# LMGN统一策略模型解决四足机器人末端抓取导航难题

> 原文链接：https://robotics.hellobike.com/papers/2026-11-06-2611-07515-4f771571
> 频道：papers | 更新日期：2026-11-06 | 标签：auto, arxiv
> 核心摘要：针对四足机器人末端抓取导航割裂痛点，提出LMGN统一策略学习模型。通过ED-DR可达性表征与语义对齐HMoE分层专家策略，联合优化导航与操作，在Habitat及Isaac Gym仿真中显著提升目标抓取成功率。

# LMGN统一策略模型解决四足机器人末端抓取导航难题

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[LMGN: A Unified Policy Learning Model for Last-Mile Grasp-Navigation](https://arxiv.org/abs/2611.07515)（arXiv 2611.07515）

## 核心内容

针对带臂四足机器人在复杂环境中“最后一公里”抓取导航难题，研究提出Last-Mile Grasp-Navigation（LMGN）统一策略学习模型。该方法旨在解决现有方案将全局导航与操作独立处理、忽视基座放置与抓取执行联合决策的缺陷。实验表明，在Habitat和Isaac Gym仿真器中，LMGN性能持续优于当前最先进方法，验证了融合抓取感知可达性与阶段感知策略学习对提升末端导航及抓取成功率的有效性。

技术上引入显式距离与方向可达性（ED-DR）表征，量化描述兼容抓取的基座位置与接近方向特征。构建语义对齐的分层混合专家（HMoE）策略，针对基座调整、预抓取对齐、抓取执行及物体提升四个阶段建模差异化行为。提出联合优化方法，同步对齐导航操作目标、阶段依赖的专家路由及动作级一致性，确保HMoE策略在多阶段任务中的稳定输出与精准控制。

## 关键看点

- **ED-DR表征**：引入显式距离与方向可达性表示，精确量化兼容抓取的基座放置位置与接近方向特征
- **HMoE策略架构**：采用语义对齐分层混合专家模型，针对基座调整、预抓取对齐、抓取执行及提升四阶段建模
- **联合优化机制**：提出新优化方法同步对齐导航操作、阶段依赖专家路由及动作一致性，解决多阶段控制割裂
- **仿真验证优越性**：在Habitat与Isaac Gym测试中持续超越SOTA，证实抓取感知与阶段感知融合提升抓取率

## 工程与产业观察

该工作为四足移动操作提供了从“全局规划”向“末端精细作业”跨越的算法范式。ED-DR表征与HMoE架构有效解决了非结构化环境下基座-机械臂耦合控制难题，对具身智能在非工厂场景下的灵巧操作落地具有直接参考价值，也为Sim-to-Real迁移提供了高质量策略先验。

## 英文摘要 (Abstract)

Legged robots equipped with manipulators have shown significant potential in the fields of daily life and industry in complex environments. However, existing methods mainly focus on global navigation or manipulation independently, while overlooking the last-mile navigation problem, where the robot must jointly determine the base placement, approach direction, and grasp execution to achieve reliable object grasping, and different manipulation stages require distinct control behaviors. To address these challenges, we propose Last-Mile Grasp-Navigation (LMGN), a unified policy learning model for Quadruped robot loco-manipulation. An Explicit Distance and Directional Reachability (ED-DR) representation is first introduced to explicitly represent the features of grasp-compatible base placement and approach direction. We then develop a semantically aligned Hierarchical Mixture-of-Experts (HMoE) policy that models stage-aware behaviors across the stages of base adjustment, pre-grasp alignment and grasp execution, and object lift. Finally, a new optimization method that jointly aligns navigation and manipulation, stage-dependent expert routing, and action-level consistency is proposed to optimize the HMoE policy. Extensive experiments on the Habitat and Isaac Gym simulators demonstrate that LMGN consistently outperforms state-of-the-art methods, denoting that integrating grasp-aware reachability with stage-aware policy learning significantly improves the success rates of last-mile navigation and target grasp for robots.

作者：Xuenmin Hu, Qingxue Qian, Wei Luo, Benyi Ma, Bo Tang, Long Chen
:::

## 原始参考来源 (Sources)

- [arXiv 2611.07515：LMGN: A Unified Policy Learning Model for Last-Mile Grasp-Navigation](https://arxiv.org/abs/2611.07515)