Driverless Vehicles Research Articles

The Aspects of Artificial Intelligence in Different Phases of the Food Value and Supply Chain.

The types of artificial intelligence, artificial intelligence integration to the food value and supply chain, other technologies embedded with artificial intelligence, artificial intelligence adoption barriers in the food value and supply chain, and solutions to overcome these barriers were analyzed by the authors. It was demonstrated by the analysis that artificial intelligence can be integrated vertically into the entire food supply and value chain, owing to its wide range of functions. Different phases of the chain are affected by developed technologies such as robotics, drones, and smart machines. Different capabilities are provided for different phases by the interaction of artificial intelligence with other technologies such as big data mining, machine learning, the Internet of services, agribots, industrial robots, sensors and drones, digital platforms, driverless vehicles and machinery, and nanotechnology, as revealed by a systematic literature analysis. However, the application of artificial intelligence is hindered by social, technological, and economic barriers. These barriers can be overcome by developing the financial and digital literacy of farmers and by disseminating good practices among the participants of the food supply and value chain.

An Aerial Robotics Investigation into the Stability, Coordination, and Movement of Strategies for Directing Swarm and Formation of Autonomous MAVs and Diverse Groups of Driverless Vehicles (UGVs)

This study will discuss the matter of movement communication and preparation of tight configurations of land & flying robots. Remotely Operated Cars (UGVs) and Unmanned Aerial Vehicles (UAVs), in specific Micro Aerial Vehicles (MAVs), would be used to fix circumstances where a creation of UGVs and UAVs, in specific Micro Aerial Vehicles (MAVs), should counteract their velocity and direction to finish a mission of traffic sequence to a targeted area. The motion planning and stabilisation strategy given here is a useful tool for deploying closely collaborating robot teams including both outdoor and indoor settings. The installation of large groups of Micro Aerial Vehicles (MAVs) in a legitimate (indoor and outdoor) environment without the use of auxiliary positioning applications (such as Vicon or GPS) is indeed a natural development in the area of autonomously flying systems. Stability, control, and trajectory planning techniques for guiding swarm or configurations of unmanned MAVs, as well as diverse groups with Unmanned Ground Vehicles (UGVs) operating alongside MAVs, will be discussed in greater detail. These approaches discussed all are designed for the use of inter squads in true complex scenarios even without necessity for worldwide translation or motion capture systems, as they are predicated on board optical comparative localisation of single MAVs. This multi - objective optimisation being an enabler for the introduction of swarming of tiny autonomous drones beyond the labs with equipment for precise robot positioning. Model Predictive Control (MPC) is being used to address a formations to goal territory issue, and the form drive idea is based on a simulated approach. The Particle swarm optimization approach is utilised for digital leader trajectories planning, as well as control and stabilisation of follows (MAVs and UGVs). The proposed technique could be tested in the future using a range of simulation and practical tests.

Near‐Infrared Persistent Phosphor‐Mediated Smart Sensing Light‐Emitting Diodes for Advanced Driver Assistance Systems

Compared with conventional phosphor‐converted near‐infrared light‐emitting diodes (NIR pc‐LEDs), near‐infrared persistent phosphor‐converted LEDs (NIR ppc‐LEDs) are applicable not only in conventional systems but also novel devices in the fields of intelligent security, driverless vehicle technology, and virtual reality. However, NIR ppc‐LEDs have not been extensively investigated. Herein, a novel NIR ppc‐LEDs with the prepared SrAl12O19: Fe3+, Mg2+, Ti4+ NIR persistent phosphors is designed. In relation to pc‐LEDs, the new ppc‐LED exhibits full‐spectral responsive sensing ability during the photostimulated mediation of lattice defects. Furthermore, using the ppc‐LED as a smart sensing LED in a digital NIR imaging system, optical feedback could be converted to a digital signal in a self‐regulated visible‐to‐NIR operation mode. These results imply that the designed ppc‐LED, as a smart sensing LED with full‐spectral responsive ability, greatly enhances the sensitivity of digital NIR imaging, particularly low‐light digital NIR imaging, which has recently drawn considerable attention in the fields of advanced driver assistance systems and VR/AR technology.

Research on path tracking control of unmanned vehicle

With the continuous progress of science and technology, driverless vehicles have become one of the development trends of automobiles in the future. Path tracking control is a key problem in the research of driverless vehicles. Based on one control theory or by combining several different theories, different control algorithms are proposed, and some achievements have been made. This paper mainly studies the tracking control research method, which is a key problem in driverless vehicles. By analyzing and comparing the LQR control method and MPC control method, we compare their advantages and disadvantages, understand the concepts and related algorithms of various path-tracking control methods, and analyze the advantages and disadvantages of various control methods.

Algorithms and Mathematics Education A Response and Review of Hannah Fry’s Hello World: Being Human in the Age of Algorithms

At the outset, Dr. Hannah Fry’s book Hello World: Being Human in the Age of Algorithms is an engaging survey of how algorithms are being used in modern life. The book is written for a general audience with a focus on concepts and principles. As such, the narrative does not dig deeply into the details of any particular topic but instead offers a snapshot of how algorithms reside within a variety of contexts in the modern world. Through relatable examples, Dr. Fry builds a narrative that explains how algorithms are used as tools to predict, influence, augment, and mimic human behavior. Woven throughout the narrative are stories that reveal the power and pitfalls of algorithms. We learn about algorithms used by advertisers, data brokers, judges, chess masters, and healthcare workers. Along the way, Dr. Fry reveals how algorithms are being used to identify cancerous cells, build driverless vehicles, influence an online behavior, and create art. After reading the book, I was left asking practical questions such as, did that recent grocery store advertisement arrive by chance or is it based on my previous shopping behavior? How is my online browsing influencing the advertisements I see on social media? At the same time, the book inspired broader questions such as, how are algorithms being used for sentencing within the local court system? In what ways is care at the nearby hospital influenced by algorithms? In what follows, I have sought to craft a response to the book from my own lens of mathematics education rather than a detailed analysis of the particular merits. For those seeking a recommendation on whether or not to read the book, my response is: Read it. It is inextricably connected to the work that you do.

How and why humans trust: A meta-analysis and elaborated model.

Trust exerts an impact on essentially all forms of social relationships. It affects individuals in deciding whether and how they will or will not interact with other people. Equally, trust also influences the stance of entire nations in their mutual dealings. In consequence, understanding the factors that influence the decision to trust, or not to trust, is crucial to the full spectrum of social dealings. Here, we report the most comprehensive extant meta-analysis of experimental findings relating to such human-to-human trust. Our analysis provides a quantitative evaluation of the factors that influence interpersonal trust, the initial propensity to trust, as well as an assessment of the general trusting of others. Over 2,000 relevant studies were initially identified for potential inclusion in the meta-analysis. Of these, (n = 338) passed all screening criteria and provided therefrom a total of (n = 2,185) effect sizes for analysis. The identified dependent variables were trustworthiness, propensity to trust, general trust, and the trust that supervisors and subordinates express in each other. Correlational results demonstrated that a large range of trustor, trustee, and shared, contextual factors impact each of trustworthiness, the propensity to trust, and trust within working relationships. The emphasis in the present work on contextual factors being one of several trust dimensions herein originated. Experimental results established that the reputation of the trustee and the shared closeness of trustor and trustee were the most predictive factors of trustworthiness outcome. From these collective findings, we propose an elaborated, overarching descriptive theory of trust in which special note is taken of the theory's application to the growing human need to trust in non-human entities. The latter include diverse forms of automation, robots, artificially intelligent entities, as well as specific implementations such as driverless vehicles to name but a few. Future directions as to the momentary dynamics of trust development, its sustenance and its dissipation are also evaluated.

MOP-SLAM: A real time SLAM system based on multi-head optical flow estimation network

SLAM (simultaneous localization and mapping) is becoming a significant technology in driverless vehicles nowadays. Sometimes the optical flow method can be used to track feature points to reduce the amount of calculation. But the traditional optical flow method is based on the assumption that the luminosity will not change and has high requirements for the environment. Therefore, an optical flow calculation method based on neural network called Optical-Net is proposed in this paper to match and track feature and corner points. We use the multi-head attention module to extract and fuse the features of different scales. The training results show that the Optical-Net designed in this study effectively improves the robustness and accuracy of optical flow estimation when the object has large displacement and small displacement. Meanwhile, to address the problem of reduced matching accuracy during video input due to dynamic blurring, a video dynamic deblurring algorithm based on the one-dimensional Wineman filter is adopted to preprocess the input video. Finally, we replaced the tracking thread in traditional SLAM. The performance of the improved algorithm is verified by experiments on our own driverless car.

