CETINIA Book Series
CETINIA has launched this publication series to boost the dissemmination of results from the research activities of its members. The series includes PhD theses, other monographs, as well as collections of scientífic articles.
Distributed, Scalable, Efficient and Fair Coordination for Agriculture Mobile Robot Fleets
Aitor López Sánchez authored the book Distributed, Scalable, Efficient and Fair Coordination for Agriculture Mobile Robot Fleets which was published as monograph number 10 of the CETINIA series.
Agricultural mobile robots (or agribots) are an example of new technologies designed to increase efficiency and productivity in agricultural practices. Agricultural cooperatives manage fleets of vehicles, such as autonomous tractors, agribots, and implements (tools). Because these vehicles may belong to different owners or companies, the goal is not only to reduce overall costs when completing all tasks, but also to ensure a fair distribution of profits among participants. Although cooperatives promote collaborative work, a tension persists between the collective effort and the individual interest of each farmer to maximize their profits, while maintaining autonomy and control over their decisions. In this work we develop routing techniques for cooperative agricultural fleets aimed at balancing efficiency and fairness, promoting long-term collaboration. The techniques used belong to the area of operations research, mathematical optimization and multi-agent systems. For each model, we design a centralized exact model based on mixed integer linear programming (MILP), which captures the constraints and objectives of the system, and which also serves as a basis for validating subsequent developments. Thanks to the distributed structure of the problem, we design a distributed multi-agent architecture (DIMASA), in which each decision maker is modeled as an agent. The proposed methods have been validated through empirical tests that confirm their effectiveness.
Dr. José Antonio Rodríguez García authored the book Laicidad e Inteligencia Artificial which was published as monograph number 11 of the CETINIA series (ISBN: 9-788410-707405).
The book comprises three main blocks: Artificial Intelligence and Values, Theoretical Framework of Secularism, and Use Cases. In the first block, the concept of AI is characterised and the ethical and legal values that should guide its implementation are discussed, the paying special attention to Regulation 2024/1689 of the European Union. The second block addresses secularism, its definition and relevance in the Spanish legal system. Secularism is explored as a universal value in International Law and its role in democratic coexistence, as well as the relationship of the implementation of religious and transhumanist values in AI systems with secularism. In addition, the secular perspective in computational law and the implementation of secularism in AI systems which was published as monograph number 9 of the CETINIA series. The third block presents specific use cases, such as the manipulation of consciousness, equality and non-discrimination (algorithmic biases), and freedom of expression in relation to AI, especially in social networks. It also explores whether AI systems may have any fundamental rights recognized, the use of AI in educational contexts, and the impact of AI systems in sensitive fields such as healthcare. Finally, the use of AI systems by religious groups are analyzed.
Dr. Jeremías Dötterl authored the book Mobile Crowdsourcing with Task Transfers: A Market-based Multiagent Approach which was published as monograph number 10 of the CETINIA series.
In mobile crowdsourcing, spatial tasks are outsourced to an on-demand workforce of autonomous individuals who find nearby tasks using their smartphones. However, operating such systems reliably is difficult, as tasks get frequently assigned to crowd workers who during task execution struggle to complete these tasks successfully, causing high failure rates and low service quality. A promising remedy is to respond to failure-provoking events by transferring tasks to better-suited workers who use other routes or vehicles. However, workers are autonomous and may reject transfers that, though globally efficient, are not beneficial to them individually. Furthermore, task outcomes are uncertain and must be predicted. Also, in crowdsourced delivery, transfers require the handover of parcels, which makes the coordination of task transfers even more challenging. This book studies the problem of coordinating task transfers among autonomous self-interested crowd workers. It presents a market-based solution that allows crowd workers, represented by software agents, to trade tasks on a computational marketplace. The agents apply machine learning on sensor data obtained from the workers’ mobile devices to predict task outcomes and to exploit the predictions in their decisions. Simulation experiments show that the approach can reduce task failures effectively and help to operate mobile crowdsourcing systems more reliably.
