2D LiDAR SLAM Back-End Optimization with Control Network Constraint for Mobile Mapping

Simultaneous localization and mapping (SLAM) has been investigated in the field of robotics for two decades, as it is considered to be an effective method for solving the positioning and mapping problem in a single framework. In the SLAM community, the Extended Kalman Filter (EKF) based SLAM and particle filter SLAM are the most mature technologies. After years of development, graph-based SLAM is becoming the most promising technology and a lot of progress has been made recently with respect to accuracy and efficiency. No matter which SLAM method is used, loop closure is a vital part for overcoming the accumulated errors. However, in 2D Light Detection and Ranging (LiDAR) SLAM, on one hand, it is relatively difficult to extract distinctive features in LiDAR scans for loop closure detection, as 2D LiDAR scans encode much less information than images; on the other hand, there is also some special mapping scenery, where no loop closure exists. Thereby, in this paper, instead of loop closure detection, we first propose the method to introduce extra control network constraint (CNC) to the back-end optimization of graph-based SLAM, by aligning the LiDAR scan center with the control vertex of the presurveyed control network to optimize all the poses of scans and submaps. Field tests were carried out in a typical urban Global Navigation Satellite System (GNSS) weak outdoor area. The results prove that the position Root Mean Square (RMS) error of the selected key points is 0.3614 m, evaluated with a reference map produced by Terrestrial Laser Scanner (TLS). Mapping accuracy is significantly improved, compared to the mapping RMS of 1.6462 m without control network constraint. Adding distance constraints of the control network to the back-end optimization is an effective and practical method to solve the drift accumulation of LiDAR front-end scan matching.

Download Full-text

Aerial and Ground Robot Collaboration for Autonomous Mapping in Search and Rescue Missions

Drones ◽

10.3390/drones4040079 ◽

2020 ◽

Vol 4 (4) ◽

pp. 79

Author(s):

Dimitrios Chatziparaschis ◽

Michail G. Lagoudakis ◽

Panagiotis Partsinevelos

Keyword(s):

Humanoid Robot ◽

Satellite System ◽

Search And Rescue ◽

Localization Algorithm ◽

Localization And Mapping ◽

Planning Algorithm ◽

Crisis Scenarios ◽

Trained Neural Network ◽

Unknown Area ◽

Global Navigation Satellite

Humanitarian Crisis scenarios typically require immediate rescue intervention. In many cases, the conditions at a scene may be prohibitive for human rescuers to provide instant aid, because of hazardous, unexpected, and human threatening situations. These scenarios are ideal for autonomous mobile robot systems to assist in searching and even rescuing individuals. In this study, we present a synchronous ground-aerial robot collaboration approach, under which an Unmanned Aerial Vehicle (UAV) and a humanoid robot solve a Search and Rescue scenario locally, without the aid of a commonly used Global Navigation Satellite System (GNSS). Specifically, the UAV uses a combination of Simultaneous Localization and Mapping and OctoMap approaches to extract a 2.5D occupancy grid map of the unknown area in relation to the humanoid robot. The humanoid robot receives a goal position in the created map and executes a path planning algorithm in order to estimate the FootStep navigation trajectory for reaching the goal. As the humanoid robot navigates, it localizes itself in the map while using an adaptive Monte-Carlo Localization algorithm by combining local odometry data with sensor observations from the UAV. Finally, the humanoid robot performs visual human body detection while using camera data through a Darknet pre-trained neural network. The proposed robot collaboration scheme has been tested under a proof of concept setting in an exterior GNSS-denied environment.

Download Full-text

Georeferencing of Laser Scanner-Based Kinematic Multi-Sensor Systems in the Context of Iterated Extended Kalman Filters Using Geometrical Constraints

Sensors ◽

10.3390/s19102280 ◽

2019 ◽

Vol 19 (10) ◽

pp. 2280 ◽

Cited By ~ 3

Author(s):

Sören Vogel ◽

Hamza Alkhatib ◽

Johannes Bureick ◽

Rozhin Moftizadeh ◽

Ingo Neumann

Keyword(s):

State Constraints ◽

Laser Scanner ◽

Measurement Data ◽

Satellite System ◽

Sensor Systems ◽

Measurement Models ◽

Non Linear ◽

Geometrical Constraints ◽

Global Navigation Satellite ◽

The Impact

Georeferencing is an indispensable necessity regarding operating with kinematic multi-sensor systems (MSS) in various indoor and outdoor areas. Information from object space combined with various types of prior information (e.g., geometrical constraints) are beneficial especially in challenging environments where common solutions for pose estimation (e.g., global navigation satellite system or external tracking by a total station) are inapplicable, unreliable or inaccurate. Consequently, an iterated extended Kalman filter is used and a general georeferencing approach by means of recursive state estimation is introduced. This approach is open to several types of observation inputs and can deal with (non)linear systems and measurement models. The capability of using both explicit and implicit formulations of the relation between states and observations, and the consideration of (non)linear equality and inequality state constraints is a special feature. The framework presented is evaluated by an indoor kinematic MSS based on a terrestrial laser scanner. The focus here is on the impact of several different combinations of applied state constraints and the dependencies of two classes of inertial measurement units (IMU). The results presented are based on real measurement data combined with simulated IMU measurements.

