A practical 2D/3D SLAM using directional patterns of an indoor structure

Lee, Keon Yong; Ryu, Soo-Hyun; Nam, Changjoo; Doh, Nakju Lett

doi:10.1007/s11370-017-0234-9

Cited by 16 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We acquire the registered point cloud and trajectory, which are the optimized poses of raw LiDAR measurements, using the LiDAR-IMU based simultaneous localization and mapping (SLAM) [ 29 , 30 ]. The structural points are constructed using the architectural point cloud construction described in our previous work [ 16 ].…”

Section: Methodsmentioning

confidence: 99%

“…The robot system is a combination of a spherical camera, two 3D LiDARs, and an inertial sensor, while the backpack system consists of a 3D LiDAR and an inertial sensor. The registered point cloud and trajectory of the real-world indoor spaces were generated by LiDAR-IMU based SLAM [29,30]. For efficient contextualization, datasets are classified according to their environmental characteristics:…”

Section: Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Reconstruction of Multi-Level Indoor Spaces from Point Cloud and Trajectory

Lim

Doh

2021

Sensors

View full text Add to dashboard Cite

Remarkable progress in the development of modeling methods for indoor spaces has been made in recent years with a focus on the reconstruction of complex environments, such as multi-room and multi-level buildings. Existing methods represent indoor structure models as a combination of several sub-spaces, which are constructed by room segmentation or horizontal slicing approach that divide the multi-room or multi-level building environments into several segments. In this study, we propose an automatic reconstruction method of multi-level indoor spaces with unique models, including inter-room and inter-floor connections from point cloud and trajectory. We construct structural points from registered point cloud and extract piece-wise planar segments from the structural points. Then, a three-dimensional space decomposition is conducted and water-tight meshes are generated with energy minimization using graph cut algorithm. The data term of the energy function is expressed as a difference in visibility between each decomposed space and trajectory. The proposed method allows modeling of indoor spaces in complex environments, such as multi-room, room-less, and multi-level buildings. The performance of the proposed approach is evaluated for seven indoor space datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

Automatic Reconstruction of Multi-Level Indoor Spaces from Point Cloud and Trajectory

Lim

Doh

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The following experiments are conducted to complete the simulation of EKF-v SLAM algorithm in a 2D plane environment and prove the positioning and composition accuracy in a 2D environment 10 , which is carried out in the following steps:…”

Section: D Ekf-vslam Simulation Experimentsmentioning

confidence: 99%

Implementation of monocular 2D EKF-vSLAM algorithm

2023

Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023)

View full text Add to dashboard Cite

Aiming at the localization and composition of mobile robots in unknown environments, this paper briefly summarizes the connotation of SLAM, analyzes the principle of extended Kalman filter theory, which is an algorithm process of gradually approaching the real state of the system through recursive estimation of the state of nonlinear random dynamic system, and finally verifies the relevant theories and algorithms through two-dimensional EKF vSLAM simulation experiments. The experimental results show that the EKF-vSLAM algorithm can effectively improve the accuracy of robot positioning and landmark positioning in two-dimensional environments, reduce the uncertainty of mobile robot positioning and composition in unknown environments, and to some extent improve the autonomy of mobile robots.

show abstract

“…In 2018, Lee, K. et al have worked on a pole star model and have made a study that the direction finding problem will be solved in the case of an object or structure that is to be noticed from everywhere such as pole star in the environment to be mapped. They proposed the Direction Landmark-based SLAM (DLSLAM) algorithm to detect the pole star model they called Direction Landmark (DL) and determine the direction accordingly (Lee, Ryu, Nam & Doh, 2018). Hosseinzadeh M. et al made a study that transforms the point sets of the environment mapped with an autonomous robot into meaningful objects with deep learning methods.…”

Section: Introductionmentioning

confidence: 99%

Otonom Robotlarla Lokalizasyon ve Nokta Bulutu Tabanlı 3B Haritalama

Açıkel¹,

Gökçen²

2019

European Journal of Science and Technology

View full text Add to dashboard Cite

In this study, localization and environment mapping application is aimed with an autonomous robot. A new algorithm is presented to scan a larger area, to produce faster and more accurate results. The mapping process is intended not to be affected by environmental movements. It can be used in military areas to gain manpower in the mine area or to model the environment in virtual reality applications. In autonomous robot design, the horizontal and vertical angle values of the Lidar Lite V3 are provided by two servo motors. A fourwheeled car model was used. Ultrasonic sensors are placed on the front, right and left surfaces of the robot, Raspberry Pi 3 and Pi Camera was placed on top. It is seen that the moving average filter removes the noise generated on the map. The Lidar Lite V3 was able to take measurements at longer distances. Noise generation is prevented by motion detection algorithm. It can be used in interior space mapping, environment modeling, virtual reality applications, military areas, mining sector and graphic applications. In outdoor mapping, it can be used to create a map of an area of 40 meters in diameter. The mapping process was performed as close to the actual values by using the moving average filter and the Lidar Lite V3. The mapping process with the motion detection system is paused and actual position data are obtained using GPS.

show abstract

A practical 2D/3D SLAM using directional patterns of an indoor structure

Cited by 16 publications

References 25 publications

Automatic Reconstruction of Multi-Level Indoor Spaces from Point Cloud and Trajectory

Automatic Reconstruction of Multi-Level Indoor Spaces from Point Cloud and Trajectory

Implementation of monocular 2D EKF-vSLAM algorithm

Otonom Robotlarla Lokalizasyon ve Nokta Bulutu Tabanlı 3B Haritalama

Contact Info

Product

Resources

About