Inteligencia Artificial: Umbrales éticos, Derecho y Administraciones Públicas (Artificial Intelligence: Ethical Thresholds, Law and Public Administrations)
Dr. Mar Moreno Rebato authored the book Inteligencia Artificial – Umbrales éticos, Derecho y Administraciones Públicas which was published as monograph number 9 of the CETINIA series (ISBN: 978-84-1391-029-1).
In its proposal for a Regulation on Artificial Intelligence (AI), the EU is committed to a lawful, ethical, and robust AI that guarantees the ethical principles built around it. The ethical guidelines formulated by the independent group of experts, created by the European Commission, set out from four ethical principles from which seven requirements are extracted that AI systems must meet. This book is structured precisely in this manner. First, it explains where these ethical principles arise from and then how they have been transferred, at the normative level, to aforementioned proposal for an EU Regulation. Finally, on the basis of this background, the book analyses the current situation of the use of AI by the Spanish Public Administration: its deployment, the changes that are beginning to be detected at an institutional and organizational level, the degree of impact on administrative legislation and administrative procedures, as well as legal problems that arise with regard to the proposed EU Regulation on AI.
Dr. Radu-Casian Mihailescu authored the book Coordination Mechanisms for Agent-Based Smart Grids which was published as monograph number 8 of the CETINIA series.
This book introduces a multiagent approach for modelling the emerging complexity of the energy industry. While the traditionally centralized management of the system becomes less viable in the context of distributed generation and controllable loads, the underlying thread of this work advocates the design and implementation of coordination mechanisms capable to integrate and manage a large-scale integration of such devices via agent-based control. We begin by proposing mechanisms for micro-grid formation and enhance their operation along two aspects: on the one hand (supply-side) we are concerned with seamlessly integrating distributed generation to ensure a reliable service of energy supply comparable to what a large power plant delivers today. We first address the economic benefits of virtual power plants in a game-like setting and then go on to propose a DCOP-based formalism for solving the schedule generation problem, while accounting for the stochastic behaviour of intermittent supply. On the other hand (consumer-side), we apply the use of game mechanics to drive the behaviour of prosumers towards efficient grid-wise use of energy. Finally, we propose a collusion detection mechanism that complements the above-mentioned solutions in the sense of inspecting for patterns where agents tacitly cooperate through illicit monopoly tactics to manipulate energy markets.
Dr. Luís Peña Sánchez authored the book Gaming with Emotions which was published as monograph number 7 of the CETINIA series.
The book studies the emotional component of the behavior of artificial characters in video games. The author develops an emotion simulation model called EEP that accounts for the impact of external events on a character’s mood state, and analyzes its relevance for the development of mood-driven behaviors as part of the control strategies of artificial characters. In addition, he provides a mechanism that improves the development procedure of video game characters, by developing a new hybrid machine learning model called WEREWoLF that purposefully combines reinforcement learning and evolutionary techniques, so as to automatically generate character control strategies associated to different mood states. Both models are integrated into the AGCBAR architecture, that supports the efficient design of mood-driven strategies for artificial characters in video games. The adequacy of the above architecture and its components is first assessed seperately through individual experiments. Then, the author implements the complete architecture together with an experimental video game framework in a complex case study, comparing the development effort of mood-driven artificial characters using the AGCBAR architecture together with EEP and WEREWoLF, to traditional implementation techniques.
Dr. Moser Silva Fagundes authored the book Sequential Decision Making in Normative Environments which was published as monograph number 6 of the CETINIA series (ISBN: 978-84-9031-276-6).
This book compiles the latest scientific advances in normative multiagent systems carried out within CETINIA. A wide variety of norm-aware agent models and architectures have been developed in the literature, wose purpose is to implement the normative reasoning of agents. However, approaches that allow autonomous agents to generate complex plans in dynamic and non-deterministic normative environments are rare. This book introduces an extension of the Markov Decision Processes (MDPs), called Normative Markov Decision Processes (NMDPs), to model rational and norm-aware agents acting in stochastic environments, as well as two utilitarian models of normative reasoning for selfish and norm-compliant agents. While selfish agents prioritize utility maximization, norm-compliant agents prioritize compliance with norms. Different experiments have been carried out to measure the performance of different populations of agents.
