Search

The commercial driver profession – operators of trucks, busses and other specialized vehicles is a hazardous one. People in these positions are required to possess a high level of awareness, to have quick reactions to changes on the road, to be able to adapt, maintain and repair the vehicle if necessary. Professional drivers sometimes have to drive long routes, even when they are paired with another colleague. Sometimes, situational and spatial awareness must always be kept in high regards, despite factors, such as fatigue, sleep deprivation, dizziness, nausea, etc. In this study, we try to analyze and evaluate professional drivers' performance, simulating some of those extreme conditions. Performing such an experiment in a real-world scenario is dangerous, financially intensive and generally undesirable. That is why, in order to perform our experiment, we use a Euro Truck Simulator 2 and the Varjo VR with integrated tracking sensor, in order to record and evaluate where the driver's eyes are focused during operational procedures and how their awareness changes with time, fatigue and other limiting factors. As a result, we found out that a large percentage of all evaluated drivers tend to lose focus on the road, pay less attention on the gauges and truck instruments and tend to cause more incidents. [ABSTRACT FROM AUTHOR]

The engineering design problems have been highly complex and time-consuming. Real-world engineering systems also suffer many systems and subsystems levels challenges during the entire product life cycle because of their inevitable multidisciplinary nature and complex coupling between different subsystems. Therefore, any effort in direction of alleviating difficulties in the field of Multidisciplinary Systems Design Optimization (MSDO) will receive remarkable attention. Artificial Intelligence (AI) which is a massive field encompassing many goals has recently triggered a paradigm shift in numerous industries around the world and also could be led to a revolution in the MSDO field of research. Currently, the most influential topic in AI is machine learning (ML) which is decomposed into supervised learning, unsupervised learning, semi-supervised learning, and Reinforcement Learning (RL). The focus of this article is to show the further applications of RL in the field of MSDO research area. To demonstrate the potential capability of this strategy, it is applied to solve some optimization benchmark problems and also design optimization of an aerial vehicle. [ABSTRACT FROM AUTHOR]

This paper tackles the problem of airplane automatic landing by making a modification to and using the Lyapunov stability method of model reference adaptive control for state tracking of multivariable systems. The modification is made to improve the controller's output tracking capabilities under dynamics model uncertainties whilst avoiding the issues that high adaption gains cause. In order to construct a reference model that is practical for the adaption law to track, the ideal dynamics model coupled with a linear quadratic regulator was used. The resulting controller shows an improved consistency in dealing with model uncertainty. [ABSTRACT FROM AUTHOR]