This thesis proposes a new software framework that facilitates the study of agent interaction models in early development stages from a designer's perspective. Its purpose is to help reduced the design decision space through simulation experiments that provide early feedback on comparative performance of alternative solutions. This is achieved through interactive concurrent simulation of multiple teams in a representative microworld context. The generic simulator's architecture accommodates an open class of different microworlds and permits multiple communication mechanisms. It also supports interoperability with other software tools, distributed simulation, and various extensions. The framework was validated in the context of two different research projects on helpful behavior in agent teams: the Mutual Assistance Protocol, based on rational criteria for help, and the Empathic Help Model, based on a concept of empathy for artificial agents. The results show that the framework meets its design objectives and provides the flexibility needed for research experimentation. --Leaf i.
This thesis proposes a novel protocol for incorporating helpful behavior into multiagent teamwork. In the proposed protocol, call the Mutual Assistance Protocol (MAP), an agent can use its own abilities and resources to advance a subtask assigned to another agent. The helpful act is performed only when the two agents jointly determine that it is in the interest of the team. The underlying design principle is that each agent assesses the team impact of changes in its own local plan. The distributed decision is reached through a bidding sequence similar to the Contract Net Protocol. The helpful act may consist in performing an action or in granting resources. The advantages of MAP over protocols that use unilateral help decisions are demonstrated through simulation experiments, using varying levels of mutual awareness in the team, dynamic disturbance in the environment, communication costs, and computation costs. --P. ii.
This Thesis proposes and investigates a novel framework for the study of multiagent solutions for computer-aided process planning (CAPP) in manufacturing systems. The framework is based on a domain-specific microworld model of CAPP, called the CAPP World. The motivation comes from the current literature on multiagent systems (MAS) for CAPP, which emphasized the need for comparative studies that would identify the most suitable domain-specific multiagent solutions, and from the observation that a simple, manageable framework for such studies had not been developed. The proposed CAPP World is characterized by a product class, a model of a manufacturing cell, and appropriate adaptation and simplification of CAPP modeling concepts from the literature. These abstractions lead to a collection of specific actions that jointly construct a process plan in CAPP World. The analysis shows that the model meets its design objectives of being: simple integral in the sense of including the main aspects of CAPP representative of properties and difficulties in real-world CAPP and suitable for formulation and investigation of MAS solutions for CAPP. The suitability of CAPP World for domain-specific MAS studies is demonstrated through construction of concrete scenarios addressing topics such as: agent encapsulation, cooperation and coordination among team members, cooperative iterative improvements of process plan, improving the efficiency of process planning through caching of design solutions, team composition, and communication mechanisms. The Thesis also identifies some topics for future research. --P.[i]
This thesis proposes a novel approach to accessing information stored in legacy relational databases (RDB), based on Semantic Web and multiagent systems technologies. It introduces an architectural model of the Semantic Report Generation System (SRGS), designed to address the rising demand for flexible access to information in decision support systems. SRGS is composed of server Database Subsystems (DBS) and client User Subsystems (US). In a DBS, an agent interacts with the administrator to build a reference ontology from the RDB schema, which enables semantic queries without modifying the database. In a US, the decision-making user accesses the system through a simplified natural language interface, using customized extensions to the reference ontology that was imported from DBS an agent helps build the custom ontology, and facilitates query formulation and report generation. The proposed approach is illustrated by several scenarios that highlight the key behavioral aspects of accessing information and developing ontologies. --P. ii.
This thesis investigates how one can design a team of intelligent software agents that helps its human partner develop a formal ontology from a relational database and enhance it with higher-level abstractions. The resulting efficiency of ontology development could facilitate the building of intelligent decision support systems that allow: high-level semantic queries on legacy relational databases autonomous implementation within a host organization and incremental deployment without affecting the underlying database or its conventional use. We introduce a set of design principles, formulate the prototype system requirements and architecture, elaborate agent roles and interactions, develop suitable design techniques, and test the approach through practical implementation of selected features. We endow each agent with model meta-ontology, which enables it to reason and communicate about ontology, and planning meta-ontology, which captures the role-specific know-how of the ontology building method. We also assess the maturity of development tools for a larger-scale implementation. --Leaf i.
This thesis proposes a new interaction protocol for direct help in agent teamwork. It addresses design questions that may arise in practical systems development, and achieves higher teamwork performance impact than previous versions of the Mutual Assistance Protocol (MAP). Direct help, such as performing an action on teammate's behalf, is deliberated by team members as need arises, rather than imposed by team organization or centralized mechanisms. The deliberation can start with a request for help, or with an offer of help the two design principles have been embodied in two distinct versions of MAP. Based on their observed complementarity, we refine and combine them into a single protocol that leverages their individual advantages. Its novel features let an agent initiate help deliberation with request or offer, and also simultaneously provide and receive help. Simulation experiments demonstrate its team performance gains while varying the environment dynamism, agent resources, and communication costs. --Leaf i.
This thesis introduces a model of empathy as a basis for helpful behaviour in teams consisting purely of artificial agents that collaborate on practical problem-solving tasks, and investigates whether the performance of such teams can benefit from empathic help between members as the analogy with human teams might suggest. Guided by existing models of natural empathy in psychology and neuroscience, it identifies the potential empathy factors for artificial agents, as well as the mechanisms by which they produce affective and behavioural responses. The performance of empathic agent teams situated in a microworld similar to the Coloured Trails game is studied through simulation experiments, with the model parameters optimized by a genetic algorithm. For low to moderate levels of random disturbance in the environment, empathic help is superior to random help, and it outperforms rational help as rational decision complexity grows, in particular at higher levels of environmental disturbance. --P. ii.