Download Full-text

RTK GNSS-Assisted Terrestrial SfM Photogrammetry without GCP: Application to Coastal Morphodynamics Monitoring

Remote Sensing ◽

10.3390/rs12111889 ◽

2020 ◽

Vol 12 (11) ◽

pp. 1889 ◽

Cited By ~ 3

Author(s):

Marion Jaud ◽

Stéphane Bertin ◽

Mickaël Beauverger ◽

Emmanuel Augereau ◽

Christophe Delacourt

Keyword(s):

Standard Deviation ◽

Low Cost ◽

Laser Scanner ◽

Satellite System ◽

Mean Error ◽

Ground Control Points ◽

Participatory Science ◽

Gnss Network ◽

Global Navigation Satellite

The present article describes a new and efficient method of Real Time Kinematic (RTK) Global Navigation Satellite System (GNSS) assisted terrestrial Structure-from-Motion (SfM) photogrammetry without the need for Ground Control Points (GCPs). The system only requires a simple frame that mechanically connects a RTK GNSS antenna to the camera. The system is low cost, easy to transport, and offers high autonomy. Furthermore, not requiring GCPs enables saving time during the in situ acquisition and during data processing. The method is tested for coastal cliff monitoring, using both a Reflex camera and a Smartphone camera. The quality of the reconstructions is assessed by comparison to a synchronous Terrestrial Laser Scanner (TLS) acquisition. The results are highly satisfying with a mean error of 0.3 cm and a standard deviation of 4.7 cm obtained with the Nikon D800 Reflex camera and, respectively, a mean error of 0.2 cm and a standard deviation of 3.8 cm obtained with the Huawei Y5 Smartphone camera. This method will be particularly interesting when simplicity, portability, and autonomy are desirable. In the future, it would be transposable to participatory science programs, while using an open RTK GNSS network.

Download Full-text

Monitoring and Computation of the Volumes of Stockpiles of Bulk Material by Means of UAV Photogrammetric Surveying

Remote Sensing ◽

10.3390/rs11121471 ◽

2019 ◽

Vol 11 (12) ◽

pp. 1471 ◽

Cited By ~ 3

Author(s):

Grazia Tucci ◽

Antonio Gebbia ◽

Alessandro Conti ◽

Lidia Fiorini ◽

Claudio Lubello

Keyword(s):

Bulk Material ◽

Laser Scanner ◽

Ground Truth ◽

Point Clouds ◽

3D Models ◽

Satellite System ◽

3D Data ◽

Current Survey ◽

Close Range ◽

Global Navigation Satellite

The monitoring and metric assessment of piles of natural or man-made materials plays a fundamental role in the production and management processes of multiple activities. Over time, the monitoring techniques have undergone an evolution linked to the progress of measure and data processing techniques; starting from classic topography to global navigation satellite system (GNSS) technologies up to the current survey systems like laser scanner and close-range photogrammetry. Last-generation 3D data management software allow for the processing of increasingly truer high-resolution 3D models. This study shows the results of a test for the monitoring and computing of stockpile volumes of material coming from the differentiated waste collection inserted in the recycling chain, performed by means of an unmanned aerial vehicle (UAV) photogrammetric survey and the generation of 3D models starting from point clouds. The test was carried out with two UAV flight sessions, with vertical and oblique camera configurations, and using a terrestrial laser scanner for measuring the ground control points and as ground truth for testing the two survey configurations. The computations of the volumes were carried out using two software and comparisons were made both with reference to the different survey configurations and to the computation software.

