Autonomous Vehicle Concept Research Articles

Autonomous vehicle security: Current survey and future research challenges

SummaryThe advancement in technology and the adoption of innovative developments have made our lives easier. Every industry, from agriculture to transport, has experienced this advancement. The entire transportation system is in the process of becoming intelligent. Smart mobility of autonomous vehicles is an important part of the upcoming smart cities. The autonomous vehicle provides functionalities for safety and convenience. It has been an emerging field with a lot of attention and still under advancement and requires a thorough study and solutions for potential challenges and opportunities. Despite impressive advantages, it has some security vulnerabilities which could lead to life‐threatening consequences. Though they could prevent road accidents by eliminating human errors from the driving process, they also create the possibility of cyber‐physical attacks on the vehicular controlling system. For this, many researchers have focused on the security attacks and defenses in autonomous vehicular systems. A 360‐degree research has been undertaken to understand the concept of autonomous vehicles entirely, such as history, social impacts, difficulties and challenges, current product developments, and security aspects. Also, a vehicular architecture is proposed by integrating various technologies such as 5G, SDN, cloud, and so forth, its possible security attacks are mentioned.

A deep learning based stereo matching model for autonomous vehicle

<p><span lang="EN-US">Autonomous vehicle is one the prominent area of research in computer vision. In today’s AI world, the concept of autonomous vehicles has become popular largely to avoid accidents due to negligence of driver. Perceiving the depth of the surrounding region accurately is a challenging task in autonomous vehicles. Sensors like light detection and ranging can be used for depth estimation but these sensors are expensive. Hence stereo matching is an alternate solution to estimate the depth. The main difficulties observed in stereo matching is to minimize mismatches in the ill-posed regions, like occluded, texture less and discontinuous regions. This paper presents an efficient deep stereo matching technique for estimating disparity map from stereo images in ill-posed regions. The images from Middlebury stereo data set are used to assess the efficacy of the model proposed. The experimental outcome dipicts that the proposed model generates reliable results in the occluded, texture less and discontinuous regions as compared to the existing techniques.</span></p>

AxV: An autonomous vehicle concept capable of operating throughout the ocean space: air, surface and subsea

This paper presents a concept design for an Autonomous Vehicle (AxV) capable of operating throughout the ocean space; air, surface and subsea. With current autonomous platforms limited in their operation, for example aerial platforms only operate in air, ASVs only operate on the ocean surface and AUVs operate subsea, a platform which can operate, transiting and transitioning in and between air, surface and subsea, providing increased mobility is very attractive. In this paper, a novel AxV platform is described. The governing equations are presented, describing each operational mode and the transitions between modes (air to surface, surface to subsea, subsea to surface, surface to air). Results are presented based on the dimensions of existing vehicles, showing that the system is theoretically feasible.

SECURITY OF AUTONOMOUS VEHICLES: 5G IOV (INTERNET OF VEHICLES) ENVIRONMENT

Abstract. An autonomous vehicle is designed to move partially or totally without the intervention of the driver. It is a system equipped with sensors, communication and processing units that make it able to monitor and analyse traffic information in real time to improve road safety. In addition, Internet of Vehicles is the latest technology dedicated to autonomous vehicles, the integration of this technology with 5G serves as a platform to interconnect sensors, vehicles, infrastructure, pedestrian, and network. Hence, the 5G Internet of Vehicles environment provides significant benefits, including increased security, high reliability, wide communication coverage and low service latency. On the other hand, due to the ubiquity of network connectivity, it also presents serious confidentiality, integrity, and availability issues for autonomous vehicles. This paper provides an overview of the autonomous vehicle concept by highlighting its technologies and the 5G IoV environment, presenting some susceptible attacks that can touch the security of this environment, and some good practices to ensure the autonomous vehicle security.

