this article.

A routine is a habitually repeated performance of some actions. Agents use routines to guide their everyday activities and to enrich their abstract concepts about acts. This dissertation addresses the question of how an agent who is engaged in ordinary, routine activities changes its behavior over time, how the agent's internal representations about the world is affected by its interactions, and what is a good agent architecture for learning routine interactions with the world. In it, I develop a theory that proposes several key processes: (1) automaticity, (2) habituation and skill refinement, (3) abstraction-bychunking, and (4) discovery of new knowledge chunks. The process of automaticity caches the agent's knowledge about actions into a flat stimulus-response data structure that eliminates knowledge of action consequences. The stimulus-response data structure produces a response to environmental stimuli in constant time. The process of habituation and skill refinement uses environm...

In the elephant paper [Bro90], Brooks criticized the ungroundedness of traditional symbol systems, and proposed physically grounded systems as an alternative, in particular the subsumption architecture. Although we are still struggling with many of the issues involved, we believe we have some contributions to make towards solving some of the open problems with physically grounded systems, particularly with respect to whether or how to integrate the old with the new. In this paper we describe an agent architecture that specifies an integration of explicit representation and reasoning mechanisms, embodied semantics through grounding symbols in perception and action, and implicit representations of specialpurpose mechanisms of sensory processing, perception, and motor control. We then present components that we place in our general architecture to build agents that exhibit situated activity and learning, and finally a physical agent implementation and two simulation studies. The gist of o...

Abstract not found

We provide an overview of the use of intelligent agents, implemented in the new MGLAIR architecture, in a virtual reality drama. For us, a virtual reality drama is a scripted play in which the computational agents are actors who have copies of the script, and one human audience member has been drafted to be a participant, but doesn’t have a copy of the script. The computational actors must improvise reactions to the human partpicipant’s actions, but keep the play moving along in as close agreement to the script as possible. The goal is to provide the human participant with a specific emotional experience. We explicate this philosophy; outline the previously described GLAIR architecture; explain the introduction of an organization into modalities that results in the new MGLAIR architecture; describe our current VR drama, The Trial, The Trail; and discuss the implementation of our actor-agents. Our discussion of the actor-agents focuses on their abilities to react to triggers (cues), their performance of contingent actions that are off the main-line arc of the script, their use of timers to pace the drama, and the organization of the cast of actor-agents into a multi-agent system. 1 Virtual Reality Drama Our goal is to produce immersive virtual reality experiences that engage a participant as a central protagonist in compelling interactive dramas. We use a passive stereo system to project life-sized three dimensional images onto a large screen in front of the participant, who has tracking sensors on her head and both hands. Virtual reality and mixed reality have been shown to be powerful presentation media for interactive fiction (Bobick,

It is sometimes necessary to reason non-monotonically, to withdraw previously held beliefs. Default rules and defeasible reasoning have been frequently used to handle such situations. Some years ago, J. Terry Nutter proposed a form of defeasible reasoning involving additional truthvalues that would avoid non-monotonicity in many situations. We adopt and implement much of Nutter's underlying concept, but use a structure of case frames in our knowledge representation to avoid the need for more than the standard truth values. Our implementation captures most of the advantages of the original proposal and in some cases allows more flexibility.

GLAIR (Grounded Layered Architecture with Integrated Reasoning) is a multi-layered cognitive architecture for embodied agents operating in real, virtual, or simulated environments containing other agents. The highest layer of the GLAIR Architecture, the Knowledge Layer (KL), contains the beliefs of the agent, and is the layer in which conscious reasoning, planning, and act selection is performed. The lowest layer of the GLAIR Architecture, the Sensori-Actuator Layer (SAL), contains the controllers of the sensors and effectors of the hardware or software robot. Between the KL and the SAL is the Perceptuo-Motor Layer (PML), which grounds the KL symbols in perceptual structures and subconscious actions, contains various registers for providing the agent’s sense of situatedness in the environment, and handles translation and communication between the KL and the SAL. The motivation for the development of GLAIR has been “Computational Philosophy”, the computational understanding and implementation of human-level intelligent behavior without necessarily being bound by the actual implementation of the human mind. Nevertheless, the approach has been inspired by human psychology and biology.

In this paper we sketch a new approach for agent design and operability called co-designing agents (CDA). As a working definition, we take a CDA to be an agent that participates in some aspect of its own design. The precise manner and degree of a CDA’s participation will ultimately be a design-time decision, but by considering a specific agent implementation (that of AI actor-agents in a virtual drama) we are able to extract a general set of CDA requirements. The CDA approach utilizes concepts from several areas of active research in AI. We present a broad summary of the relevant literature and discuss its applicability to CDA design. We then consider the SNePS knowledge representation, reasoning, and acting system as a potential CDA implementation platform.

We present an AI architecture used for modeling computational rational cognitive agents-- agents that can reason, and act in an environment based on their representations of beliefs, acts, and intentions. A unified representational formalism is employed for representation of propositions (beliefs), goals (desires), actions, and plans. The representational formalism is described using a conceptual object-oriented hierarchy. An object-oriented design facilitates a uniform method (message) protocol that is naturally amenable to concurrency. The reasoning and acting behavior of the modeled agent is defined by an actor-like [Agha 1986, Agha and Hewitt 1987] message passing scheme. Semantically speaking, messages can be viewed as meta-level propositional attitudes (corresponding to ’belief’ and ’intention’) that are sent to/from propositions and acts in parallel. The message passing model, called a Rational Engine (as opposed to an inference engine), implements a BDI-architecture.

this document is to describe the FevahrCassie cognitive agent, and to provide instructions for building SNePS/GLAIR cognitive agents based on FevahrCassie in the ASCII world. Throughout this document "entity" will mean a mental entity denoted by a SNePS term (node), and "object" will mean an object in the real or simulated world in which the agent operates. 2 The Fevahr Environment The Fevahr operates in a 17 # 17 # room containing: