Autonomous Decision-making Process Research Articles

Architecture for Multiagent Systems with UNS Middleware and mediator agent using object-centric process mining

The increasing complexity of industrial processes demands innovative solutions for the integration and management of multi-agent systems. This work proposes a hierarchical multi-agent system architecture to unify these systems, aiming for efficiency and autonomy in complex and connected production environments. The proposal focuses on the integration of multiple tasks and layers, promoting operational freedom without compromising security and agility. To optimize the use and understanding of data flows, the system uses Object-Centric Process Mining techniques at runtime, an innovative approach for processes with autonomous agents, given its ability to manage event- and object-oriented data. The architecture adopts the OCEL 2.0 log standard, which provides a structured and interoperable basis for the administration of large volumes of production data, facilitating detailed analyses and quick, accurate decisions. The proposed structure is aligned with the requirements of Industry 4.0, especially the RAMI 4.0 model, and relies on the mediation of a unified system core (UNS), which integrates subsystems such as SCADA, intelligent devices, and Process Mediators. Performance tests have demonstrated that the architecture is robust, scalable, and agile, with the OCPM Mediator accelerating secure responses to agents and promoting a resilient, autonomous, and data-driven decision-making process. This work highlights that the proposed architecture offers an effective solution for multi-agent systems in advanced manufacturing, enabling the industry to address the challenges of digital transformation.

Swarm Intelligence and Unmanned Systems: The Potentıal Impact of The Principles of Swarm Intelligence and Collective Behaviour in Nature On Unmanned Systems and Autonomous Organizational Structures

This paper examines the potential implications of the principles of swarm intelligence and collective behavior in nature for unmanned systems and autonomous organizational structures. Swarm intelligence is inspired by natural systems in which individual units interact according to simple rules to form a complex and organized whole. These principles can be observed in a wide range of situations, from the synchronized flight of flocks of birds to the harmonized swimming behavior of schools of fish. The study emphasizes that swarm intelligence principles have the potential to create more flexible, resilient and efficient systems with decentralized control mechanisms and autonomous decision-making processes. Furthermore, it is suggested that these approaches can find applications in many fields, from military operations to agricultural and environmental monitoring, from disaster response to urban planning. The study provides a detailed analysis of swarm behavior in nature and discusses how these behaviors can be emulated and optimized in unmanned systems. In this context, the potential impacts of swarm intelligence and collective behavior principles on unmanned systems are evaluated in terms of increasing their adaptability, optimizing energy efficiency and maximizing mission success. It is also argued that these principles can contribute to making unmanned systems more resilient to contingencies and changing environmental conditions. This theoretical study suggests that swarm intelligence principles can provide innovative solutions for future unmanned systems and autonomous organizational structures.

Data driven digital twin system for the cross-domain vehicle

The Cross-Domain Vehicle (CDV) is a sophisticated marine equipment capable of performing tasks across different domains. This paper aims to develop a data-driven digital twin system for the CDV to achieve precise motion control and data monitoring during its operation. Leveraging the kinematic physical characteristics of the CDV, the digital twin system constructs a virtual counterpart of the vehicle, establishing a mapping relationship between the physical and virtual entities. The use of a Long Short-Term Memory (LSTM) network model is proposed for forecasting the motion state of the CDV within the digital twin framework, supporting the vehicle's autonomous motion decision-making process. Additionally, an innovative model predictive control strategy is employed to achieve surface speed tracking control for the CDV, leveraging predictive data within the digital twin system. Utilizing the digital twin system to optimize control parameters, better underwater depth control effects can be achieved for the CDV. Finally, through the system implementation and experiment verification, the effectiveness of the digital twin system is successfully demonstrated, providing reliable results for both surface speed tracking control and underwater depth control.

