With the emerging environment-aware applications, ubiquitous sensing is expected to play a key role in future networks. In this paper, we study a 3-dimensional (3D) multi-target localization system where multiple intelligent reflecting surfaces (IRSs) are applied to create virtual line-of-sight (LoS) links that bypass the base station (BS) and targets. To fully unveil the fundamental limit of IRS for sensing, we first study a single-target-single-IRS case and propose a novel \textit{two-stage localization protocol} by controlling the on/off state of IRS. To be specific, in the IRS-off stage, we derive the Cram\'{e}r-Rao bound (CRB) of the azimuth/elevation direction-of-arrival (DoA) of the BS-target link and design a DoA estimator based on the MUSIC algorithm. In the IRS-on stage, the CRB of the azimuth/elevation DoA of the IRS-target link is derived and a simple DoA estimator based on the on-grid IRS beam scanning method is proposed. Particularly, the impact of echo signals reflected by IRS from different paths on sensing performance is analyzed. Moreover, we prove that the single-beam of the IRS is not capable of sensing, but it can be achieved with \textit{multi-beam}. Based on the two obtained DoAs, the 3D single-target location is constructed. We then extend to the multi-target-multi-IRS case and propose an \textit{IRS-adaptive sensing protocol} by controlling the on/off state of multiple IRSs, and a multi-target localization algorithm is developed. Simulation results demonstrate the effectiveness of our scheme and show that sub-meter-level positioning accuracy can be achieved.

翻译：随着新兴的环境感知应用需求，泛在感知将在未来网络中发挥关键作用。本文研究了一种三维多目标定位系统，该系统利用多个智能反射面构建虚拟视距链路，以绕过基站与目标之间的直视路径。为充分揭示智能反射面在感知中的理论极限，我们首先针对单目标-单智能反射面场景，通过控制反射面的开关状态提出了一种新颖的**两阶段定位协议**。具体而言，在反射面关闭阶段，推导了基站-目标链路方位角/俯仰角波达方向的克拉美罗界，并基于MUSIC算法设计了角度估计器；在反射面开启阶段，推导了反射面-目标链路方位角/俯仰角波达方向的克拉美罗界，并提出了一种基于网格反射面波束扫描的简易角度估计方法。特别地，本文分析了经反射面不同路径反射的回波信号对感知性能的影响。此外，我们证明了单波束反射面无法实现感知功能，而**多波束**配置则可实现该功能。基于获取的两组角度信息，构建了三维单目标位置估计。随后将方案扩展至多目标-多反射面场景，通过控制多个反射面的开关状态提出了**反射面自适应感知协议**，并开发了多目标定位算法。仿真结果表明，所提方案具有有效性，可实现亚米级定位精度。