arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05467cs.CVcs.CLcs.RO
收藏

MerNav:一种高度可泛化的记忆-执行-审查框架用于零样本物体目标导航

MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal Navigation

Amap, Alibaba Group(高德,阿里巴巴集团);Xi’an Jiaotong University(西安交通大学)

Dekang Qi, Shuang Zeng, Xinyuan Chang, Feng Xiong, Shichao Xie, Xiaolong Wu, Mu Xu

AI总结:

本文提出MerNav框架,通过记忆、执行和审查模块提升视觉语言导航任务中的成功率和泛化能力,在多个数据集上均取得显著提升。

摘要:

视觉语言导航(VLN)是具身智能的基本能力之一,也是亟需解决的关键挑战。然而,现有方法在成功率(SR)和泛化能力方面仍不尽如人意:监督微调(SFT)方法通常能获得更高的SR,而无训练(TF)方法往往泛化性更好,但难以同时取得。为此,我们提出了一种记忆-执行-审查框架。该框架包含三个部分:一个分层记忆模块用于提供信息支持,一个执行模块用于常规决策和行动,以及一个审查模块用于处理异常情况并纠正行为。我们验证了该框架在物体目标导航任务中的有效性。在四个数据集中,我们的平均SR在TF和零样本(ZS)设置下分别实现了7%和5%的绝对提升。在最常用的HM3D_v0.1和更具挑战性的开放词汇数据集HM3D_OVON上,SR在ZS设置下分别提升了8%和6%。此外,在MP3D和HM3D_OVON数据集中,我们的方法不仅优于所有TF方法,还超越了所有SFT方法,在SR(5%和2%)和泛化能力方面均取得全面领先地位。此外,我们还将在双足机器人上部署MerNav模型,并在现实世界中进行实验。项目地址为:https://qidekang.github.io/MerNav.github.io/

英文摘要:

Visual Language Navigation (VLN) is one of the fundamental capabilities for embodied intelligence and a critical challenge that urgently needs to be addressed. However, existing methods are still unsatisfactory in terms of both success rate (SR) and generalization: Supervised Fine-Tuning (SFT) approaches typically achieve higher SR, while Training-Free (TF) approaches often generalize better, but it is difficult to obtain both simultaneously. To this end, we propose a Memory-Execute-Review framework. It consists of three parts: a hierarchical memory module for providing information support, an execute module for routine decision-making and actions, and a review module for handling abnormal situations and correcting behavior. We validated the effectiveness of this framework on the Object Goal Navigation task. Across 4 datasets, our average SR achieved absolute improvements of 7% and 5% compared to all baseline methods under TF and Zero-Shot (ZS) settings, respectively. On the most commonly used HM3D_v0.1 and the more challenging open vocabulary dataset HM3D_OVON, the SR improved by 8% and 6%, under ZS settings. Furthermore, on the MP3D and HM3D_OVON datasets, our method not only outperformed all TF methods but also surpassed all SFT methods, achieving comprehensive leadership in both SR (5% and 2%) and generalization. Additionally, we deployed the MerNav model on the humanoid robot and conducted experiments in the real world. The project address is: https://qidekang.github.io/MerNav.github.io/

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