Sensors

Research

Jump to: Review

17 pages, 7885 KiB

Open AccessArticle

Determination of USV’s Direction Using Satellite and Fluxgate Compasses and GNSS-RTK

by Artur Makar

Sensors 2022, 22(20), 7895; https://doi.org/10.3390/s22207895 - 17 Oct 2022

Cited by 12 | Viewed by 2313

Abstract

The measurement of a mobile object’s movement direction is performed by means of various analogue and digital devices, including both autonomous and non-autonomous ones. They represent different measuring qualities, dimensions, weights and tolerance to ambient disturbances. They allow measuring the course of heading [...] Read more.

The measurement of a mobile object’s movement direction is performed by means of various analogue and digital devices, including both autonomous and non-autonomous ones. They represent different measuring qualities, dimensions, weights and tolerance to ambient disturbances. They allow measuring the course of heading and course over ground (COG) in sea navigation. They are used for the determination of motion vectors on the water’s surface and with respect to the sea bed, in integrated systems, DP and autopilots. Results of dynamic tests of three heading meters: electronic and satellite compasses, and Global Navigation Satellite Systems (GNSS) determining COG are presented in this paper. The measurements were conducted in good measuring conditions, in an open upper hemisphere for satellite receivers and at no or minimal disturbances of the magnetic field. Sensors were mounted on an unmanned survey vessel (USV) that was moving straight, performing quick turns and circulations. Each of them has some limitations with respect to its use in the water area in which a hydrographic sounding is to be performed; attention was paid to the possibility of using a given compass on board a small autonomous ship navigating automatically. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

12 pages, 5724 KiB

Open AccessArticle

A Measurement-Aided Control System for Stabilization of the Real-Life Stewart Platform

by Wojciech P. Hunek, Paweł Majewski, Jarosław Zygarlicki, Łukasz Nagi, Dariusz Zmarzły, Roman Wiench, Paweł Młotek and Piotr Warmuzek

Sensors 2022, 22(19), 7271; https://doi.org/10.3390/s22197271 - 26 Sep 2022

Cited by 5 | Viewed by 2206

Abstract

In the paper, an innovative control system devoted to the stabilization of the parallel manipulator-type Hexapod is presented. The device consists of three main parts, allowing us to reach the desired location during various external disturbances. Indeed, the telescopic boom located on the [...] Read more.

In the paper, an innovative control system devoted to the stabilization of the parallel manipulator-type Hexapod is presented. The device consists of three main parts, allowing us to reach the desired location during various external disturbances. Indeed, the telescopic boom located on the car along with the system providing the correction of the boom column deflection as well as the gyroscopic self-leveling head constitute a complex tool covering a plethora of modern techniques and solutions. Through the application of advanced issues strictly derived from nonlinear identification and multivariable control theory branches, the dynamical behavior of the discussed device has been handled in order to achieve a proper reference operation. Naturally, it has been supported by a set of accompanying approaches related to the processes of the real-time measurement and robust data transmission. It should be emphasized that the proposed computer-aided system is intended for the film industry, where image stabilization plays a crucial role. Such a statement has additionally been confirmed by other innovative products introduced by a company placed in Opole, Poland, called MovieBird International. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

17 pages, 2606 KiB

Open AccessArticle

Autonomous Trajectory Generation Comparison for De-Orbiting with Multiple Collision Avoidance

by Karla Raigoza and Timothy Sands

Sensors 2022, 22(18), 7066; https://doi.org/10.3390/s22187066 - 19 Sep 2022

Cited by 56 | Viewed by 4058

Abstract

Over the past four decades, space debris has been identified as a growing hazard for near-Earth space systems. With limited access to space debris tracking databases and only recent policy advancements made to secure a sustainable space environment and mission architecture, this manuscript [...] Read more.

