Emilio Remolina

Towards a general theory of topological maps

We present a general theory of topological maps whereby sensory input, topological and local metrical information are combined to define the topological maps explaining such information. Topological maps correspond to the minimal models of an axiomatic theory describing the relationships between the different sources of information explained by a map. We use a circumscriptive theory to specify the minimal models associated with this representation.The theory here proposed is independent of the exploration strategy the agent follows when building a map. We provide an algorithm to calculate the models of the theory. This algorithm supports different exploration strategies and facilitates map disambiguation when perceptual aliasing arises.

Integrating Vision and Spatial Reasoning for Assistive Navigation

This paper describes the goals and research directions of the University of Texas Artificial Intelligence Labs Intelligent Wheelchair Project (IWP). The IWP is a work in progress. The authors are part of a collaborative effort to bring expertise from knowledge representation, control, planning, and machine vision to bear on this difficult and interesting problem domain. Our strategy uses knowledge about the semantic structure of space to focus processing power and sensing resources. The semi-autonomous assistive control of a wheelchair shares many sub-problems with mobile robotics, including those of sensor interpretation, spatial knowledge representation, and real-time control. By enabling the wheelchair with active vision and other sensing modes, and by application of our theories of spatial knowledge representation and reasoning, we hope to provide substantial assistance to people with severe mobility impairments.

Formalizing Regions in the Spatial Semantic Hierarchy: An AH-Graphs Implementation Approach

We are interested in the problem of how an agent organizes its sensorimotor experiences in order to create a spatial representation. Our approach to solve this problem is the Spatial Semantic Hierarchy (SSH), an ontological hierarchy of representations for knowledge of large-scale space. At the SSH topological level, space is represented by places and connectivity relationships among them. Places are arranged into paths so that the topological representation looks like the street network of a city. Grouping places into regions allows an agent to reason efficiently about its spatial knowledge. Regions can be organized in a hierarchical structure suitable for hierarchical planning and human-level interface. In this paper we show how a hierarchy of regions can be automatically created by an agent. We extend the SSH axiomatic theory to include regions as first order objects at the SSH topological level. Based on this formalization, an implementation using Annotated Hierarchical graphs (AH-graphs) is proposed. The AH-graph model is chosen for its efficiency to perform basic operations like path planning, its facility to integrate information needed by different agents tasks, and because it provides a large indexed database of knowledge about the world with a friendly flow of information from and to human operators.

FlexiTrainer: A Visual Authoring Framework for Case-Based Intelligent Tutoring Systems

The need for rapid and cost-effective development Intelligent Tutoring Systems with flexible pedagogical approaches has led to a demand for authoring tools. The authoring systems developed to date provide a range of options and flexibility, such as authoring simulations, or authoring tutoring strategies. This paper describes FlexiTrainer, an authoring framework that enables the rapid creation of pedagogically rich and performance-oriented learning environments with custom content and tutoring strategies. FlexiTrainer provides tools for specifying the domain knowledge and derives its power from a visual behavior editor for specifying the dynamic behavior of tutoring agents that interact to deliver instruction. The FlexiTrainer runtime engine is an agent based system where different instructional agents carry out teaching related actions to achieve instructional goals. FlexiTrainer has been used to develop an ITS for training helicopter pilots in flying skills.

A Visual Integrated Development Environment for Automated Planning Domain Models

Automated planning software uses symbolic reasoning techniques and models of the planning domain to generate plans. Execution systems execute these plans to perform tasks or achieve goals, subject to constraints imposed by physical laws, resource limits, and environmental conditions and flight rules. Automated planning can support autonomous operations of spacecraft, habitats, and space launch systems. The Action Notation Modeling Language (ANML) is a relatively new language developed by NASA for specifying planning domain models. Developing and maintaining good planning domain models is challenging and critical to the success of applying applying automated planning technology to support autonomous systems. We developed an integrated development environment (IDE) to help modelers enter, review, test, debug, maintain, and enhance ANML planning domain models as well as review and understand ANML models developed by others. The IDE is implemented in the Java programming language using the Eclipse and Xtext open source frameworks for developing integrated development environments (IDEs). The IDE provides a syntax-aware text-based editor that color-codes ANML text based on its syntactic type, flags errors and warnings, supports browsing, suggests code completions, and provides online help. It automatically detects and highlights problems such as syntax errors, type mismatches, references to undefined variables, and incorrect numbers or types of arguments in references to variables and actions. In addition, the IDE provides graphical displays that help modelers see important patterns and relationships among planning variables and actions. An evaluation showed that PM/IDE significantly reduced the time needed to create ANML models. The syntax highlighting and tooltips helped modelers avoid many syntax errors, and the visualizations helped modelers identify logic errors and other semantic issues.

Software testbed for developing and evaluating integrated autonomous systems

To implement fault tolerant autonomy in future space systems, it will be necessary to integrate planning, adaptive control, and state estimation subsystems. However, integrating these subsystems is difficult, time-consuming, and error-prone. This paper describes Intelliface/ADAPT, a software testbed that helps researchers develop and test alternative strategies for integrating planning, execution, and diagnosis subsystems more quickly and easily. The testbeds architecture, graphical data displays, and implementations of the integrated subsystems support easy plug and play of alternate components to support research and development in fault-tolerant control of autonomous vehicles and operations support systems. Intelliface/ADAPT controls NASAs Advanced Diagnostics and Prognostics Testbed (ADAPT), which comprises batteries, electrical loads (fans, pumps, and lights), relays, circuit breakers, invertors, and sensors. During plan execution, an experimentor can inject faults into the ADAPT testbed by tripping circuit breakers, changing fan speed settings, and closing valves to restrict fluid flow. The diagnostic subsystem, based on NASAs Hybrid Diagnosis Engine (HyDE), detects and isolates these faults to determine the new state of the plant, ADAPT. Intelliface/ADAPT then updates its model of the ADAPT systems resources and determines whether the current plan can be executed using the reduced resources. If not, the planning subsystem generates a new plan that reschedules tasks, reconfigures ADAPT, and reassigns the use of ADAPT resources as needed to work around the fault. The resource model, planning domain model, and planning goals are expressed using NASAs Action Notation Modeling Language (ANML). Parts of the ANML model are generated automatically, and other parts are constructed by hand using the Planning Model Integrated Development Environment, a visual Eclipse-based IDE that accelerates ANML model development. Because native ANML planners are currently under development and not yet sufficiently capable, the ANML model is translated into the New Domain Definition Language (NDDL) and sent to NASAs EUROPA planning system for plan generation. The adaptive controller executes the new plan, using augmented, hierarchical finite state machines to select and sequence actions based on the state of the ADAPT system. Real-time sensor data, commands, and plans are displayed in information-dense arrays of timelines and graphs that zoom and scroll in unison. A dynamic schematic display uses color to show the real-time fault state and utilization of the system components and resources. An execution manager coordinates the activities of the other subsystems. The subsystems are integrated using the Internet Communications Engine (ICE), an object-oriented toolkit for building distributed applications.

Distributed Troubleshooting Agents

Key issues to address in autonomic job recovery for cluster computing are recognizing job failure; understanding the failure sufficiently to know if and how to restart the job; and rapidly integrating this information into the cluster architecture so that the failure is better mitigated in the future. The agent based high availability (ABHA) system provides an API and a collection of services for building autonomic batch job recovery into cluster and grid computing environments. An agent API allows users to define agents for failure diagnosis and recovery. It is currently being evaluated in the U.S. Department of Energys STAR project

Intelligent Data Visualization for Cross-Checking Spacecraft System Diagnoses.

Any reasoning system is fallible, so crew members and flight controllers must be able to cross-check automated diagnoses of spacecraft or habitat problems by considering alternate diagnoses and analyzing related evidence. Cross-checking improves diagnostic accuracy because people can apply information processing heuristics, pattern recognition techniques, and reasoning methods that the automated diagnostic system may not possess. Over time, cross-checking also enables crew members to become comfortable with how the diagnostic reasoning system performs, so the system can earn the crew s trust. We developed intelligent data visualization software that helps users cross-check automated diagnoses of system faults more effectively. The user interface displays scrollable arrays of timelines and time-series graphs, which are tightly integrated with an interactive, color-coded system schematic to show important spatial-temporal data patterns. Signal processing and rule-based diagnostic reasoning automatically identify alternate hypotheses and data patterns that support or rebut the original and alternate diagnoses. A color-coded matrix display summarizes the supporting or rebutting evidence for each diagnosis, and a drill-down capability enables crew members to quickly view graphs and timelines of the underlying data. This system demonstrates that modest amounts of diagnostic reasoning, combined with interactive, information-dense data visualizations, can accelerate system diagnosis and cross-checking.

ABHA: A Framework for Autonomic Job Recovery

Key issues to address in autonomic job recovery for cluster computing are recognizing job failure; understanding the failure sufficiently to know if and how to restart the job; and rapidly integrating this information into the cluster architecture so that the failure is better mitigated in the future. The Agent Based High Availability (ABHA) system provides an API and a collection of services for building autonomic batch job recovery into cluster computing environments. An agent API allows users to define agents for failure diagnosis and recovery. It is currently being evaluated in the U.S. Department of Energy’s STAR project.