Navigating the AI Frontier

The rapid digital transformation driven by Artificial Intelligence (AI) is reshaping innovation and operational efficiency across industries. As autonomous AI systems are becoming prevalent, they significantly influence traditional business models, societal norms, and legal frameworks. AI technologies are evolving beyond mere tools to become independent economic agents capable of generating assets, making decisions, commercializing products and services, and being accountable for their actions. This evolution requires a reassessment of traditional concepts of corporate and moral personhood, particularly as AI-driven businesses need to operate inside conventional legal frameworks. This paper explores the rise of entirely AI-driven entities with fully autonomous decision-making processes, advocating for the legal status of artificial personhood. It underscores the need for an ethical and regulatory framework to ensure these entities will proliferate and operate for human progress with integrity and responsibility.

Autonomous Vehicle Safety through the SIFT Method: A Conceptual Analysis

This study aims to provide a conceptual analysis of the dynamic transformations occurring in an autonomous vehicle (AV), placing a specific emphasis on the safety implications for pedestrians and passengers. AV, also known as self-driving automobiles, are positioned as potential disruptors in the contemporary transportation landscape, offering heightened safety and improved traffic efficiency. Despite these promises, the intricate nature of road scenarios and the looming specter of misinformation pose challenges that can compromise the efficacy of AV decision-making. A crucial aspect of the proposed verification process is the incorporation of the stop, investigate the source, find better coverage, trace claims, quotes, and media to the original context (SIFT) method. The SIFT method, originally designed to combat misinformation, emerges as a valuable mechanism for enhancing AV safety by ensuring the accuracy and reliability of information influencing autonomous decision-making processes.

Watchful waiting: public relations strategies to minimize and manage a fake news crisis

PurposeFake news stories have become a central element of crises that corporate public relations practitioners have confronted. Whether such stories are rumors, outright lies or deliberate attempts to discredit corporations, they have the same impact and require specific strategies for public relations practitioners to effectively respond. The purpose of this study is to uncover strategies to manage crises that arise from fake news and if and how these strategies differ for other corporate crises.Design/methodology/approachIn this multi-method study of 21 in-depth interviews and a 8-person focus group with senior-level corporate public relations practitioners, authors explored decision-making strategies for responding to fake news crises. Transcripts of interviews and the focus group were thematically analyzed.FindingsResults reveal insights regarding how public relations practitioners determine if and when to respond to fake news crises in corporations; what response strategies public relations practitioners have the autonomy to employ for fake news crises in corporations, and how public relations practitioners control media narratives during fake news crises in corporations.Practical implicationsThe findings guide public relations practitioners to craft an autonomous decision-making process and effective online listening strategies—establishing a watchful waiting approach—and determine if the fake news issue is a passing moment or movement swirling into a crisis.Originality/valueFew studies have examined the perspectives of crisis communication experts about minimizing and managing fake news crises. The study identifies opportunities for future research focused on crises originating from fake news and disinformation.

Dynamic task allocation in multi autonomous underwater vehicle confrontational games with multi-objective evaluation model and particle swarm optimization algorithm

In this paper, a non-zero-sum game model based on a multi-objective evaluation model was adopted to solve the dynamic task allocation problem of underwater multiple Autonomous Underwater Vehicle (multi-AUV). By introducing a functional coordination mechanism, the high degree of coordination in practical confrontation scenarios was reflected, and the autonomous decision-making and task allocation process of multiple AUVs were clarified. Secondly, a multi-objective evaluation model including survival value, strike income, and ammunition loss was constructed, and weighted processing was performed on the multiple objectives using the Analytic Hierarchy Process (AHP) method, obtaining the benefits of each non-zero-sum strategy in dynamic games. In addition, a particle swarm optimization (PSO) algorithm that combines the theory of good point sets theory (G) and speed control factors (S) for improvement, called GSPSO, was used to find the optimal strategy in the game and allocate tasks. Finally, simulation analysis showed that the collaborative system with functional coordination mechanisms significantly improved the combat capabilities of underwater multiple AUVs. The multi-objective evaluation model combined with AHP can correctly and comprehensively evaluate the advantages and disadvantages of each strategy and correctly respond to changing confrontation tasks and decision preferences. The proposed algorithm improved the convergence speed and global search ability by enhancing the diversity of the population and the effectiveness of iterative solutions, ensuring real-time decision-making and task allocation in complex high-dimensional dynamic games.