Research on Risk Detection of Autonomous Vehicle Based on Rapidly-Exploring Random Tree

There is no doubt that the autonomous vehicle is an important developing direction of the auto industry, and, thus, more and more scholars are paying attention to doing more research in this field. Since path planning plays a key role in the operation of autonomous vehicles, scholars attach great importance to this field. Although it has been applied in many fields, there are still some problems, such as low efficiency of path planning and collision risk during driving. In order to solve these problems, an automotive vehicle-based rapid exploration random tree (AV-RRT)-based non-particle path planning method for autonomous vehicles is proposed. On the premise of ensuring safety and meeting the requirements of the vehicle’s kinematic constraints through the expansion of obstacles, the dynamic step size is used for random tree growth. A non-particle collision detection (NPCD) collision detection algorithm and path modification (PM) path modification strategy are proposed for the collision risk in the turning process, and geometric constraints are used to represent the possible security threats, so as to improve the efficiency and safety of vehicle global path driving and to provide reference for the research of driverless vehicles.

Low-complex resource mapping heuristics for mobile and iot workloads on NoC-HMPSoC architecture

Network-on-chip-based heterogeneous multiprocessor system-on-a chip (NoC-HMPSoC) a single board computer is extensively utilized in many real-time applications such as mobile edge computing (MEC), cyber-physical systems, smart phones, driverless vehicles, and real-time embedded systems due to its flexible communication architecture, switching network, excellent performance, and energy efficiency. Despite its benefits, task scheduling and appropriate resource allocation is still an non-polynomial hard problem. NoC-HMPSoC includes heterogeneous processors along with interconnected communication routing structure which creates more complexity in task and resource scheduling. In this paper, a new task classification and low-complex resource mapping heuristics are developed to deal with mixed-critical workloads execution targeted on NoC-HMPSoC architecture. MethodologyTo minimize runtime scheduling cost, the deadline-based task classification (DBTC) heuristic divides the workload into three distinct classes depending on their deadline and inter-arrival limitations. The mixed-integer linear programming (MILP) statistical model, which improved task miss ratio with greater time complexity, is used to schedule the categorized task sets. Static resource mapping (SRM) and load-based dynamic resource mapping (LBDRM) heuristics are created to allocate mixed-critical activities into NoC-HMPSoC in order to overcome this. The suggested framework is a list-based scheduler that processes tasks on an unchanging processor using the SRM algorithm and prioritizes them depending on the tasks' earliest finish times. The LBDRM technique is then used to dynamically reallocate mixed-critical task groups among heterogeneous processors based on the load factor and task utilization factor. The time complexity of DBTC algorithm is O(log n) where 'n' is the task nodes, and the time complexity of the proposed scheduling heuristics are O(n2 * m) for larger graphs. The proposed framework performs classification, mapping, and scheduling in an integrated manner that is experimentally evaluated on the Samsung Exynos 5422 NoC-HMPSoC and Intel Xeon cloud server for E3S sysmark mobile benchmark workloads. Averagely 65%, 33%, is improved in execution time reduction and 45%, 36% reduction in energy consumption and 56%, 32% than JRFS-HRFS and ARSH-FATI methods.

A Crowd-Aided Vehicular Hybrid Sensing Framework for Intelligent Transportation Systems

The development of Internet of Things (IoT) techniques enables the paradigm shift in traffic data collecting. In traditional practices of transportation system's constructions, traffic-related information is collected based on dedicated sensor networks, which are not only coverage-limited but also cost-consuming. With the enrichment of the concepts concerning “social sensors” and “social transportation”, Sparse mobile crowdsensing (MCS) emerges as a promising sensing paradigm to collect data from only a few subareas by recruiting vehicles or mobile users with portable devices and to infer the data in unsensed subareas with acceptable errors at a low-cost manner. However, in real-world sensing campaigns, the Sparse MCS systems often fail to collect data from any subareas of interest since the assumption about sufficient participants is not always realistic. To be specific, the recruitment of participants is often limited by interest deficiency, privacy awareness, and distribution biases. To handle this problem, we introduce the dedicated sensing vehicles (DSVs) e.g., drones or driverless vehicles into traditional Sparse MCS to improve subarea coverage and inference performance. To achieve effective collaboration among DSVs and mobile users, we first design a crowd-aided vehicular hybrid sensing framework, which defines the order of task assignment for DSVs and mobile users as well as the budget allocation. In terms of DSVs route planning, we propose a three-step strategy, including optimal route searching, fused route selection, and final route determination. Moreover, mobile users are selected based on a proposed novel selection strategy. Experimental findings on two real-world datasets validate the effectiveness (with less inference error) of the hybrid sensing framework and the proposed strategies, in comparison with the user-only/DSV-only framework and five baselines. Results reveal important implications of applying the hybrid sensing paradigm in intelligent transportation systems to enhance data collection.

