Development Of Autonomous System Research Articles

Ethical AI in Autonomous Systems and Decision-making

The rise of autonomous systems has reshaped industries ranging from transportation to healthcare, yet their ethical implications remain a pressing concern. Ethical AI in autonomous systems and decision-making focuses on designing frameworks that prioritize fairness, accountability, and transparency while mitigating biases and unintended harm. This research investigates the ethical challenges posed by autonomy, including moral dilemmas, algorithmic biases, and the trade-off between human oversight and machine independence. Leveraging interdisciplinary insights from philosophy, computer science, and regulatory perspectives, the study proposes a roadmap for embedding ethical principles into the development and deployment of autonomous systems. The findings underscore the importance of stakeholder collaboration, ethical audits, and adaptive governance to ensure that these systems align with societal values and norms.

AINVESTIGATION OF COMPUTER VISION CAPABILITIES IN AUTONOMOUS UNMANNED AERIAL VEHICLES CONTROL SYSTEMS

The development of modern hardware and software has led to a rapid increase in the use of unmanned aerial vehicles, primarily aircraft. One of the promising areas for improving the efficiency of such platforms is the development of autonomous control systems, eliminating the need for human operators. The article presents the results of a study on the possibility of constructing elements of an automatic motion control system based on computer vision for unmanned aerial vehicles. The authors used comparative analysis to evaluate the advantages of two popular instruments: YOLO and SSD. They have also collected data for training the chosen model and tested it in various conditions, described the methodology for creating a training set and presented the model testing results on video images captured by a UAV's camera. The test results confirm that the YOLOv8n model is suitable for object detection on the UAV board using a Raspberry Pi 4 Model B as the single-board hardware platform. The object detection accuracy was from 80% to 90%, with the power consumption of 15-25 watts.

Development of a Machine stereo vision-based autonomous navigation system for orchard speed sprayers

In orchards, radio frequency scintillation caused by high vegetation density can hinder the effectiveness of machinery auto guidance based on the Global Navigation Satellite System (GNSS). Signal interference not only leads to poor quality of machine operation but can also pose operational risks. In this work, we propose an alternative trajectory positioning system to supplement traditional GNSS-based navigation for machinery used in orchards. The aim of this research was to develop a deep learning machine stereo vision guidance system onboard an orchard speed sprayer. The developed system combines a collision avoidance methodology along with deep learning-driven machine vision for interrow positioning and a dead reckoning set of rules for alternating U-turns. The developed methodology was tested in 4 rows of an artificial orchard. The results show that it is possible for the embedded EfficientDet target detection algorithm to guide the equipment at 1, 1.5 and 2 km × h−1 with minimum average root-mean-square errors (RMSEs) of 0.24 m, 0.20 m, and 0.31 m, respectively. When the system navigation was performed using YOLOv7, the minimum average RMSEs for each row were 0.40 m, 0.48 m, and 0.43 m, respectively, for the abovementioned speeds. The U-turn by dead reckoning showed minimum average RMSE values of 0.56 m, 0.22 m, and 0.35 m for row navigation based on EfficientDet at 1, 1.5 and 2 km × h−1, respectively. For YOLOv7-based navigation in rows, the minimum average RMSE values at these speeds were 0.35 m, 0.81 m, and 0.44 m, respectively. This study contributes to the field by proposing an alternative navigation system for orchard machines that operates without the limitations associated with GNSS. In addition, our proposed guidance methodology introduces an RGB-D collision avoidance system with a demonstrated safety capacity for navigation under real scenario conditions.

A bibliometric study toward quantitative research assessment of security of machine learning

Purpose Advances in machine learning (ML) have made significant contributions to the development of intelligent and autonomous systems leading to concerns about resilience of such systems against cyberattacks. This paper aims to report findings from a quantitative analysis of literature within ML security to assess current research trends in ML security. Design/methodology/approach The study focuses on statistical analysis of literature published between 2000 and 2023, providing quantitative research contributions targeting authors, countries and interdisciplinary studies of organizations. This paper reports existing surveys and a comparison of publications of attacks on ML and its in-demand security. Furthermore, an in-depth study of keywords, citations and collaboration is presented to facilitate deeper analysis of this literature. Findings Trends identified between 2021 and 2022 highlight an increase in focus on adversarial ML – 40\% more publications compared to 2020–2022 with more than 90\% publications in journals. This paper has also identified trends with respect to citations, keywords analysis, annual publications, co-author citations and geographical collaboration highlighting China and the USA as the countries with highest publications count and Biggio B. as the researcher with collaborative strength of 143 co-authors which highlight significant pollination of ideas and knowledge. Keyword analysis highlighted deep learning and computer vision as the most common domains for adversarial attacks due to the potential to perturb images whilst being challenging to identify issues in deep learning because of complex architecture. Originality/value The study presented in this paper identifies research trends, author contributions and open research challenges that can facilitate further research in this domain.

