[pt] Sistemas multiagentes foram introduzidos como um novo paradigma para a conceituação, concepção e implementação de sistemas de software que estão se tornando cada vez mais complexos, abertos, distribuídos, dinâmicos, autônomos e altamente interativos. No entanto, a engenharia de software orientada a agentes não tem sido amplamente adotada, principalmente devido à falta de linguagens de modelagem que não conseguem ser expressivas e abrangentes o suficiente para representar abstrações relacionadas aos agentes de software e apoiar o refinamento dos modelos de projeto em código. A maioria das linguagens de modelagem não define como essas abstrações devem interagir em tempo de execução, mas muitas aplicações de software precisam adaptar o seu comportamento, reagir à mudanças em seus ambientes de forma dinâmica, e alinhar-se com algum tipo de comportamento individual ou coletivo de aplicações normativas (por exemplo, obrigações, proibições e permissões). Neste trabalho, foi proposta uma abordagem de metamodelo e uma arquitetura para o desenvolvimento de agentes adaptativos normativos. Acredita-se que a abordagem proposta vai avançar o estado da arte em sistemas de agentes de modo que tecnologias de software para aplicações dinâmicas, adaptáveis e baseadas em normas possam ser projetadas e implementadas. / [en] Multi-agent systems have been introduced as a new paradigm for conceptualizing, designing and implementing software systems that are becoming increasingly complex, open, distributed, dynamic, autonomous and highly interactive. However, agent-oriented software engineering has not been widely adopted, mainly due to lack of modeling languages that are expressive and comprehensive enough to represent relevant agent-related abstractions and support the refinement of design models into code. Most modeling languages do not define how these abstractions interact at runtime, but many software applications need to adapt their behavior, react to changes in their environments dynamically, and align with some form of individual or collective normative application behavior (e.g., obligations, prohibitions and permissions). In this paper, we propose a metamodel and an architecture approach to developing adaptive normative agents. We believe the proposed approach will advance the state of the art in agent systems so that software technologies for dynamic, adaptive, norm-based applications can be designed and implemented.

The thesis is dealing with traffic management using telemetry networks. The problematic of telemetry networks and multiagent systems. A simulation model is proposed in Java which enables configuration simulation and assessment.

<p dir="ltr">The growth of electric vehicles (EVs) offers several benefits for air quality improvement and emissions reduction. Nonetheless, EVs also pose several challenges in the area of highway transportation. These barriers are related to the limitations of EV technology, particularly the charge duration and speed of battery recharging, which translate to vehicle range anxiety for EV users. A promising solution to these concerns is V2V DWC technology (Vehicle to Vehicle Dynamic Wireless Charging), particularly mobile energy disseminators (MEDs). The MED is mounted on a large vehicle or truck that charges all participating EVs within a specified locus from the MED. However, current research on MEDs offers solutions that are widely considered impractical for deployment, particularly in urban environments where range anxiety is common. Acknowledging such gap in the literature, this thesis proposes a comprehensive methodological framework for optimal MED deployment decisions. In the first component of the framework, a practical system, termed “ChargingEnv” is developed using reinforcement learning (RL). ChargingEnv simulates the highway environment, which consists of streams of EVs and an MED. The simulation accounts for a possible misalignment of the charging panel and incorporates a realistic EV battery model. The second component of the framework uses multiple deep RL benchmark models that are trained in “ChargingEnv” to maximize EV service quality within limited charging resource constraints. In this study, numerical experiments were conducted to demonstrate the MED deployment decision framework’s efficacy. The findings indicate that the framework’s trained model can substantially improve EV travel range and alleviate battery depletion concerns. This could serve as a vital tool that allows public-sector road agencies or private-sector commercial entities to efficiently orchestrate MED deployments to maximize service cost-effectiveness.</p>