3D camera augmented Autonomous Mobile Robot for intralogistics purposes

AMRs (Autonomous Mobile Robots) are driverless vehicles programmed to perform a variety of tasks and are often used to transport goods or materials. However, there can be several problems with the driving performance of this type of vehicle. Safety in the workplace is important everywhere, but there are some areas that are particularly exposed to safety risks. Limited visibility is the main cause of accidents at work. Yet, robots can map these dangerous areas with their sensors. We will present a mobile robotic sensor development that can be implemented to increase the security of robotic warehouses. Testing is necessary in order to check the quality of existing defects in safety elements before delivery and to carry out a risk assessment. Our goal was to add a safety element to the robot to prevent the most common problem, namely it is colliding with a forklift truck, hitting objects outside the sensor planes or hanging in. Based on our experience with robots over the years, this has been a big challenge, as we have had several such collisions. Therefore, we selected and installed a modern 3D camera system and tested its compliance with the safety requirements and the difference between the safety level of a robot without 3D sensor (Alpha) and a robot with 3D sensor (Beta), based on the knowledge of the installed camera.

SEAT-YOLO: A squeeze-excite and spatial attentive you only look once architecture for shadow detection

Recently, several deep learning-based architectures have been utilized for the recognition of shadow regions in images and videos with the aim of classification and segmentation of shadow instances. The present work aims towards solving the problem of shadow recognition as a detection and regression problem. To solve the problem of shadow detection in images and videos, we have developed SEAT-YOLO, a deep learning-based shadow detection architecture. The backbone network of the proposed architecture is based on convolution layers, squeeze-excite blocks, spatial attention module, and spatial pyramid pooling layer and the detection network utilizes YOLO detection heads. The proposed SEAT-YOLO architecture is trained and tested on the publicly available SBU shadow detection dataset. For shadow detection on the SBU dataset, it achieved a mAP value of 59.53 %. Furthermore, the proposed SEAT-YOLO is capable of detecting small shadow regions with high accuracy which is a challenge with most deep learning-based detection architectures. Moreover, the other advantage of the proposed SEAT-YOLO is its ability to detect multiple shadow regions in a single image by drawing precise bounding boxes for overlapping shadows. The proposed SEAT-YOLO architecture has high practical implications in driverless vehicles for detection of shadow regions and take effective driving decisions.

Factors Influencing Driver’s Psychological Vulnerability Judgment When Sharing the Road With Driverless Vehicles

To judge whether drivers of manned vehicles sharing the road with driverless vehicles think they are in a vulnerable state and find out what makes drivers feel they will be in a state we called “driver’s psychological vulnerability judgment”, this paper conducted a questionnaire to collect information about the attitude, perceived usefulness, trust, perceived risk, and demographic information of drivers in a hypothetical situation involving driving on the same road as driverless vehicles. Our goal was to identify areas where the drivers felt that they would be in a “vulnerable psychological state”, i.e., that they would be more vulnerable to making poor psychological judgments. A total of 945 valid questionnaires were collected through Credamo questionnaire survey platform. The survey results indicated that 43.7 % of the respondents believed that they would be in a vulnerable state in mixed traffic competition, 30.2 % of the respondents did not know whether they would be in a vulnerable state. Further, women, people with a higher education, people with a more aggressive driving personality, older people, and those with more driving experience were more inclined to think that they would not be in a vulnerable state. Attitude, trust, and perceived usefulness all had positive impacts on driver’s psychological vulnerability judgment, and perceived risk had a negative impact. Therefore, the early promotion of driverless technology should give priority to people with a higher education, more driving experience, older age, and more aggressive driving personality, and focus on attitudes towards this technology, and perceived usefulness, trust, perceived risk.

Effect of Cyber Vulnerabilities on the Adoption of Self-Driving Vehicles – A Review

One of the leading disruptive technologies in the upcoming technological revolution is Self-Driving vehicles. However, the absence of security is the greatest obstacle to adoption. This study looks at how cybersecurity impacts the adoption of driverless cars. The purpose of this paper is to perform a literature review supporting the in-depth analysis of cybersecurity and its impacts on the slower adoption rate of Self-Driving Vehicles. The study's primary goal is to determine the connection between worries about cybersecurity and the rate of adoption of self-driving vehicles. Driverless vehicles are the most effective and cutting-edge technology in the transportation sector, yet there are barriers to their widespread adoption because of cybersecurity worries. As a result, this study will clarify the cybersecurity issues that contributed to the slower deployment of autonomous vehicles. The NIST Cybersecurity Framework serves as the study's theoretical foundation. This paradigm consistently identifies the barriers to new technology adoption in cybersecurity.