Optimal path planning for unmanned aerial vehicles in power line inspection in rechargeable scenario

To address the issue that a single charge of UAVs (Unmanned Aerial Vehicles) do not satisfy task requirements, this paper proposes a solution involving the deployment of charging stations in the mission area. An energy-efficient path planning method is designed for UAVs with charging stations, which simultaneously determines the deployment locations and quantities of charging stations. The method formulates the energy optimization path planning problem of UAVs as an integer linear programming and an algorithm based on greedy strategy is designed for solving the model. A numerical example including simulations across various scenarios demonstrate that the proposed method can search a more energy-efficient paths compared to single-agent multi-sortie schemes with a greedy strategy. This research contributes to the development of intelligent and autonomous UAV systems for power line inspection, enhancing grid reliability and safety.

Evaluation of Autonomous Navigation and Path Accuracy for Unmanned Surface Vehicles Using IMU Sensor and GPS Data

The development of autonomous systems for environmental monitoring is becoming increasingly important. This project focuses on creating a robotic marine vessel, Aqua Sense, for efficient water quality monitoring. Existing methods are often labour-intensive, time-consuming, and lack real-time data capability. The objective is to develop a robotic vessel with autonomous navigation for water quality applications. A comprehensive design approach, including a literature review and careful component selection, was employed. Key components include the Arduino Mega, Blue Robotics T200 thruster, GlobalSat BU-353N5 GPS sensor, BNO055 Inertial Measurement Unit (IMU), and a Li-po 11.1v battery. In this paper, several field trials data collection is presented to evaluate the navigation algorithm. These findings validate the feasibility of Aqua Sense for real-world applications. The varying distance errors at points B and C demonstrate an error range, with a maximum error of approximately 1.130m at point B (about 0.11% of the target location) and a significant variation at point C, reaching up to 1.660m (approximately 0.15%).

Leveraging Synthetic Data for Star and Satellite Photometry

In the realm of Space Domain Awareness (SDA), precise photometric measurements are essential for applications such as stability analysis, shape recovery, and material studies of satellites. However, current methods that rely on manual data collection and analysis are not scalable to autonomous frameworks, which are increasingly necessary due to the growing congestion in space. This research presents an approach to automate photometric measurements within a network of telescopes operating in non-ideal conditions. Our work focuses on achieving reliable photometry in degraded weather conditions, where traditional methods might fail, leading to false detections and unnecessary follow-up efforts. We utilize the SatSim space scene simulator to generate synthetic data for training and testing photometry algorithms. These algorithms include both traditional aperture photometry and machine learning-based approaches. Our methodology employs dynamic segmentation techniques to optimize the detection of satellites and stars under various adverse conditions. The segmentation methods were evaluated for their robustness in different scenarios, with the Depth-First Search + Interquartile Range (DFS + IQR) approach showing the most promise. Through extensive experimentation, we demonstrate that our approach can achieve a photometric precision of approximately 10<sup>−1</sup>, even in adverse conditions. This represents a significant advancement in the field, as it enables more reliable satellite detection and tracking in real-world, non-photometric environments. Additionally, our ablation studies highlight the importance of balanced datasets in reducing error metrics, particularly for underrepresented satellite classes. This work contributes to the development of more effective autonomous SDA systems, capable of operating efficiently in a wide range of environmental conditions.

Development of autonomous navigation system based on neural network and visual servoing for row-crop tracking in vegetable greenhouses

