# 具身智能时代基于物理仿真器的机器人导航与操作综述

> 原文链接：https://robotics.hellobike.com/papers/2026-10-03-2505-01458
> 频道：papers | 更新日期：2026-10-03 | 标签：arxiv, cs.RO
> 核心摘要：本文综述物理仿真器如何缓解机器人导航与操作的 Sim-to-Real 差距，并分析任务特性、硬件需求与相关资源。

# 具身智能时代基于物理仿真器的机器人导航与操作综述

::: v-pre
> 原文链接：[A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI](https://arxiv.org/abs/2505.01458)（arXiv 2505.01458 · 发布日期：2026-10-03）

**A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI**

本文综述物理仿真器如何缓解机器人导航与操作的 Sim-to-Real 差距，并分析任务特性、硬件需求与相关资源。

## 核心要点

- 现实中直接训练导航与操作智能体成本高、耗时且存在安全风险。
- 论文从既有综述较少关注的属性出发，分析物理仿真器如何应对差距。
- 比较仿真器在导航和操作任务中的功能特性，并讨论硬件需求。
- 整理基准数据集、指标、仿真平台和方法，辅助研究者按硬件约束选型。

## 英文摘要 (Abstract)

Navigation and manipulation are core capabilities in Embodied AI, but training agents to perform them directly in the real world is costly, time-consuming, and unsafe. Therefore, sim-to-real transfer has emerged as a key approach, yet the sim-to-real gap persists. This survey examines how physics simulators address this gap by analyzing properties that have received limited attention in prior surveys. We also analyze their features for navigation and manipulation tasks, as well as their hardware requirements. Additionally, we offer a resource with benchmark datasets, metrics, simulation platforms, and methods to help researchers select suitable tools while accounting for hardware constraints.

作者：Liang Wei Wong, Xueyang Kang, Kaixin Bai, Jianwei Zhang
:::

## 原始参考来源 (Sources)

- [arXiv 2505.01458：A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI](https://arxiv.org/abs/2505.01458)