M.Sc. (Information Technology) / Please refer to full text to view abstract

M.Com. (Information Technology) / ADLOA is an Architecture Description Language (ADL) proposed to describe biologicallyinspired complex adaptive architectures such as ontogenetic architectures. The need for an ontogenetic ADL stems from the lack of support from existing ADLs. This dissertation further investigates the similarities between existing intelligent architectures and ontogenetic architectures. The research conducted on current ADLs, artificial ontogeny and intelligent architectures reveals that there are similarities between ontogenetic architectures and other intelligent architectures. However, the dynamism of artificial ontogeny indicates a lack of support for architecture description. Therefore, the dissertation proposes two core mechanisms to address ontogenetic architecture description. Firstly, the ADLOA process is defined as a systematisation of artificial ontogeny. The process specifies a uniform approach to defining ontogenetic architectures. Secondly, a demonstration of the implemented ADLOA process is used, in conjunction with the ADLOA model, mechanisms and Graphical User Interface (GUI), to present a workable description environment for software architects. The result of the dissertation is a standalone ADL that has the ability to describe ontogenetic architectures and to produce language-dependent code frameworks using the Extensible Markup Language (XML) and Microsoft Visual Studio platform.

M.Sc. (Information Technology) / The purpose of the research is to investigate agent-based approaches to virtual crowd simulation. Crowds are ubiquitous and are becoming an increasingly common phenomena in modern society, particularly in urban settings. As such, crowd simulation systems are becoming increasingly popular in training simulations, pedestrian modelling, emergency simulations, and multimedia. One of the primary challenges in crowd simulation is the ability to model realistic, large-scale crowd behaviours in real time. This is a challenging problem, as the size, visual fidelity, and complex behaviour models of the crowd all have an impact on the available computational resources. In the last few years, the graphics processing unit (GPU) has presented itself as a viable computational resource for general purpose computation. Traditionally, GPUs were used solely for their ability to efficiently compute operations related to graphics applications. However, the modern GPU is a highly parallel programmable processor, with substantially higher peak arithmetic and memory bandwidth than its central processing unit (CPU) counterpart. The GPU’s architecture makes it a suitable processing resource for computations that are parallel or distributed in nature. One attribute of multi-agent systems (MASs) is that they are inherently decentralised. As such, a MAS that leverages advancements in GPU computing may provide a solution for crowd simulation. The research investigates techniques and methods for general purpose crowd simulation, including topics in agent behavioural modes, pathplanning, collision avoidance and agent steering. The research also investigates how GPU computing has been utilised to address these computationally intensive problem domains. Based on the outcomes of the research, an agent-based model, Massively Parallel Crowds (MPCrowds), is proposed to address virtual crowd simulation, using the GPU as an additional resource for agent computation.

M.Sc. (Computer Science) / General machine intelligence represents the principal ambition of artificial intelligence research: creating machines that readily adapt to their environment. Machine learning represents the driving force of adaptation in artificial intelligence. However, two pertinent dilemmas emerge from research into machine learning. Firstly, how do intelligent agents learn effectively in real-world environments, in which randomness, perceptual aliasing and dynamics complicate learning algorithms? Secondly, how can intelligent agents exchange knowledge and learn from one another without introducing mathematical anomalies that might impede on the effectiveness of the applied learning algorithms? In a robotic search and rescue scenario, for example, the control system of each robot must learn from its surroundings in a fast-changing and unpredictable environment while at the same time sharing its learned information with others. In well-understood problems, an intelligent agent that is capable of solving task-specific problems will suffice. The challenge behind complex environments comes from fact that agents must solve arbitrary problems (Kaelbling et al. 1996; Ryan 2008). General problem-solving abilities are hence necessary for intelligent agents in complex environments, such as robotic applications. Although specialized machine learning techniques and cognitive hierarchical planning and learning may be a suitable solution for general problem-solving, such techniques have not been extensively explored in the context of cooperative multi-agent learning. In particular, to the knowledge of the author, no cognitive architecture has been designed which can support knowledge-sharing or self-organisation in cooperative multi-agent learning systems. It is therefore social learning in real-world applications that forms the basis of the research presented in this dissertation. This research aims to develop a distributed cognitive architecture for cooperative multi-agent learning in complex environments. The proposed Multi-agent Learning through Distributed Adaptive Contextualization Distributed Cognitive Architecture for Multi-agent Learning (MALDAC) Architecture comprises a self-organising multi-agent system to address the communication constraints that the physical hardware imposes on the system. The individual agents of the system implement their own cognitive learning architecture. The proposed Context-based Adaptive Empathy-deliberation Agent (CAEDA) Architecture investigates the applicability of emotion, ‘consciousness’, embodiment and sociability in cognitive architecture design. Cloud computing is proposed as a method of service delivery for the learning system, in which the MALDAC Architecture governs multiple CAEDA-based agents. An implementation of the proposed architecture is applied to a simulated multi-robot system to best emulate real-world complexities. Analyses indicate favourable results for the cooperative learning capabilities of the proposed MALDAC and CAEDA architectures.