Download Full-text

ANALYSIS OF THE VOLUME COMPARATION OF 3’S (TS, GNSS and TLS)

E3S Web of Conferences ◽

10.1051/e3sconf/20199401014 ◽

2019 ◽

Vol 94 ◽

pp. 01014

Author(s):

Khomsin ◽

Danar Guruh Pratomo ◽

Ira Mutiara Anjasmara ◽

Faizzuddin Ahmad

Keyword(s):

3D Model ◽

Laser Scanner ◽

Satellite System ◽

Navigation Satellite ◽

Scanner Data ◽

Total Station ◽

Volume Calculation ◽

Laser Scanners ◽

Technological Developments ◽

Global Navigation Satellite

Recently, technological developments in the field of surveys and mapping are growing very rapidly such as total station, navigation satellite (Global Navigation Satellite System), drones and laser scanners. One application of this technology is to measure a stockpile area quickly and accurately. This research will measure two stockpiles (coal warehouses) using total station (TS), GNSS and terrestrial laser scanner (TLS). This research will compare the results of volume calculations with the data generated by 3’S (TS, GNSS and TLS). Research is conducted at Coal Yard PT. Barkalin Surabaya in Benowo District, Surabaya, East City with geographically located at 112°39'11'’ E and 7°07’13‘' S. The first step is to make 3D model of Laser Scanner data by TLS Faro 3D 120 and to do regristrastion and filltering using Faro Scene. After that the data export to be 3D model from Faro Scene format to Recap 2016 (.rcp) to present and get coordinates. The next step is to compare the coordinates from TLS, TS and GNSS RTK. Finally, the accuracy of volume calculation from TS and GNSS RTK can be compared to TLS. The volume differences between TS and TLS data are -7.31 m3 (-0.45%) for the 1st location and -6.89 m3 (-0.24%) for the 2nd location. While the volume differences between GNSS RTK and TLS are -10.34 m3 (-0.63%) and -9.05 m3 (-0.31%) for the 1st location and the 2nd location respectively. Generally, the volume differences between TLS, TS and GNSS RTK are not significant. Therefore, 3’S can be used to measure a volume of stockpile.

Download Full-text

Automatic Mapping of Center Line of Railway Tracks using Global Navigation Satellite System, Inertial Measurement Unit and Laser Scanner

Remote Sensing ◽

10.3390/rs12030411 ◽

2020 ◽

Vol 12 (3) ◽

pp. 411 ◽

Cited By ~ 2

Author(s):

Sangeetha Shankar ◽

Michael Roth ◽

Lucas Andreas Schubert ◽

Judith Anne Verstegen

Keyword(s):

Laser Scanner ◽

Satellite System ◽

Sensor Data ◽

Measurement Unit ◽

Center Line ◽

Railway Tracks ◽

Combination Of Methods ◽

Global Navigation Satellite ◽

Inertial Measurements ◽

Gnss Data

Up-to-date geodatasets on railway infrastructure are valuable resources for the field of transportation. This paper investigates three methods for mapping the center lines of railway tracks using heterogeneous sensor data: (i) conditional selection of satellite navigation (GNSS) data, (ii) a combination of inertial measurements (IMU data) and GNSS data in a Kalman filtering and smoothing framework and (iii) extraction of center lines from laser scanner data. Several combinations of the methods are compared with a focus on mapping in tree-covered areas. The center lines of the railway tracks are extracted by applying these methods to a test dataset collected by a road-rail vehicle. The guard rails in the test area were also extracted during the center line detection process. The combination of methods (i) and (ii) gave the best result for the track on which the measurement vehicle had moved, mapping almost 100% of the track. The combination of methods (ii) and (iii) and the combination of all three methods gave the best result for the other parallel tracks, mapping between 25% and 80%. The mean perpendicular distance of the mapped center lines from the reference data was 1.49 meters.

Download Full-text

The Katwijk beach planetary rover dataset

The International Journal of Robotics Research ◽

10.1177/0278364917737153 ◽

2017 ◽

Vol 37 (1) ◽

pp. 3-12 ◽

Cited By ~ 8

Author(s):

Robert A Hewitt ◽

Evangelos Boukas ◽

Martin Azkarate ◽

Marco Pagnamenta ◽

Joshua A Marshall ◽

...

Keyword(s):

Satellite System ◽

Entire Area ◽

Mapping Algorithms ◽

Planetary Rover ◽

Localization And Mapping ◽

Stereo Cameras ◽

Landing Sites ◽

Aerial Vehicle ◽

Global Navigation Satellite ◽

Rock Size

This paper describes a dataset collected along a 1 km section of beach near Katwijk, The Netherlands, which was populated with a collection of artificial rocks of varying sizes to emulate known rock size densities at current and potential Mars landing sites. First, a fixed-wing unmanned aerial vehicle collected georeferenced images of the entire area. Then, the beach was traversed by a rocker-bogie-style rover equipped with a suite of sensors that are envisioned for use in future planetary rover missions. These sensors, configured so as to emulate the ExoMars rover, include stereo cameras, and time-of-flight and scanning light-detection-and-ranging sensors. This dataset will be of interest to researchers developing localization and mapping algorithms for vehicles traveling over natural and unstructured terrain in environments that do not have access to the global navigation satellite system, and where only previously taken satellite or aerial imagery is available.