<p dir="ltr">The concept of reinforcement learning has become increasingly relevant in learning- based applications, especially in the field of autonomous navigation, because of its fundamental nature to operate without the necessity of labeled data. However, the infeasibility of training reinforcement learning based autonomous navigation applications in a real-world setting has increased the popularity of researching and developing on autonomous navigation systems by creating simulated environments in game engine platforms. This thesis investigates the comparative performance of Unity and Unreal Engine 5 within the framework of a reinforcement learning system applied to autonomous race car navigation. A rudimentary simulated setting featuring a model car navigating a racetrack is developed, ensuring uniformity in environmental aspects across both Unity and Unreal Engine 5. The research employs reinforcement learning with genetic algorithms to instruct the model car in race track navigation; while the tools and programming methods for implementing reinforcement learning vary between the platforms, the fundamental concept of reinforcement learning via genetic algorithms remains consistent to facilitate meaningful comparisons. The implementation includes logging of key performance variables during run times on each platform. A comparative analysis of the performance data collected demonstrates Unreal Engine's superior performance across the collected variables. These findings contribute insights to the field of autonomous navigation systems development and reinforce the significance of choosing an optimal underlying simulation platform for reinforcement learning applications.</p>

<p dir="ltr">Autonomous vehicles require motion forecasting of their surrounding multiagents (pedestrians</p><p dir="ltr">and vehicles) to make optimal decisions for navigation. The existing methods focus on</p><p dir="ltr">techniques to utilize the positions and velocities of these agents and fail to capture semantic</p><p dir="ltr">information from the scene. Moreover, to mitigate the increase in computational complexity</p><p dir="ltr">associated with the number of agents in the scene, some works leverage Euclidean distance to</p><p dir="ltr">prune far-away agents. However, distance-based metric alone is insufficient to select relevant</p><p dir="ltr">agents and accurately perform their predictions. To resolve these issues, we propose the</p><p dir="ltr">Semantics-aware Interactive Multiagent Motion Forecasting (SIMMF) method to capture</p><p dir="ltr">semantics along with spatial information and optimally select relevant agents for motion</p><p dir="ltr">prediction. Specifically, we achieve this by implementing a semantic-aware selection of relevant</p><p dir="ltr">agents from the scene and passing them through an attention mechanism to extract</p><p dir="ltr">global encodings. These encodings along with agents’ local information, are passed through</p><p dir="ltr">an encoder to obtain time-dependent latent variables for a motion policy predicting the future</p><p dir="ltr">trajectories. Our results show that the proposed approach outperforms state-of-the-art</p><p dir="ltr">baselines and provides more accurate and scene-consistent predictions. </p>

<p dir="ltr">The original definition of Nash Equilibrium applied to normal form games, but the notion has now been extended to various other forms of games including leader-follower games (Stackelberg games), extensive form games, stochastic games, games of incomplete information, cooperative games, and so on. We focus on general-sum stochastic Stackelberg games in this work. An example where such games would be natural to consider is in security games where a defender wishes to protect some targets through deployment of limited resources and an attacker wishes to strategically attack the targets to benefit themselves. The hierarchical order of play arises naturally since the defender typically acts first and deploys a strategy, while the attacker observes the strategy ofthe defender before attacking. Another example where this framework fits is in testing during epidemics, where the leader (the government) sets testing policies and the follower (the citizens) decide at every time step whether to get tested. The government wishes to minimize the number of infected people in the population while the follower wishes to minimize the cost of getting sick and testing. This thesis presents a learning algorithm for players to converge to their stationary policies in a general sum stochastic sequential Stackelberg game. The algorithm is a two time scale implicit policy gradient algorithm that provably converges to stationary points of the optimization problems of the two players. Our analysis allows us to move beyond the assumptions of zero-sum or static Stackelberg games made in the existing literature for learning algorithms to converge.</p><p dir="ltr"><br></p>

Formation control is a classical problem and has been a prime topic of interest among the scientific community in the past few years. Although a vast amount of literature exists in this field, there are still many open questions that require an in-depth understanding and a new perspective. This thesis contributes towards exploring the wide dimensions of formation control and implementing a formation control scheme for a group of multi-agent systems. These systems are autonomous in nature and are represented by double integrated dynamics. It is assumed that the agents are connected in an undirected graph and use a leader-follower architecture to reach formation when the leading agent is given a velocity that is piecewise constant. A MATLAB code is written for the implementation of formation and the consensus-based control laws are verified. Understanding the effects on formation due to a fixed formation geometry is also observed and reported. Also, a link that describes the functional similarity between desired formation geometry and the Laplacian matrix has been observed. The use of Laplacian matrix in stability analysis of the formation is of special interest.

Doctor of Philosophy / Computing and Information Sciences / Scott A. DeLoach / As sensor prices drop and computing devices continue to become more compact and powerful, computing capabilities are being embedded throughout our physical environment. Connecting these devices in cyber-physical systems (CPS) enables applications with significant societal impact and economic benefit. However, engineering CPS poses modeling, architecture, and engineering challenges and, to fully realize the desired benefits, many outstanding challenges must be addressed. For the cyber parts of CPS, two decades of work in the design of autonomous agents and multiagent systems (MAS) offers design principles for distributed intelligent systems and formalizations for agent-oriented software engineering (AOSE). MAS foundations offer a natural fit for enabling distributed interacting devices. In some cases, complex control structures such as holarchies can be advantageous. These can motivate complex organizational strategies when implementing such systems with a MAS, and some designs may require agents to act in multiple groups simultaneously. Such agents must be able to manage their multiple associations and assignments in a consistent and unambiguous way. This thesis shows how designing agents as systems of intelligent subagents offers a reusable and practical approach to designing complex systems. It presents a set of flexible, reusable components developed for OBAA++, an organization-based architecture for single-group MAS, and shows how these components were used to develop the Adaptive Architecture for Systems of Intelligent Systems (AASIS) to enable multigroup agents suitable for complex, multigroup MAS. This work illustrates the reusability and flexibility of the approach by using AASIS to simulate a CPS for an intelligent power distribution system (IPDS) operating two multigroup MAS concurrently: one providing continuous voltage control and a second conducting discrete power auctions near sources of distributed generation.

Thesis (M. Tech. (Information Technology)) -- Central University of technology, Free State, 2011 / Traditional designs for component-handling platforms are rigidly linked to the product being produced. Control and monitoring methods for these platforms consist of various proprietary hardware controllers containing the control logic for the production process. Should the configuration of the component handling platform change, the controllers need to be taken offline and reprogrammed to take the changes into account. The current thinking in component-handling system design is the notion of re-configurability. Reconfigurability means that with minimum or no downtime the system can be adapted to produce another product type or overcome a device failure. The re-configurable component handling platform is built-up from groups of independent devices. These groups or cells are each responsible for some aspect of the overall production process. By moving or swopping different versions of these cells within the component-handling platform, re-configurability is achieved. Such a dynamic system requires a flexible communications platform and high-level software control architecture to accommodate the reconfigurable nature of the system. This work represents the design and testing of the core of a re-configurable production control software platform. Multiple software components work together to control and monitor a re-configurable component handling platform. The design and implementation of a production database, production ontology, communications architecture and the core multi-agent control application linking all these components together is presented.

Thesis (M. Tech. (Engineering: Electrical)) -- Central University of technology, Free State, [2014] / The project is aimed at exploring the application of Machine Vision in a Reconfigurable Manufacturing System (RMS) Environment. The Machine Vision System interfaces with the RMS to verify the reconfiguration and positioning of devices within the assembly system, and inspects the product for defects that infringe on the quality of that product. The vision system interfaces to the Multi-agent System (MAS), which is in charge of scheduling and allocating resources of the RMS, in order to communicate and exchange data regarding the quality of the product. The vision system is comprised of a Compact Vision System (CVS) device with fire-wire cameras to aid in the image acquisition, inspection and verification process. Various hardware and software manufacturers offer a platform to implement this with a multiple array of vision equipment and software packages. The most appropriate devices and software platform were identified for the implementation of the project. An investigation into illumination was also undertaken in order to determine whether external lighting sources would be required at the point of inspection. Integration into the assembly system involved the establishment communication between the vision system and assembly system controller.