arxiv.org ·
HarnessVLN：通过智能体框架统一免训练具身导航
该论文提出 HarnessVLN，一个零样本、免训练的具身导航框架。其 Agent Harness 通过统一工具接口协调感知、检索、定位、导航、恢复和终止，并依据空间证据、几何可行性和子目标一致性校验规划器提案，将结构化工具反馈纳入后续决策。分层事件记忆跟踪任务进度与执行历史，持久时空图保存可复用的空间证据和失败标注以支持验证与恢复；可替换的 Navigation Executor 将校验后的目标转为可执行动作，使同一协议同时支持指令跟随和物体目标导航。论文报告在 R2R、RxR、HM3D-v2 和 HM3D-OVON 上成功率分别为 60.8%、53.9%、76.0% 和 59.3%，称超过此前免训练 SOTA，并展示人形机器人真实环境部署。
AI推荐理由 arXiv 新提交的机器人学论文，提出零样本、免训练的具身导航框架 HarnessVLN，通过统一工具接口协调感知、检索、定位、导航、恢复与终止，并用分层事件记忆和持久时空图校验规划器提案。摘要给出 R2R 60.8%、RxR 53.9%、HM3D-v2 76.0%、HM3D-OVON 59.3% 的成功率，称超过此前免训练 SOTA，并提及人形机器人真实环境部署。信息密度高、方法描述具体，但结果均为作者自报，尚无第三方复现或代码验证，人形部署细节未展开。
78
正文
Computer Science > Robotics
arXiv:2609.15195 (cs)
[Submitted on 14 Sep 2026]
Title:HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
Authors:Yang Chen, Lirong Che, Zhenyu Huang, Wenbo Fu, Chuang Wang, Xu Cao, Daqi Liu, Yuzhe Yang, Jian Su, Lan-Zhe Guo
View a PDF of the paper titled HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness, by Yang Chen and 9 other authors
View PDF
HTML (experimental)
Abstract:Embodied navigation requires agents to interpret visual observations, accumulate spatial knowledge, and execute actions to follow instructions or locate objects. Training-based methods face generalization challenges, while training-free methods exploit multimodal large language models (MLLMs) but often lack mechanisms to reconcile proposed actions with spatial evidence, task progress, and execution failures. 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. The Harness validates planner proposals against spatial evidence, geometric feasibility, and subgoal consistency, incorporating structured tool feedback into subsequent decisions. Hierarchical event memory tracks task progress and execution history, while a persistent Spatiotemporal Graph maintains reusable spatial evidence and failure annotations for verification and recovery. A replaceable Navigation Executor converts validated targets into executable motions, allowing the same Harness protocol to support instruction-following and object-goal navigation. HarnessVLN achieves success rates of 60.8%, 53.9%, 76.0%, and 59.3% on R2R, RxR, HM3D-v2, and HM3D-OVON, respectively, surpassing prior training-free SOTA results. Humanoid deployment further demonstrates its applicability to both tasks in real-world environments. The project page is: this https URL.
Subjects:
Robotics (cs.RO)
Cite as:
arXiv:2609.15195 [cs.RO]
(or
arXiv:2609.15195v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.15195
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yang Chen [view email]
[v1]
Mon, 14 Sep 2026 08:15:56 UTC (5,975 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness, by Yang Chen and 9 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)