Download Full-text

Incremental Loop Closure Verification by Guided Sampling

Journal of Advanced Computational Intelligence and Intelligent Informatics ◽

10.20965/jaciii.2017.p0059 ◽

2017 ◽

Vol 21 (1) ◽

pp. 59-66

Author(s):

Tanaka Kanji ◽

Keyword(s):

Image Retrieval ◽

Good Precision ◽

Sampling Strategies ◽

Detection Problem ◽

Loop Closure ◽

Loop Closure Detection ◽

Robot Trajectory ◽

Localization And Mapping ◽

Random Sample Consensus ◽

Closure Constraints

Loop closure detection, which is the task of identifying locations revisited by a robot in a sequence of odometry and perceptual observations, is typically formulated as a combination of two subtasks: (1) bag-of-words image retrieval and (2) post-verification using random sample consensus (RANSAC) geometric verification. The main contribution of this study is the proposal of a novel post-verification framework that achieves good precision recall trade-off in loop closure detection. This study is motivated by the fact that not all loop closure hypotheses are equally plausible (e.g., owing to mutual consistency between loop closure constraints) and that if we have evidence that one hypothesis is more plausible than the others, then it should be verified more frequently. We demonstrate that the loop closure detection problem can be viewed as an instance of a multi-model hypothesize-and-verify framework. Thus, we can build guided sampling strategies on this framework where loop closures proposed using image retrieval are verified in a planned order (rather than in a conventional uniform order) to operate in a constant time. Experimental results using a stereo simultaneous localization and mapping (SLAM) system confirm that the proposed strategy, the use of loop closure constraints and robot trajectory hypotheses as a guide, achieves promising results despite the fact that there exists a significant number of false positive constraints and hypotheses.

Download Full-text

MOVING OBJECT CLASSIFICATION USING MULTILAYER LASER SCANNING WITH SPACE SUBDIVISION FRAMEWORK

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-v-4-2020-103-2020 ◽

2020 ◽

Vol V-4-2020 ◽

pp. 103-108

Author(s):

M. Nakagawa ◽

M. Taguchi

Keyword(s):

Real Time ◽

Urban Areas ◽

Laser Scanning ◽

Laser Scanner ◽

Object Classification ◽

Point Clouds ◽

Satellite System ◽

Space Subdivision ◽

Position Data ◽

Global Navigation Satellite

Abstract. In this paper, we focus on the development of intelligent construction vehicles to improve the safety of workers in construction sites. Generally, global navigation satellite system positioning is utilized to obtain the position data of workers and construction vehicles. However, construction fields in urban areas have poor satellite positioning environments. Therefore, we have developed a 3D sensing unit mounted on a construction vehicle for worker position data acquisition. The unit mainly consists of a multilayer laser scanner. We propose a real-time object measurement, classification and tracking methodology with the multilayer laser scanner. We also propose a methodology to estimate and visualize object behaviors with a spatial model based on a space subdivision framework consisting of agents, activities, resources, and modifiers. We applied the space subdivision framework with a geofencing approach using real-time object classification and tracking results estimated from temporal point clouds. Our methodology was evaluated using temporal point clouds acquired from a construction vehicle in drilling works.

Download Full-text

SVG-Loop: Semantic–Visual–Geometric Information-Based Loop Closure Detection

Remote Sensing ◽

10.3390/rs13173520 ◽

2021 ◽

Vol 13 (17) ◽

pp. 3520

Author(s):

Zhian Yuan ◽

Ke Xu ◽

Xiaoyu Zhou ◽

Bin Deng ◽

Yanxin Ma

Keyword(s):

Detection Algorithm ◽

Detection Methods ◽

Vector Model ◽

Limited Information ◽

Complex Environments ◽

Dynamic Features ◽

Geometric Information ◽

Loop Closure ◽

Loop Closure Detection ◽

Localization And Mapping

Loop closure detection is an important component of visual simultaneous localization and mapping (SLAM). However, most existing loop closure detection methods are vulnerable to complex environments and use limited information from images. As higher-level image information and multi-information fusion can improve the robustness of place recognition, a semantic–visual–geometric information-based loop closure detection algorithm (SVG-Loop) is proposed in this paper. In detail, to reduce the interference of dynamic features, a semantic bag-of-words model was firstly constructed by connecting visual features with semantic labels. Secondly, in order to improve detection robustness in different scenes, a semantic landmark vector model was designed by encoding the geometric relationship of the semantic graph. Finally, semantic, visual, and geometric information was integrated by fuse calculation of the two modules. Compared with art-of-the-state methods, experiments on the TUM RBG-D dataset, KITTI odometry dataset, and practical environment show that SVG-Loop has advantages in complex environments with varying light, changeable weather, and dynamic interference.

Download Full-text