Over the past four decades, space debris has been identified as a growing hazard for near-Earth space systems. With limited access to space debris tracking databases and only recent policy advancements made to secure a sustainable space environment and mission architecture, this manuscript aims to establish an autonomous trajectory maneuver to de-orbit spacecrafts back to Earth using collision avoidance techniques for the purpose of decommissioning or re-purposing spacecrafts. To mitigate the risk of colliding with another object, the spacecraft attitude slew maneuver requires high levels of precision. Thus, the manuscript compares two autonomous trajectory generations, sinusoidal and Pontragin’s method. In order to determine the Euler angles (roll, pitch, and yaw) necessary for the spacecraft to safely maneuver around space debris, the manuscript incorporates way-point guidance as a collision avoidance approach. When the simulation compiled with both sinusoidal and Pontryagin trajectories, there were differences within the Euler angle spacecraft tracking that could be attributed to the increased fuel efficiency by over five orders of magnitude and lower computation time by over 15 min for that of Pontryagin’s trajectory compared with that of the sinusoidal trajectory. Overall, Pontryagin’s method produced an autonomous trajectory that is more optimal by conserving 37.9% more fuel and saving 40.5% more time than the sinusoidal autonomous trajectory. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

16 pages, 5488 KiB

Open AccessArticle

Comparison of Deep Learning and Deterministic Algorithms for Control Modeling

by Hanfeng Zhai and Timothy Sands

Sensors 2022, 22(17), 6362; https://doi.org/10.3390/s22176362 - 24 Aug 2022

Cited by 19 | Viewed by 3668

Abstract

Controlling nonlinear dynamics arises in various engineering fields. We present efforts to model the forced van der Pol system control using physics-informed neural networks (PINN) compared to benchmark methods, including idealized nonlinear feedforward (FF) control, linearized feedback control (FB), and feedforward-plus-feedback combined (C). [...] Read more.

Controlling nonlinear dynamics arises in various engineering fields. We present efforts to model the forced van der Pol system control using physics-informed neural networks (PINN) compared to benchmark methods, including idealized nonlinear feedforward (FF) control, linearized feedback control (FB), and feedforward-plus-feedback combined (C). The aim is to implement circular trajectories in the state space of the van der Pol system. A designed benchmark problem is used for testing the behavioral differences of the disparate controllers and then investigating controlled schemes and systems of various extents of nonlinearities. All methods exhibit a short initialization accompanying arbitrary initialization points. The feedforward control successfully converges to the desired trajectory, and PINN executes good controls with higher stochasticity observed for higher-order terms based on the phase portraits. In contrast, linearized feedback control and combined feed-forward plus feedback failed. Varying trajectory amplitudes revealed that feed-forward, linearized feedback control, and combined feed-forward plus feedback control all fail for unity nonlinear damping gain. Traditional control methods display a robust fluctuation for higher-order terms. For some various nonlinearities, PINN failed to implement the desired trajectory instead of becoming “trapped” in the phase of small radius, yet idealized nonlinear feedforward successfully implemented controls. PINN generally exhibits lower relative errors for varying targeted trajectories. However, PINN also shows evidently higher computational burden compared with traditional control theory methods, with at least more than 30 times longer control time compared with benchmark idealized nonlinear feed-forward control. This manuscript proposes a comprehensive comparative study for future controller employment considering deterministic and machine learning approaches. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

17 pages, 19072 KiB

Open AccessArticle

Methods of Wood Volume Determining and Its Implications for Forest Transport

by Tadeusz Moskalik, Łukasz Tymendorf, Jan van der Saar and Grzegorz Trzciński

Sensors 2022, 22(16), 6028; https://doi.org/10.3390/s22166028 - 12 Aug 2022

Cited by 14 | Viewed by 4582

Abstract

Proper measurements are extremely significant for the forest owner, the harvesting company, the hauler, the final buyer, and the wood processing company. The accuracy of round wood volume determination is of fundamental importance in planning and accounting for individual processes related to the [...] Read more.

Proper measurements are extremely significant for the forest owner, the harvesting company, the hauler, the final buyer, and the wood processing company. The accuracy of round wood volume determination is of fundamental importance in planning and accounting for individual processes related to the wood trade. It is the basis for determining the maximum quantity in single load of wood that allows for using the permissible total gross vehicle weight. The determination of wood load in cubic meters does not allow unequivocally determining its weight, which often leads to overloading of vehicles. This paper presents a comparison of the photo-optical method for determining the volume of wood to be transported with the real measurement and determination of the weight of a load and the total gross vehicle weight (GVW) with the simultaneous application of conversion factors determining the weight of the load from the volume of wood. The measurement included 23 broadleaf round wood piles (193.73 m³) and 14 coniferous round wood piles (149.23 m³). The measurement error for broadleaf wood piles ranges from −47.67% to 63.16%, and from −43.31% to 24.72% for coniferous wood piles. Determination of the volume of a broadleaf wood pile using the iFOVEA method had an average error of 1.34%, while the Timbeter method had an average error of −1.83%. In the coniferous wood pile measurement, the error is −12.82% and 2.41%, respectively. Verification of the volume of the large-sized wood indicated on the delivery note (reference value) on the log sorting line (by laser scanning) showed larger volumes by 0.10 m³ to 2.54 m³, giving a percentage error of 0.35% and 8.62%, respectively. As a consequence of the application of such methods for determining the weight of wood loads, the transport truck sets are often significantly overloaded, which has a significant impact on the accelerated degradation of roads and safety in traffic and timber transportation. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