Bringing Together Ergonomic Concepts and Cognitive Mechanisms for Human—AI Agents Cooperation

The deployment of artificial intelligence from experimental settings to concrete applications implies to consider the social aspects of the environment and consequently to conceive the interaction between humans and computers endowed with the aim of being partners in action. This article proposes a review of the research initiatives regarding human-artificial agents interaction, including eXplainable Artificial Intelligence (XAI) and HRI/HCI. We argue that even if vocabulary and approaches are different, the concepts converge on the necessity for the artificial agents to provide an accurate mental model of their behavior to the humans they are interacting with. This has different implications depending on whether we consider a tool/user interaction or a cooperation interaction—which is far less documented despite being at the heart of the future concepts of autonomous vehicles. From this observation, the article uses the cognitive science corpus on joint-action to raise finer cognitive mechanisms proved to be essential for human joint-action which could be considered as cognitive requirements for future artificial agents, including shared task representation and mentalization. Finally, interactions content hypotheses are arisen to satisfy the identified mechanisms, including the ability for the artificial agent to elicit its intentions and to trigger mentalization toward them from the human cooperators.

Consideration on Contemporary Tasks about the Realization of Autonomous Vehicles Public Road Driving - Focusing on the revision of the Road Traffic Act and driver's license regulations -

Autonomous Vehicles are one of the representative products of the 4th industrial revolution from which we can expect benefits such as the reduction of traffic accidents and the decrease of casualties and loosening of traffic congestion by that. It can be said that interest in and movement about the development and commercialization of Autonomous Vehicles are considerable globally. Autonomous Vehicles can be described as the ones that perceive surroundings and do things dynamically on their own through recognition, judgment, and control. Also, to realize the driving and operation of Autonomous Vehicles on public roads, basically, it is needed to examine and revise the Road Traffic Act that has been institutionalized to keep cars moving smoothly by preventing and eliminating all the dangerous and hindrance factors of traffic on roads. We cannot deny the fact that the safe and desirable commercialization of those cars will be never obtained without it. Therefore, it is necessary not only to reflect technological perspectives to the revision of the Road Traffic Act but also to understand Autonomous Vehicles from the standpoint of the Road Traffic Act. From the viewpoint of the Road Traffic Act, Autonomous Vehicles can be regarded as the cars that support driving, but it is somewhat different in the perspective of technology. We cannot say that operating capacity directly means driving ability. Accordingly, in the situation to develop Autonomous Vehicles, we carry out recognition based on the technological concept of Autonomous Vehicles. To realize the reflection of it diversely into legislation, however, it is needed to perform consideration more precisely. In other words, not only technological development but efforts and attempts have been made multilaterally to commercialize and generalize Autonomous Vehicles from which we can expect various advantages associated with the decrease of traffic accidents. Yet, what is related to autonomous driving is not just from today or yesterday but has been a part of technological advancement and development that have been done continuously from long before. To wit, the emergence of Autonomous Vehicles did not take place in a day along with the 4th industrial revolution, and it can also be considered as part of the acceptance of technological development. Moreover, it seems to be necessary to establish definite criteria or such regarding what should be the focus in the realization of Autonomous Vehicles. In other words, on which should we put the emphasis, the acceptance of developed and advanced technology or the enhancement of safety? In conclusion, basically, it is needed to consider and arouse opinions about two aspects; one is to advocate technology as much as possible immediately, and the other is to accept it stepwise through discussion and examination. Therefore, it is necessary to consider all those things generally and revise the law practically and realistically in order to realize the public road driving of Autonomous Vehicles.

Transition of mobility in companies – A semi-systematic literature review and bibliographic analysis on corporate mobility and its management

Advancement measures and negative externalities of the current transport system have been extensively researched but significant changes concerning greenhouse gas (GHG) emission reduction is yet to be achieved. The expected mobility changes, triggered by the introduction of electric mobility, sharing concepts, modern vehicle concepts, new planning approaches and future autonomous vehicle concepts open up new options for an improved efficiency in the corporate mobility sector. The purpose of this article is to review literature between 2016 and mid-2020 on all transport-related activities of corporations and critically review research conclusions and their implication to determine research gaps for potential alternative ways of system transition. This is achieved by a semi-systematic review of international scientific journals and conference papers independently from their research field with a set of a-priori defined terms on corporate mobility and logistics. The article concludes with a summary of major research motivations and outcomes to the mobility transition in companies and identified research gaps with potential added value to the transport system. The review reveals that the major objective of analysed articles is the zero-emission future. An examination of new mobility solutions, technologies, and their potential impact is ongoing. The potentials to design future systems and ways of system transition have yet to be sufficiently examined. The relevant question is how mobility management in corporations could be upgraded. The integration into companies’ strategic management and inter-company mobility concepts could be potential fields. These findings are important for policymakers and mobility managers to jointly work on the zero-emission future.