Accurate navigation line localization strategy and robust path tracking control scheme are two key techniques for advancing precision agriculture and enhancing the sustainability of smart farms. In this paper, a superior and cost-effective autonomous navigation system for a visual servoing-based agricultural vehicle in the greenhouse scenario with a distinct layout of two crop rows in each ridge is presented. First, based on image segmentation techniques, a neural network model named DGLNet integrating recognition of crop rows and prediction of the effective area of the navigation line is designed. The linear equation of the navigation line we required is obtained through post-processing operations of linear fitting completed in the effective area. According to experimental results, directly teaching the neural network to learn navigation line localization features utilizes the semantic and spatial information in the feature map to establish a stronger relationship between crop rows and the navigation line, which greatly improves the generalization of the navigation line localization in the case of large-angle yaw scenarios without additional training datasets. In addition, the performance of the network is significantly enhanced by adding an attention mechanism in the backbone based on U-Net. Subsequently, a dataset of cabbage vegetable images covering a wide range of complexities in the greenhouse scenario is created, and is available to support future academic research now. Further, a path tracking control scheme based on point-feature and line-feature is proposed, which can control the agricultural vehicle using the information from camera images without the need to perform explicit localization or maintain a global map. Finally, extensive field experiments have been carried out to show that this autonomous navigation system can preserve the stability of the vehicle and ensure timely convergence of deviations in different complex scenarios, which indicates that this control scheme is reliable and robust. Meanwhile, benefit from the efficiency of this recognition algorithm and the unnecessity of the complete representation of the path in the control scheme, the system has high real-time performance in every scenario.

Empowering Chemical AI Through Systems Chemistry

AbstractThis work presents some ambitious perspectives on how Systems Chemistry can contribute to developing the quite new research line of Chemical Artificial Intelligence (CAI). CAI refers to the efforts of devising liquid chemical systems mimicking some performances of biological and human intelligence, which ultimately emerge from wetware. The CAI systems implemented so far assist humans in making decisions. However, such CAI systems lack autonomy and cannot substitute humans. The development of autonomous chemical systems will allow the colonization of the molecular world with remarkable repercussions on human well‐being. As a beneficial side effect, this research line will help establish a deeper comprehension of the mesmerizing phenomenon of the origin of life on Earth and how cognitive capabilities emerge at a basic physico‐chemical level.

Fundamentals of legislation in autonomous artificial intelligence systems

The paper proposes a method for defining a dedicated operational context as part of the development and deployment of autonomous corporate governance systems. The case study of autonomous board of directors systems is examined. A significant part of the operational context for the autonomous corporate governance systems consists of the regulatory and legal framework that regulates the company’s operations. A special operational context for autonomous artificial intelligence systems can be defined by simultaneously formulating local regulatory documents in two versions, i.e., to be used by people and by autonomous systems. In such a case, the artificial intelligence system receives a clearly defined operational context that allows such a system to perform its functions with a required operational quality. Local regulations that take into account the specificity of operations involving individuals and autonomous artificial intelligence systems can become the foundation of the relevant legislation that would regulate the development and deployment of autonomous systems.

What Will the Delivery Robots Bring Us Tomorrow?

ABSTRACTAutonomous delivery robots offer a promising solution to the challenges of last mile logistics, a crucial topic in times of increasing logistics volume, environmental concern, and ongoing urbanization. This study investigates the acceptance of such robots in various application scenarios for last mile delivery in Germany. A first, quantitative, study investigating the overall acceptance of autonomous delivery robots for the primary predominant usage scenarios of meal and package delivery tested an adapted technology acceptance model via a structural equation model. A second, qualitative, study was conducted to better understand possible future use cases for these robots included semistandardized interviews with 14 individuals and employed a qualitative content structuring analysis method for data analysis. The results of Study 1 confirm that performance expectancy and effort expectancy influence the acceptance of delivery robots, with performance expectancy and behavioral intention being significantly higher for the package than for meal deliveries. However, in both cases, the average intention to use these robots only slightly exceeded the scale mean. Study 2 reveals that autonomous delivery robots are perceived as more convenient than existing alternatives in grocery and pharmaceutical delivery and return processing. The further application of emergency situations, such as illness or the risk of infection, also emerged from the data; even respondents who generally reject the idea of such robots would still use them in such exceptional situations. These results should be considered in the further development of autonomous delivery robot systems.

The Ethics of Artificial Intelligence and Autonomous Systems: Review

Artificial intelligence (AI) and autonomous systems are rapidly advancing technologies that offer significant benefits but also pose new ethical challenges. This review aims to comprehensively analyze the key ethical issues related to AI and autonomy through an expanded discussion of relevant literature. The development of advanced AI and autonomous systems could enable unprecedented capabilities but also risks that are unprecedented in their nature and scale. Ensuring these technologies are developed and applied in an ethical manner will require addressing issues around safety, transparency, accountability, and the prioritization of human values. Researchers have proposed technical and philosophical approaches to building "friendly" or "beneficial" AI that avoids potential harms. However, many open questions remain about how to properly specify and validate ethical constraints for systems that may surpass human levels of intelligence. Autonomous systems like self-driving vehicles also introduce new ethical dilemmas around responsibility and decision- making in safety-critical situations. Standards are needed to help guide the design of autonomous functions to be transparent, predictable, and respectful of human dignity and diversity. Governments and international organizations have begun outlining policy recommendations for developing AI that is trustworthy and compatible with human rights, privacy, and democratic values.