Local knowledge matters: understanding the decision-making processes of communities under climate change in Suriname

IntroductionTraditionally, local communities have relied on practical observations accumulated over extended periods to inform their decision-making. This knowledge is now recognized as a viable solution for communities to adapt to climate change effectively. The impact of climate change brings an extra layer of complexity to local communities' detection- and decision-making processes, which needs to be better comprehended.MethodologyOur study builds on the foundation of conflict resolution and examines the knowledge systems and corresponding decision-making processes of local communities living in urban, rural, and tropical forest regions of Suriname, South America.ResultsThe mixed-method study showed that the autonomous decision-making processes of these communities are guided by their knowledge systems, intertwined with values and interests. Forest communities in remote locations rely solely on their robust knowledge base for crafting adaptation solutions, while urban and rural communities near the administrative centers develop adaptation strategies primarily considering their access to social networks and relative power.DiscussionThe study highlights local knowledge as the primary determinant for the direction communities take in adaptation, with tradeoffs becoming evident as communities navigate the broader social context. The recognition and integration of this knowledge emerge as a critical factor in enhancing climate change adaptation at the local level.

Why Do Retail Customers Adopt Artificial Intelligence (AI) Based Autonomous Decision-Making Systems?

Advancements in Artificial Intelligence (AI) have led to the development of autonomous decision-making processes, allowing customers to delegate decisions and tasks. Such technologies have the potential to alter the retailing landscape. Grounded in the unified theory of acceptance and use of technology and Hofstede's cultural theory, this article investigates customers’ adoption of AI-based autonomous decision-making processes by analyzing 454 customer responses using covariance-based structural equation modeling. The results reveal that effort expectancy, performance expectancy, facilitating conditions, and social influence are positively associated with customers’ adoption of autonomous decision-making processes. Collectivism strengthened the positive association of social influence with customer attitude, whereas uncertainty avoidance dampened the associations of performance expectancy, effort expectancy, and social influence with attitude. The findings provide useful implications for system developers and managers while providing future researchers with directions to further explore autonomous decision-making processes.

Industry 4.0: Makes Manufacturing Factory Smatter

The purpose of this article is to present an overview of industry 4.0. The goal of this presentation is to give a brief perspective of what Industry 4.0 is, its challenges in today’s manufacturing environments. Many researchers have mentioned that implementing industry 4.0 is a response to the current challenges in fast changing environments. In this paper, I have provided a comprehensive introduction and definition about this Industry 4.0 concept, transformation steps and explain the technologies involved in Industry 4.0 ecosystem. After that, I have presented several points about challenges and issues of Industry 4.0, then the most relevant and potential benefits of this new industrial paradigm. Lastly, I have ended this presentation by drawing a conclusion. The successful path to smatter Industry 4.0 depends on having a vision and enterprise-wide strategy, rather than taking a piecemeal approach to implementing technology solutions. Focus on business drivers, tech enablers that overcome pain points, and working with the right partner ecosystem to accelerate sustainable transformation for greater business value and opportunity outcomes. Now in competitive market, it is more likely a company will be more profitable and create jobs when it produces products with higher flexibility, quality and technology content and applying Industry 4.0 than by competing on low-price products. In addition, companies can take advantage of the broad range of aspects of Industry 4.0, including smart products, smart assets, and optimized factories operating sustainably and creating optimal conditions for empowered workers. Manufacturing organizations need an enterprise-wide strategy to gain the full business value of Industry 4.0, including productivity, sustainability, and competitive edge. A smatter Industry 4.0 approach helps organizations overcome the challenges they currently face, and it also enables them to become future-ready to build anything, anytime, anywhere. The goal of Industry 4.0 implement is to enable autonomous decision-making processes, monitor assets and processes in real-time, maintaining improved quality and enable equally real-time connected value creation networks through early involvement of stakeholders, and vertical and horizontal integration.

