Skip to content

论文arXiv 2611.07417今天

MessyNav:VLM驱动零样本交互式导航,真机成功率提升27pp ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:MessyNav: Zero-Shot Navigation via Manipulation in Messy Environments(arXiv 2611.07417)

核心内容 ​

针对真实场景中路径被椅子、玩具等日常物品阻塞的问题,arXiv论文提出MessyNav零样本交互式导航框架。该方法摒弃了传统依赖大规模仿真学习或逐场景指令的模式,旨在解决机器人在新物体、多样化环境及不同上下文(如区分易碎品与空推车)下的泛化难题。在移动操作机器人的室内外真机测试中,MessyNav在无任务特定训练的前提下,导航成功率比最强基线提高27个百分点,并在大规模离线评估中取得统计学显著增益。

技术上,MessyNav将问题形式化为开放世界交互式导航,核心在于任务规划前引入基于视觉语言模型(VLM)的显式Affordance推理机制。系统通过VLM分析当前视觉输入,判断对阻挡物体应执行拨开、拾取还是规避动作,进而生成高层级导航计划。这种“先推理后规划”的架构使机器人能理解物体物理属性与语义约束,实现了从感知到操作的端到端零样本决策,有效弥补了纯几何导航在非结构化环境中的能力短板。

关键看点 ​

  • 零样本泛化:无需任务特定训练或逐场景指令,仅凭VLM推理即可应对新物体与多变上下文,真机成功率提升27pp
  • 显式Affordance推理:在规划前通过VLM分析物体可操作性,动态决策拨开、拾取或规避,解决语义与物理交互对齐难题
  • 开放世界导航范式:将杂乱环境通行定义为交互式导航问题,摆脱对大规模仿真数据的依赖,支持室内外非结构化场景
  • 移动操作验证:在真实移动操作平台上完成室内外测试,证明语义驱动的交互策略优于传统几何避障与仿真学习方法

工程与产业观察 ​

该工作证实VLM可作为具身导航的“常识推理引擎”,通过显式Affordance分析替代隐式策略学习,大幅降低非结构化环境部署门槛。对于移动操作机器人研发,这提示应将语义理解前置为规划模块的核心组件,而非仅作为后置识别器,是实现Open-World具身智能的关键技术路径。

英文摘要 (Abstract) ​

Real-world environments are messy, with paths often blocked by everyday objects like chairs and toys, requiring robots to perform interactive navigation by manipulating obstacles to clear a path. Existing methods rely on extensive simulation-based learning or per-scene instructions specifying which objects to avoid or manipulate. They struggle to generalize across novel objects, diverse environments, and varied contexts such as a cart of fragile glassware that should be avoided while an empty one can be pushed. We formalize this problem as open-world interactive navigation and present MessyNav, a zero-shot framework based on vision-language models (VLMs). At its core, MessyNav performs explicit VLM-based affordance reasoning before task planning to decide whether to swipe, pick up, or avoid an object and produce a high-level plan. Evaluated on a mobile manipulator across real-world indoor and outdoor environments, MessyNav improves success rate by 27 percentage points (pp) over the strongest baseline in real-robot trials and achieves statistically significant gains in a larger-scale offline evaluation, without task-specific training.

作者:Kenneth Llontop, Cherie Ho, Dylan Zhou, Anuva Banwasi, Priya Sundaresan, Carlota Par'es-Morlans, Jeannette Bohg

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

来源

本页事实对应的公开页面,以原文为准。

  1. arXiv 2611.07417:MessyNav: Zero-Shot Navigation via Manipulation in Messy Environments访问 2026-11-06