Princess Cassie: An Embodied Cognitive Agent in a Virtual World
نویسندگان
چکیده
This thesis presents the development of an embodied cognitive agent called Princess Cassie and her implementation as a cognitive actor in a Virtual Reality drama. This work effectively bridges the gap between, and builds upon previous work carried out on cognitive agent modeling and development and work carried out on the development of dramatic agents that are richly expressive, believable and that portray characters with emotional depth. Princess Cassie is expected to serve as an ideal test framework, upon which an effective model of cognitive agency for dramatic and socially interesting agents can be built. Several issues central to the development of such embodied cognitive agency have been considered and implemented in this implementation. Princess Cassie’s capabilities include: an ability to identify and process a rich array of perceptual information both about the world and about its own embodiment; true multi-modal behavior involving several channels of asynchronous communication between the mind and the body; adherence to a tight script for performance; a sophisticated model for interrupt and contingency handling; achievement of goals by the formulation and execution of plans and ability to dissemble effectively in the face of unpredictability in the scene. The development and subsequent implementation of Princess Cassie has allowed us to experiment with the various ways that an embodied cognitive agent can be used to effectively enhance a VR experience for a human user. This work has been carried out as part of a larger project which has the goal of eventually constructing an entire dramatic story around a human user, in which all the actors are computational agents sophisticated enough to draw dramatic responses from the user. The agent presented in this thesis therefore represents a first step towards accomplishing this goal.
منابع مشابه
Crystal Cassie: Use of a 3-D Gaming Environment for a Cognitive Agent
The SNePS research group has built several implementations of an embodied computational cognitive agent called Cassie, based on the Grounded Layered Architecture with Integrated Reasoning (GLAIR). In this document we describe a new implementation, in which Cassie’s body and the world are simulated in Crystal Space, an environment for building 3-D games. We describe the implementation of Cassie ...
متن کاملSymbol-Anchoring in Cassie
We have been engaged in a series of projects in which Cassie, the SNePS cognitive agent, has been incorporated into a hardwareor software-simulated cognitive robot. In this paper, we present an informal summary of our approach to anchoring the abstract symbolic terms that denote Cassie’s mental entities in the lowerlevel structures used by embodied-Cassie to operate in the real (or simulated) w...
متن کاملAnchoring in a grounded layered architecture with integrated reasoning
The GLAIR grounded layered architecture with integrated reasoning for cognitive robots and intelligent autonomous agents has been used in a series of projects in which Cassie, the SNePS cognitive agent, has been incorporated into hardwareor software-simulated cognitive robots. In this paper, we present an informal, but coherent, overview of the GLAIR approach to anchoring the abstract symbolic ...
متن کاملEmotional agent in serious game (DINO)
In this paper, we introduce an novel emotional agent system in 3D virtual world based on OCC (Ortony, Clore and Collins) theory, FCM (Fuzzy Cognitive Map) and GoalNet. The agent system is designed based on Goal Net model. Emotional modeling and decision making are based on OCC and FCM inference. Emotions modeled by the OCC model are incorporated into FCM inference. It has been shown emotion has...
متن کاملProspective Storytelling Agents
Prospective Logic Programming is a declarative framework supporting the specification of autonomous agents capable of anticipating and reasoning about hypothetical future scenaria. This capability for prediction is essential for proactive agents working with partial information in dynamically changing environments. The present work explores the use of state-of-the-art declarative non-monotonic ...
متن کامل