Agent-based Decision Making and Control of Manufacturing System Considering the Joint Production, Maintenance, and Quality by Reinforcement Learning

Taking an integrated approach towards production, maintenance, and control in manufacturing systems is crucial due to the profound impact of their interconnections. Investigating these aspects in isolation may lead to infeasible solutions. This research focuses on the real-time and autonomous decision-making process concerning joint production planning, maintenance, and quality problems in a stochastic deteriorating production system with limited maintenance activities. Formulating the problem as a continuous semi-Markov decision process accounts for the complexities of the real production system and the occurrence of events over an uneven and continuous period. While dynamic programming is a common tool for addressing joint optimization problems, it has limitations, such as the curse of dimensionality. In this study, the optimal policy of the decision-maker agent is obtained by the goal-directed machine learning method called (R-SMART) and agent-based modeling. To the author's knowledge, the proposed approach is novel, and there is little research on such an implementation of the joint optimization problem. The quality of the optimal policy is evaluated through heuristic and simulation-optimization methods in various scenarios. The results demonstrate that the proposed RL-based method outperforms others in most scenarios, achieving a stable, integrated optimal policy.

Automated Speed and Lane Change decision-making Model using Support Vector Machine

One of the major obstacles that the auto industry must overcome is the rise of autonomous vehicles. The study of lane-changing is an important part of this problem. Previous studies on autonomous vehicle lane changes have predominantly focused on lane change path planning and path monitoring, with limited attention given to the autonomous vehicle's lane change decision-making process. This paper introduces a novel Lane Change Decision-Making Model for autonomous vehicles using the Support Vector Machine (SVM) method. The suggested model employs real-time sensor data to assess whether or not a lane change is possible, taking into account the proximity of other vehicles (cars, buses, motorbikes), and adjusting speed as necessary to ensure a seamless transition. Researching the various facets of lane changes in autonomous vehicles allows for decision-making that is grounded in utility, safety, and tolerance. The implementation of a support vector machine (SVM) technique with Bayesian parameter optimization is used to deal with the non-linearity and complexity of the process of autonomous lane change decision-making. Finally, we compare the suggested SVM model against a rule-based lane change model using the test data. The SVM-based strategy is shown to improve lane change decision-making in a comprehensive simulation exercise, which in turn improves the safety and efficiency of autonomous driving systems. The experiment also use a real vehicle to gauge the efficacy of the underlying decision-making model.

Teoria racjonalnego wyboru w świetle biopolityki

Both rational choice theory and biopolitics are extremely important paradigms in the social sciences - including political science. It would seem that their basic axioms contradict each other because the influence of biopolitical power microstructures excludes sovereign and autonomous decision-making processes. Thus, the paper adopts the hypothesis that the assumptions of biopolitics falsify the basic axioms of rational choice theory, and therefore we can consider it as the antithesis of rational choice theory. In order to verify the hypothesis, the method of content analysis was applied - with particular emphasis on studies concerning both paradigms and primary sources supported by elements of comparative studies. On the basis of the analyses carried out, it was proved that the assumptions of both paradigms do not have to contradict each other - they may even be complementary. Human actions based on the principle of rationality and self-interest can be justified by the actions of biopolitics, and therefore the hypothesis has been falsified.