Os múltiplos trabalhos de sistemas multiagentes musicais realizados nos últimos anos demonstram o interesse crescente na pesquisa de sistemas de composição e de performance musical que utilizem a tecnologia de agentes computacionais, sendo que apresentam um interesse maior por aqueles sistemas que integram técnicas de composição algorítmica, componentes de vida artificial e interatividade. Observamos também que a maioria dos trabalhos existentes apresentam muitas limitações em termos de escopo e flexibilidade, normalmente apresentando codificação musical simbólica e a resolução de um único problema, sendo que a motivação é mais técnica do que musical. Nesse contexto, surgem arcabouços voltados à criação de sistemas multiagentes musicais, como o Ensemble e o Interactive Swarm Orchestra, oferecendo flexibilidade para a modelagem e implementação de sistemas desse tipo, diversificando tanto os tipos de aplicação, tendo um propósito composicional ou performático, como os tipos de codificação musical que podem ser utilizados. Partimos da aparição dessas ferramentas para estudar o agente musical a partir de uma perspectiva interna, focando nos seus raciocínios, que são processos que definem o comportamento do agente no ambiente virtual do sistema e que são fundamentais para determinar e melhorar o seu valor composicional. Os arcabouços estudados se diferenciam por permitir a utilização de áudio como possível formato de codificação musical, o aproveitamento da espacialização sonora e a exploração da interatividade nos aplicativos, seja esta apenas entre agentes computacionais ou entre agentes e usuários humanos. Pretendemos portanto, nessa pesquisa, abordar sistemas com essas características. Através de extensões nos arcabouços e estudos de caso com motivação estética pretendemos dar continuidade a esses projetos e ao mesmo tempo validar e divulgar a sua utilização entre os potenciais usuários das ferramentas, como compositores, músicos interessados em performance e outros entusiastas dos sistemas musicais interativos. / Multiple musical multiagent systems have been developed in the last years proving the increasing interest in composition and musical performance systems that exploit intelligent agents technology. Theres an special focus on systems that integrate algorithmic composition techniques, artificial life and interactivity. We can also observe that most of these existing projects show many flexibility and scope limitations, as they normally use symbolic musical notation and they solve a single issue or scenario, as well as they have a technical motivation rather than a musical one. In that context, some musical multiagent systems frameworks as Ensemble and Interactive Swarm Orchestra emerge, trying to help the modeling and development of this kind of musical systems, diversifying the applications\' types, as they can be composition problems or musical performances, and allowing the inclusion of other kind of musical content communication. Through these new tools we study the musical agent from an internal perspective, focusing on its reasoning components, processes that define the behavior of an agent on its system\'s virtual environment and that are essential to determine and improve its compositional value. The studied frameworks show unique features as they support audio as a possible musical notation format; they exploit sound spatialization and they work with interactivity in their applications, including agent-to-agent or human-to-agent interaction. We will explore this type of systems on this research. Through framework extensions and aesthetics-oriented study cases we pretend to continue these projects and validate them at same time. We also will contact potential users for these tools, as composers and musicians interested in performances or other musical interactive systems enthusiasts.