32 pages, 19977 KiB

Open AccessArticle

Real-Time Efficient FPGA Implementation of the Multi-Scale Lucas-Kanade and Horn-Schunck Optical Flow Algorithms for a 4K Video Stream

by Krzysztof Blachut and Tomasz Kryjak

Sensors 2022, 22(13), 5017; https://doi.org/10.3390/s22135017 - 3 Jul 2022

Cited by 16 | Viewed by 4533

Abstract

The information about optical flow, i.e., the movement of pixels between two consecutive images from a video sequence, is used in many vision systems, both classical and those based on deep neural networks. In some robotic applications, e.g., in autonomous vehicles, it is [...] Read more.

The information about optical flow, i.e., the movement of pixels between two consecutive images from a video sequence, is used in many vision systems, both classical and those based on deep neural networks. In some robotic applications, e.g., in autonomous vehicles, it is necessary to calculate the flow in real time. This represents a challenging task, especially for high-resolution video streams. In this work, two gradient-based algorithms—Lucas–Kanade and Horn–Schunck—were implemented on a ZCU 104 platform with Xilinx Zynq UltraScale+ MPSoC FPGA. A vector data format was used to enable flow calculation for a 4K (Ultra HD, 3840 × 2160 pixels) video stream at 60 fps. In order to detect larger pixel displacements, a multi-scale approach was used in both algorithms. Depending on the scale, the calculations were performed for different data formats, allowing for more efficient processing by reducing resource utilisation. The presented solution allows real-time optical flow determination in multiple scales for a 4K resolution with estimated energy consumption below 6 W. The algorithms realised in this work can be a component of a larger vision system in advanced surveillance systems or autonomous vehicles. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

22 pages, 2177 KiB

Open AccessArticle

Hierarchical Novelty Detection for Traffic Sign Recognition

by Idoia Ruiz and Joan Serrat

Sensors 2022, 22(12), 4389; https://doi.org/10.3390/s22124389 - 10 Jun 2022

Cited by 3 | Viewed by 2518

Abstract

Recent works have made significant progress in novelty detection, i.e., the problem of detecting samples of novel classes, never seen during training, while classifying those that belong to known classes. However, the only information this task provides about novel samples is that they [...] Read more.

Recent works have made significant progress in novelty detection, i.e., the problem of detecting samples of novel classes, never seen during training, while classifying those that belong to known classes. However, the only information this task provides about novel samples is that they are unknown. In this work, we leverage hierarchical taxonomies of classes to provide informative outputs for samples of novel classes. We predict their closest class in the taxonomy, i.e., its parent class. We address this problem, known as hierarchical novelty detection, by proposing a novel loss, namely Hierarchical Cosine Loss that is designed to learn class prototypes along with an embedding of discriminative features consistent with the taxonomy. We apply it to traffic sign recognition, where we predict the parent class semantics for new types of traffic signs. Our model beats state-of-the art approaches on two large scale traffic sign benchmarks, Mapillary Traffic Sign Dataset (MTSD) and Tsinghua-Tencent 100K (TT100K), and performs similarly on natural images benchmarks (AWA2, CUB). For TT100K and MTSD, our approach is able to detect novel samples at the correct nodes of the hierarchy with 81% and 36% of accuracy, respectively, at 80% known class accuracy. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

13 pages, 6568 KiB

Open AccessArticle

Fabrication and Performance Evolution of AgNP Interdigitated Electrode Touch Sensor for Automotive Infotainment

by K. P. Srinivasan and T. Muthuramalingam

Sensors 2021, 21(23), 7961; https://doi.org/10.3390/s21237961 - 29 Nov 2021

Cited by 14 | Viewed by 2911

Abstract

In the present scenario, a considerable assiduity is provided to develop novel human-machine interface technologies that rapidly outpace the capabilities of display technology in automotive industries. It is necessary to use a new cockpit design in conjunction with a fully automated driving environment [...] Read more.