Explainable autonomous robots in continuous state space based on graph-structured world model

Autonomous robots using deep reinforcement learning have demonstrated superior capabilities on relatively simple specific tasks, but they often lack high-level, abstract planning capabilities when faced with complex, long-horizon tasks. Even if the autonomous robot successfully achieves long-horizon goals, users find it difficult to trust their decision-making process. To increase user trust in the decision-making process when an autonomous robot executes a long-horizon task, this paper proposes an algorithm that empowers the autonomous agent to explain to users the transition from the current state to the target state in a continuous state space, as well as to explain the errors in user estimates. A framework that uses a graph-based world model is proposed to identify important nodes and reachability between nodes in the decision-making process; based on these nodes and reachability, the model generates the required explanations. To validate our proposed method's ability to generate long-horizon plans and explanations, we conducted experiments in PointMaze environments. Our simulation results confirm the effectiveness of our approach in generating reliable world models for long-horizon tasks. Moreover, our explanations, based on these world models, significantly enhance the user's understanding of the autonomous robotic decision-making process and the system's capabilities and limitations.

Conditions for autonomous reproductive decision-making in prenatal screening: A mixed methods study

BackgroundPregnant women should be able to make autonomous and meaningful decisions about prenatal screening for fetal abnormalities. It remains largely unclear which circumstances facilitate or hinder such a decision-making process. ObjectiveTo investigate what conditions Dutch pregnant women and professional experts consider important for autonomous reproductive decision-making in prenatal screening for fetal abnormalities, and the extent to which, according to women, those conditions are met in practice. MethodsA mixed methods study was conducted in the Netherlands in 2016–2017. A conceptual model was used to interview professional experts (n = 16) and pregnant women (n = 19). Thematic analysis was performed to identify important conditions. Subsequently, a questionnaire assessed the perceived importance of those conditions and the extent to which these were met, in the experience of pregnant women (n = 200). ResultsProfessional experts stressed the importance of information provision, and emphasized a rational decision-making model. Pregnant women differed in what information they felt was needed, and this depended on the screening decision made. Questionnaire findings showed that women prioritized discussion and consensus with partners. Information about test accuracy and miscarriage risk of invasive follow-up testing was also considered important. Two key conditions were not adequately met, in the experience of women: (1) having information about miscarriage risk; (2) not being directed by health professionals in decision-making. ConclusionAccording to women, discussion and consensus with partners was considered a highly important condition for an autonomous and meaningful decision-making process. Access to information about safety of testing and ensuring that women are not being directed in their decision-making by health professionals seem to be areas for improvement in prenatal care practice.

A Simple and Accurate Energy-Detector-Based Transient Waveform Detection for Smart Grids: Real-World Field Data Performance

Integration of distributed energy sources, advanced meshed operation, sensors, automation, and communication networks all contribute to autonomous operations and decision-making processes utilized in the grid. Therefore, smart grid systems require sophisticated supporting structures. Furthermore, rapid detection and identification of disturbances and transients are a necessary first step towards situationally aware smart grid systems. This way, high-level monitoring is achieved and the entire system kept operational. Even though smart grid systems are unavoidably sophisticated, low-complexity algorithms need to be developed for real-time sensing on the edge and online applications to alert stakeholders in the event of an anomaly. In this study, the simplest form of anomaly detection mechanism in the absence of any a priori knowledge, namely, the energy detector (also known as radiometer in the field of wireless communications and signal processing), is investigated as a triggering mechanism, which may include automated alerts and notifications for grid anomalies. In contrast to the mainstream literature, it does not rely on transform domain tools; therefore, utmost design and implementation simplicity are attained. Performance results of the proposed energy detector algorithm are validated by real power system data obtained from the DOE/EPRI National Database of power system events and the Grid Signature Library.

Integrated Bayesian and association-rules methods for autonomously orienting COVID-19 patients.

