Feature Based Mapping Procedure with Application on Simultaneous Localization and Mapping (SLAM)

2010 ◽  
Vol 166-167 ◽  
pp. 265-270
Author(s):  
Razvan Luca ◽  
Fritz Tröster ◽  
Robert Gall ◽  
Carmen Simion
Keyword(s):  
Autonomous Navigation ◽  
Autonomous Vehicle ◽  
Laser Scanner ◽  
Relevant Information ◽  
Process Data ◽  
Mapping Procedure ◽  
Localization And Mapping ◽  
Laser Scanners ◽  
Map Generation ◽  
Feature Based

We are presenting a feature based mapping procedure applied on data reduction to the relevant information used for autonomous navigation. The proceeding is based on the evaluation of the environment using a SICK LD laser scanner. We assume that laser scanners have the advantage of producing reliable data with well understood characteristics for map generation. By implementing evolutive algorithms we process data into lines representing edges of the surrounding objects and create a simplified representation of the environment (feature based). Because of the dynamic generation and evolution of the map, during the movement of the autonomous vehicle we are considering of merging and fitting the data by applying a shape correlation. The goal of our project defines the capability of a fully autonomous vehicle to safely drive through the environment until reaching the standard parking lots and complete autonomous parking procedures.

scholarly journals A Normalization scheme for Terrestrial LiDAR Intensity Data by Range and Incidence Angle

2018 ◽  
Author(s):  
Sandeep Sasidharan
Keyword(s):  
Incidence Angle ◽  
Autonomous Vehicle ◽  
Laser Scanner ◽  
Spectral Information ◽  
Intensity Data ◽  
Automatic Registration ◽  
Terrestrial Lidar ◽  
Intensity Information ◽  
Laser Scanners ◽  
Normalization Scheme

Automatic registration, classification and segmentation of Terrestrial Laser Scanner (TLS) data are of great interest in Geoinformatics & Autonomous vehicle research. Along with dense and accurate 3D geometric data, laser scanners also collect return intensity information. Inclusion of this spectral information has potential to improve the working of the above mentioned processes. However, these intensity values need to be normalized, prior to their use, as they are subject to a large number of errors. This paper presents a technique to carry out normalization of intensity values using the range and incidence angle corrections. The developed approach has been tested on a large number of data and results are found satisfactory.

scholarly journals An Orthogonal Weighted Occupancy Likelihood Map with IMU-Aided Laser Scan Matching for 2D Indoor Mapping

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1742 ◽  
Author(s):  
Chuang Qian ◽  
Hongjuan Zhang ◽  
Jian Tang ◽  
Bijun Li ◽  
Hui Liu
Keyword(s):  
Laser Scanner ◽  
Location Based Services ◽  
Experimental Result ◽  
Measurement Unit ◽  
Indoor Environments ◽  
Localization And Mapping ◽  
Map Generation ◽  
Representation Method ◽  
Rigid Body Transformation ◽  
Grid Based

An indoor map is a piece of infrastructure associated with location-based services. Simultaneous Localization and Mapping (SLAM)-based mobile mapping is an efficient method to construct an indoor map. This paper proposes an SLAM algorithm based on a laser scanner and an Inertial Measurement Unit (IMU) for 2D indoor mapping. A grid-based occupancy likelihood map is chosen as the map representation method and is built from all previous scans. Scan-to-map matching is utilized to find the optimal rigid-body transformation in order to avoid the accumulation of matching errors. Map generation and update are probabilistically motivated. According to the assumption that the orthogonal is the main feature of indoor environments, we propose a lightweight segment extraction method, based on the orthogonal blurred segments (OBS) method. Instead of calculating the parameters of segments, we give the scan points contained in blurred segments a greater weight during the construction of the grid-based occupancy likelihood map, which we call the orthogonal feature weighted occupancy likelihood map (OWOLM). The OWOLM enhances the occupancy likelihood map by fusing the orthogonal features. It can filter out noise scan points, produced by objects, such as glass cabinets and bookcases. Experiments were carried out in a library, which is a representative indoor environment, consisting of orthogonal features. The experimental result proves that, compared with the general occupancy likelihood map, the OWOLM can effectively reduce accumulated errors and construct a clearer indoor map.

scholarly journals LiDAR-based Simultaneous Localization and Mapping in an underground mine in Złoty Stok, Poland

2021 ◽  
Vol 942 (1) ◽  
pp. 012035
Author(s):  
P Trybała
Keyword(s):  
Mobile Robot ◽  
Spatial Data ◽  
Laser Scanner ◽  
Simultaneous Localization And Mapping ◽  
Point Clouds ◽  
Working Environment ◽  
Accuracy Evaluation ◽  
Process Data ◽  
3D Point Clouds ◽  
Localization And Mapping

