In this paper, we discuss the concept of autobiographic agent and how memory may extend an agent's temporal horizon and increase its adaptability. These concepts are applied to an implementation of a scenario where agents are interacting in a complex virtual artificial life environment. We present computational memory architectures for autobiographic virtual agents that enable agents to retrieve meaningful information from their dynamic memories which increases their adaptation and survival in the environment. The design of the memory architectures, the agents, and the virtual environment are described in detail. Next, a series of experimental studies and their results are presented which show the adaptive advantage of autobiographic memory, i.e. from remembering significant experiences. Also, in a multi-agent scenario where agents can communicate via stories based on their autobiographic memory, it is found that new adaptive behaviours can emerge from an individual's reinterpretation of experiences received from other agents whereby higher communication frequency yields better group performance. An interface is described that visualises the memory contents of an agent. From an observer perspective, the agents' behaviours can be understood as individually structured, and temporally grounded, and, with the communication of experience, can be seen to rely on emergent mixed narrative reconstructions combining the experiences of several agents. This research leads to insights into how bottom-up story-telling and autobiographic reconstruction in autonomous, adaptive agents allow temporally grounded behaviour to emerge. The article concludes with a discussion of possible implications of this research direction for future autobiographic, narrative agents.

This article describes the prototyping of human–robot interactions in the University of Hertfordshire (UH) Robot House. Twelve participants took part in a long-term study in which they interacted with robots in the UH Robot House once a week for a period of 10 weeks. A prototyping method using the narrative framing technique allowed participants to engage with the robots in episodic interactions that were framed using narrative to convey the impression of a continuous long-term interaction. The goal was to examine how participants responded to the scenarios and the robots as well as specific robot behaviours, such as agent migration and expressive behaviours. Evaluation of the robots and the scenarios were elicited using several measures, including the standardised System Usability Scale, an ad hoc Scenario Acceptance Scale, as well as single-item Likert scales, open-ended questionnaire items and a debriefing interview. Results suggest that participants felt that the use of this prototyping technique allowed them insight into the use of the robot, and that they accepted the use of the robot within the scenario.

This work proposes an initial memory model for a long-term artificial companion, which migrates among virtual and robot platforms based on the context of interactions with the human user. This memory model enables the companion to remember events that are relevant or significant to itself or to the user. For other events which are either ethically sensitive or with a lower long-term value, the memory model supports forgetting through the processes of generalisation and memory restructuring. The proposed memory model draws inspiration from the human short-term and long-term memories. The short-term memory will support companions in focusing on the stimuli that are relevant to their current active goals within the environment. The long-term memory will contain episodic events that are chronologically sequenced and derived from the companion's interaction history both with the environment and the user. There are two key questions that we try to address in this work: 1) What information should the companion remember in order to generate appropriate behaviours and thus smooth the interaction with the user? And, 2) What are the relevant aspects to take into consideration during the design of memory for a companion that can have different types of virtual and physical bodies? Finally, we show an implementation plan of the memory model, focusing on issues of information grounding, activation and sensing based on specific hardware platforms.

Abstract. This paper describes an approach to create coherent life stories for Intelligent Virtual Agents (IVAs) in order to achieve long-term believability. We integrate a computational autobiographic memory, which allows agents to remember significant past experiences and reconstruct their life stories from these experiences, into an emotion-driven planning architecture. Starting from the literature review on episodic memory modelling and narrative agents, we discuss design considerations for believable agents which interact with users repeatedly and over a long period of time. In the main body of the paper we present the narrative structure of human life stories. Based on this, we incorporate three essential discourse units and other characteristics into the design of the autobiographic memory structure. We outline part of the implementation of this memory architecture and describe the plan for evaluating the architecture in long-term user studies.

According to traditional animators, the art of building believable characters resides in the ability to successfully portray a character's behaviour as the result of its internal emotions, intentions and thoughts. Following this direction, we want our agents to be able to explicitly talk about their internal thoughts and report their personal past experiences. In order to achieve it, we look at a specific type of episodic long term memory. This paper describes the integration of Autobiographic Memory into FAtiMA, an emotional agent architecture that generates emotions from a subjective appraisal of events.