Actualmente existe una creciente demanda de sistemas flexibles, adaptables y con gran escalabilidad para apoyar las interacciones de personas e instituciones distribuidas en entornos heterogéneos. Esto se debe principalmente al incremento en la necesidad de trabajo colaborativo y la descentralización de los procesos en muchos dominios de aplicación. Por lo general, estas aplicaciones de software deben seguir legislaciones y normativas específicas, es decir, las entidades que participan en el sistema tienen derechos, deberes y restricciones específicas. Al igual que en otros trabajos del área, en esta tesis se utiliza el término sistemas normativos abiertos para referirse a los sistemas de este tipo. El desarrollo de sistemas normativos abiertos puede producir importantes beneficios para las compañías que los usen, ya que permiten la comunicación de instituciones, entidades heterogéneas y diferentes dispositivos con el fin de lograr tanto los objetivos globales del sistema como los individuales de cada institución y entidad. Sin embargo, también hay algunas cuestiones importantes que potencialmente pueden complicar el análisis, diseño e implementación de estos sistemas. La mayoría de estos problemas están relacionados con la interoperabilidad de sus procesos, la privacidad, la combinación de los objetivos individuales y la combinación de las restricciones y la legislación de cada una de las entidades del sistema. Por lo tanto, es necesario el uso de métodos de ingeniería del software y herramientas de desarrollo para hacer frente a estos problemas y guiar a los desarrolladores durante el proceso de desarrollo. La tecnología basada en sistemas multiagente (SMA) es considerada una buena candidata para el desarrollo de sistemas normativos abiertos. Durante los últimos años, el uso de las tecnologías SMA se ha incrementado no sólo en el ámbito académico, sino también en el desarrollo e implementación de aplicaciones industriales. Los SMA se han establecido como un paradigma de la ingeniería de software para la creación de sistemas adaptativos complejos, en entornos distribuidos y heterogéneos. Esta tesis se centra en el análisis y diseño de sistemas normativos abiertos utilizando la tecnología SMA. Algunas metodologías SMA se dedican al desarrollo de sistemas de este tipo. Sin embargo, después de analizar en qué medida las metodologías SMA actuales soportan el análisis y el diseño de estos sistemas, podemos concluir que todavía hay importantes problemas a resolver en el área. Algunos de estos problemas son la integración del contexto normativo del sistema durante el proceso de desarrollo, la falta de directrices para identificar y formalizar este contexto normativo, la falta de técnicas de validación y verificación que garanticen la coherencia del diseño final respecto a los requisitos del sistema, la coherencia entre los objetivos individuales, y la coherencia de las restricciones de cada entidad respecto al contexto normativo del sistema global. La principal aportación de esta tesis es una nueva metodología SMA llamada ROMAS (Sistemas Multiagente Regulados y Abiertos), que se centra en el análisis y diseño de procesos para el desarrollo de sistemas multiagente organizacionales, donde los agentes interactúan por medio de servicios estándares, y donde las relaciones sociales y contractuales se formalizan mediante normas y contratos. La metodología ROMAS define un proceso de desarrollo orientado a agentes y proporciona guías específicas para identificar y formalizar el marco normativo del sistema, así como las comunicaciones y los intercambios de servicios y recursos. ROMAS especifica tanto el comportamiento global del sistema como las características individuales de cada entidad. En la metodología ROMAS, agentes, roles y organizaciones se definen a través de una estructura social formal basada en un arquitectura orientada a servicios. Aquí, las organizaciones representan un conjunto de personas e instituciones que tienen que coor / Garcia Marques, ME. (2013). Engineering Regulated Open Multiagent Systems [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/28588 / TESIS

As problems in the world become increasingly complex, designers in multiple disciplines have begun to propose swarms as a solution. The espoused benefits include flexibility, resilience, and potential for decentralized control, yet there lacks consensus on what a swarm is, what characteristics they possess, and what applications they are able to address. This study addresses these questions by creating a unified approach for understanding and analyzing swarms, called the Swarm Analysis Framework. The framework pursues three goals: 1) provide extensive analysis on the many characteristics and applications that define a swarm, 2) remain flexible enough to facilitate design, testing, analysis, and other problems in understanding swarms, and 3) outline swarm applications specific to aircraft and spacecraft based swarms. Afterwards, the Swarm Analysis Framework is used to guide a case study in which the application is a swarm was developed to study one of these aerospace applications. Ultimately, the Swarm Analysis Framework, along with its extensions improvements, should be able to act as a guide or roadmap in understanding how swarms behave across multiple disciplines.<br>

