Millimeter Wave Wireless Communication Assisted Three-Dimensional Simultaneous Localization and Mapping

TL;DR

This paper introduces a novel millimeter-wave wireless communication-based 3D SLAM framework that uses deep learning and reflection point analysis to achieve real-time localization and environment mapping without prior knowledge.

Contribution

The paper presents a new communication-based SLAM framework combining deep learning, reflection point analysis, and inertial data for environment mapping and localization.

Findings

Effective 3D environment mapping in complex settings

High-precision real-time localization achieved

Validated through extensive outdoor and indoor simulations

Abstract

In this paper, we study the three-dimensional (3D) simultaneous localization and mapping (SLAM) problem in complex outdoor and indoor environments based only on millimeter-wave (mmWave) wireless communication signals. Firstly, we propose a deep-learning based mapping (DLM) algorithm that can leverage the reflections point on the first-order none line-of-sight (NLOS) communications links (CLs) to build the 3D point cloud map of the environment. Specifically, we design a classification neural network to identify the first-order NLOS CL and theoretically calculate the geometric coordinates of the reflection points on it. Secondly, we take the advantage of both the inertial measurement unit and the beam-squint assisted localization method to realize real-time and precise localizations. Then, combining the DLM and the adopted localization algorithm, we develop the communication-based SLAM (C-SLAM) framework that can carry out SLAM without any prior knowledge of the environment. Moreover, extensive simulations of both complex outdoor and indoor environments validate the effectiveness of our approach.