Visual Features Assisted Robot Localization in Symmetrical Environment Using Laser SLAM

Ge, Gengyu; Zhang, Yi; Jiang, Qin; Wang, Wei

doi:10.3390/s21051772

Cited by 10 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the mobile robot still cannot localize correctly even if there had a highly accurate map. This situation always appears in symmetrical or similar environments [37], because there are many possible positions where the mobile robot may locate. Without the help of other sensor information, the robot cannot distinguish itself at the door of room 214 or room 215 using data from the laser sensor.…”

Section: Mapping In a Simulated Environmentmentioning

confidence: 99%

Medical Mobile Robot Localization in Hospital Corridor Environment Using Laser SLAM and Text Features

Ge¹,

Zhang²,

Wang³

et al. 2022

jist

Self Cite

View full text Add to dashboard Cite

Localization is an important capability for a medical service robot navigating in the hospital environment. Recently, by using laser-based simultaneous localization and mapping (SLAM) and Monte Carlo localization (MCL) techniques, the mobile robot can localize itself in those places with obvious geometric features, like corners, lines, breakpoints, and curves. However, when a robot moves in a long corridor environment inside a building, there are only a few geometric features for reference, especially in symmetrical or similar areas. Consequently, the mobile robot can neither localize itself correctly in the global localization phase without a known initial pose nor recover the correct pose from the kidnapped robot problem. To solve this problem, we propose an approach that uses text features on the doorplate to assist localization. In the mapping stage, we control the mobile robot moves along a fixed path using both text features and laser scans data. In the localization stage, the mobile robot moving according to a strategy to find text features and initializes the particles, then navigates and localizes using an improved MCL method. The experimental results show that our approach achieves over 90% mapping accuracy and 93.3% successful localization rate, which outperforms traditional methods.

show abstract

Section: Mapping In a Simulated Environmentmentioning

confidence: 99%

Medical Mobile Robot Localization in Hospital Corridor Environment Using Laser SLAM and Text Features

Ge¹,

Zhang²,

Wang³

et al. 2022

jist

Self Cite

View full text Add to dashboard Cite

show abstract

“…The test results showed that the positioning accuracy of the system was improved. Literature (Ge et al , 2021) proposes an intensity difference weighting method for LOAM feature point matching. In fact, in an environment with obvious structural features, the accuracy requirements can be satisfied by relying only on the geometric information of the point cloud, without consuming more computing resources to add the intensity information of the point cloud.…”

Section: Introductionmentioning

confidence: 99%

LIDAR-based SLAM system for autonomous vehicles in degraded point cloud scenarios: dynamic obstacle removal

Ma,

Li,

Wang

et al. 2024

View full text Add to dashboard Cite

Purpose This study aims to achieve superior localization and mapping performance in point cloud degradation scenarios through the effective removal of dynamic obstacles. With the continuous development of various technologies for autonomous vehicles, the LIDAR-based Simultaneous localization and mapping (SLAM) system is becoming increasingly important. However, in SLAM systems, effectively addressing the challenges of point cloud degradation scenarios is essential for accurate localization and mapping, with dynamic obstacle removal being a key component. Design/methodology/approach This paper proposes a method that combines adaptive feature extraction and loop closure detection algorithms to address this challenge. In the SLAM system, the ground point cloud and non-ground point cloud are separated to reduce the impact of noise. And based on the cylindrical projection image of the point cloud, the intensity features are adaptively extracted, the degradation direction is determined by the degradation factor and the intensity features are matched with the map to correct the degraded pose. Moreover, through the difference in raster distribution of the point clouds before and after two frames in the loop process, the dynamic point clouds are identified and removed, and the map is updated. Findings Experimental results show that the method has good performance. The absolute displacement accuracy of the laser odometer is improved by 27.1%, the relative displacement accuracy is improved by 33.5% and the relative angle accuracy is improved by 23.8% after using the adaptive intensity feature extraction method. The position error is reduced by 30% after removing the dynamic target. Originality/value Compared with LiDAR odometry and mapping algorithm, the method has greater robustness and accuracy in mapping and localization.

show abstract

“…In early SLAM implementations, range-bearing sensors were usually used for visual robot navigation. With the development of computer vision, the problem of loop closure detection has been taken as image based visual appearance alignment problem, in which image is captured by the robot cameras [5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, many researchers employ the idea of bag-of-words model (BoW) to SLAM [1,4,5,[7][8][9][10][11][12]. Due to its flexibility, simplicity, BoW has become very popular in visual-related tasks.…”

Section: Introductionmentioning

confidence: 99%

An entropy based unsupervised visual vocabulary optimization for visual loop closure detection

Li¹,

Yu²,

Feng³

et al. 2023

International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2023)

View full text Add to dashboard Cite

In the task of simultaneous localization and mapping (SLAM), a mobile robot should be able to recognize the location that it has previously visited. This is termed as the loop closure detection. Current loop closure detection is implemented by matching of image features extracted from present image and previous images, where good feature representation is highly required. Bag-of-visual words (BoW) is known to be an effect feature representation for image and video matching task. However, to build the visual feature vocabulary in the unsupervised manner is still challenging. In this paper, we are aiming at evaluating the representability of the visual words and generating the discriminative vocabulary representation. We first present an entropy ranking based scheme to improve the spectral clustering algorithm by leveraging eigenvector selection and feature embedding simultaneously. We then propose to evaluate the representative ability of the visual vocabulary quantitatively based on the complexity of the decomposition of similarity matrix in the unsupervised manner. We perform experiments on the loop closure detection datasets. which contains strong perceptual aliasing in both indoor and outdoor scenarios. Results demonstrate that the proposed BoW based feature representation has strong representation ability in measuring the similarity of loop closure events and differentiating new visited places.

show abstract

Visual Features Assisted Robot Localization in Symmetrical Environment Using Laser SLAM

Cited by 10 publications

References 33 publications

Medical Mobile Robot Localization in Hospital Corridor Environment Using Laser SLAM and Text Features

Medical Mobile Robot Localization in Hospital Corridor Environment Using Laser SLAM and Text Features

LIDAR-based SLAM system for autonomous vehicles in degraded point cloud scenarios: dynamic obstacle removal

An entropy based unsupervised visual vocabulary optimization for visual loop closure detection

Contact Info

Product

Resources

About