The Future of Autonomous Vehicles in the Opinion of Automotive Market Users

Contemporary trends are focused on the development of the so-called smart, connected and multimedia cars as well as actions in the field of driving autonomy, and these trends may lead to changes in the structure of the industry through the emergence and growth of the importance of new entities. The article presents the concept of autonomous vehicles (AVs) and the way it is perceived by users of traditional cars. Surveys were carried out in various age groups on the possibilities of developing AVs in Poland. The group of respondents were inhabitants of a rural area, small towns and cities with over 300,000 inhabitants. Based on our own research, it can be concluded that, due to many different factors, including costs, legal regulations and conviction, among others, AVs will not appear so soon in common use on Polish roads. The results of the research showed that the majority of respondents consider hybrid vehicles (HVs) and then electric vehicles (EVs) to be the dominant type of vehicles in the near future in Poland, at the same time pointing at the long process of adopting AV technology.

USER NEED-ORIENTED CONCEPT DEVELOPMENT OF AUTONOMOUS VEHICLES

AbstractVehicle concept development is a domain that has applied and detailed its process over decades. The megatrends of the 21st century of “automation” and “sharing” influence the vehicle concept in such a manner that this well-running process needs an update. The vehicle itself and the customer of the vehicle are changing and therefore the components of the vehicle and the input variables of the useroriented design of the vehicle concept must be changed as well. We present a development process for autonomous vehicle concepts to address these challenges. We are therefore analyzing the current definition of a vehicle concept and its development process. Based on a literature review of a selection of common design methodologies, we update this definition for autonomous vehicle concepts and present a development process that presents design concepts of autonomous vehicle in a user need oriented way. This includes the sharing of models since user needs could be fulfilled by more than one vehicle concept. We believe that the presented process can be a starting point for vehicle concept development of the 21st century.

Anatomy of Self Driving Vehicle

The concept of Autonomous Vehicles portrayed in several Science Fiction mediums is now close to commercial reality. The new technology has the potential to change the conventional Transportation Industry. If implemented successfully, it will benefit society as a whole. As emerging as it seems; it also raises some serious challenges. This paper presents a systematic outline of the key components of Self Driving vehicles, current systems used, an overview of the Decision-making models, future scope and the practical challenges faced while developing and deploying the technology.

Spatial Components Guidelines in a Face-to-Face Seating Arrangement for Flexible Layout of Autonomous Vehicles

Fully autonomous vehicles are not yet available for consumers to experience; however, as experts predict they will be ready for the consumer market in the not-too-distant future, it is important to consider the spatial design of such vehicles. As the interior of a vehicle is a confined space, it is important to design a flexible layout in different aspects of the overall space. Therefore, this study aimed to analyze the relationships among various elements related to the use of space in a face-to-face seating arrangement. Using mock-up, observational surveys, questionnaires, and the think-aloud research method within an ethnographic observation framework, we conducted experiments on three study participants who were aware of the changing concept of autonomous vehicles. One of the key findings of our analysis is that various activities and actions can occur in a face-to-face seating arrangement. It is important to recognize that face-to-face seating arrangements are not just to facilitate conversation but can be seen as an environment in which each passenger can conduct other in-vehicle activities individually. Based on these findings, we recommend that needs for activities be considered when designing spatial components in a face-to-face seating arrangement.