The coronavirus infection continues to spread rapidly worldwide, having a devastating impact on the health of the global population. To fight against COVID-19, we propose a novel autonomous decision-making process which combines two modules in order to support the decision-maker: (1) Bayesian Networks method–based data-analysis module, which is used to specify the severity of coronavirus symptoms and classify cases as mild, moderate, and severe, and (2) autonomous decision-making module–based association rules mining method. This method allows the autonomous generation of the adequate decision based on the FP-growth algorithm and the distance between objects. To build the Bayesian Network model, we propose a novel data–based method that enables to effectively learn the network’s structure, namely, MIGT-SL algorithm. The experimentations are performed over pre-processed discrete dataset. The proposed algorithm allows to correctly generate 74%, 87.5%, and 100% of the original structure of ALARM, ASIA, and CANCER networks. The proposed Bayesian model performs well in terms of accuracy with 96.15% and 94.77%, respectively, for binary and multi-class classification. The developed decision-making model is evaluated according to its utility in solving the decisional problem, and its accuracy of proposing the adequate decision is about 97.80%.Graphical abstract

Digital freedom and corporate power in social media

ABSTRACT The impact of large digital corporations on our freedom is often lamented but rarely investigated systematically. This paper aims to fill this desideratum by focusing on the power of social media corporations and the freedom of their users. In order to analyze this relationship, I distinguish two forms of freedom and two corresponding forms of power. Social media corporations extend their users’ freedom of choice by providing many new options. This provision, however, comes with the domination by these corporations because it is based on their power of uncontrolled interference. Users could escape this domination through exit. One reason why they do not choose this option is that they would lose the benefits associated with the network effects provided by social media services. A second reason is that the power of social media corporations runs so deep that they are able to manipulate the autonomous decision-making processes of their users. Users are provided with many new avenues for authentic self-presentation on social media. By using them, however, users need to conform to a web interface that is designed by corporations to undermine self-control. Through these two mechanisms, corporations are able to promote an interest in users to present themselves on their platforms. Insofar as this works, they secure the users’ compliance to their domination through subjectivation. This double conjunction of choice and domination, on the one hand, and autonomy and subjectivation, on the other, makes the case that the very power of corporate social media stems from their intrinsic connection to genuine practices of freedom.

Adaptive intelligent autonomous system using artificial somatic markers and Big Five personality traits

This work presents the design of an adaptive, intelligent, autonomous system based on the use of artificial somatic markers and personality traits of the Big Five model. The aim is for the system to be capable of performing decision-making processes autonomously without human intervention, adapting its decision strategy according to the domain conditions and obtained results. For this, the system permanently has one of the five different personality profiles of the Big Five model, and the ability to adapt its personality profile in real time based on artificial somatic activation, that is, to the reactions experienced by the system in the face of perceived stimuli during the autonomous decision-making process. The novelties of this work include the following: design of a general operational framework of an adaptive, intelligent, autonomous system, which integrates domain indicators, artificial somatic markers, personality profiles, domain profiles, and business rules; design of a somatic index function; design of a scheme for the translation of artificial somatic reactions to personality profiles of the Big Five model; and definition of a case study based on stock markets. The promising results show that the system achieves effectiveness and efficiency from the decisions made.

Ancillary mechanism for autonomous decision-making process in asymmetric confrontation: a view from Gomoku

ABSTRACT This paper investigates how agents learn and perform efficient strategies by trying different actions in asymmetric confrontation setting. Firstly, we use Gomoku as an example to analyse the causes and impacts of asymmetric confrontation: the first mover gains higher power than the second mover. We find that the first mover learns how to attack quickly while it is difficult for the second mover to learn how to defend since it cannot win the first mover and always receives negative rewards. As such, the game is stuck at a deadlock in which the first mover cannot make further advances to learn how to defend, and the second mover learns nothing. Secondly, we propose an ancillary mechanism (AM) to add two principles to the agent’s actions to overcome this difficulty. AM is a guidance for the agents to reduce the learning difficulty and to improve their behavioural quality. To the best of our knowledge, this is the first study to define asymmetric confrontation in reinforcement learning and propose approaches to tackle such problems. In the numerical tests, we first conduct a simple human vs AI experiment to calibrate the learning process in asymmetric confrontation. Then, an experiment of 15*15 Gomoku game by letting two agents (with AM and without AM) compete is applied to check the potential of AM. Results show that adding AM can make both the first and the second movers become stronger in almost the same amount of calculation.