Sensors

Editorial

Jump to: Research, Other

4 pages, 191 KiB

Open AccessEditorial

Advances in Intelligent Vehicle Control

by Juan A. Cabrera

Sensors 2022, 22(22), 8622; https://doi.org/10.3390/s22228622 - 09 Nov 2022

Cited by 1 | Viewed by 1163

Abstract

Advanced intelligent vehicle control systems have evolved in the last few decades thanks to the use of artificial-intelligence-based techniques, the appearance of new sensors, and the development of technology necessary for their implementation [...] Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

Research

Jump to: Editorial, Other

19 pages, 5842 KiB

Open AccessArticle

Service-Centric Heterogeneous Vehicular Network Modeling for Connected Traffic Environments

by Ahmad M. Khasawneh, Mamoun Abu Helou, Aanchal Khatri, Geetika Aggarwal, Omprakash Kaiwartya, Maryam Altalhi, Waheeb Abu-ulbeh and Rabah AlShboul

Sensors 2022, 22(3), 1247; https://doi.org/10.3390/s22031247 - 07 Feb 2022

Cited by 15 | Viewed by 2428

Abstract

Heterogeneous vehicular communication on the Internet of connected vehicle (IoV) environment is an emerging research theme toward achieving smart transportation. It is an evolution of the existing vehicular ad hoc network architecture due to the increasingly heterogeneous nature of the various existing networks [...] Read more.

Heterogeneous vehicular communication on the Internet of connected vehicle (IoV) environment is an emerging research theme toward achieving smart transportation. It is an evolution of the existing vehicular ad hoc network architecture due to the increasingly heterogeneous nature of the various existing networks in road traffic environments that need to be integrated. The existing literature on vehicular communication is lacking in the area of network optimization for heterogeneous network environments. In this context, this paper proposes a heterogeneous network model for IoV and service-oriented network optimization. The network model focuses on three key networking entities: vehicular cloud, heterogeneous communication, and smart use cases as clients. Most traffic-related data–oriented computations are performed at cloud servers for making intelligent decisions. The connection component enables handoff-centric network communication in heterogeneous vehicular environments. The use-case-oriented smart traffic services are implemented as clients for the network model. The model is tested for various service-oriented metrics in heterogeneous vehicular communication environments with the aim of affirming several service benefits. Future challenges and issues in heterogeneous IoV environments are also highlighted. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

15 pages, 3393 KiB

Open AccessArticle

Overcoming Challenges of Applying Reinforcement Learning for Intelligent Vehicle Control

by Rafael Pina, Haileleol Tibebu, Joosep Hook, Varuna De Silva and Ahmet Kondoz

Sensors 2021, 21(23), 7829; https://doi.org/10.3390/s21237829 - 25 Nov 2021

Cited by 6 | Viewed by 2125

Abstract

Reinforcement learning (RL) is a booming area in artificial intelligence. The applications of RL are endless nowadays, ranging from fields such as medicine or finance to manufacturing or the gaming industry. Although multiple works argue that RL can be key to a great [...] Read more.

Reinforcement learning (RL) is a booming area in artificial intelligence. The applications of RL are endless nowadays, ranging from fields such as medicine or finance to manufacturing or the gaming industry. Although multiple works argue that RL can be key to a great part of intelligent vehicle control related problems, there are many practical problems that need to be addressed, such as safety related problems that can result from non-optimal training in RL. For instance, for an RL agent to be effective it should first cover all the situations during training that it may face later. This is often difficult when applied to the real-world. In this work we investigate the impact of RL applied to the context of intelligent vehicle control. We analyse the implications of RL in path planning tasks and we discuss two possible approaches to overcome the gap between the theorical developments of RL and its practical applications. Specifically, firstly this paper discusses the role of Curriculum Learning (CL) to structure the learning process of intelligent vehicle control in a gradual way. The results show how CL can play an important role in training agents in such context. Secondly, we discuss a method of transferring RL policies from simulation to reality in order to make the agent experience situations in simulation, so it knows how to react to them in reality. For that, we use Arduino Yún controlled robots as our platforms. The results enhance the effectiveness of the presented approach and show how RL policies can be transferred from simulation to reality even when the platforms are resource limited. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

22 pages, 4860 KiB

Open AccessArticle

On–Off Scheduling for Electric Vehicle Charging in Two-Links Charging Stations Using Binary Optimization Approaches

by Rafał Zdunek, Andrzej Grobelny, Jerzy Witkowski and Radosław Igor Gnot

Sensors 2021, 21(21), 7149; https://doi.org/10.3390/s21217149 - 28 Oct 2021

Cited by 4 | Viewed by 1968

Abstract

In this study, we deal with the problem of scheduling charging periods of electrical vehicles (EVs) to satisfy the users’ demands for energy consumption as well as to optimally utilize the available power. We assume three-phase EV charging stations, each equipped with two [...] Read more.