Traffic Flow Prediction For Intelligent Transportation System Using Machine Learning

This study attempts to develop a model that forecasts precise data on traffic flow. Everything that can impact the flow of traffic on the road is referred to as the traffic environment, including traffic signals, accidents, rallies, and even road repairs that could result in a traffic bottleneck. The driver or passenger can make an informed choice if they have prior knowledge about the vehicle crowd close to the area that will have the greatest impact on traffic. Additionally, it can be utilised in driverless vehicles, which are the automobiles of the future. Today’s traffic is increasing tremendously, and big data transportation concepts are becoming more popular. We are motivated to develop a machine learning model that forecasts traffic flow because the present prediction techniques and models are still insufficient for use in practical applications. The amount of data available to forecast traffic flow is so enormous that it is awkward and laborious. In this work, we intended to evaluate the data for the transportation with significantly less complexity using machine learning and deep learning methods. The user will be informed of the projected information and the constructed machine learning model will predict the traffic flow.

Impact on Platooning of Autonomous Vehicles using Macro to Micro simulations

Social costs increase as traffic problems continue. Driverless vehicles are attracting attention as a way to overcome this issue. Many said that fully autonomous driving is not a distant future. As one of the autonomous vehicle operations, vehicle platooning has been paid attention. Therefore, this study analyzes the effects of vehicle platooning on the road network. As a large-scale network, Jeju island, one of the cities in Korea was selected to test the platooning arrangement. A macro simulation was developed and calibrated based on the collected traffic counts, and then the network and assigned paths were imported to the micro simulation, which is capable of forming the platoon. The analysis was conducted by changing various parameters of the platooning vehicle. According to the investigation, it can be seen that as the market share of autonomous vehicles increases, delays decrease, and speed increases. Traffic efficiency was improved through platooning in general. It is expected that the results of this study can be used as primary data to develop an optimal traffic flow management strategy for cluster operation.

Examining the legality of artificial intelligence in driverless vehicles and its impact on road traffic laws-comparative analysis

Examining the legality of artificial intelligence in driverless vehicles and its impact on road traffic laws-comparative analysis

The City of Frictionless Mobility

Abstract'Frictionless mobility’, such as through driverless vehicles, has of course been a goal for a very long time in the minds of engineers and designers. But what type of contemporary city might evolve from this? And what happens to other, perhaps more sustainable modes of transport in its wake? Ian Woodcock, Senior Lecturer in Urbanism at the School of Architecture, Design and Planning at the University of Sydney, and Adjunct Associate Professor at the Centre for Design Innovation, Swinburne University of Technology, Melbourne, explores these questions and speculates about the city of the future.

Context-Aware Navigation Protocol for Safe Driving in Vehicular Cyber-Physical Systems

A connected network of automated vehicles on roads can increase the driving safety of driverless vehicles (i.e., autonomous vehicles). The critical level of dangerous situations on the road while driving can be increased by the speed, orientation, and traffic density of the vehicles involved. Therefore, there is a need for a maneuvering mechanism that handles both the current driving vehicle and the oncoming vehicles headed toward an emergency zone (e.g., road hazard and road accident spot). In this paper, we present a context-aware navigation protocol (CNP) that enhances the safety of vehicles driving in urban roads. Firstly, CNP includes a collision avoidance module that builds on both vehicular networks and on-board sensors to track vehicles’ behaviors, and this module analyzes the driving risks to determine the necessary maneuvers in dangerous situations. Secondly, CNP establishes a collision mitigation strategy that limits the severity of collision damages in hazardous road during non-maneuverable scenarios. We conducted a theoretical analysis as well as extensive simulations to prove and evaluate the effectiveness of CNP. The results show that CNP can reduce communication overhead from a baseline scheme by up to 60% while the risk of road collisions is less than 5%.

Cybersecurity and Data Privacy Certification Gaps of Connected and Automated Vehicles

Protecting Connected and Automated Vehicles (CAVs) from cyber attacks and data breaches is a major challenge facing the deployment of driverless vehicles. The CAV is a complex interconnected system consisting of sensors, Artificial Intelligence (AI) processors and external units to assure the automated driving without human interaction. Such complexity increases the surface attacks and makes the CAV highly vulnerable to cyber assaults. It also entangles security audits and certifications procedures. Our work lays out a novel approach towards CAV's certification focused on cybersecurity and data privacy aspects. Stipulated by the analysis on existing standards’ limitations, we propose a Standards Coverage Map (SCM) outlining the CAV's entire ecosystem and linking organisational and technical aspects to the latest standards and regulations from the cyber perspective