Cox, Michael T.


Rationale-Based Visual Planning Monitors for Cognitive Systems

AAAI Conferences

In this paper, we introduce a new technique for planning in a world under continuous change. We focus on the relationship between vision, interpretation and planning. Our approach is to make vision sensitive to relevant changes in the environment that can affect plans and goals. For this purpose, we applied a rationale-based monitor technique to a hierarchical planner. The planner generates plan monitors that interact with a vision system and react only to those environmental changes that bear on current planning decisions. Thus when the monitors detect these changes, they execute specific plan transformations as needed. We present results with a cognitive architecture using the monitors to focus vision and adapt plans. An experiment in a blocks world demonstrates the effectiveness of our approach.


Goal Operations for Cognitive Systems

AAAI Conferences

Cognitive agents operating in complex and dynamic domains benefit from significant goal management. Operations on goals include formulation, selection, change, monitoring and delegation in addition to goal achievement. Here we model these operations as transformations on goals. An agent may observe events that affect the agent’s ability to achieve its goals. Hence goal transformations allow unachievable goals to be converted into similar achievable goals. This paper examines an implementation of goal change within a cognitive architecture. We introduce goal transformation at the metacognitive level as well as goal transformation in an automated planner and discuss the costs and benefits of each approach. We evaluate goal change in the MIDCA architecture using a resource-restricted planning domain, demonstrating a performance benefit due to goal operations.


MIDCA: A Metacognitive, Integrated Dual-Cycle Architecture for Self-Regulated Autonomy

AAAI Conferences

We present a metacognitive, integrated, dual-cycle architecture whose function is to provide agents with a greater capacity for acting robustly in a dynamic environment and managing unexpected events. We present MIDCA 1.3, an implementation of this architecture which explores a novel approach to goal generation, planning and execution given surprising situations. We formally define the mechanism and report empirical results from this goal generation algorithm. Finally, we describe the similarity between its choices at the cognitive level with those at the metacognitive.


Data-Driven Goal Generation for Integrated Cognitive Systems

AAAI Conferences

We describe our Meta-cognitive, Integrated, Dual-Cycle Architecture (MIDCA), whose purpose is to provide agents with a greater capacity for acting in an open world and dealing with unexpected events. We present MIDCA 1.0, a partial implementation which explores a novel machine-learning approach to goal generation using the Tilde and FOIL algorithms. We describe results from this goal generation algorithm and preview MIDCA 1.1, a partially implemented version that will guide the goal insertion process using statistical anomaly detection and categorization techniques. Finally, we outline the next steps towards a complete, functional implementation of the MIDCA architecture.


Toward an Integrated Metacognitive Architecture

AAAI Conferences

Researchers have studied problems in metacognition both in computers and in humans. In response some have implemented models of cognition and metacognitive activity in various architectures to test and better define specific theories of metacognition. However, current theories and implementations suffer from numerous problems and lack of detail. Here we illustrate the problems with two different computational approaches. The Meta-Cognitive Loop and Meta-AQUA both examine the metacognitive reasoning involved in monitoring and reasoning about failures of expectations, and they both learn from such experiences. But neither system presents a full accounting of the variety of known metacognitive phenomena, and, as far as we know, no extant system does. The problem is that no existing cognitive architecture directly addresses metacognition. Instead, current architectures were initially developed to study more narrow cognitive functions and only later were they modified to include higher level attributes. We claim that the solution is to develop a metacognitive architecture outright, and we begin to outline the structure that such a foundation might have.


AAAI 2008 Workshop Reports

AI Magazine

AAAI 2008 Workshop Reports


AAAI 2008 Workshop Reports

AI Magazine

AAAI was pleased to present the AAAI-08 Workshop Program, held Sunday and Monday, July 13–14, in Chicago, Illinois, USA. The program included the following 15 workshops: Advancements in POMDP Solvers; AI Education Workshop Colloquium; Coordination, Organizations, Institutions, and Norms in Agent Systems, Enhanced Messaging; Human Implications of Human-Robot Interaction; Intelligent Techniques for Web Personalization and Recommender Systems; Metareasoning: Thinking about Thinking; Multidisciplinary Workshop on Advances in Preference Handling; Search in Artificial Intelligence and Robotics; Spatial and Temporal Reasoning; Trading Agent Design and Analysis; Transfer Learning for Complex Tasks; What Went Wrong and Why: Lessons from AI Research and Applications; and Wikipedia and Artificial Intelligence: An Evolving Synergy.


Mixed-Initiative Goal Manipulation

AI Magazine

In state-space planning, search consists of backward and forward chaining through the effects and preconditions of operator representations. Although search is an acceptable mechanism to use in performing automated planning, we present an alternative model to present to the user at the interface of a mixed-initiative planning assistant. That is, we propose to model planning as a goal-manipulation task. This article empirically examines user performance under both the search and the goal-manipulation models of planning and shows that many users do better with the latter.


Seven Aspects of Mixed-Initiative Reasoning:An Introduction to this Special Issue on Mixed-Initiative Assistants

AI Magazine

Mixed-initiative assistants are agents that interact seamlessly with humans to extend their problem-solving capabilities or provide new capabilities. Developing such agents requires the synergistic integration of many areas of AI, including knowledge representation, problem solving and planning, knowledge acquisition and learning, multiagent systems, discourse theory, and human-computer interaction. This paper introduces seven aspects of mixed-initiative reasoning (task, control, awareness, communication, personalization, architecture, and evaluation) and discusses them in the context of several state-of-the-art mixed-initiative assistants. The goal is to provide a framework for understanding and comparing existing mixed-initiative assistants and for developing general design principles and methods.


Seven Aspects of Mixed-Initiative Reasoning:An Introduction to this Special Issue on Mixed-Initiative Assistants

AI Magazine

Mixed-initiative assistants are agents that interact seamlessly with humans to extend their problem-solving capabilities or provide new capabilities. Developing such agents requires the synergistic integration of many areas of AI, including knowledge representation, problem solving and planning, knowledge acquisition and learning, multiagent systems, discourse theory, and human-computer interaction. This paper introduces seven aspects of mixed-initiative reasoning (task, control, awareness, communication, personalization, architecture, and evaluation) and discusses them in the context of several state-of-the-art mixed-initiative assistants. The goal is to provide a framework for understanding and comparing existing mixed-initiative assistants and for developing general design principles and methods.