International Journal of Vehicle Autonomous Systems
Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.
Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.
Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.
Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.
Articles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.
International Journal of Vehicle Autonomous Systems (6 papers in press)
The safety potential of automatic emergency braking and adaptive cruise control and actions to improve the potential by Roni Utriainen, Markus Utriainen And Pöllänen Abstract: The study investigates the potential of automatic emergency braking (AEB)
and adaptive cruise control (ACC) systems to prevent fatal rear-end, intersection and
pedestrian crashes in Finland. The systems' possibilities to prevent crashes were
assessed using data on 115 in-depth investigated fatal crashes. The data includes all
fatal crashes in the three studied crash types in 2014-2016. This study considers the
impact of estimated speed, weather conditions and intentionality on the systems
operation. AEB and ACC could potentially have prevented 41% of the crashes. The
highest safety potential in terms of share of hypothetically prevented crashes was
recognised in rear-end (45%) and pedestrian crashes (45%) and the lowest in
intersection crashes (36%). This study complements previous research, which amount is
low especially considering the potential to reduce pedestrian and intersection crashes, and which has typically been limited in the aspects that are considered in analysing the safety potential. Additionally, issues related to systems operational conditions are discussed and the possibilities to further increase the safety potential are assessed. Keywords: automatic emergency braking; AEB; adaptive cruise control; ACC; safety potential; crash analysis; rear-end crashes; pedestrian crashes; intersection crashes.
Indirect self-tuning controller for a two degree of freedom tracker model by Amir Naderolasli Abstract: Tracker systems have turned into an increasingly important issue in guidance systems and play a key role in navigational tracking. Accordingly, the aim of this study is to investigate a newly developed self-tuning adaptive strategy for increasing the precision of stabilisation and control in two-degree-of-freedom (2-DOF) tracker systems. For this purpose, a new self-tuning adaptive strategy is proposed for boosting the degree of stabilisation and regulation in 2-DOF tracker systems. The strategy is, in effect, an identifier-based adaptive strategy operating on Recursive Least Squares (RLS), which results in a non-minimum phase model. Together, the self-tuning stabiliser and tracker act as inner and outer loops of the targeted control system in order to track a desired command for ensuring a consistent and desirable stabilisation. The performance of the proposed method is further examined by using simulation techniques to show its functional capability in coupling with possible external disturbances and uncertainties. Keywords: two-DOF tracker; gimbal system; stabilisation mode; tracking mode; self-tuning; adaptive strategy,.
Automated vehicle lateral guidance using multi PID steering control and look-ahead point reference by Nolwenn Monot, Xavier Moreau, André Benine-Neto, Audrey RIZZO, François AIOUN Abstract: In this paper, a complete analysis of the influence of a look-ahead distance and the longitudinal vehicle velocity on the vehicle lateral dynamics is made in order to choose an adequate control strategy for lane keeping. Since the longitudinal velocity can be easily and accurately measured, a gain scheduling strategy based on the longitudinal velocity is employed in the design of a robust multi PID for the lateral control. Implemented onboard of a C4 Picasso prototype vehicle, the proposed controller showed promising results at variable speed and a satisfactory accuracy for lateral positioning.
Keywords: autonomous vehicles; robust control; driver assistance systems; self steering; steering behaviour; lane keeping; lane change assist.
Developing a novel rear steering angle control strategy for a modern three-wheeler by Saeid Shabzendehdar, Masoud Masih-Tehrani, Khashayar Moridpour Abstract: In this paper, a new rear steering angle control strategy is developed. This strategy is derived from the nonlinear 3DOF bicycle model in order to improve three-wheeler stability and manoeuvrability. However, common strategies have derived from the linear 2DOF bicycle model which has simpler assumptions. This new strategy has additional input comprising lateral velocity in comparison with the common strategies. This additional input could be simply observed using a suitable sensor. The nonlinear 3DOF tricycle equations have been implemented in MATLAB/Simulink for the modelling of the three-wheeler. Configurations of the handmade MATLAB/Simulink model were obtained from the information of the CarSim three-wheeled car. The developed model is validated using CarSim three-wheeled car, which is in good agreement with the experimental results. The three-wheeler model is used to compare the results of the strategies under different moving conditions. The results confirm that the new strategy provides better stability at high velocities and better manoeuvrability at middle velocities. Furthermore, the new strategy has acceptable performance at low velocities (parking manoeuvres). In addition, the new strategy has a suitable settling time and overshoot performance at transient manoeuvres. Keywords: all-wheel steering system; manoeuvrability; rear steering angle control strategy; stability; three-wheeler.
Unmanned ground vehicles: adaptive control system for real-time rollover prevention by MALAVI CLIFFORD Mlati, Zenghui Wang Abstract: Real-time rollover prevention of Unmanned Ground Vehicles (UGV) is paramount to their reliability and survivability when operating on unknown and rough terrains, such as mines or other planets of our solar system. Rollover index, which indicates the propensity for rollover and the roll angle variables, is a vital input to the rollover prevention system including active suspension control and speed control. To compute the rollover index, the roll angle must be measured, which requires expensive sensors and cannot be measured easily. Here, we use an adaptive control algorithm based on the recursive least squares estimator; the rollover index and roll angle can be computed and subsequently real-time adjust the UGV speed, suspension or steering angle to prevent vehicle rollover. The whole system is realised within Matlab/Simulink environment to emulate real-world application. Simulation and comparison results confirm that the adaptive control algorithm and technique perform reliably in preventing UGV rollover. Keywords: adaptive control system; unmanned ground vehicle; roll angle; rollover index; recursive least squares.
Traffic sign recognition using deep learning by Vraj Patel, Joy Mehta, Saurab Iyer, Ankit Sharma Abstract: Recognition of traffic signs is an integral step towards achieving Advanced Driver Assistance Systems (ADAS) as distracted driving is one of the primary causes of road accidents and fatalities. This paper attempts to exploit the capabilities of Convolutional Neural Networks (CNN) to recognise traffic signs under various computational and environmental constraints. The German Traffic Sign Recognition Benchmark (GTSRB) dataset is used for the classification of images. The dataset is subjected to various image processing techniques, such as gray scaling, denoising, filtering, and thresholding, to obtain a generalised model for the recognition of traffic signs. The neural network used here comprises three convolution layers, each followed by a max pooling layer, which further are followed by four fully connected dense layers. The models are trained for 100 epochs with a validation split of 20%. The model performs best with Adam optimiser with a learning rate of 0.001. Keywords: traffic sign recognition; advanced driver assistance systems; German traffic sign recognition benchmark; deep learning; computer vision; image processing; convolutional neural network.