David E. Wilkins

Bio: David E. Wilkins is an academic researcher from SRI International. The author has contributed to research in topics: Cognitive radio & Sand dune stabilization. The author has an hindex of 21, co-authored 49 publications receiving 2487 citations. Previous affiliations of David E. Wilkins include University of Utah & Boise State University.

Practical Planning: Extending the Classical AI Planning Paradigm

Abstract: 1 Reasoning about Actions and Planning 2 Basic Assumptions and Limitations 3 SIPE and Its Representations 4 Hierarchical Planning as Differing Abstraction Levels 5 Constraints 6. The Truth Criterion 7 Deductive Causal Theories 8 Plan Critics 9 Resources: Reusable, Consumable, Temporal 10 Search 11 Replanning During Execution 12 Planning and Reactivity 13 Achieving Heuristic Adequacy 14 Comparison with Other Systems

Planning and reacting in uncertain and dynamic environments

Abstract: Agents situated in dynamic and uncertain environments require several capabilities for successful operation. Such agents must monitor the world and respond appropriately to important events. The agents should be able to accept goals, synthesize complex plans for achieving those goals, and execute the plans while continuing to be responsive to changes in the world. As events render some current activities obsolete, the agents should be able to modify their plans while continuing activities unaffected by those events. The Cypress system is a domain-independent framework for defining persistent agents with this full range of behaviour. Cypress has been used for several demanding applications, including military operations, real-time tracking, and fault diagnosis.

Can AI planners solve practical problems

Abstract: While there has been recent interest in research on planning and reasoning about actions, nearly all research results have been theoretical. We know of no previous examples of a planning system that has made a significant impact on a problem of practical importance. One of the primary goals during the development of the SIPE-2 planning system has been the balancing of efficiency with expressiveness and flexibility. With a major new extension, SIPE-2 has begun to address practical problems. This paper describes this new extension and the new applications of the planner. One of these applications is the problem of producing products from raw materials on process lines under production and resource constraints. This is a problem of commercial importance and SiPE-2's application to it is described in some detail. Bien que Ton ait constate recemment un interět pour la planification et le raisonnement a propos des actions, presque tous les resuhats des recherches sont theoriques. Nous ne connaissons pas d'exemple de systeme de planification qui ait eu une influence majeure dans la resolution d'un probleme de nature pratique. L'un des prihcipaux objectifs de l'elaboration du systeme de planification SIPE-2 a ete la recherche d'un equilibfe entre l'efficacite, l'expressivite et la flexibilitye. La capacitye du systeme SIPE-2 a ete augmentee considerablement afin qu'il puisse s'attaquer a la resolution de problemes de nature pratique. Cet article traite de 1'extension du systeme et des nouvelles applications du planificateur. L'une de ces nouvelles applications est relative au probleme de la production a la chaine de biens a partir de matieres premieres, en tenant compte de contraintes de production et de ressources. Ce probleme est d'une importance commerciale et l'application du systeme SIPE-2 a sa resolution est decrite avec plus ou moins de details.

A Call for Knowledge- Based Planning

Abstract: We are interested in solving real-world planning problems and, to that end, argue for the use of domain knowledge in planning. We believe that the field must develop methods capable of using rich knowledge models to make planning tools useful for complex problems. We discuss the suitability of current planning paradigms for solving these problems. In particular, we compare knowledge rich approaches such as hierarchical task network planning to minimal-knowledge methods such as STRIPS-based planners and disjunctive planners. We argue that the former methods have advantages such as scalability, expressiveness, continuous plan modification during execution, and the ability to interact with humans. However, these planners also have limitations, such as requiring complete domain models and failing to model uncertainty, that often make them inadequate for real-world problems. In this article, we define the terms knowledge-based and primitive-action planning and argue for the use of knowledge-based planning as a paradigm for solving real-world problems. We next summarize some of the characteristics of real-world problems that we are interested in addressing. Several current real-world planning applications are described, focusing on the ways in which knowledge is brought to bear on the planning problem. We describe some existing knowledge-based approaches and then discuss additional capabilities, beyond those available in existing systems, that are needed. Finally, we draw an analogy from the current focus of the planning community on disjunctive planners to the experiences of the machine learning community over the past decade.

Technological Pedagogical Content Knowledge: A Framework for Teacher Knowledge

Abstract: Research in the area of educational technology has often been critiqued for a lack of theoretical grounding. In this article we propose a conceptual framework for educational technology by building on Shulman’s formulation of ‘‘pedagogical content knowledge’’ and extend it to the phenomenon of teachers integrating technology into their pedagogy. This framework is the result of 5 years of work on a program of research focused on teacher professional development and faculty development in higher education. It attempts to capture some of the essential qualities of teacher knowledge required for technology integration in teaching, while addressing the complex, multifaceted, and situated nature of this knowledge. We argue, briefly, that thoughtful pedagogical uses of technology require the development of a complex, situated form of knowledge that we call Technological Pedagogical Content Knowledge (TPCK). In doing so, we posit the complex roles of, and interplay among, three main components of learning environments: content, pedagogy, and technology. We argue that this model has much to offer to discussions of technology integration at multiple levels: theoretical, pedagogical, and methodological. In this article, we describe the theory behind our framework, provide examples of our teaching approach based upon the framework, and illustrate the methodological contributions that have resulted from this work.

Intelligent Agents: Theory and Practice

Abstract: The concept of an agent has become important in both Artificial Intelligence (AI) and mainstream computer science. Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide these issues into three areas (though as the reader will see, the divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents;researchers in this area are primarily concerned with the problem of designing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; these languages may embody principles proposed by theorists. The paper is not intended to serve as a tutorial introduction to all the issues mentioned; we hope instead simply to identify the most important issues, and point to work that elaborates on them. The article includes a short review of current and potential applications of agent technology.

A Survey of Dynamic Spectrum Access

Abstract: Compounding the confusion is the use of the broad term cognitive radio as a synonym for dynamic spectrum access. As an initial attempt at unifying the terminology, the taxonomy of dynamic spectrum access is provided. In this article, an overview of challenges and recent developments in both technological and regulatory aspects of opportunistic spectrum access (OSA). The three basic components of OSA are discussed. Spectrum opportunity identification is crucial to OSA in order to achieve nonintrusive communication. The basic functions of the opportunity identification module are identified

Bayesian Reinforcement Learning in Factored POMDPs

Abstract: Model-based Bayesian Reinforcement Learning (BRL) provides a principled solution to dealing with the exploration-exploitation trade-off, but such methods typically assume a fully observable environments. The few Bayesian RL methods that are applicable in partially observable domains, such as the Bayes-Adaptive POMDP (BA-POMDP), scale poorly. To address this issue, we introduce the Factored BA-POMDP model (FBA-POMDP), a framework that is able to learn a compact model of the dynamics by exploiting the underlying structure of a POMDP. The FBA-POMDP framework casts the problem as a planning task, for which we adapt the Monte-Carlo Tree Search planning algorithm and develop a belief tracking method to approximate the joint posterior over the state and model variables. Our empirical results show that this method outperforms a number of BRL baselines and is able to learn efficiently when the factorization is known, as well as learn both the factorization and the model parameters simultaneously.