Michael Wolverton

A Survey of Research in Distributed, Continual Planning

Complex, real-world domains require rethinking traditional approaches to AI planning. Planning and executing the resulting plans in a dynamic environment implies a continual approach in which planning and execution are interleaved, uncertainty in the current and projected world state is recognized and handled appropriately, and replanning can be performed when the situation changes or planned actions fail. Furthermore, complex planning and execution problems may require multiple computational agents and human planners to collaborate on a solution. In this article, we describe a new paradigm for planning in complex, dynamic environments, which we term distributed, continual planning (DCP). We argue that developing DCP systems will be necessary for planning applications to be successful in these environments. We give a historical overview of research leading to the current state of the art in DCP and describe research in distributed and continual planning.

Toward establishing trust in adaptive agents

As adaptive agents become more complex and take increasing autonomy in their users lives, it becomes more important for users to trust and understand these agents. Little work has been done, however, to study what factors influence the level of trust users are willing to place in these agents. Without trust in the actions and results produced by these agents, their use and adoption as trusted assistants and partners will be severely limited. We present the results of a study among test users of CALO, one such complex adaptive agent system, to investigate themes surrounding trust and understandability. We identify and discuss eight major themes that significantly impact user trust in complex systems. We further provide guidelines for the design of trustable adaptive agents. Based on our analysis of these results, we conclude that the availability of explanation capabilities in these agents can address the majority of trust concerns identified by users.

AR-mentor: Augmented reality based mentoring system

AR-Mentor is a wearable real time Augmented Reality (AR) mentoring system that is configured to assist in maintenance and repair tasks of complex machinery, such as vehicles, appliances, and industrial machinery. The system combines a wearable Optical-See-Through (OST) display device with high precision 6-Degree-Of-Freedom (DOF) pose tracking and a virtual personal assistant (VPA) with natural language, verbal conversational interaction, providing guidance to the user in the form of visual, audio and locational cues. The system is designed to be heads-up and hands-free allowing the user to freely move about the maintenance or training environment and receive globally aligned and context aware visual and audio instructions (animations, symbolic icons, text, multimedia content, speech). The user can interact with the system, ask questions and get clarifications and specific guidance for the task at hand. A pilot application with AR-Mentor was successfully built to instruct a novice to perform an advanced 33-step maintenance task on a training vehicle. The initial live training tests demonstrate that AR-Mentor is able to help and serve as an assistant to an instructor, freeing him/her to cover more students and to focus on higher-order teaching.

Task-based information management

Effective collaboration in fast-changing environment can put great dem ands on a collaborators time. Therefore, information retrieval and filtering tools for these environments should impose as little on that time as possible. Not only should they exclude as many irrelevant documents as possible from those presented to the user (to avoid the time wasted sorting through and reading those documents), they should also minimize the users effort in characterizing his or her information needs. The goal of the Task-based Information Distribution Environment (TIDE) system is to achieve these objectives by explicitly representing each collaborators current task and using those representations to deliver documents that meet the information needs implied by those tasks. It does this by treating information gathering as a diagnosis problem, in which the situation (i.e., the current state of beliefs about various questions related to a task) leads probabilistically to test that will provide the most evidence toward reaching a diagnosis (i.e., a description of the documents most likely to be useful to that task). It encodes tasks as nodes in a Bayesian network, and computes document descriptions based on the probabilistic relationship among tasks and their corresponding information requirements.

Mixed-initiative visual analytics using task-driven recommendations

Visual data analysis is composed of a collection of cognitive actions and tasks to decompose, internalize, and recombine data to produce knowledge and insight. Visual analytic tools provide interactive visual interfaces to data to support discovery and sensemaking tasks, including forming hypotheses, asking questions, and evaluating and organizing evidence. Myriad analytic models can be incorporated into visual analytic systems at the cost of increasing complexity in the analytic discourse between user and system. Techniques exist to increase the usability of interacting with analytic models, such as inferring data models from user interactions to steer the underlying models of the system via semantic interaction, shielding users from having to do so explicitly. Such approaches are often also referred to as mixed-initiative systems. Sensemaking researchers have called for development of tools that facilitate analytic sensemaking through a combination of human and automated activities. However, design guidelines do not exist for mixed-initiative visual analytic systems to support iterative sensemaking. In this paper, we present candidate design guidelines and introduce the Active Data Environment (ADE) prototype, a spatial workspace supporting the analytic process via task recommendations invoked by inferences about user interactions within the workspace. ADE recommends data and relationships based on a task model, enabling users to co-reason with the system about their data in a single, spatial workspace. This paper provides an illustrative use case, a technical description of ADE, and a discussion of the strengths and limitations of the approach.

Exploiting enterprise models for the automatic distribution of corporate information

Effectively distributing information to members of a large organization poses a number of challenges. Ideal information distribution within an organization will betimely, selective, and (to some degree) automatic. It is difficult to meet all three of these criteria simultaneously using existing techniques in information retrieval and information filtering. This paper introduces a new method of distributing information automatically, based on e terprise models — representations of the pertinent aspects of an organization’s structure and operation. The approach is based on the premise that often information needs within an organization are implicitly represented by paths through the enterprise model. These paths are discovered in our approach through the use of Generalized Path Models (GPMs). A GPM specifies (1) the conditions that instigate a path search when new information is created, (2) a general class of paths for which to search, and (3) an action to take when a suitable path is found. The approach has been implemented in a software module called IDIST, an extension to a large commercial enterprise modelling tool.

A Process Catalog for Workflow Generation

As AI developers increasingly look to workflow technologies to perform complex integrations of individual software components, there is a growing need for the workflow systems to have expressive descriptions of those components. They must know more than just the types of a components inputs and outputs; instead, they need detailed characterizations that allow them to make fine-grained distinctions between candidate components and between candidate workflows. This paper describes ProCat , an implemented ontology-based catalog for components, conceptualized as processes , that captures and communicates this detailed information. ProCat is built on a layered representation that allows reasoning about processes at varying levels of abstraction, from qualitative constraints reflecting preconditions and effects, to quantitative predictions about output data and performance. ProCat employs Semantic Web technologies RDF, OWL, and SPARQL, and builds on Semantic Web services research. We describe ProCats approach to representing and answering queries about processes, discuss some early experiments evaluating the quantitative predictions, and report on our experience using ProCat in a system producing workflows for intelligence analysis.