Abstract The mining sector is one of the most promising areas for implementing advanced autonomous robots. The benefits of increased safety, robot actions’ repeatability, and reducing human presence in hazardous locations are especially important in underground mines. One of the core functionalities of such a device is the robot’s ability to localize and navigate itself in the working environment. To achieve this, simultaneous localization and mapping (SLAM) techniques are used. In selected cases, they also allow the acquisition of dense spatial data in the form of 3D point clouds, which can be utilized for various 3D modeling and spatial analysis purposes. In this work, a mobile robot, equipped only with a compact laser scanner, is used to acquire spatial data in the adit of a closed mine in Zloty Stok, Poland. This data is further processed with selected SLAM algorithms to create a homogeneous 3D point cloud. Results are visualized and compared to a model obtained with a survey-grade laser scanner. Accuracy evaluation shows that employing SLAM algorithms to process data collected by a mobile robot can produce a reasonably accurate 3D geometrical model of an underground tunnel, even without incorporating any additional sensors.

scholarly journals LINE SEGMENTATION OF 2D LASER SCANNER POINT CLOUDS FOR INDOOR SLAM BASED ON A RANGE OF RESIDUALS

2017 ◽  
Vol IV-2/W4 ◽  
pp. 363-369 ◽  
Author(s):  
M. Peter ◽  
S. R. U. N. Jafri ◽  
G. Vosselman
Keyword(s):  
Laser Scanning ◽  
Degrees Of Freedom ◽  
Large Scale ◽  
Laser Scanner ◽  
Point Clouds ◽  
Indoor Environments ◽  
Six Degrees Of Freedom ◽  
Localization And Mapping ◽  
Feature Based ◽  
Definition Of

Indoor mobile laser scanning (IMLS) based on the Simultaneous Localization and Mapping (SLAM) principle proves to be the preferred method to acquire data of indoor environments at a large scale. In previous work, we proposed a backpack IMLS system containing three 2D laser scanners and an according SLAM approach. The feature-based SLAM approach solves all six degrees of freedom simultaneously and builds on the association of lines to planes. Because of the iterative character of the SLAM process, the quality and reliability of the segmentation of linear segments in the scanlines plays a crucial role in the quality of the derived poses and consequently the point clouds. The orientations of the lines resulting from the segmentation can be influenced negatively by narrow objects which are nearly coplanar with walls (like e.g. doors) which will cause the line to be tilted if those objects are not detected as separate segments. State-of-the-art methods from the robotics domain like Iterative End Point Fit and Line Tracking were found to not handle such situations well. Thus, we describe a novel segmentation method based on the comparison of a range of residuals to a range of thresholds. For the definition of the thresholds we employ the fact that the expected value for the average of residuals of <i>n</i> points with respect to the line is <i>σ</i>&amp;thinsp;/&amp;thinsp;&amp;radic;<i>n</i>. Our method, as shown by the experiments and the comparison to other methods, is able to deliver more accurate results than the two approaches it was tested against.

Development of the Autonomous Mobile Robot for Target-Searching in Urban Areas in the Tsukuba Challenge 2013

2014 ◽  
Vol 26 (2) ◽  
pp. 166-176 ◽  
Author(s):  
Junji Eguchi ◽  
◽  
Koichi Ozaki
Keyword(s):  
Urban Areas ◽  
Autonomous Navigation ◽  
Laser Scanner ◽  
Common Space ◽  
Occupancy Grid ◽  
Laser Scanners ◽  
Color Detection ◽  
Occupancy Grid Maps ◽  
Target Searching ◽  
User Friendly

This paper describes a navigation method for autonomous mobile robots and the knowledge obtained through trial runs conducted during the Tsukuba Challenge 2013 whose main tasks were autonomous navigation by robots to a goal and searching for target persons in several urban areas. Accurate maps are an important tool in localization on complex courses. We constructed occupancy grid map making method using laser scanners, gyro-assisted odometry and a DGPS. In trial runs, robots detect target parsons two ways – one involving color detection in images and the other involving laser scanner intensity data. The major problem with these methods is misdetection. To minimize this, we mask areas in which target persons should not exist on occupancy grid maps. Target candidates detected in masked areas are rejected, which indicates the possibility of using accurate occupancy grid maps as a user-friendly graphical interface. This paper focuses on the localization method, the target detection method and autonomous navigation knowledge in common space through the challenge.

Evidential SLAM Fusing 2D Laser Scanner and Stereo Camera

2019 ◽  
Vol 07 (03) ◽  
pp. 149-159
Author(s):  
Michelle Valente ◽  
Cyril Joly ◽  
Arnaud de La Fortelle
Keyword(s):  
Laser Scanner ◽  
Relevant Information ◽  
Mapping Data ◽  
Matching Algorithm ◽  
Localization Method ◽  
Stereo Camera ◽  
Accurate Localization ◽  
Localization And Mapping ◽  
The World ◽  
High Level

This work introduces a new complete Simultaneous Localization and Mapping (SLAM) framework that uses an enriched representation of the world based on sensor fusion and is able to simultaneously provide an accurate localization of the vehicle. A method to create an Evidential grid representation from two very different sensors, laser scanner and stereo camera, allows a better handling of the dynamic aspects of the urban environment and a proper management of errors to create a more reliable map, thus having a more precise localization. A life-long layer with high level states is presented, it maintains a global map of the entire vehicle’s trajectory and distinguishes between static and dynamic obstacles. Finally, we propose a method that at each current map creation estimates the vehicle’s position by a grid matching algorithm based on image registration techniques. Results on a real road dataset show that the environment mapping data can be improved by adding relevant information that could be missed without the proposed approach. Moreover, the proposed localization method is able to reduce the drift and improve the localization compared to other methods using similar configurations.

Handheld Laser Scanner Research

2019 ◽  
Vol 952 (10) ◽  
pp. 47-54
Author(s):  
A.V. Komissarov ◽  
A.V. Remizov ◽  
M.M. Shlyakhova ◽  
K.K. Yambaev
Keyword(s):  
Point Cloud ◽  
Three Dimensional ◽  
Laser Scanner ◽  
Test Site ◽  
Optical Systems ◽  
Advantages And Disadvantages ◽  
Site Survey ◽  
Laser Scanners ◽  
Three Dimensional Models ◽  
The Stability

The authors consider hand-held laser scanners, as a new photogrammetric tool for obtaining three-dimensional models of objects. The principle of their work and the newest optical systems based on various sensors measuring the depth of space are described in detail. The method of simultaneous navigation and mapping (SLAM) used for combining single scans into point cloud is outlined. The formulated tasks and methods for performing studies of the DotProduct (USA) hand-held laser scanner DPI?8X based on a test site survey are presented. The accuracy requirements for determining the coordinates of polygon points are given. The essence of the performed experimental research of the DPI?8X scanner is described, including scanning of a test object at various scanner distances, shooting a test polygon from various scanner positions and building point cloud, repeatedly shooting the same area of the polygon to check the stability of the scanner. The data on the assessment of accuracy and analysis of research results are given. Fields of applying hand-held laser scanners, their advantages and disadvantages are identified.

scholarly journals LiDAR-Based Glass Detection for Improved Occupancy Grid Mapping

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2263
Author(s):  
Haileleol Tibebu ◽  
Jamie Roche ◽  
Varuna De Silva ◽  
Ahmet Kondoz
Keyword(s):  
Laser Scanner ◽  
Point Clouds ◽  
Light Detection And Ranging ◽  
Test Results ◽  
New Approach ◽  
Occupancy Grid ◽  
Laser Scanners ◽  
Novel Method ◽  
Occupancy Grid Mapping ◽  
Cartesian Coordinate

Creating an accurate awareness of the environment using laser scanners is a major challenge in robotics and auto industries. LiDAR (light detection and ranging) is a powerful laser scanner that provides a detailed map of the environment. However, efficient and accurate mapping of the environment is yet to be obtained, as most modern environments contain glass, which is invisible to LiDAR. In this paper, a method to effectively detect and localise glass using LiDAR sensors is proposed. This new approach is based on the variation of range measurements between neighbouring point clouds, using a two-step filter. The first filter examines the change in the standard deviation of neighbouring clouds. The second filter uses a change in distance and intensity between neighbouring pules to refine the results from the first filter and estimate the glass profile width before updating the cartesian coordinate and range measurement by the instrument. Test results demonstrate the detection and localisation of glass and the elimination of errors caused by glass in occupancy grid maps. This novel method detects frameless glass from a long range and does not depend on intensity peak with an accuracy of 96.2%.

Accuracy improvement in 3D laser scanner based on dynamic triangulation for autonomous navigation system

2017 ◽  
Author(s):  
Oscar Real-Moreno ◽  
Julio C. Rodriguez-Quinonez ◽  
Oleg Sergiyenko ◽  
Luis C. Basaca-Preciado ◽  
Daniel Hernandez-Balbuena ◽  
...  
Keyword(s):  
Navigation System ◽  
Autonomous Navigation ◽  
Laser Scanner ◽  
Accuracy Improvement ◽  
Autonomous Navigation System

scholarly journals Decision-related feedback in visual cortex lacks spatial selectivity

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Katrina R. Quinn ◽  
Lenka Seillier ◽  
Daniel A. Butts ◽  
Hendrikje Nienborg
Keyword(s):  
Contextual Information ◽  
Relevant Information ◽  
Common Mechanism ◽  
Spatial Selectivity ◽  
Population Responses ◽  
Stimulus Choice ◽  
Visual Areas ◽  
Computational Work ◽  
Feature Based ◽  
The Brain

AbstractFeedback in the brain is thought to convey contextual information that underlies our flexibility to perform different tasks. Empirical and computational work on the visual system suggests this is achieved by targeting task-relevant neuronal subpopulations. We combine two tasks, each resulting in selective modulation by feedback, to test whether the feedback reflected the combination of both selectivities. We used visual feature-discrimination specified at one of two possible locations and uncoupled the decision formation from motor plans to report it, while recording in macaque mid-level visual areas. Here we show that although the behavior is spatially selective, using only task-relevant information, modulation by decision-related feedback is spatially unselective. Population responses reveal similar stimulus-choice alignments irrespective of stimulus relevance. The results suggest a common mechanism across tasks, independent of the spatial selectivity these tasks demand. This may reflect biological constraints and facilitate generalization across tasks. Our findings also support a previously hypothesized link between feature-based attention and decision-related activity.

Sign in / Sign up

Export Citation Format

Share Document