Dr. Levan Uridia authored the book From Belief to Knowledge which was published as monograph number 5 of the CETINIA series (ISBN: 978-84-9031-260-5).
This book collects research within CETINIA that has focused on combining two basic concepts in epistemology, belief and knowledge, in a unique formalism. One of the central questions in philosophy is to define the concept of knowledge in a universal way. One of the central ideas is that knowledge and belief can be understood as relationships between a cognitive agent a and a proposition p. The book presents a new formalism based on modal logic, called doxepi-formalism, which on the basis of a known epistemic logic LE finds a doxastic logic L that combines sufficiently with LE. In the book, this task is accomplished for logics S5 and S4, and various concepts and doxepi-formalisms based on these logics have been studied.
Mecanismos incentivos para la regulación de sistemas multiagente abiertos basados en organizaciones (Incentive mechanisms for the regulation of open multi-agent systems based on organizations)
Dr. Roberto Centeno authored the book Mecanismos incentivos para la regulación de sistemas multiagente abiertos basados en organizaciones which was published as monograph number 4 of the CETINIA series (ISBN: 978-84-9031-256-8).
This book presents the results obtained within CETINIA in the field of incentive mechanisms to influence the behavior of a population of agents. A common solution adopted to regulate this type of systems is based on organizational concepts. In most of the proposed models, normative systems appear to be a key concept. Due to the openness of such systems, the task of defining effective sanctions for an unknown and heterogeneous population of agents is complex and difficult. To solve this problem, the author proposes the use of incentive mechanisms capable of learning effective sanctions at execution time, adapting them to the different individuals as well as to the specific situation of the system.
Dr. Ramón Hermoso authored the book El concepto de confianza en sistemas organizativos which was published as monograph number 3 of the CETINIA series (ISBN: 978-84-9982-179-5).
This book presents the latest results obtained within CETINIA in the field of trust and reputation mechanisms in open multi-agent systems. Trust models in computer systems have been commonly used over time to infer expectations about the future behavior of the different entities that compose them from information based on past experiences. These models are of particular relevance when agents must decide with which other individuals to interact at any given time in order to carry out a certain action. This work addresses the use of organizational structures to face this problem, as well as the application of mechanisms that allow their evolution in open environments.
Descripción, Descubrimiento y Composición de Servicios en Entornos Multiagente Abiertos. Un Enfoque Organizacional (Description, Discovery and Composition of Services in Open Multiagent Environments. An Organizational Approach)
Dr. Alberto Fernández authored the book Descripción, Descubrimiento y Composición de Servicios en Entornos Multiagente Abiertos. Un Enfoque Organizacional which was published as monograph number 2 of the CETINIA series (ISBN: 978-84-9982-058-3).
This book compiles the results of the research carried out within CETINIA in the field of the description, discovery and composition of services in open multi-agent environments, where agents are capable of engaging in different types of social interactions during the provision of the service. An approach that uses organizational concepts, such as roles and interactions, is proposed to extend current trends in semantic description, matching, and composition of services in MAS. A matching algorithm is described that makes use of the semantic descriptions of the services. In addition, a generic method is presented for filtering those services that are likely to be irrelevant for the planning process of composite services. The method uses various heuristics based on past plans. The results of the empirical evaluation of the proposed methods allowed to check their validity. Finally, examples of the application of the proposals are shown in the fields of transportation management and coordination of services in medical emergencies.
Dr. Matteo Vasirani authored the book Vehicle-centric coordination for urban road traffic management. A market-based multiagent approach which was published as monograph number 1 of the CETINIA series (ISBN: 978-84-9849-790-8).
This book compiles the latest results obtained within CETINIA in the field of intelligent systems for road traffic management. The book explores the application to the traffic domain of resource management and allocation techniques based on artificial markets for agents. The application of combinatorial auctions for the allocation of slots at junctions is investigated, as well as mechanisms based on general equilibrium theory that aim at a better distribution of traffic in an urban road network. The experimental results collected in this publication demonstrate how a high level of automation within the road infrastructure, and its integration with the vehicles, can increase the efficiency of an urban transportion system.