In the present scenario, a considerable assiduity is provided to develop novel human-machine interface technologies that rapidly outpace the capabilities of display technology in automotive industries. It is necessary to use a new cockpit design in conjunction with a fully automated driving environment in order to enhance the driving experience. It can create a seamless and futuristic dashboard for automotive infotainment application. In the present study, an endeavor was made to equip the In-vehicle bezels with printed capacitive sensors for providing superior sensing capabilities. Silver Nanoparticles based interdigitated pattern electrodes were formed over polycarbonate substrates to make printed capacitive sensors using screen printing process. The developed sensor was investigated to evaluate the qualitative and quantitative measures using direct and in-direct contact of touch. The proposed approach for sensors pattern and fabrication can highly impact on sensor performance in automotive infotainment application due to the excellent spatial interpolation with lower cost, light weight, and mechanical flexibility. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

21 pages, 5600 KiB

Open AccessArticle

Performance of Mobile LiDAR in Real Road Driving Conditions

by Jisoo Kim, Bum-jin Park, Chang-gyun Roh and Youngmin Kim

Sensors 2021, 21(22), 7461; https://doi.org/10.3390/s21227461 - 10 Nov 2021

Cited by 17 | Viewed by 3389

Abstract

The performance of LiDAR sensors deteriorates under adverse weather conditions such as rainfall. However, few studies have empirically analyzed this phenomenon. Hence, we investigated differences in sensor data due to environmental changes (distance from objects (road signs), object material, vehicle (sensor) speed, and [...] Read more.

The performance of LiDAR sensors deteriorates under adverse weather conditions such as rainfall. However, few studies have empirically analyzed this phenomenon. Hence, we investigated differences in sensor data due to environmental changes (distance from objects (road signs), object material, vehicle (sensor) speed, and amount of rainfall) during LiDAR sensing of road facilities. The indicators used to verify the performance of LiDAR were numbers of point cloud (NPC) and intensity. Differences in the indicators were tested through a two-way ANOVA. First, both NPC and intensity increased with decreasing distance. Second, despite some exceptions, changes in speed did not affect the indicators. Third, the values of NPC do not differ depending on the materials and the intensity of each material followed the order aluminum > steel > plastic > wood, although exceptions were found. Fourth, with an increase in rainfall, both indicators decreased for all materials; specifically, under rainfall of 40 mm/h or more, a substantial reduction was observed. These results demonstrate that LiDAR must overcome the challenges posed by inclement weather to be applicable in the production of road facilities that improve the effectiveness of autonomous driving sensors. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

21 pages, 12973 KiB

Open AccessArticle

Analysis of the Possibility to Detect Road Vehicles via Bluetooth Technology

by Răzvan Andrei Gheorghiu, Valentin Iordache and Angel Ciprian Cormoș

Sensors 2021, 21(21), 7281; https://doi.org/10.3390/s21217281 - 1 Nov 2021

Cited by 5 | Viewed by 3413

Abstract

As road traffic networks become more congested and information systems are implemented to manage traffic flows, real-time data gathering becomes increasingly important. Classic detectors are placed in one point of the network and are able to provide information only from that area. As [...] Read more.

As road traffic networks become more congested and information systems are implemented to manage traffic flows, real-time data gathering becomes increasingly important. Classic detectors are placed in one point of the network and are able to provide information only from that area. As useful as this is, it lacks the big picture of the routes the vehicles usually travel. There are applications developed to help individuals make their way into the road network, but these are no solutions that deal with the cause of traffic; rather, they counteract the effects. It becomes obvious that a proper management system, with knowledge of all the relevant aspects will better serve all travelers. The detection solution proposed in this paper is based on Bluetooth detectors. This system is able to match detected devices in the road network, filter the results, and generate a vehicle count that is proved to follow RADAR detection results. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

15 pages, 4187 KiB

Open AccessArticle

Technical Proposal for Monitoring Thermal and Mechanical Stresses of a Runway Pavement

by Salvatore Bruno, Giulia Del Serrone, Paola Di Mascio, Giuseppe Loprencipe, Eugenio Ricci and Laura Moretti

Sensors 2021, 21(20), 6797; https://doi.org/10.3390/s21206797 - 13 Oct 2021

Cited by 14 | Viewed by 3105

Abstract

Airport pavements should ensure regular and safe movements during their service life; the management body has to monitor the functional and structural characteristics, and schedule maintenance work, balancing the often conflicting goals of safety, economic and technical issues. This paper presents a remote [...] Read more.