In this study, we deal with the problem of scheduling charging periods of electrical vehicles (EVs) to satisfy the users’ demands for energy consumption as well as to optimally utilize the available power. We assume three-phase EV charging stations, each equipped with two charging ports (links) that can serve up to two EVs in the scheduling period but not simultaneously. Considering such a specification, we propose an on–off scheduling scheme wherein control over an energy flow is achieved by flexibly switching the ports in each station on and off in a manner such as to satisfy the energy demand of each EV, flatten the high energy-consuming load on the whole farm, and to minimize the number of switching operations. To satisfy these needs, the on–off scheduling scheme is formulated in terms of a binary linear programming problem, which is then extended to a quadratic version to incorporate the smoothness constraints. Various algorithmic approaches are used for solving a binary quadratic programming problem, including the Frank–Wolfe algorithm and successive linear approximations. The numerical simulations demonstrate that the latter is scalable, efficient, and flexible in a charging procedure, and it shaves the load peak while maintaining smooth charging profiles. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

21 pages, 3789 KiB

Open AccessArticle

Roll Angle Estimation of a Motorcycle through Inertial Measurements

by Diego Maceira, Alberto Luaces, Urbano Lugrís, Miguel Á. Naya and Emilio Sanjurjo

Sensors 2021, 21(19), 6626; https://doi.org/10.3390/s21196626 - 05 Oct 2021

Cited by 8 | Viewed by 5527

Abstract

Currently, the interest in creating autonomous driving vehicles and progressively more sophisticated active safety systems is growing enormously, being a prevailing importance factor for the end user when choosing between either one or another commercial vehicle model. While four-wheelers are ahead in the [...] Read more.

Currently, the interest in creating autonomous driving vehicles and progressively more sophisticated active safety systems is growing enormously, being a prevailing importance factor for the end user when choosing between either one or another commercial vehicle model. While four-wheelers are ahead in the adoption of these systems, the development for two-wheelers is beginning to gain importance within the sector. This makes sense, since the vulnerability for the driver is much higher in these vehicles compared to traditional four-wheelers. The particular dynamics and stability that govern the behavior of single-track vehicles (STVs) make the task of designing active control systems, such as Anti-lock Braking System (ABS) systems or active or semi-active suspension systems, particularly challenging. The roll angle can achieve high values, which greatly affects the general behavior of the vehicle. Therefore, it is a magnitude of the utmost importance; however, its accurate measurement or estimation is far from trivial. This work is based on a previous paper, in which a roll angle estimator based on the Kalman filter was presented and tested on an instrumented bicycle. In this work, a further refinement of the method is proposed, and it is tested in more challenging situations using the multibody model of a motorcycle. Moreover, an extension of the method is also presented to improve the way noise is modeled within this Kalman filter. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

15 pages, 3111 KiB

Open AccessArticle

Semantics Aware Dynamic SLAM Based on 3D MODT

by Muhammad Sualeh and Gon-Woo Kim

Sensors 2021, 21(19), 6355; https://doi.org/10.3390/s21196355 - 23 Sep 2021

Cited by 9 | Viewed by 2321

Abstract

The idea of SLAM (Simultaneous Localization and Mapping) being a solved problem revolves around the static world assumption, even though autonomous systems are gaining environmental perception capabilities by exploiting the advances in computer vision and data-driven approaches. The computational demands and time complexities [...] Read more.

The idea of SLAM (Simultaneous Localization and Mapping) being a solved problem revolves around the static world assumption, even though autonomous systems are gaining environmental perception capabilities by exploiting the advances in computer vision and data-driven approaches. The computational demands and time complexities remain the main impediment in the effective fusion of the paradigms. In this paper, a framework to solve the dynamic SLAM problem is proposed. The dynamic regions of the scene are handled by making use of Visual-LiDAR based MODT (Multiple Object Detection and Tracking). Furthermore, minimal computational demands and real-time performance are ensured. The framework is tested on the KITTI Datasets and evaluated against the publicly available evaluation tools for a fair comparison with state-of-the-art SLAM algorithms. The results suggest that the proposed dynamic SLAM framework can perform in real-time with budgeted computational resources. In addition, the fused MODT provides rich semantic information that can be readily integrated into SLAM. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

18 pages, 3377 KiB

Open AccessArticle

Advanced Driver Assistance Systems (ADAS) Based on Machine Learning Techniques for the Detection and Transcription of Variable Message Signs on Roads

by Gonzalo De-Las-Heras, Javier Sánchez-Soriano and Enrique Puertas

Sensors 2021, 21(17), 5866; https://doi.org/10.3390/s21175866 - 31 Aug 2021

Cited by 19 | Viewed by 6827

Abstract

Among the reasons for traffic accidents, distractions are the most common. Although there are many traffic signs on the road that contribute to safety, variable message signs (VMSs) require special attention, which is transformed into distraction. ADAS (advanced driver assistance system) devices are [...] Read more.