A cooperative control framework of multiple unmanned aerial vehicles for dynamic oil spill cleanup

Oil spills within the marine environment are undesirable events caused by unavoidable economic activities of huge sea lane traffics. A tremendous effort has been made to tackle this problem within academia and industries; among them, the concept of autonomous vehicles for oil spill combating seems to provide a promising solution. This paper mainly proposes a cooperative deployment framework for unmanned aerial vehicles (UAVs) to perform oil spill cleanup missions with dispersant spraying. An appropriate oil density function is introduced by applying a Gaussian mixture model based on NOAA’s advanced oil spill model (General NOAA Operational Modeling Environment). UAVs are then deployed to cover oil spills for spraying operations. This deployment problem is formulated as a coverage problem based on centroidal Voronoi tessellation to determine UAVs’ optimal location. By transforming the coverage control problem into a target tracking one, an Integral Terminal Super Twisting Sliding Mode Control is provided to drive the UAVs to the optimal configuration. Furthermore, a novel spraying adjustment strategy is also designed to target the oil spills more accurately at the appropriate dosage. The effectiveness of the proposed framework is studied through a case study in the Abuzar oil field in the Persian Gulf. The results verify the performance of the cooperative oil spill cleanup framework in conjunction with advanced oil spill modeling. Moreover, it is concluded that the oil spill can be more effectively dispersed if the proposed spraying adjustment strategy is implemented.

Combining a Genetic Algorithm and a Fuzzy System to Optimize User Centricity in Autonomous Vehicle Concept Development

The megatrends of individualization and sharing will dramatically change our consumer behavior. The needs of a product’s users will be central input for its development. Current development processes are not suitable for this product development; thus, we propose a combination of a genetic algorithm and a fuzzy system for user-centered development. We execute our new methodological approach on the example of autonomous vehicle concepts to demonstrate its implementation and functionality. The genetic algorithm minimizes the required number of vehicle concepts to satisfy the mobility needs of a user group, and the fuzzy system transfers user needs into vehicle-related properties, which are currently input for vehicle concept development. To present this method, we use a typical family and their potential mobility behavior. Our method optimizes their minimal number of vehicle concepts to satisfy all mobility needs and derives the properties of the vehicle concepts. By integrating our method into the entire vehicle concept development process, autonomous vehicles can be designed user-centered in the context of the megatrends of individualization and sharing. In summary, our method enables us to derive an optimized number of products for qualitatively described, heterogeneous user needs and determine their product-related properties.

A Study of Hazard Analysis and Monitoring Concepts of Autonomous Vehicles Based on V2V Communication System at Non-signalized Intersections

A Study of Hazard Analysis and Monitoring Concepts of Autonomous Vehicles Based on V2V Communication System at Non-signalized Intersections

SOCIAL DISTANCING, AUTONOMOUS VEHICLES' UNEXPECTED SUPPORTER – HOW COVID-19 HAS CHANGED FUTURE MOBILITY BEHAVIOUR AND PERCEPTION IN EUROPE

ABSTRACT The future concept of autonomous vehicles is based on assumptions, that the mobility world moves further towards sharing economies, such as car-sharing business and car-pooling opportunities, and away from private vehicle ownership. But the pandemic resulted in the opposite. People are avoiding strangers through social distancing, using fewer public transport options and instead an increasing number of private vehicles. If fully autonomous vehicles are for individual use only, and correct hygiene measures are put into place, the technology could provide a good transport alternative to current options. On the assumption, that theoretically the acceptance of self-driving cars should rise due to social distancing possibilities, this study was created. Focusing on perceived ease of use, perceived usefulness and social distancing attitude, the hypothetical use of robo-taxis during this pandemic is assessed. Pre COVID-19, previous studies revealed that acceptance of the technology was declining. With a changing mobility attitude and perception, could this be the time to market autonomous vehicles as a useful alternative to public transport and grow its acceptance? Using the Technology Acceptance Model, this paper asses the opinion of 1593 Europeans towards robo-taxis, self-driving cars as a whole, and the changing mobility behaviour as a result of COVID-19. The results show that 47.5% of participants, an increase of 5.3% compared to pre-pandemic times, would use robo-taxis during the pandemic and 48.6% would like to own a self-driving vehicle if they were available. While the pandemic has resulted in a decline of mobility movement across the world, it opened up the opportunity of rethinking the future mobility world. Keywords Autonomous vehicles, pandemic, acceptance, mobility behaviour, change

Development of a parametric packaging and sizing tool for autonomous electric bus system

