Fig 1 - available via license: CC BY
Content may be subject to copyright.
A very simple model of memory
Source publication
Background: Autonomous cars could make traffic safer, more convenient, efficient and sustainable. They promise the convenience of a personal taxi, without the need for a human driver. Artificial intelligence would operate the vehicle instead. Especially deep neural networks (DNNs) offer a way towards this vision due to their exceptional performance...
Context in source publication
Context 1
... are capable of remembering information. If asked, subjects are able to recall the information and their origin from the last month. Apparently, there is something inside the brain that is capable of retaining information: memory. But humans also forget information over time. This can be visualised in a very simple model (Fig. ...
Similar publications
Security Assessment of large networks is a challenging task. Penetration testing (pentesting) is a method of analyzing the attack surface of a network to find security vulnerabilities. Current network pentesting techniques involve a combination of automated scanning tools and manual exploitation of security issues to identify possible threats in a...
Citations
... On the other hand, the author [8] mentions that if an artificial intelligence -driven vehicle encounters an inevitable eventuality, software must be responsible for making the most accurate decision so as to mitigate the damage as dimly as possible considering that human beings exercise ample discretion and evidently the possibility that they come to a total agreement is dim in other words, regardless of the decision made by the software program, the "machine" would always be at fault. ...
Esta investigación documental-descriptiva pretende explorar el avance de la inteligencia artificial (IA) en los vehículos autoconducidos y su repercusión en beneficio de la sociedad. Si bien es innegable que los vehículos autoconducidos se han convertido prácticamente en una realidad tecnológica en el campo de la informática, tanto en la actualidad como en un futuro previsible. Sin embargo, es necesario abordar varios aspectos aparentemente problemáticos en términos de legislación, ya que los coches autónomos están llamados a convertirse en parte integrante de la vida cotidiana. Por ello, esta investigación examina mediante una revisión bibliográfica los importantes avances y esfuerzos dedicados al diseño de software en este ámbito de estudio centrado en el funcionamiento de los vehículos autónomos en entornos urbanos y su capacidad para sortear los obstáculos de la ciudad, así como los retos ante eventualidades imprevistas.
... • Conduct regular assessments on ITS implementation in the countryrefer to Appendix I (MOW, 2019). • Black box and digital data concerns are more obvious in AV scenarios; thus, this is another big challenge for modern cars, especially in the local context (Bonnefon et al., 2016;Kassim et al., 2019;Utesch et al., 2020;Karjanto et al., 2021). More assessments regarding available autonomous functions such as Adaptive Cruise Control (ACC) will help in giving early indications (Chan, 2021;Li et al., 2021). ...
Generally used in aircraft to record and store operational data, the black box has also been used in road vehicles, either commercial or private, for safety, control, and investigative mechanism. Technological advancements have allowed the development of data-generating items in modern-day cars such as EDR and dashcams. Despite their benefits in road safety especially in vehicular forensics, there are concerns about safety, privacy, and users' rights. This warrants refreshed approaches to gradually embed a digital culture into the existing automotive ecosystem. They include a collaborative effort to create an inclusive discussion among a group of local experts recognized as the Modern Vehicle Expert Consortium (MOVE), and a review of related laws and regulations to protect the end users, government, and related stakeholders.
... Vehicle to vehicle (V2V) communication transmits information between vehicles on the road in realtime, enables the anticipation of other cars' actions and contributes to the stability of traffic flow. While it is not clear how autonomous cars and traditional drivers would interact, especially because we do not know how the autonomous cars will be programmed or how the artificially intelligent car [62] will react to traditional drivers, autonomous cars should be able to avoid facilitating phantom jams, and may therefore be exempt from phantom jam tolls. In a perfect world of autonomous cars, there should be no phantom jams and thus no longer any phantom jam externality. ...
If not restricted by tolls, private decisions to drive on a highway result in inefficiently high usage which leads to traffic jams. When traffic demand is high, traffic jams can occur simply because of the interaction of vehicle drivers on the road, a phenomenon called phantom jam. The probability of phantom jams occurring increases with traffic flow. Unpriced externalities lead to inefficiently high road usage. We offer a method for quantifying traffic jam externalities and identifying and isolating the phantom jam externality. We examine the method by applying it to a specific highway section in Germany. The maximal congestion externality for the analyzed highway section is about 38 cents per vehicle and kilometer. Congestion charges that are calculated ignoring phantom jam externalities, can only internalize two-thirds of the true externality.
... Driving will be made safer by avoiding human-driven accidents caused by distraction or fatigue. Traveling will be more efficient and sustainable by facilitating car-sharing services, preventing traffic congestion, and providing time savings and comfort through AVs [4]. AVDSs are also considered as one of the socio-technical innovations in the transportation sector [5]. ...
