[Paper Review] A Survey of Simultaneous Localization and Mapping with an Envision in 6G Wireless Networks

Baichuan Huang, Jun Zhao+1 more|arXiv (Cornell University)|Aug 24, 2019

Robotics and Sensor-Based Localization273 references33 citations

TL;DR

This paper surveys SLAM across Lidar, visual, and fused approaches, surveys sensors, open-source systems, deep learning integrations, challenges, and future directions including 6G-enabled SLAM.

ABSTRACT

Simultaneous Localization and Mapping (SLAM) achieves the purpose of simultaneous positioning and map construction based on self-perception. The paper makes an overview in SLAM including Lidar SLAM, visual SLAM, and their fusion. For Lidar or visual SLAM, the survey illustrates the basic type and product of sensors, open source system in sort and history, deep learning embedded, the challenge and future. Additionally, visual inertial odometry is supplemented. For Lidar and visual fused SLAM, the paper highlights the multi-sensors calibration, the fusion in hardware, data, task layer. The open question and forward thinking with an envision in 6G wireless networks end the paper. The contributions of this paper can be summarized as follows: the paper provides a high quality and full-scale overview in SLAM. It's very friendly for new researchers to hold the development of SLAM and learn it very obviously. Also, the paper can be considered as a dictionary for experienced researchers to search and find new interesting orientation.

Motivation & Objective

• Provide a comprehensive overview of SLAM, including Lidar SLAM, visual SLAM, and their fusion.
• Summarize sensors, open-source systems, and deep learning techniques applied to SLAM.
• Identify challenges and future directions, including the envisioned role of 6G networks in SLAM.

Proposed method

• Catalog existing Lidar and visual SLAM systems and categorize by 2D/3D, mono/stereo/RGB-D, and direct vs feature-based approaches.
• Summarize sensor types (Lidar, cameras, IMU, event cameras) and a spectrum of open-source SLAM tools.
• Discuss deep learning efforts in feature, recognition/segmentation, and semantic SLAM.
• Highlight challenges (cost, low-texture, dynamic environments, adversarial attacks) and multi-sensor fusion strategies.
• Outline the envisioned 6G-enabled future for SLAM and its integration with wireless networks.

Experimental results

Research questions

• RQ1 What are the main SLAM paradigms (Lidar, Visual, and fusion) and their core components?
• RQ2 What sensors, open-source systems, and deep learning techniques currently shape SLAM practice?
• RQ3 What are the major challenges and future directions for SLAM, including the 6G envision?
• RQ4 How does multi-sensor fusion and visual-inertial integration enhance SLAM performance?

Key findings

• The paper provides a high-quality, full-scale overview of SLAM, useful for both new and experienced researchers.
• It catalogs and contrasts Lidar SLAM and Visual SLAM systems, sensors, and deep-learning integrations.
• It discusses challenges such as cost, low-texture/dynamic environments, and adversarial sensor attacks.
• It highlights multi-sensor fusion in hardware, data, and task layers, and Visual Inertial Odometry as a key augmentation.
• It outlines an envisioning of SLAM within 6G wireless networks, pointing to future research directions and applications.