Among the reasons for traffic accidents, distractions are the most common. Although there are many traffic signs on the road that contribute to safety, variable message signs (VMSs) require special attention, which is transformed into distraction. ADAS (advanced driver assistance system) devices are advanced systems that perceive the environment and provide assistance to the driver for his comfort or safety. This project aims to develop a prototype of a VMS (variable message sign) reading system using machine learning techniques, which are still not used, especially in this aspect. The assistant consists of two parts: a first one that recognizes the signal on the street and another one that extracts its text and transforms it into speech. For the first one, a set of images were labeled in PASCAL VOC format by manual annotations, scraping and data augmentation. With this dataset, the VMS recognition model was trained, a RetinaNet based off of ResNet50 pretrained on the dataset COCO. Firstly, in the reading process, the images were preprocessed and binarized to achieve the best possible quality. Finally, the extraction was done by the Tesseract OCR model in its 4.0 version, and the speech was done by the cloud service of IBM Watson Text to Speech. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

17 pages, 15246 KiB

Open AccessCommunication

A Redundant Configuration of Four Low-Cost GNSS-RTK Receivers for Reliable Estimation of Vehicular Position and Posture

by Jesús Morales, Jorge L. Martínez and Alfonso J. García-Cerezo

Sensors 2021, 21(17), 5853; https://doi.org/10.3390/s21175853 - 30 Aug 2021

Cited by 3 | Viewed by 2039

Abstract

This paper proposes a low-cost sensor system composed of four GNSS-RTK receivers to obtain accurate position and posture estimations for a vehicle in real-time. The four antennas of the receivers are placed so that every three-antennas combination is optimal to get the most [...] Read more.

This paper proposes a low-cost sensor system composed of four GNSS-RTK receivers to obtain accurate position and posture estimations for a vehicle in real-time. The four antennas of the receivers are placed so that every three-antennas combination is optimal to get the most precise 3D coordinates with respect to a global reference system. The redundancy provided by the fourth receiver allows to improve estimations even more and to maintain accuracy when one of the receivers fails. A mini computer with the Robotic Operating System is responsible for merging all the available measurements reliably. Successful experiments have been carried out with a ground rover on irregular terrain. Angular estimates similar to those of a high-performance IMU have been achieved in dynamic tests. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

21 pages, 21286 KiB

Open AccessArticle

A Bidirectional Versatile Buck–Boost Converter Driver for Electric Vehicle Applications

by Catalina González-Castaño, Carlos Restrepo, Samir Kouro, Enric Vidal-Idiarte and Javier Calvente

Sensors 2021, 21(17), 5712; https://doi.org/10.3390/s21175712 - 25 Aug 2021

Cited by 11 | Viewed by 4171

Abstract

This work presents a novel dc-dc bidirectional buck–boost converter between a battery pack and the inverter to regulate the dc-bus in an electric vehicle (EV) powertrain. The converter is based on the versatile buck–boost converter, which has shown an excellent performance in different [...] Read more.

This work presents a novel dc-dc bidirectional buck–boost converter between a battery pack and the inverter to regulate the dc-bus in an electric vehicle (EV) powertrain. The converter is based on the versatile buck–boost converter, which has shown an excellent performance in different fuel cell systems operating in low-voltage and hard-switching applications. Therefore, extending this converter to higher voltage applications such as the EV is a challenging task reported in this work. A high-efficiency step-up/step-down versatile converter can improve the EV powertrain efficiency for an extended range of electric motor (EM) speeds, comprising urban and highway driving cycles while allowing the operation under motoring and regeneration (regenerative brake) conditions. DC-bus voltage regulation is implemented using a digital two-loop control strategy. The inner feedback loop is based on the discrete-time sliding-mode current control (DSMCC) strategy, and for the outer feedback loop, a proportional-integral (PI) control is employed. Both digital control loops and the necessary transition mode strategy are implemented using a digital signal controller TMS320F28377S. The theoretical analysis has been validated on a 400 V

1.6

kW prototype and tested through simulation and an EV powertrain system testing. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

21 pages, 3037 KiB

Open AccessArticle

Investigation on the Model-Based Control Performance in Vehicle Safety Critical Scenarios with Varying Tyre Limits

by Aleksandr Sakhnevych, Vincenzo Maria Arricale, Mattia Bruschetta, Andrea Censi, Enrico Mion, Enrico Picotti and Emilio Frazzoli

Sensors 2021, 21(16), 5372; https://doi.org/10.3390/s21165372 - 09 Aug 2021

Cited by 10 | Viewed by 2552

Abstract

In recent years the increasing needs of reducing the costs of car development expressed by the automotive market have determined a rapid development of virtual driver prototyping tools that aims at reproducing vehicle behaviors. Nevertheless, these advanced tools are still not designed to [...] Read more.