Autonomous vehicle driving systems (AVDSs) have independent decision structures from the users to manage and control the operations of the vehicles both in normal conditions and unexpected situations. Although there are some advantages, such as decreasing accidents reasoned by human errors and efficient energy usage, it is obvious that some risks are rooted in this technology usage. Therefore, it will be beneficial to realize a risk assessment application for autonomous vehicles (AVs) and/or driving systems (DSs) since whose risks are crucial to test and solve. In this paper, a multi-criteria decision making (MCDM) methodology integrating DEcision MAking Trial and Evaluation Laboratory (DEMATEL), Analytical Network Process (ANP), and VlseKriterijuska Optimizacija I Komoromisno Resenje (VIKOR) techniques under spherical fuzzy environment have been suggested to evaluate AVDS alternatives in terms of considered risk criteria. Spherical fuzzy sets (SFS), which are the extension of the ordinary fuzzy sets, have been used to consider the hesitancy of experts and decision-makers as well as uncertainty and impreciseness in the available data. In the application, six AVDS alternatives have been evaluated in terms of seven main criteria and forty sub-criteria. The factors “Software Specifications” and “Reliability” have been determined as the most important main and sub-criteria with the weights 0.193 and 0.066, respectively. Additionally, comparative and sensitivity analyses have been applied to present flexibility, validation and verification of the proposed methodology together with the sensitivity of the given decisions. Based on the application results and conducted analyses, possible implications by views of theoretical, managerial, and policy context have been discussed.
This review examines the utilization of Artificial Neural Networks (ANNs) in the analysis of road crash data and their prospective contribution to autonomous vehicles. Artificial neural networks (ANNs) have exhibited considerable promise in the realm of modeling and forecasting crash occurrences, thereby offering valuable insights for enhancing road safety. Artificial neural networks (ANNs) play a crucial role in the functionality of autonomous vehicles by enabling them to effectively perceive their surroundings, make informed decisions, and operate with a high level of safety and efficiency. Nevertheless, the deployment of Artificial Neural Networks (ANNs) encounters various obstacles, such as their inherent opaqueness, the necessity for substantial quantities of meticulously curated data, and the demanding computational capabilities they demand. Possible solutions to these challenges encompass the advancement of methodologies for interpreting artificial neural networks (ANNs) and the utilization of more intricate ANN models. Notwithstanding the advancements achieved in this particular domain, it is imperative to acknowledge and rectify the existing deficiencies in the present body of research. These encompass the necessity for conducting more extensive research on the utilization of Artificial Neural Networks (ANNs) in the analysis of road crashes, the requirement for developing more resilient testing methodologies for these systems, and the demand for further investigation into the effective implementation of ANNs in autonomous vehicles. This review makes a significant contribution to the current academic conversation in the field, offering valuable insights for researchers, policymakers, and practitioners engaged in the domains of road safety and autonomous vehicles.
The number of electronic control units (ECU) installed in vehicles is increasingly high. Manufacturers must improve the software quality and reduce cost by proposing innovative techniques.
This chapter proposes a technique being able to generate not only test-cases in real time but to decide the best means to run them (hardware-in-the-loop simulations or prototype vehicles) to reduce the cost and software testing time. It is focused on the engine ECU software which is one of the most complex software installed in vehicles. This software is coded by using Simulink® models. Two genetic algorithms (GAs) were coded. The first one is in charge of choosing which parts of the Simulink® models should be validated by using hardware-in-the-loop (HIL) simulations and which ones by using prototype vehicles. The second one tunes the inputs of the software module (SM) under validation to cover these parts of the Simulink® models. The usage of dynamic-linked libraries (dlls) is described to deal with the issues linked to SM interactions when running HIL simulations. In addition to this, this chapter focuses on the validation of engine electronic control unit software by using expert systems (EXs) and dynamic link libraries (dlls) with the aim of checking if this technique performs better than traditional ones. Finally, the chapter aims to check if two rule-based EXs combined with dynamic-link libraries (dlls) perform better than other techniques widely employed in the automotive sector when validating the engine control unit (ECU) software by using a hardware-in-the-loop simulation (HIL).
The article discusses the importance of selfdriving cars to improve road safety and reduce the number of accidents caused by human error. Self-driving cars not only reduce human error but also help reduce driver fatigue. We further explore the use of computer vision in autonomous cars, with previous research relying on deep learning algorithms with LiDAR sensors which can be expensive. The authors propose a more cost-effective approach using simple computer vision algorithms such as color space transformation, Canny edge detection, and Hough line transformation to detect lane lines and steer the car accordingly. This approach requires less operational hardware and can be implemented using affordable boards like Raspberry Pi and Nvidia Jetson Nano. The article also highlights the reconstruction of a remote-controlled car that had a 95% accuracy using a certain set of parameters was a tool for understanding autonomous cars better.