The International Law Dilemma of Autonomous Weapon System

This paper aims to highlight the potential for serious humanitarian disasters caused by the rapid development of autonomous weapons systems, as they are currently unable to fully grasp the ability to analyze their targets and clearly distinguish between combatants and military targets due to current technological limitations. There is also controversy over whether autonomous weapons systems are combatants, and there is a certain degree of regulatory deficiencies in the field of international law. Existing international treaties are unable to perfectly regulate autonomous weapons systems and punish unlawful behavior. The paper mainly uses the method of analyzing specific problems based on legal principles and draws conclusions by referring to some cases. The conclusion of this paper is that the international community needs to establish a new, targeted international legal treaty, establish a more reasonable and realistic international soft law, establish and improve a broader international exchange system, and encourage countries to work together to solve this problem.

Recent Developments and Future Prospects in Collision Avoidance Control for Unmanned Aerial Vehicles (UAVS): A Review

The industry has been significantly enhanced by recent developments in UAV collision avoidance systems. They made collision avoidance controllers for self-driving drones both affordable and hazardous. These low-maintenance, portable devices provide continuous monitoring in near-real time. It is inaccurate due to the fact that collision avoidance controllers necessitate trade-offs regarding data reliability. Collision avoidance control research is expanding significantly and is disseminated through publications, initiatives, and grey literature. This paper provides a concise overview of the most recent research on the development of autonomous vehicle collision avoidance systems from 2017 to 2024. In this paper, the state-of-the-art collision avoidance system used in drone systems, the capabilities of the sensors used, and the distinctions between each type of drone are discussed. The pros and cons of current approaches are analyzed using seven metrics: complexity, communication dependency, pre-mission planning, resilience, 3D compatibility, real-time performance, and escape trajectories.

Ontology for BIM-Based Robotic Navigation and Inspection Tasks

The availability of inspection robots in the construction and operation phases of buildings has led to expanding the scope of applications and increasing technological challenges. Furthermore, the building information modeling (BIM)-based approach for robotic inspection is expected to improve the inspection process as the BIM models contain accurate geometry and relevant information at different phases of the lifecycle of a building. Several studies have used BIM for navigation purposes. Also, some studies focused on developing a knowledge-based ontology to perform activities in a robotic environment (e.g., CRAM). However, the research in this area is still limited and fragmented, and there is a need to develop an integrated ontology to be used as a first step towards logic-based inspection. This paper aims to develop an ontology for BIM-based robotic navigation and inspection tasks (OBRNIT). This ontology can help system engineers involved in developing robotic inspection systems by identifying the different concepts and relationships between robotic inspection and navigation tasks based on BIM information. The developed ontology covers four main types of concepts: (1) robot concepts, (2) building concepts, (3) navigation task concepts, and (4) inspection task concepts. The ontology is developed using Protégé. The following steps are taken to reach the objectives: (1) the available literature is reviewed to identify the concepts, (2) the steps for developing OBRNIT are identified, (3) the basic components of the ontology are developed, and (4) the evaluation process is performed for the developed ontology. The semantic representation of OBRNIT was evaluated through a case study and a survey. The evaluation confirms that OBRNIT covers the domain’s concepts and relationships, and can be applied to develop robotic inspection systems. In a case study conducted in a building at Concordia University, OBRNIT was used to support an inspection robot in navigating to identify a ceiling leakage. Survey results from 33 experts indicate that 28.13% strongly agreed and 65.63% agreed on the usage of OBRNIT for the development of robotic navigation and inspection systems. This highlights its potential in enhancing inspection reliability and repeatability, addressing the complexity of interactions within the inspection environment, and supporting the development of more autonomous and efficient robotic inspection systems.

The commission of crimes using autonomous weapon systems: Issues of causation and attribution

Today’s military takes advantage of technological progress primarily through developments in the war industry. Of particular importance is the development and use of advanced autonomous weapon systems, which are changing the way conflicts are fought and redefining the basic strategies on the modern battlefield. The use of these systems raises ethical, philosophical, and legal questions about the relationship of causality and attribution that must exist between an act and its criminal result.

