Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directions
Beijing Institute of Technology（北京理工大学）；University of Science and Technology Beijing（北京科技大学）；Nanyang Technological University（南洋理工大学）；Shanghai AI Laboratory（上海人工智能实验室）
Li Wang, Ruixuan Gong, Yumo Han, Lei Yang, Lu Yang, Ying Li, Bin Xu, Huaping Liu, Rong Fu
Traditional Simultaneous Localization and Mapping (SLAM) systems often face limitations including coarse rendering quality, insufficient recovery of scene details, and poor robustness in dynamic environments. 3D Gaussian Splatting (3DGS), with its efficient explicit representation and high-quality rendering capabilities, offers a new reconstruction paradigm for SLAM. This survey comprehensively reviews key technical approaches for integrating 3DGS with SLAM. We analyze performance optimization of representative methods across four critical dimensions: rendering quality, tracking accuracy, reconstruction speed, and memory consumption, delving into their design principles and breakthroughs. Furthermore, we examine methods for enhancing the robustness of 3DGS-SLAM in complex environments such as motion blur and dynamic environments. Finally, we discuss future challenges and development trends in this area. This survey aims to provide a technical reference for researchers and foster the development of next-generation SLAM systems characterized by high fidelity, efficiency, and robustness.
Stanford University（斯坦福大学）；Instituto de Investigación en Ingeniería de Aragón, Universidad de Zaragoza（阿拉贡工程研究所，萨拉戈萨大学）
We present a consensus-based distributed pose graph optimization algorithm for obtaining an estimate of the 3D translation and rotation of each pose in a pose graph, given noisy relative measurements between poses. The algorithm, called GeoD, implements a continuous time distributed consensus protocol to minimize the geodesic pose graph error. GeoD is distributed over the pose graph itself, with a separate computation thread for each node in the graph, and messages are passed only between neighboring nodes in the graph. We leverage tools from Lyapunov theory and multi-agent consensus to prove …
EndoFlow-SLAM: Real-Time Endoscopic SLAM with Flow-Constrained Gaussian Splatting
School of Advanced Technology, Xi'an Jiaotong Liverpool University（西安交通大学利物浦大学先进技术学院）；School of AI and Advanced Computing, Xi'an Jiaotong Liverpool University（西安交通大学利物浦大学人工智能与高级计算学院）；School of Physical Sciences, University of Liverpool（利物浦大学物理科学学院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
A framework for online simultaneous localization, mapping and self-calibration is presented which can detect and handle significant change in the calibration parameters. Estimates are computed in constant-time by factoring the problem and focusing on segments of the trajectory that are most informative for the purposes of calibration. A novel technique is presented to detect the probability that a significant change is present in the calibration parameters. The system is then able to re-calibrate. Maximum likelihood trajectory and map estimates are computed using an asynchronous and adaptive o…
Massachusetts Institute of Technology（麻省理工学院）；Laboratory for Information and Decision Systems（信息与决策系统实验室）；Computer Science and Artificial Intelligence Laboratory（计算机科学与人工智能实验室）
Simultaneous localization and mapping (SLAM) is the process of constructing a global model of an environment from local observations of it; this is a foundational capability for mobile robots, supporting such core functions as planning, navigation, and control. This article reviews recent progress in SLAM, focusing on advances in the expressive capacity of the environmental models used in SLAM systems (representation) and the performance of the algorithms used to estimate these models from data (inference). A prominent theme of recent SLAM research is the pursuit of environmental representatio…
In this paper we present ProSLAM, a lightweight stereo visual SLAM system designed with simplicity in mind. Our work stems from the experience gathered by the authors while teaching SLAM to students and aims at providing a highly modular system that can be easily implemented and understood. Rather than focusing on the well known mathematical aspects of Stereo Visual SLAM, in this work we highlight the data structures and the algorithmic aspects that one needs to tackle during the design of such a system. We implemented ProSLAM using the C++ programming language in combination with a minimal se…
Laboratoire des Sciences du Numérique de Nantes (LS2N)（南特数字科学实验室（LS2N））；CNRS（法国国家科学研究中心）；Ecole Centrale de Nantes（南特中央理工学院）；Capgemini Engineering（凯捷工程）
Institute for Intelligent Systems, Esslingen University of Applied Sciences（埃斯林根应用科学大学智能系统研究所）；Department of Computer Science, University of Freiburg（弗莱堡大学计算机科学系）
Institute of Robotics and Machine Intelligence, Poznan University of Technology（波兹南工业大学机器人与机器智能研究所）
We propose an extension to the segment-based global localization method for LiDAR SLAM using descriptors learned considering the visual context of the segments. A new architecture of the deep neural network is presented that learns the visual context acquired from synthetic LiDAR intensity images. This approach allows a single multi-beam LiDAR to produce rich and highly descriptive location signatures. The method is tested on two public datasets, demonstrating an improved descriptiveness of the new descriptors, and more reliable loop closure detection in SLAM. Attention analysis of the network…
Mapping-Guided Task Discovery and Allocation for Robotic Inspection of Underwater Structures
Department of Mechanical Engineering, University of Washington（机械工程系，华盛顿大学）；Department of Industrial & Systems Engineering and Department of Mechanical Engineering, University of Washington（工业与系统工程系和机械工程系，华盛顿大学）
This paper uses the smoothing and mapping framework to solve the SLAM problem in indoor environments; focusing on how some key issues such as feature extraction and data association can be handled by applying probabilistic techniques. For feature extraction, an odds ratio approach to find multiple lines from laser scans is proposed, this criterion allows to decide which model must be merged and to output the best number of models. In addition, to solve the data association problem a method based on the segments of each line is proposed. Experimental results show that high quality indoor maps c…
General Place Recognition Survey: Towards Real-World Autonomy
City University of Hong Kong（香港城市大学）；University College London（伦敦大学学院）；University of Delaware（特拉华大学）；Carnegie Mellon University（卡内基梅隆大学）；Nankai University（南开大学）