Airport pavements should ensure regular and safe movements during their service life; the management body has to monitor the functional and structural characteristics, and schedule maintenance work, balancing the often conflicting goals of safety, economic and technical issues. This paper presents a remote monitoring system to evaluate the structural performance of a runway composed of concrete thresholds and a flexible central runway. Thermometers, strain gauges, and pressure cells will be embedded at different depths to continuously monitor the pavement’s response to traffic and environmental loads. An innovative system allows data acquisition and processing with specific calculation models, in order to inform the infrastructure manager, in real time, about the actual conditions of the pavement. In this way, the authors aim to develop a system that provides useful information for the correct implementation of an airport pavement management system (APMS) based on real-life data. Indeed, it permits comprehensive monitoring functions to be performed, based on the embedded sensing network. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

22 pages, 8925 KiB

Open AccessArticle

Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM

by Tomasz Nowak, Krzysztof Ćwian and Piotr Skrzypczyński

Sensors 2021, 21(20), 6781; https://doi.org/10.3390/s21206781 - 13 Oct 2021

Cited by 4 | Viewed by 3382

Abstract

This article aims at demonstrating the feasibility of modern deep learning techniques for the real-time detection of non-stationary objects in point clouds obtained from 3-D light detecting and ranging (LiDAR) sensors. The motion segmentation task is considered in the application context of automotive [...] Read more.

This article aims at demonstrating the feasibility of modern deep learning techniques for the real-time detection of non-stationary objects in point clouds obtained from 3-D light detecting and ranging (LiDAR) sensors. The motion segmentation task is considered in the application context of automotive Simultaneous Localization and Mapping (SLAM), where we often need to distinguish between the static parts of the environment with respect to which we localize the vehicle, and non-stationary objects that should not be included in the map for localization. Non-stationary objects do not provide repeatable readouts, because they can be in motion, like vehicles and pedestrians, or because they do not have a rigid, stable surface, like trees and lawns. The proposed approach exploits images synthesized from the received intensity data yielded by the modern LiDARs along with the usual range measurements. We demonstrate that non-stationary objects can be detected using neural network models trained with 2-D grayscale images in the supervised or unsupervised training process. This concept makes it possible to alleviate the lack of large datasets of 3-D laser scans with point-wise annotations for non-stationary objects. The point clouds are filtered using the corresponding intensity images with labeled pixels. Finally, we demonstrate that the detection of non-stationary objects using our approach improves the localization results and map consistency in a laser-based SLAM system. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

32 pages, 12026 KiB

Open AccessArticle

Railroad Turnout Wear Diagnostics

by Jerzy Kisilowski and Rafał Kowalik

Sensors 2021, 21(20), 6697; https://doi.org/10.3390/s21206697 - 9 Oct 2021

Cited by 16 | Viewed by 5490

Abstract

The article presents a few issues related to the technical condition of a railway turnout, an important element of the railway network where about 90% of railway accidents occur. In the first part of the article, the results of railway turnout wear are [...] Read more.

The article presents a few issues related to the technical condition of a railway turnout, an important element of the railway network where about 90% of railway accidents occur. In the first part of the article, the results of railway turnout wear are presented. A comparison of normal forces (in wheel–rail contact) in vehicle traffic on straight track without a turnout and normal forces occurring when a rail vehicle passes a turnout is presented. Then, turnout wear processes for selected speeds are presented. In the next part of the paper, the possibilities of using a vision system are presented, which, in combination with tools for image processing analysis, makes it possible to detect wear and distances between the key elements of a railway turnout. The main idea of the proposed online diagnostic system solution is to use the analysis of received images (photos) with the help of a vision system. The basic problem to be solved in the proposed system was to develop algorithms responsible for generating wear areas from high-resolution images. The algorithms created within the work were implemented and tested in the MATLAB software environment. The presented method is an original procedure for diagnosing turnout elements for each time instant. The proposed system is compatible with railway traffic control systems. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

29 pages, 13331 KiB

Open AccessArticle

A Novel Kalman Filter Design and Analysis Method Considering Observability and Dominance Properties of Measurands Applied to Vehicle State Estimation

by Julian Ruggaber and Jonathan Brembeck

Sensors 2021, 21(14), 4750; https://doi.org/10.3390/s21144750 - 12 Jul 2021

Cited by 14 | Viewed by 4005

Abstract

In Kalman filter design, the filter algorithm and prediction model design are the most discussed topics in research. Another fundamental but less investigated issue is the careful selection of measurands and their contribution to the estimation problem. This is often done purely on [...] Read more.