In recent years the increasing needs of reducing the costs of car development expressed by the automotive market have determined a rapid development of virtual driver prototyping tools that aims at reproducing vehicle behaviors. Nevertheless, these advanced tools are still not designed to exploit the entire vehicle dynamics potential, preferring to assure the minimum requirements in the worst possible operating conditions instead. Furthermore, their calibration is typically performed in a pre-defined strict range of operating conditions, established by specific regulations or OEM routines. For this reason, their performance can considerably decrease in particularly crucial safetycritical situations, where the environmental conditions (rain, snow, ice), the road singularities (oil stains, puddles, holes), and the tyre thermal and ageing phenomena can deeply affect the adherence potential. The objective of the work is to investigate the possibility of the physical model-based control to take into account the variations in terms of the dynamic behavior of the systems and of the boundary conditions. Different scenarios with specific tyre thermal and wear conditions have been tested on diverse road surfaces validating the designed model predictive control algorithm in a hardware-in-the-loop real-time environment and demonstrating the augmented reliability of an advanced virtual driver aware of available information concerning the tyre dynamic limits. The multidisciplinary proposal will provide a paradigm shift in the development of strategies and a solid breakthrough towards enhanced development of the driving automatization systems, unleashing the potential of physical modeling to the next level of vehicle control, able to exploit and to take into account the multi-physical tyre variations. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

23 pages, 2436 KiB

Open AccessArticle

Deep Transfer Learning Based Intrusion Detection System for Electric Vehicular Networks

by Sk. Tanzir Mehedi, Adnan Anwar, Ziaur Rahman and Kawsar Ahmed

Sensors 2021, 21(14), 4736; https://doi.org/10.3390/s21144736 - 11 Jul 2021

Cited by 51 | Viewed by 6069

Abstract

The Controller Area Network (CAN) bus works as an important protocol in the real-time In-Vehicle Network (IVN) systems for its simple, suitable, and robust architecture. The risk of IVN devices has still been insecure and vulnerable due to the complex data-intensive architectures which [...] Read more.

The Controller Area Network (CAN) bus works as an important protocol in the real-time In-Vehicle Network (IVN) systems for its simple, suitable, and robust architecture. The risk of IVN devices has still been insecure and vulnerable due to the complex data-intensive architectures which greatly increase the accessibility to unauthorized networks and the possibility of various types of cyberattacks. Therefore, the detection of cyberattacks in IVN devices has become a growing interest. With the rapid development of IVNs and evolving threat types, the traditional machine learning-based IDS has to update to cope with the security requirements of the current environment. Nowadays, the progression of deep learning, deep transfer learning, and its impactful outcome in several areas has guided as an effective solution for network intrusion detection. This manuscript proposes a deep transfer learning-based IDS model for IVN along with improved performance in comparison to several other existing models. The unique contributions include effective attribute selection which is best suited to identify malicious CAN messages and accurately detect the normal and abnormal activities, designing a deep transfer learning-based LeNet model, and evaluating considering real-world data. To this end, an extensive experimental performance evaluation has been conducted. The architecture along with empirical analyses shows that the proposed IDS greatly improves the detection accuracy over the mainstream machine learning, deep learning, and benchmark deep transfer learning models and has demonstrated better performance for real-time IVN security. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

Other

Jump to: Editorial, Research

16 pages, 915 KiB

Open AccessLetter

Nonlinear Ride Height Control of Active Air Suspension System with Output Constraints and Time-Varying Disturbances

by Rongchen Zhao, Wei Xie, Jin Zhao, Pak Kin Wong and Carlos Silvestre

Sensors 2021, 21(4), 1539; https://doi.org/10.3390/s21041539 - 23 Feb 2021

Cited by 6 | Viewed by 2992

Abstract

This paper addresses the problem of nonlinear height tracking control of an automobile active air suspension with the output state constraints and time-varying disturbances. The proposed control strategy guarantees that the ride height stays within a predefined range, and converges closely to an [...] Read more.

This paper addresses the problem of nonlinear height tracking control of an automobile active air suspension with the output state constraints and time-varying disturbances. The proposed control strategy guarantees that the ride height stays within a predefined range, and converges closely to an arbitrarily small neighborhood of the desired height, ensuring uniform ultimate boundedness. The designed nonlinear observer is able to compensate for the time-varying disturbances caused by external random road excitation and perturbations, achieving robust performance. Simulation results obtained from the co-simulation (AMESim-Matlab/Simulink) are given and analyzed, demonstrating the efficiency of the proposed control methodology. Full article

(This article belongs to the Special Issue Advances in Intelligent Vehicle Control)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances in Intelligent Vehicle Control

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (12 papers)

Editorial

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI