Article
Robotics
Yibin Wu, Jian Kuang, Xiaoji Niu, Jens Behley, Lasse Klingbeil, Heiner Kuhlmann
Summary: A reliable pose estimator for mobile robots is desired, which is robust to environmental disturbances. Inertial measurement units (IMUs) are important for perceiving the full motion state of the vehicle independently, but suffer from accumulative error. We propose to exploit the environmental perception ability of Wheel-INS to achieve SLAM using only one IMU, significantly improving positioning accuracy.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Remote Sensing
Jia Xie, Xiaofeng He, Jun Mao, Lilian Zhang, Xiaoping Hu
Summary: Collaborative simultaneous localization and mapping (SLAM) plays a crucial role in various applications. This paper proposes a centralized collaborative SLAM system using a monocular camera, an inertial measurement unit (IMU), and a UWB device as onboard sensors. The system utilizes visual-inertial odometry for motion estimation and local map construction, and incorporates a global optimization algorithm to merge the local maps into a global map using cross-agent map match information and agent-to-agent range measurements.
Article
Construction & Building Technology
Cassio K. Hui, Tess X. Luo, Wallace W. Lai, Ray K. Chang
Summary: This study proposes a method to synchronize GPR scans in areas with poor or no GNSS coverage, using a mobile mapping system (MMS) backpack guided by SLAM. It aims to improve the efficiency of GPR surveys in dense urban areas where good GNSS coverage is unavailable.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2022)
Article
Computer Science, Hardware & Architecture
Petros Kapsalas, Aris S. Lalos, Dimitrios Serpanos, Konstantinos Moustakas
Summary: SLAM involves mapping an environment and estimating sensor motion simultaneously, requiring modular architectures for widespread adoption in emerging mobile computing systems.
Article
Automation & Control Systems
Hae Min Cho, HyungGi Jo, Euntai Kim
Summary: This article proposes a novel SLAM method named SP-SLAM using surfels as features to handle both high texture and low texture environments. The method can represent spacious environments with relatively small memory usage and achieves better performance in both types of environments compared to previous feature-based visual SLAM methods.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
Hae Min Cho, HyungGi Jo, Euntai Kim
Summary: In this article, a novel SP-SLAM method using surfels as features for both high and low texture environments is proposed, with new objective functions to simultaneously optimize points, surfels, and cameras, demonstrating better performance and lower memory usage compared to previous feature-based visual SLAM methods.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Robotics
Chao Xia, Chenfeng Xu, Patrick Rim, Mingyu Ding, Nanning Zheng, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan
Summary: Current LiDAR odometry, mapping, and localization methods based on point-wise representations of 3D scenes face space-inefficiency issues. To address this, we propose a novel method that describes scenes using compact quadric surface representations instead of point clouds. Our method segments the point cloud into patches and fits each patch to a quadric implicit function, providing a more efficient representation. We also introduce an incremental growing method that eliminates the need for repeated fitting. Experimental results demonstrate that our method achieves competitive accuracy with low latency and memory usage.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Environmental Sciences
Yuan Lin, Haiqing Dong, Wentao Ye, Xue Dong, Shuogui Xu
Summary: This work presents an information-based landmarks assisted simultaneous localization and mapping (InfoLa-SLAM) method using single-line lidar in large-scale scenes. The proposed approach reduces the computational cost of SLAM and achieves accurate mapping through a keyframe selection method based on Fisher information and an efficient global descriptor for place recognition. The results show a significant reduction in the number of keyframes, high probability of relocalization correction, and lightweight performance compared to traditional strategies.
Article
Robotics
Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer, Javier Civera, Holger Voos
Summary: In this paper, an evolved version of Situational Graphs called S-Graphs+ is presented, which jointly models a pose graph and a 3D scene graph in a single optimizable factor graph. S-Graphs+ includes four layers: keyframes, walls, rooms, and floors, and is optimized in real-time to achieve accurate robot pose estimation and map construction. Novel room and floor segmentation algorithms utilizing mapped wall planes and free-space clusters are also introduced. Experimental results demonstrate that S-Graphs+ outperforms other methods in terms of accuracy and scene modeling capabilities. The software is made available as a docker file.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Robotics
Dengxiang Chang, Runbang Zhang, Shengjie Huang, Manjiang Hu, Rongjun Ding, Xiaohui Qin
Summary: Accurate localization is crucial for autonomous driving systems, and LiDAR is commonly used due to its reliability. This paper proposes a robust and accurate LiDAR SLAM that innovates feature point extraction and motion constraint construction. Feature points are extracted using adaptive point roughness evaluation and outliers are removed with a dynamic threshold filter. Motion constraint construction uses weighted bimodal least squares to optimize the relative pose between current frame and point map. The solution achieves better performance in terms of accuracy and robustness according to multiple datasets.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Robotics
Chongjian Yuan, Wei Xu, Xiyuan Liu, Xiaoping Hong, Fu Zhang
Summary: This study proposes an efficient and probabilistic adaptive voxel mapping method for LiDAR odometry. The method utilizes voxel maps to probabilistically represent the environment and accurately register new LiDAR scans, achieving high accuracy and efficiency compared to other state-of-the-art methods.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Xi Zheng, Rui Ma, Rui Gao, Qi Hao
Summary: In this study, a phase-based SLAM framework is proposed for fast and accurate estimation of SLI sensor pose and 3D object reconstruction. By developing a reprojection model, a local optimizer, and a compressive phase comparison method, phase registration with low computational complexity and efficient loop closure detection are achieved. The experimental results demonstrate that the proposed Phase-SLAM outperforms other methods in terms of efficiency and accuracy.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Qiuyuan Wang, Zike Yan, Junqiu Wang, Fei Xue, Wei Ma, Hongbin Zha
Summary: The article proposes a visual SLAM method based on line flows to predict and update 2-D projections of 3-D line segments in challenging scenes. Through Bayesian network modeling, LF-SLAM effectively addresses problems like occlusions, blurred images, and repetitive textures, achieving state-of-the-art localization and mapping results in complex environments.
IEEE TRANSACTIONS ON ROBOTICS
(2021)
Article
Robotics
Lintong Zhang, Michael Helmberger, Lanke Frank Tarimo Fu, David Wisth, Marco Camurri, Davide Scaramuzza, Maurice Fallon
Summary: To drive the advancement of SLAM systems, we created the Hilti-Oxford Dataset, which includes various challenges to test the performance of SLAM algorithms in different scenarios. We implemented a novel ground truth collection method to accurately measure pose errors with millimeter accuracy. The dataset attracted a large number of researchers to participate in the Hilti SLAM challenge.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Dengxiang Chang, Shengjie Huang, Runbang Zhang, Manjiang Hu, Rongjun Ding, Xiaohui Qin
Summary: This article proposes a highly accurate and robust LiDAR SLAM method based on features with well motion observability. The method screens features with well motion observability by estimating their contribution to motion constraints and reduces redundant features and constraints through weighted reprojection constraints. Experimental results show that the proposed method achieves higher accuracy and robustness in feature-poor environments.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Civil
Paulo Vinicius Koerich Borges, Robert Zlot, Ashley Tews
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2013)
Article
Robotics
Michael Bosse, Robert Zlot
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2008)
Article
Automation & Control Systems
Michael Bosse, Robert Zlot
ROBOTICS AND AUTONOMOUS SYSTEMS
(2009)
Proceedings Paper
Automation & Control Systems
Michael Bosse, Robert Zlot
ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7
(2009)
Article
Engineering, Electrical & Electronic
M. Bernardine Dias, Robert Zlot, Nidhi Kalra, Anthony Stentz
PROCEEDINGS OF THE IEEE
(2006)
Article
Robotics
R Zlot, A Stentz
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2006)