In Kalman filter design, the filter algorithm and prediction model design are the most discussed topics in research. Another fundamental but less investigated issue is the careful selection of measurands and their contribution to the estimation problem. This is often done purely on the basis of empirical values or by experiments. This paper presents a novel holistic method to design and assess Kalman filters in an automated way and to perform their analysis based on quantifiable parameters. The optimal filter parameters are computed with the help of a nonlinear optimization algorithm. To determine and analyze an optimal filter design, two novel quantitative nonlinear observability measures are presented along with a method to quantify the dominance contribution of a measurand to an estimate. As a result, different filter configurations can be specifically investigated and compared with respect to the selection of measurands and their influence on the estimation. An unscented Kalman filter algorithm is used to demonstrate the method’s capabilities to design and analyze the estimation problem parameters. For this purpose, an example of a vehicle state estimation with a focus on the tire-road friction coefficient is used, which represents a challenging problem for classical analysis and filter parameterization. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

31 pages, 3006 KiB

Open AccessArticle

Large-Scale LiDAR SLAM with Factor Graph Optimization on High-Level Geometric Features

by Krzysztof Ćwian, Michał R. Nowicki, Jan Wietrzykowski and Piotr Skrzypczyński

Sensors 2021, 21(10), 3445; https://doi.org/10.3390/s21103445 - 15 May 2021

Cited by 17 | Viewed by 6020

Abstract

Although visual SLAM (simultaneous localization and mapping) methods obtain very accurate results using optimization of residual errors defined with respect to the matching features, the SLAM systems based on 3-D laser (LiDAR) data commonly employ variants of the iterative closest points algorithm and [...] Read more.

Although visual SLAM (simultaneous localization and mapping) methods obtain very accurate results using optimization of residual errors defined with respect to the matching features, the SLAM systems based on 3-D laser (LiDAR) data commonly employ variants of the iterative closest points algorithm and raw point clouds as the map representation. However, it is possible to extract from point clouds features that are more spatially extended and more meaningful than points: line segments and/or planar patches. In particular, such features provide a natural way to represent human-made environments, such as urban and mixed indoor/outdoor scenes. In this paper, we perform an analysis of the advantages of a LiDAR-based SLAM that employs high-level geometric features in large-scale urban environments. We present a new approach to the LiDAR SLAM that uses planar patches and line segments for map representation and employs factor graph optimization typical to state-of-the-art visual SLAM for the final map and trajectory optimization. The new map structure and matching of features make it possible to implement in our system an efficient loop closure method, which exploits learned descriptors for place recognition and factor graph for optimization. With these improvements, the overall software structure is based on the proven LOAM concept to ensure real-time operation. A series of experiments were performed to compare the proposed solution to the open-source LOAM, considering different approaches to loop closure computation. The results are compared using standard metrics of trajectory accuracy, focusing on the final quality of the estimated trajectory and the consistency of the environment map. With some well-discussed reservations, our results demonstrate the gains due to using the high-level features in the full-optimization approach in the large-scale LiDAR SLAM. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

21 pages, 9397 KiB

Open AccessArticle

LiDAR Point Cloud Generation for SLAM Algorithm Evaluation

by Łukasz Sobczak, Katarzyna Filus, Adam Domański and Joanna Domańska

Sensors 2021, 21(10), 3313; https://doi.org/10.3390/s21103313 - 11 May 2021

Cited by 22 | Viewed by 7465

Abstract

With the emerging interest in the autonomous driving level at 4 and 5 comes a necessity to provide accurate and versatile frameworks to evaluate the algorithms used in autonomous vehicles. There is a clear gap in the field of autonomous driving simulators. It [...] Read more.