Human feedback enhanced autonomous intelligent systems: a perspective from intelligent driving

Artificial intelligence empowers the rapid development of autonomous intelligent systems (AISs), but it still struggles to cope with open, complex, dynamic, and uncertain environments, limiting its large-scale industrial application. Reliable human feedback provides a mechanism for aligning machine behavior with human values and holds promise as a new paradigm for the evolution and enhancement of machine intelligence. This paper analyzes the engineering insights from ChatGPT and elaborates on the evolution from traditional feedback to human feedback. Then, a unified framework for self-evolving intelligent driving (ID) based on human feedback is proposed. Finally, an application in the congested ramp scenario illustrates the effectiveness of the proposed framework.

Putting algorithmic bias on top of the agenda in the discussions on autonomous weapons systems

Biases in artificial intelligence have been flagged in academic and policy literature for years. Autonomous weapons systems—defined as weapons that use sensors and algorithms to select, track, target, and engage targets without human intervention—have the potential to mirror systems of societal inequality which reproduce algorithmic bias. This article argues that the problem of engrained algorithmic bias poses a greater challenge to autonomous weapons systems developers than most other risks discussed in the Group of Governmental Experts on Lethal Autonomous Weapons Systems (GGE on LAWS), which should be reflected in the outcome documents of these discussions. This is mainly because it takes longer to rectify a discriminatory algorithm than it does to issue an apology for a mistake that occurs occasionally. Highly militarised states have controlled both the discussions and their outcomes, which have focused on issues that are pertinent to them while ignoring what is existential for the rest of the world. Various calls from civil society, researchers, and smaller states for a legally binding instrument to regulate the development and use of autonomous weapons systems have always included the call for recognising algorithmic bias in autonomous weapons, which has not been reflected in discussion outcomes. This paper argues that any ethical framework developed for the regulation of autonomous weapons systems should, in detail, ensure that the development and use of autonomous weapons systems do not prejudice against vulnerable sections of (global) society.

Comprehensive Survey of Autonomous Driving Systems and Advanced Technologies: Literature Review, Gap Analysis and Future Directions

Abstract: This article presents a literature review of numerous research papers focusing around the topic ‘Development of Autonomous Driving Vehicle System’, and related works. The advent of autonomous driving technology has revolutionized the automotive industry, promising enhanced safety, efficiency, and convenience on the road. A critical aspect of autonomous vehicle development is the assessment of their performance ina controlled and risk-free environment. Virtual environments, enabled by cutting-edge technologies, offer a dynamic plat- form for rigorous testing and training of autonomous vehicles. This paper aims to study and analyze different approaches and methodologies that are implemented for the development of Autonomous Driving Systems(ADS). Some of the primary aspects that are found common in most papers are Virtual Environment, pedestrians’ safety, privacy, security, real-time datapresentation, precise torque control, Reinforcement Learning, Deep Learning, Hardware-in-the-loop (HIL)- simulation, Model- in-the-loop (MIL)-simulation, etc. The sole idea of extracting valuable information from a virtual environment ensures a sense of safety as there are no humans involuntarily involved to take part in the development. However, the data extracted from the virtual environment must be highly accurate and reliable, as it will be trained and tested in real environments post deployment. Collision scenarios need to be carefully studied, for which relative positioning of vehicle and pedestrians should be taken into account, so as to examine their velocities, time to collision, and appropriately taking actions. Above all, it should be noted that the safety of human lives holds the highest priority, if a method suggests a high risk factor for a human life, then it should be either discarded, or improved

Towards Autonomous Driving: Technologies and Data for Vehicles-to-Everything Communication.

Autonomous systems are becoming increasingly relevant in our everyday life. The transportation field is no exception and the smart cities concept raises new tasks and challenges for the development of autonomous systems development which has been progressively researched in literature. One of the main challenges is communication between different traffic objects. For instance, a mobile robot system can work as a standalone autonomous system reacting to a static environment and avoiding obstacles to reach a target. Nevertheless, more intensive communication and decision making is needed when additional dynamic objects and other autonomous systems are present in the same working environment. Traffic is a complicated environment consisting of vehicles, pedestrians, and various infrastructure elements. To apply autonomous systems in this kind of environment it is important to integrate object localization and to guarantee functional and trustworthy communication between each element. To achieve this, various sensors, communication standards, and equipment are integrated via the application of sensor fusion and AI machine learning methods. In this work review of vehicular communication systems is presented. The main focus is the researched sensors, communication standards, devices, machine learning methods, and vehicular-related data to find existing gaps for future vehicular communication system development. In the end, discussion and conclusions are presented.