# GG-Nav：面向目标的 Grounding Chain-of-Thought 激发导航基础模型推理

> 原文链接：https://robotics.hellobike.com/papers/2026-10-10-2610-14541
> 频道：papers | 更新日期：2026-10-10 | 标签：arxiv, cs.RO
> 核心摘要：针对目标导向导航表现不足，GG-Nav以监督微调学习结构化CoT，并在多个基准和真机上验证。

# GG-Nav：面向目标的 Grounding Chain-of-Thought 激发导航基础模型推理

::: v-pre
> 原文链接：[GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models](https://arxiv.org/abs/2610.14541)（arXiv 2610.14541 · 发布日期：2026-10-10）

**GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models**

针对目标导向导航表现不足，GG-Nav以监督微调学习结构化CoT，并在多个基准和真机上验证。

## 核心要点

- 动机研究指出，现有导航基础模型对流式观测利用不足，且目标定位不够精确。
- GG-Nav通过结构化CoT显式定位目标相关实例、累积grounding证据并支持决策。
- 方法包含Observation-to-Evidence与Evidence-to-Decision两阶段，利用中间帧证据生成动作或澄清问题。
- 实验显示其在HM3D ObjectNav、VL-LN和CoIN成功率优于现有方法，并在Unitree Go2上展示零样本泛化。

**验证范围与局限**：验证范围包括HM3D ObjectNav、VL-LN、CoIN基准，以及一台Unitree Go2机器人在未见真实环境中的部署。

## 英文摘要 (Abstract)

Emerging strong Vision-Language Models (VLMs) have advanced navigation foundation models. However, these models still have unsatisfactory performance on goal-oriented navigation settings. In this paper, we first conduct a motivating study revealing that the key issue lies in the insufficient utilization of streaming observations and imprecise target localization. To tackle these challenges, we propose GG-Nav, a simple yet effective navigation framework that learns a structured chain-of-thought (CoT) mechanism via supervised fine-tuning to explicitly localize goal-relevant instances, accumulate grounding evidence, and support more reliable decision-making. Specifically, the structured CoT is designed with two key stages: (i) Observation-to-Evidence, which reasons over all intermediate frames between adjacent decision steps to retain useful goal-related evidence; and (ii) Evidence-to-Decision, which integrates the current observation with accumulated evidence to ground the target and support the generation of navigation actions or clarification questions. Extensive experiments show that GG-Nav outperforms the state-of-the-art methods in terms of success rates on the HM3D ObjectNav, VL-LN, and CoIN benchmarks by 3.1%, 16.6%, and 5.3%, respectively. Ablation studies further show that accumulating evidence from intermediate observations reduces evidence-missing failures by 11.6%, while explicit grounding reduces stopping errors by 49.4%. We also deploy GG-Nav on a Unitree Go2 robot, demonstrating its zero-shot generalization capability in unseen real-world environments.

作者：Shaohao Zhu, Wensi Huang, Siqi Zhang, Yuqiang Yang, Meng Wei, Chenyang Wan, Tianle Liu, Tai Wang, Jinming Xu
:::

## 原始参考来源 (Sources)

- [arXiv 2610.14541：GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models](https://arxiv.org/abs/2610.14541)