With the emerging interest in the autonomous driving level at 4 and 5 comes a necessity to provide accurate and versatile frameworks to evaluate the algorithms used in autonomous vehicles. There is a clear gap in the field of autonomous driving simulators. It covers testing and parameter tuning of a key component of autonomous driving systems, SLAM, frameworks targeting off-road and safety-critical environments. It also includes taking into consideration the non-idealistic nature of the real-life sensors, associated phenomena and measurement errors. We created a LiDAR simulator that delivers accurate 3D point clouds in real time. The point clouds are generated based on the sensor placement and the LiDAR type that can be set using configurable parameters. We evaluate our solution based on comparison of the results using an actual device, Velodyne VLP-16, on real-life tracks and the corresponding simulations. We measure the error values obtained using Google Cartographer SLAM algorithm and the distance between the simulated and real point clouds to verify their accuracy. The results show that our simulation (which incorporates measurement errors and the rolling shutter effect) produces data that can successfully imitate the real-life point clouds. Due to dedicated mechanisms, it is compatible with the Robotic Operating System (ROS) and can be used interchangeably with data from actual sensors, which enables easy testing, SLAM algorithm parameter tuning and deployment. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

15 pages, 1903 KiB

Open AccessArticle

Measuring Kinematic Viscosity of Engine Oils: A Comparison of Data Obtained from Four Different Devices

by Artur Wolak, Grzegorz Zając and Tomasz Słowik

Sensors 2021, 21(7), 2530; https://doi.org/10.3390/s21072530 - 4 Apr 2021

Cited by 15 | Viewed by 5280

Abstract

The aim of this paper is to compare the results of kinematic viscosity of lubricating oils measurements at 40 °C, obtained with three different rapid evaluation devices, and the standardized method using an Ubbelohde Capillary viscometer. The following instruments were selected to measure: [...] Read more.

The aim of this paper is to compare the results of kinematic viscosity of lubricating oils measurements at 40 °C, obtained with three different rapid evaluation devices, and the standardized method using an Ubbelohde Capillary viscometer. The following instruments were selected to measure: a mid-FTIR spectrophotometer, a microchannel viscometer, and a Stabinger viscometer. The study material comprised 42 fresh engine oils, all of which are commercially available. The main data analysis tools used in the study were multiple regression, Mahala Nobis distance, post-hoc analysis, and the Wilcoxon signed-rank test with the Bonferroni correction. Consistent outcomes were obtained for the Stabinger viscometer only, whereas the microchannel viscometer and the mid-FTIR spectrophotometer were not as precise as the reference method. It was also found that the results obtained with the use of the mid-FTIR spectrophotometer were burdened with a very large measurement error. Therefore, a very careful approach is suggested when choosing these instruments. The study fills an important gap in empirical research in the context of the reliability of measurement results obtained using various research techniques. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

25 pages, 2137 KiB

Open AccessArticle

Mini-AUV Hydrodynamic Parameters Identification via CFD Simulations and Their Application on Control Performance Evaluation

by José J. Castillo-Zamora, Karla A. Camarillo-Gómez, Gerardo I. Pérez-Soto, Juvenal Rodríguez-Reséndiz and Luis A. Morales-Hernández

Sensors 2021, 21(3), 820; https://doi.org/10.3390/s21030820 - 26 Jan 2021

Cited by 18 | Viewed by 3826

Abstract

This manuscript presents a fully detailed methodology in order to identify the hydrodynamic parameters of a mini autonomous underwater vehicle (mini-AUV) and evaluate its performance using different controllers. The methodology consists of close-to-reality simulation using a Computed Fluid Dynamics (CFD) module of the [...] Read more.

This manuscript presents a fully detailed methodology in order to identify the hydrodynamic parameters of a mini autonomous underwater vehicle (mini-AUV) and evaluate its performance using different controllers. The methodology consists of close-to-reality simulation using a Computed Fluid Dynamics (CFD) module of the ANSYS™ Workbench software, the processing of the data, obtained by simulation, with a set of Savistky–Golay filters; and, the application of the Least Square Method in order to estimate the hydrodynamic parameters of the mini-AUV. Finally, these parameters are considered to design the three different controllers that are based on the robot manipulators theory. Numerical simulations are carried out to evaluate the performance of the controllers. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

25 pages, 3186 KiB

Open AccessArticle

Comparative Analysis of Kinect-Based and Oculus-Based Gaze Region Estimation Methods in a Driving Simulator

by David González-Ortega, Francisco Javier Díaz-Pernas, Mario Martínez-Zarzuela and Míriam Antón-Rodríguez

Sensors 2021, 21(1), 26; https://doi.org/10.3390/s21010026 - 23 Dec 2020

Cited by 10 | Viewed by 3073

Abstract

Driver’s gaze information can be crucial in driving research because of its relation to driver attention. Particularly, the inclusion of gaze data in driving simulators broadens the scope of research studies as they can relate drivers’ gaze patterns to their features and performance. [...] Read more.

