综述物理仿真在具身智能导航与操作中的应用与选型指南
A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI
- 分析仿真器如何缩小真实世界与虚拟环境的差距
- 对比不同仿真平台在导航与操作任务中的表现
- 提供工具选型资源，兼顾性能与硬件限制
导航与操作是具身智能的核心能力，但在真实世界中直接训练成本高、耗时长且存在安全隐患。因此，仿真到真实世界的迁移成为关键方法，但仿真与现实之间的差距依然存在。本文综述了物理仿真器如何通过分析此前研究较少关注的特性来缩小这一差距，同时评估其在导航与操作任务中的功能表现及硬件需求。此外，本文还提供了一个包含基准数据集、评估指标、仿真平台与方法的资源集合，帮助研究人员在考虑硬件约束的前提下选择合适的工具。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。