<p> In this thesis, we investigate and characterize policies for task allocation to teams of agents in settings with heterogeneity and risk. We first consider a scenario consisting of a set of heterogeneous mobile agents located at a base (or depot), and a set of tasks dispersed over a geographic area. The agents are partitioned into different types. The tasks are partitioned into specialized tasks that can only be done by agents of a certain type, and generic tasks that can be done by any agent. The distances between every pair of tasks are specified and satisfy the triangle inequality. Given this scenario, we address the problem of allocating these tasks among the available agents (subject to type compatibility constraints) while minimizing the maximum travel cost for any agent. We first look at the Heterogeneous Agent Cycle Problem (HACP) where agents start at a common base (or depot) and need to tour the set of tasks allocated to them before returning to the base. This problem is NP-hard, and we provide a 5-approximation algorithm. We then consider the Heterogeneous Agent Path Problem (HAPP) where agents can start from arbitrary locations and are not constrained to return to their start location. We consider two approaches to solve HAPP and provide a 15-approximation algorithm for HAPP.</p> <p> We then look at the effect of risk on path planning by considering a scenario where a mobile agent is required to collect measurements from a geographically dispersed set of sensors and return them to a base. The agent faces a risk of destruction while traversing the environment to reach the sensors and gets the reward for gathering a sensor measurement only if it successfully returns to base. We call this the Single Agent Risk Aware Task Execution (SARATE) problem. We characterize several properties of the optimal policy for the agent. We provide the optimal policy when the risk of destruction is sufficiently high and evaluate several heuristic policies via simulation. We then extend the analysis to multiple heterogeneous agents. We show that the scoring scheme is submodular when the risk is sufficiently high, and the greedy algorithm gives solutions that provide a utility that is guaranteed to be within 50% of the optimal utility. </p>

In the first part of this thesis, we propose a distributed consensus algorithm under multi-layer multi-group structure with communication time delays. It is proven that the consensus will be achieved in both time-varying and fixed communication delays. In the second part, we study the distributed optimization problem with a finite-time mechanism. It is shown that our distributed proportional-integral algorithm can exponentially converge to the unique global minimizer when the gain parameters satisfy the sufficient conditions. Moreover, we equip the proposed algorithm with a decentralized algorithm, which enables an arbitrarily chosen agent to compute the exact global minimizer within a finite number of time steps, using its own states observed over a successive time steps. In the third part, it is shown the implementation of accelerated distributed energy management for microgrids is achieved. The results presented in the thesis are corroborated by simulations or experiments.

We develop a computational framework for risk mitigation in high population density events. With increased global population, the frequency of high population density events is naturally increased. Therefore, risk-free crowd management plans are critical for efficient mobility, convenient daily life, resource management and most importantly mitigation of any inadvertent incidents and accidents such as stampedes. The status-quo for crowd management plans is the use of human experience/expert advice. However, most often such dependency on human experience is insufficient, flawed and results in inconvenience and tragic events. Motivated by these issues, we propose an agent-based mathematical model describing realistic human motion and simulating large dense crowds in a wide variety of events as a potential simulation testbed to trial crowd management plans. The developed model incorporates stylized mindset characteristics as an internal drive for physical behavior such as walking, running, and pushing. Furthermore, the model is combined with a visualisation of crowd movement. We develop analytic tools to quantify crowd dynamic features. The analytic tools will enable verification and validation to empirical evidence and surveillance video feed in both local and holistic representations of the crowd. This work addresses research problems in computational modeling of crowd dynamics, specifically: understanding and modeling the impact of a collective mindset on crowd dynamics versus mixtures of heterogeneous mindsets, the effect of social contagion of behaviors and decisions within the crowd, the competitive and aggressive pushing behaviors, and torso and steering dynamics.