Driver’s gaze information can be crucial in driving research because of its relation to driver attention. Particularly, the inclusion of gaze data in driving simulators broadens the scope of research studies as they can relate drivers’ gaze patterns to their features and performance. In this paper, we present two gaze region estimation modules integrated in a driving simulator. One uses the 3D Kinect device and another uses the virtual reality Oculus Rift device. The modules are able to detect the region, out of seven in which the driving scene was divided, where a driver is gazing at in every route processed frame. Four methods were implemented and compared for gaze estimation, which learn the relation between gaze displacement and head movement. Two are simpler and based on points that try to capture this relation and two are based on classifiers such as MLP and SVM. Experiments were carried out with 12 users that drove on the same scenario twice, each one with a different visualization display, first with a big screen and later with Oculus Rift. On the whole, Oculus Rift outperformed Kinect as the best hardware for gaze estimation. The Oculus-based gaze region estimation method with the highest performance achieved an accuracy of 97.94%. The information provided by the Oculus Rift module enriches the driving simulator data and makes it possible a multimodal driving performance analysis apart from the immersion and realism obtained with the virtual reality experience provided by Oculus. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

Review

Jump to: Research

27 pages, 2623 KiB

Open AccessReview

Research Scenarios of Autonomous Vehicles, the Sensors and Measurement Systems Used in Experiments

by Leon Prochowski, Patryk Szwajkowski and Mateusz Ziubiński

Sensors 2022, 22(17), 6586; https://doi.org/10.3390/s22176586 - 31 Aug 2022

Cited by 9 | Viewed by 4444

Abstract

Automated and autonomous vehicles are in an intensive development phase. It is a phase that requires a lot of modelling and experimental research. Experimental research into these vehicles is in its initial state. There is a lack of findings and standardized recommendations for [...] Read more.

Automated and autonomous vehicles are in an intensive development phase. It is a phase that requires a lot of modelling and experimental research. Experimental research into these vehicles is in its initial state. There is a lack of findings and standardized recommendations for the organization and creation of research scenarios. There are also many difficulties in creating research scenarios. The main difficulties are the large number of systems for simultaneous checking. Additionally, the vehicles have a very complicated structure. A review of current publications allowed for systematization of the research scenarios of vehicles and their components as well as the measurement systems used. These include perception systems, automated response to threats, and critical situations in the area of road safety. The scenarios analyzed ensure that the planned research tasks can be carried out, including the investigation of systems that enable autonomous driving. This study uses passenger cars equipped with highly sophisticated sensor systems and localization devices. Perception systems are the necessary equipment during the conducted study. They provide recognition of the environment, mainly through vision sensors (cameras) and lidars. The research tasks include autonomous driving along a detected road lane on a curvilinear track. The effective maintenance of the vehicle in this lane is assessed. The location used in the study is a set of specialized research tracks on which stationary or moving obstacles are often placed. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

19 pages, 1352 KiB

Open AccessReview

Trends and Future Prospects of the Drowsiness Detection and Estimation Technology

by Toshiya Arakawa

Sensors 2021, 21(23), 7921; https://doi.org/10.3390/s21237921 - 27 Nov 2021

Cited by 29 | Viewed by 8698

Abstract

Drowsiness is among the important factors that cause traffic accidents; therefore, a monitoring system is necessary to detect the state of a driver’s drowsiness. Driver monitoring systems usually detect three types of information: biometric information, vehicle behavior, and driver’s graphic information. This review [...] Read more.

Drowsiness is among the important factors that cause traffic accidents; therefore, a monitoring system is necessary to detect the state of a driver’s drowsiness. Driver monitoring systems usually detect three types of information: biometric information, vehicle behavior, and driver’s graphic information. This review summarizes the research and development trends of drowsiness detection systems based on various methods. Drowsiness detection methods based on the three types of information are discussed. A prospect for arousal level detection and estimation technology for autonomous driving is also presented. In the case of autonomous driving levels 4 and 5, where the driver is not the primary driving agent, the technology will not be used to detect and estimate wakefulness for accident prevention; rather, it can be used to ensure that the driver has enough sleep to arrive comfortably at the destination. Full article

(This article belongs to the Special Issue Advance in Sensors and Sensing Systems for Driving and Transportation: Part B)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advance in Sensors and Sensing Systems for Driving and Transportation: Part B

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (21 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI