What kinds of social relationships can people have with computers? Are there activities that computers can engage in that actively draw people into relationships with them? What are the potential benefits to the people who participate in these human-computer relationships? To address these questions this work introduces a theory of Relational Agents, which are computational artifacts designed to build and maintain long-term, social-emotional relationships with their users. These can be purely software humanoid animated agents--as developed in this work--but they can also be non-humanoid or embodied in various physical forms, from robots, to pets, to jewelry, clothing, hand-helds, and other interactive devices. Central to the notion of relationship is that it is a persistent construct, spanning multiple interactions; thus, Relational Agents are explicitly designed to remember past history and manage future expectations in their interactions with users. Finally, relationships are fundamentally social and emotional, and detailed knowledge of human social psychology--with a particular emphasis on the role of affect--must be incorporated into these agents if they are to effectively leverage the mechanisms of human social cognition in order to build relationships in the most natural manner possible. People build

‘‘This evidence leads us to wonder whether intimacy is as much a ‘negotiated collusion ’ as it is a state of ‘true oneness’’’ (Brown and Rogers, 1991) Abstract. Building a collaborative trusting relationship with users is crucial in a wide range of applications, such as advice-giving or financial transactions, and some minimal degree of cooperativeness is required in all applications to even initiate and maintain an interaction with a user. Despite the importance of this aspect of human–human relationships, few intelligent systems have tried to build user models of trust, credibility, or other similar interpersonal variables, or to influence these variables during interaction with users. Humans use a variety of kinds of social language, including small talk, to establish collaborative trusting interpersonal relationships. We argue that such strategies can also be used by intelligent agents, and that embodied conversational agents are ideally suited for this task given the myriad multimodal cues available to them for managing conversation. In this article we describe a model of the relationship between social language and interpersonal relationships, a new kind of discourse planner that is capable of generating social language to achieve interpersonal goals, and an actual implementation in an embodied conversational agent. We discuss an evaluation of our system in which the use of social language was demonstrated to have a significant effect on users ’ perceptions of the agent’s knowledgableness and ability to engage users, and on their trust, credibility, and how well they felt the system knew them, for users manifesting particular personality traits.

This thesis describes the incremental development and main features of a synthetic multi-agent system called UvA Trilearn 2001. UvA Trilearn 2001 is a robotic soccer simulation team that consists of eleven autonomous software agents. It operates in a physical soccer simulation system called soccer server which enables teams of autonomous software agents to play a game of soccer against each other. The soccer server provides a fully distributed and real-time multi-agent environment in which teammates have to cooperate to achieve their common goal of winning the game. The simulation models many real-world complexities such as noise in object movement, noisy sensors and actuators, limited physical abilities and restricted communication. This thesis addresses the various components that make up the UvA Trilearn 2001 robotic soccer simulation team and provides an insight into the way in which these components have been (incrementally) developed. Our main contributions include a multi-threaded three-layer agent architecture, a flexible agent-environment synchronization scheme, accurate methods for object localization and velocity estimation using particle filters, a layered skills hierarchy, a scoring policy for simulated soccer agents and an e#ective team strategy. Ultimately, the thesis can be regarded as a handbook for the development of a complete robotic soccer simulation team which also contains an introduction to robotic soccer in general as well as a survey of prior research in soccer simulation. As such it provides a solid framework which can serve as a basis for future research in the field of simulated robotic soccer. Throughout the project UvA Trilearn 2001 has participated in two international robotic soccer competitions: the team reached 5th place at the German ...

The problem of action selection by autonomous agents becomes increasingly difficult when acting in continuous, non-deterministic and dynamic environments pursuing multiple and possibly conflicting goals. We propose a method that exploits additional information gained from continuous states, is able to deal with unexpected situations, and takes multiple and conflicting goals into account including additional motivational aspects such as dynamic goals, which allow for situation-dependent motivational influence on the agent. Further we show some domain independent properties of this algorithm along with empirical results gained using the RoboCup simulated soccer environment. 1

In this paper we descibe the process of action control used by the agents of the magmaFreiburg team. It is based on extended behavior networks, which add situation-dependent motivational influence on the agent and extend original behavior networks to exploit information from continuous domains. Advantages of the original networks, such as reactivity, planning capabilities, robustness, accountance for multiple goals and its cheap and distributed calculations are maintained. 1 Extended Behavior Networks Maes [4, 5, 6] suggested a mechanism for action selection in dynamic and unpredictable domains based on so-called behavior networks. Although Maes' networks do work in continuous domains, they do not exploit the additional information provided by continuous states. Similarly, though there are mechanisms to distinguish different types of goals in MASM, there are no means to support goals with a continuous truth state (like 'have stamina') to become increasingly demanding the less they...

If behavior networks, which use spreading activation to select actions, are analogous to connectionist methods of pattern recognition, then we suggest that recurrent behavior networks, which use energy minimization, are analogous to Hopfield networks. Hopfield networks memorize patterns by making them attractors. We argue that, similarly, each behavior of a recurrent behavior network should be an attractor of the network, to inhibit fruitless, repeated switching between different behaviors in response to small changes in the environment and in motivations. We demonstrate that the performance in a test domain of the Do the Right Thing recurrent behavior network is improved by redesigning it to create desirable attractors and basins of attraction. We further show that this performance increase is correlated with an increase in persistence and a decrease in undesirable behavior-switching.

Abstract. The Extended Behavior Network (EBN) is an architecture and action selection mechanism to design agents capable of selecting sets of concurrent actions in dynamic and continuous environments. It allows one to specify context-dependent motivations and build agents modularly, and has achieved good results in the Robocup and in the 3D action game Unreal Tournament. PHISH-Nets, another behavior network model capable of selecting just single actions, was applied to character modeling, with promising results. We investigate how EBNs fare on agent personality modeling via the design and analysis of 5 stereotypes in Unreal Tournament. We discuss three ways to build character personas and situate our work within other approaches. We conclude that EBNs provide a straightforward way to develop and experiment with different personalities, being interesting for building agents with simple personas and for character prototyping. 1

Introduction The purpose of this work is to endow an embodied conversational computer agent with the ability to establish and maintain an on-going social relationship with a user. This ability is not only important in entertainment applications (e.g., as in Tamagotchis and Furbies which are specifically designed to establish on-going relationships with their users) and affect support systems (such as computer therapists or frustration management systems), but plays a crucial role in any application in which we want to manage how a user interacts with an agent. If we want our users to feel comfortable with our agents, trust them or be persuaded or comforted by them, then we must understand how humans perform these functions and endow our agents with similar behavior. In this work I am particularly interested in embodied conversational agents (Cassell, Bickmore et al. 1999), which are agents that use natural speech and an animated humanoid represent

Abstract: In this paper we present the development of an episodic memory module for the cognitive architecture controlling an autonomous mobile simulated robot, in a simulated 3D environment. The episodic memory has the role of improving the navigation system of the robot, by evoking the objects to be considered in planning, according to episodic remembrance of earlier contacts with those objects in the past. We introduce the main background on human memory systems and episodic memory study, and provide the main ideas behind our experiment. Keywords: navigation 1.