The demand for autonomous electric public transport is increasing globally. New vehicle models and variants are increasing the development complexity and hence the overall development time. Therefore, there is a requirement for a vehicle-packaging tool that can translate user inputs into an optimised vehicle package and can be visualised instantly. The aim of this paper is to develop a parametric tool for designing different concepts for electric autonomous buses. The scope of application is intended in the early phase of the vehicle development process to enable a fast and efficient creation of a flexible bus concept. Through a graphical user interface (GUI), the user is able to size and select all the required components for the autonomous vehicle concepts. The vehicle specification is initiated by selection of one of the three classes of vehicle, the desired number of passengers and then the bus interior’s seat arrangement design. An appropriate powertrain and chassis will then automatically be configured in the next steps. The HVAC simulation allows for the design of different components of the refrigeration circuit to ensure proper cabin temperature. For evaluating the concept, the energy consumption is analysed through simulations, and an estimated initial cost of vehicle concepts and individual systems completes the concept. A spider chart summarises all characteristics and offers an overview of the vehicle concept, providing the possibility to compare with other concepts simultaneously. The tool can create 9600 different bus concepts and provides interfaces for expansion.

Augmenting Cybersecurity in Autonomous Vehicles: Innovative Recommendations for Aspiring Entrepreneurs

Autonomous and connected vehicles are a collection of smart components such as sensors, Radar/Lidar, Electronic Control Units (ECUs), and cameras programmed through voluminous lines of codes, which enable a seamless communication system between the user, vehicle, and infrastructure. The concept of autonomous vehicles is gaining significant traction in the global markets, generating higher revenues, and witnessing high market penetration, thus attracting entrepreneurs to make new and disruptive innovations. However, the underlying technology and communication system of autonomous and connected vehicles are prone to the cybersecurity threats, which circumvent any product that uses sensors, transmits data over the network, and can be controlled through a remote computer or a mobile application. In this article, we attempt to outline the concerns that an aspiring entrepreneur should be aware of before entering into the autonomous vehicle industry, followed by innovative recommendations that can guide addressing the article's issues. The presented recommendations and guidelines are based on the cybersecurity principles of confidentiality, integrity, and availability.

USING DEEP LEARNING TO DIGITIZE ROAD ARROW MARKINGS FROM LIDAR POINT CLOUD DERIVED IMAGES

Abstract. The concept of Autonomous vehicles or self-driving cars has recently been gaining a lot of popularity. Because of this, a lot of research is being done to develop the technology. One of which is High Definition (HD) Maps, which are centimeter-level precision 3D maps that contain a lot of geometric and semantic information about the road which can assist the AV when driving. An important component of HD maps is the road markings which indicates a set of rules on how a vehicle should navigate itself on the road. For example, lane lines indicate which part of the road a vehicle can drive on in a certain direction. This research proposes a methodology that uses deep learning techniques to detect road arrows, road markings that show possible driving directions, on LIDAR derived images, and extract them as polyline vector shapefiles. The general workflow consists of (1) converting the LIDAR point cloud to images, (2) training and applying U-Net – a fully convolutional neural network, (3) creating masks from image segmentation results that have been transformed to fit the local coordinates, (4) extracting the polygons and polylines, and finally (5) exporting the vectors in shapefile format. The proposed methodology has shown promising results with object segmentation accuracies comparable with previous related works.

Maneuver-Based Objectification of User Comfort Affecting Aspects of Driving Style of Autonomous Vehicle Concepts

Driving maneuvers try to objectify user needs regarding the driving dynamics for a vehicle concept. As autonomous vehicles will not be driven by people, the driving style that merges the individual aspects of driving dynamics, like user comfort, will be part of the vehicle concept itself. New driving maneuvers are, therefore, necessary to objectify the driving style of autonomous vehicle concepts with all its interdependencies relating to the individual aspects. This paper presents a methodology to design such driving maneuvers and includes a pilot study and a user study. As an example, the methodology was applied to the parameters of user comfort and travel time. The driven maneuvers resulted in statistical equations to objectify the interdependencies of these two aspects. Finally, this paper provides an outlook for needed maneuvers in order to tackle the entire driving style with its multidimensional facets.

Autonomous Vehicle Concept for the Urban Transport of the Future

Autonomous Vehicle Concept for the Urban Transport of the Future