No description available.

No description available.

Multi-agent planning and control is an active and increasingly studied topic of research, with many practical applications, such as rescue missions, security, surveillance, and transportation. More specifically, cases that involve complex manipulator-endowed systems  deserve extra attention due to potential complex cooperative manipulation tasks and their interaction with the environment. This thesis addresses the problem of cooperative motion- and task-planning of multi-agent and multi-agent-object systems under complex specifications expressed as temporal logic formulas. We consider manipulator-endowed robotic agents that can coordinate in order to perform, among other tasks, cooperative object manipulation/transportation. Our approach is based on the integration of tools from the following areas: multi-agent systems, cooperative object manipulation, discrete abstraction design of multi-agent-object systems, and formal verification. More specifically, we divide the main problem into three different parts.The first part is devoted to the control design for the formation control of a team of rigid-bodies, motivated by its application to cooperative manipulation schemes. We propose decentralized control protocols such that desired position and orientation-based formation between neighboring agents is achieved. Moreover, inter-agent collisions and connectivity breaks are guaranteed to be avoided. In the second part, we design continuous control laws explicitly for the cooperative manipulation/transportation of an object by a team of robotic agents. Firstly, we propose robust decentralized controllers for the trajectory tracking of the object's center of mass.  Secondly, we design model predictive control-based controllers for the transportation of the object with collision and singularity constraints. In the third part, we design discrete representations of multi-agent continuous systems and synthesize hybrid controllers for the satisfaction of complex tasks expressed as temporal logic formulas. We achieve this by combining the results of the previous parts and by proposing appropriate trajectory tracking- and potential field-based continuous control laws for the transitions of the agents among the discrete states. We consider teams of unmanned aerial vehicles and mobile manipulators as well as multi-agent-object systems where the specifications of the objects are also taken into account.Numerical simulations and experimental results verify the claimed results. / <p>QC 20180219</p>

Dynamical systems that provably satisfy given specifications have become increasingly important in many engineering areas. For instance, safety-critical systems such as human-robot networks or autonomous driving systems are required to be safe and to also satisfy some complex specifications that may include timing constraints, i.e., when or in which order some tasks should be accomplished. Temporal logics have recently proven to be a valuable tool for these control systems by providing a rich specification language. Existing temporal logic-based control approaches discretize the underlying dynamical system in space and/or time, which is commonly referred to as the abstraction process. In other words, the continuous dynamical system is abstracted into a finite system representation, e.g., into a finite state automaton. Such approaches may lead to high computational burdens due to the curse of dimensionality, which makes it hard to use them in practice. Especially with respect to multi-agent systems, these methods do not scale computationally when the number of agents increases. We will address this open research question by deriving abstraction-free control methods for single- and multi-agent systems under signal temporal logic tasks. Another aim of this research is to consider robustness, which is partly taken care of by the robust semantics admitted by signal temporal logic as well as by the robustness properties of the derived control methods. In this work, we propose computationally-efficient frameworks that deal with the aforementioned problems for single- and multi-agent systems by using feedback control strategies such as optimization-based techniques, prescribed performance control, and control barrier functions in combination with hybrid systems theory that allows us to model some higher level decision-making. In each of these approaches, the temporal properties of the employed control methods are used to impose a temporal behavior on the closed-loop system dynamics, which eventually results in the satisfaction of the signal temporal logic task. With respect to the multi-agent case, we consider a bottom-up approach where each agent is subject to a local (individual) task. These tasks may depend on the behavior of other agents. Hence, the multi-agent system is subject to couplings induced on the task level as well as on the dynamical level. The main challenge then is to deal with these couplings and derive control methods that can still satisfy the given tasks or alternatively result in least violating solutions. The efficacy of the theoretical findings is demonstrated in simulations of single- and multi-agent systems under complex specifications. / <p>QC 20180502</p>

A Bayesian network approach to self-organization and learning is introduced for use with intelligent agents. Bayesian networks, with the help of influence diagrams, are employed to create a decision-theoretic intelligent agent. Influence diagrams combine both Bayesian networks and utility theory. In this research, an intelligent agent is modeled by its belief, preference, and capabilities attributes. Each agent is assumed to have its own belief about its environment. The belief aspect of the intelligent agent is accomplished by a Bayesian network. The goal of an intelligent agent is said to be the preference of the agent and is represented with a utility function in the decision theoretic intelligent agent. Capabilities are represented with a set of possible actions of the decision-theoretic intelligent agent. Influence diagrams have utility nodes and decision nodes to handle the preference and capabilities of the decision-theoretic intelligent agent, respectively. Learning is accomplished by Bayesian networks in the decision-theoretic intelligent agent. Bayesian network learning methods are discussed intensively in this paper. Because intelligent agents will explore and learn the environment, the learning algorithm should be implemented online. None of the existent Bayesian network learning algorithms has online learning. Thus, an online Bayesian network learning method is proposed to allow the intelligent agent learn during its exploration. Self-organization of the intelligent agents is accomplished because each agent models other agents by observing their behavior. Agents have belief, not only about environment, but also about other agents. Therefore, an agent takes its decisions according to the model of the environment and the model of the other agents. Even though each agent acts independently, they take the other agents behaviors into account to make a decision. This permits the agents to organize themselves for a common task. To test the proposed intelligent agent's learning and self-organizing abilities, Windows application software is written to simulate multi-agent systems. The software, IntelliAgent, lets the user design decision-theoretic intelligent agents both manually and automatically. The software can also be used for knowledge discovery by employing Bayesian network learning a database. Additionally, we have explored a well-known herding problem to obtain sound results for our intelligent agent design. In the problem, a dog tries to herd a sheep to a certain location, i.e. a pen. The sheep tries to avoid the dog by retreating from the dog. The herding problem is simulated using the IntelliAgent software. Simulations provided good results in terms of the dog's learning ability and its ability to organize its actions according to the sheep's (other agent) behavior. In summary, a decision-theoretic approach is applied to the self-organization and learning problems in intelligent agents. Software was written to simulate the learning and self-organization abilities of the proposed agent design. A user manual for the software and the simulation results are presented. This research is supported by the Office of Naval Research with the grant number N00014-98-1-0779. Their financial support is greatly appreciated. / Ph. D.

Past research on multi-agent simulation with cooperative reinforcement learning (RL) for homogeneous agents focuses on developing sharing strategies that are adopted and used by all agents in the environment. These sharing strategies are considered to be reciprocating because all participating agents have a predefined agreement regarding what type of information is shared, when it is shared, and how the participating agent's policies are subsequently updated. The sharing strategies are specifically designed around manipulating this shared information to improve learning performance. This thesis targets situations where the assumption of a single sharing strategy that is employed by all agents is not valid. This work seeks to address how agents with no predetermined sharing partners can exploit groups of cooperatively learning agents to improve learning performance when compared to Independent learning. Specifically, several intra-agent methods are proposed that do not assume a reciprocating sharing relationship and leverage the pre-existing agent interface associated with Q-Learning to expedite learning. The other agents' functions and their sharing strategies are unknown and inaccessible from the point of view of the agent(s) using the proposed methods. The proposed methods are evaluated on physically embodied agents in the multi-agent cooperative robotics field learning a navigation task via simulation. The experiments conducted focus on the effects of the following factors on the performance of the proposed non-reciprocating methods: scaling the number of agents in the environment, limiting the communication range of the agents, and scaling the size of the environment. / Master of Science

The efficiency, security and resiliency are very important factors for the operation of a distribution power system. Taking into account customer demand and energy resource constraints, electric utilities not only need to provide reliable services but also need to operate a power grid as efficiently as possible. The objective of this dissertation is to design, develop and deploy the Multi-Agent Systems (MAS) - together with control algorithms - that enable demand response (DR) implementation at the customer level, focusing on both residential and commercial customers. For residential applications, the main objective is to propose an approach for a smart distribution transformer management. The DR objective at a distribution transformer is to ensure that the instantaneous power demand at a distribution transformer is kept below a certain demand limit while impacts of demand restrike are minimized. The DR objectives at residential homes are to secure critical loads, mitigate occupant comfort violation, and minimize appliance run-time after a DR event. For commercial applications, the goal is to propose a MAS architecture and platform that help facilitate the implementation of a Critical Peak Pricing (CPP) program. Main objectives of the proposed DR algorithm are to minimize power demand and energy consumption during a period that a CPP event is called out, to minimize occupant comfort violation, to minimize impacts of demand restrike after a CPP event, as well as to control the device operation to avoid restrikes. Overall, this study provides an insight into the design and implementation of MAS, together with associated control algorithms for DR implementation in smart buildings. The proposed approaches can serve as alternative solutions to the current practices of electric utilities to engage end-use customers to participate in DR programs where occupancy level, tenant comfort condition and preference, as well as controllable devices and sensors are taken into account in both simulated and real-world environments. Research findings show that the proposed DR algorithms can perform effectively and efficiently during a DR event in residential homes and during the CPP event in commercial buildings. / Ph. D.

Optimizing connected automated vehicle movements through roadway intersections is a challenging problem. Traditional traffic control strategies, such as traffic signals are not optimal, especially for heavy traffic. Alternatively, centralized automated vehicle control strategies are costly and not scalable given that the ability of a central controller to track and schedule the movement of hundreds of vehicles in real-time is highly questionable. In this research, a series of fully distributed heuristic algorithms are proposed where vehicles in the vicinity of an intersection continuously cooperate with each other to develop a schedule that allows them to safely proceed through the intersection while incurring minimum delays. An algorithm is proposed for the case of an isolated intersection then a number of algorithms are proposed for a network of intersections where neighboring intersections communicate directly or indirectly to help the distributed control at each intersection makes a better estimation of traffic in the whole network. An algorithm based on the Godunov scheme outperformed optimized signalized control. The simulated experiments show significant reductions in the average delay. The base algorithm is successfully added to the INTEGRATION micro-simulation model and the results demonstrate improvements in delay, fuel consumption, and emissions when compared to roundabout, signalized, and stop sign controlled intersections. The study also shows the capability of the proposed technique to favor emergency vehicles, producing significant increases in mobility with minimum delays to the other vehicles in the network. / Ph. D.

Unfavorable environmental and (or) human displacement may engender the need for Search and Rescue (SAR). Challenges such as inaccessibility, large search areas, and heavy reliance on available responder count, limited equipment and training makes SAR a challenging problem. Additionally, SAR operations also pose significant risk to involved responders. This opens a remarkable opportunity for robotic systems to assist and augment human understanding of the harsh environments. A large body of work exists on the introduction of ground and aerial robots in visual and temporal inspection of search areas with varying levels of autonomy. Unfortunately, limited autonomy is the norm in such systems, due to the limitations presented by on-board UAV resources and networking capabilities. In this work we propose a new multi-agent approach to SAR and introduce a wearable compute cluster in the form factor of a backpack. The backpack allows offloading compute intensive tasks such as Lost Person Behavior Modelling, Path Planning and Deep Neural Network based computer vision applications away from the UAVs and offers significantly high performance computers to execute them. The backpack also provides for a strong networking backbone and task orchestrators which allow for enhanced coordination and resource sharing among all the agents in the system. On the basis of our benchmarking experiments, we observe that the backpack can significantly boost capabilities and success in modern SAR responses. / Master of Science / Unfavorable environmental and (or) human displacement may engender the need for Search and Rescue (SAR). Challenges such as inaccessibility, large search areas, and heavy reliance on available responder count, limited equipment and training makes SAR a challenging problem. Additionally, SAR operations also pose significant risk to involved responders. This opens a remarkable opportunity for robotic systems to assist and augment human understanding of the harsh environments. A large body of work exists on the introduction of ground and aerial robots in visual and temporal inspection of search areas with varying levels of autonomy. Unfortunately, limited autonomy is the norm in such systems, due to the limitations presented by on-board UAV resources and networking capabilities. In this work we propose a new multi-agent approach to SAR and introduce a wearable compute cluster in the form factor of a backpack. The backpack allows offloading compute intensive tasks such as Lost Person Behavior Modelling, Path Planning and Deep Neural Network based computer vision applications away from the UAVs and offers significantly high performance computers to execute them. The backpack also provides for a strong networking backbone and task orchestrators which allow for enhanced coordination and resource sharing among all the agents in the system. On the basis of our benchmarking experiments, we observe that the backpack can significantly boost capabilities and success in modern SAR responses.

Hoy en día los sistemas informáticos complejos se pueden ven en términos de los servicios que ofrecen y las entidades que interactúan para proporcionar o consumir dichos servicios. Los sistemas multi-agente abiertos, donde los agentes pueden entrar o salir del sistema, interactuar y formar grupos (coaliciones de agentes u organizaciones) de forma dinámica para resolver problemas, han sido propuestos como una tecnología adecuada para implementar este nuevo paradigma informático. Sin embargo, el amplio dinamismo de estos sistemas requiere que los agentes tengan una forma de armonizar los conflictos que surgen cuando tienen que colaborar y coordinar sus actividades. En estas situaciones, los agentes necesitan un mecanismo para argumentar de forma eficiente (persuadir a otros agentes para que acepten sus puntos de vista, negociar los términos de un contrato, etc.) y poder llegar a acuerdos. La argumentación es un medio natural y efectivo para abordar los conflictos y contradicciones del conocimiento. Participando en diálogos argumentativos, los agentes pueden llegar a acuerdos con otros agentes. En un sistema multi-agente abierto, los agentes pueden formar sociedades que los vinculan a través de relaciones de dependencia. Estas relaciones pueden surgir de sus interacciones o estar predefinidas por el sistema. Además, los agentes pueden tener un conjunto de valores individuales o sociales, heredados de los grupos a los que pertenecen, que quieren promocionar. Las dependencias entre los agentes y los grupos a los que pertenecen y los valores individuales y sociales definen el contexto social del agente. Este contexto tiene una influencia decisiva en la forma en que un agente puede argumentar y llegar a acuerdos con otros agentes. Por tanto, el contexto social de los agentes debería tener una influencia decisiva en la representación computacional de sus argumentos y en el proceso de gestión de argumentos. / Heras Barberá, SM. (2011). Case-Based Argumentation in Agent Societies [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/12497