Search NASA⌕ Search

SEARCH · Search NASA

Results for “actionable intelligence”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS1991

Approximate reasoning-based learning and control for proximity operations and docking in space

A recently proposed hybrid-neutral-network and fuzzy-logic-control architecture is applied to a fuzzy logic controller developed for attitude control of the Space Shuttle. A model using reinforcement learning and learning from past experience for fine-tuning its knowledge base is proposed. Two main components of this approximate reasoning-based intelligent control (ARIC) model - an action-state evaluation network and action selection network are described as well as the Space Shuttle attitude controller. An ARIC model for the controller is presented, and it is noted that the input layer in each network includes three nodes representing the angle error, angle error rate, and bias node. Preliminary results indicate that the controller can hold the pitch rate within its desired deadband and starts to use the jets at about 500 sec in the run.

Berenji, Hamid R.↗
NASA NTRS1994

Modeling actions and operations to support mission preparation

This paper describes two linked technology development projects to support Space Shuttle ground operations personnel, both during mission preparation analysis and related analyses in missions. The Space Propulsion Robust Analysis Tool (SPRAT) will provide intelligent support and automation for mission analysis setup, interpretation, reporting and documentation. SPRAT models the actions taken by flight support personnel during mission preparation and uses this model to generate an action plan. CONFIG will provide intelligent automation for procedure analyses and failure impact analyses, by simulating the interactions between operations and systems with embedded failures. CONFIG models the actions taken by crew during space vehicle malfunctions and simulates how the planned action sequences in procedures affect a device model. Jointly the SPRAT and CONFIG projects provide an opportunity to investigate how the nature of a task affects the representation of actions, and to determine a more general action representation supporting a broad range of tasks. This paper describes the problems in representing actions for mission preparation and their relation to planning and scheduling.

Malin, Jane T.↗
NASA NTRS2015

A Fast Goal Recognition Technique Based on Interaction Estimates

Goal Recognition is the task of inferring an actor's goals given some or all of the actor's observed actions. There is considerable interest in Goal Recognition for use in intelligent personal assistants, smart environments, intelligent tutoring systems, and monitoring user's needs. In much of this work, the actor's observed actions are compared against a generated library of plans. Recent work by Ramirez and Geffner makes use of AI planning to determine how closely a sequence of observed actions matches plans for each possible goal. For each goal, this is done by comparing the cost of a plan for that goal with the cost of a plan for that goal that includes the observed actions. This approach yields useful rankings, but is impractical for real-time goal recognition in large domains because of the computational expense of constructing plans for each possible goal. In this paper, we introduce an approach that propagates cost and interaction information in a plan graph, and uses this information to estimate goal probabilities. We show that this approach is much faster, but still yields high quality results.

gola recognition↗
NASA NTRS1980

RFI prevention for colocated antennas

Potential radio frequency interference problems related to the colocation of antennas for the Mark 4-A Deep Space network are analyzed. Cases discussed include effects of S-band uplinks on X-band downlinks and S-band downlinks, planetary radar at Goldstone, future X-band uplink, radiometer measurements, Search for Extraterrestrial Intelligence instrument, and radio astronomy projects. Remedial actions are suggested.

Peng, T. K.↗
NASA NTRS1990

AND/OR graph representation of assembly plans

A compact representation of all possible assembly plans of a product using AND/OR graphs is presented as a basis for efficient planning algorithms that allow an intelligent robot to pick a course of action according to instantaneous conditions. The AND/OR graph is equivalent to a state transition graph but requires fewer nodes and simplifies the search for feasible plans. Three applications are discussed: (1) the preselection of the best assembly plan, (2) the recovery from execution errors, and (3) the opportunistic scheduling of tasks. An example of an assembly with four parts illustrates the use of the AND/OR graph representation in assembly-plan preselection, based on the weighting of operations according to complexity of manipulation and stability of subassemblies. A hypothetical error situation is discussed to show how a bottom-up search of the AND/OR graph leads to an efficient recovery.

Homem De Mello, Luiz S.↗
NASA NTRS2018

Climate Lecture 20: The Educational Global Climate Model (EdGCM)

Climate change will profoundly impact Earth's environmental health as well as the world's economic and geopolitical landscape over the coming decades. The impacts of climate change are, in fact, already beginning to be experienced and have the potential to affect every living plant and animal on Earth within decades. Given this reality, every citizen of this planet should have the right to knowledge about the Earth's climate system and have the option to adapt to, or help mitigate the profound changes that are coming. In addition, a portion of the workforce needs to be capable of interpreting and analyzing climate information because, since the impacts of climate change will be widespread, pervasive, and continue to change over time, more professions will be interacting with climate data. We are already at, or past, the point where educators and their students require access to the scientific and technological resources - computer models, data, and visualization tools - that scientists use daily in the study of climate change. Although scientists use many methods to study Earth's climate system, global climate models (GCMs) have become the primary tools for exploring the complex interactions between components of the entire system: atmosphere, oceans, and land. GCMs are used to make projections of future climate change, to simulate climates of the past, and even to help scientists look for life on other planets. Like any model, a GCM can help people evaluate actions before they are taken. Like Business Intelligence software, they are Climate Intelligence tools. Unfortunately, GCMs are black boxes to most people. A previous chapter in this book by Gary Russell, entitled Building a Climate Model, is one example of the growing body of literature aimed at the general public describing the inner workings of global climate models. This literature goes a long way toward explaining climate model fundamentals. However, it will not be enough to alleviate their black-box nature unless people are afforded hands-on, authentic learning experiences as well.

Chandler, Mark A.↗
NASA NTRS1993

Toward intelligent flight control

Flight control systems can benefit by being designed to emulate functions of natural intelligence. Intelligent control functions fall in three categories: declarative, procedural, and reflexive. Declarative actions involve decision-making, providing models for system monitoring, goal planning, and system/scenario identification. Procedural actions concern skilled behavior and have parallels in guidance, navigation, and adaptation. Reflexive actions are more-or-less spontaneous and are similar to inner-loop control and estimation. Intelligent flight control systems will contain a hierarchy of expert systems, procedural algorithms, and computational neural networks, each expanding on prior functions to improve mission capability to increase the reliability and safety of flight and to ease pilot workload.

Stengel, Robert F.↗
NASA NTRS2005

Intelligent Life-Extending Controls for Aircraft Engines

Aircraft engine controllers are designed and operated to provide desired performance and stability margins. The purpose of life-extending-control (LEC) is to study the relationship between control action and engine component life usage, and to design an intelligent control algorithm to provide proper trade-offs between performance and engine life usage. The benefit of this approach is that it is expected to maintain safety while minimizing the overall operating costs. With the advances of computer technology, engine operation models, and damage physics, it is necessary to reevaluate the control strategy fro overall operating cost consideration. This paper uses the thermo-mechanical fatigue (TMF) of a critical component to demonstrate how an intelligent engine control algorithm can drastically reduce the engine life usage with minimum sacrifice in performance. A Monte Carlo simulation is also performed to evaluate the likely engine damage accumulation under various operating conditions. The simulation results show that an optimized acceleration schedule can provide a significant life saving in selected engine components.

Guo, Ten-Huei↗
NASA NTRS1989

PRIME: A bottom-up approach to probabilistic rule development

PRIME is a system to be used by an intelligent machine to allow it to operate in an abstract but uncertain (or stochastic) environment. It maintains a model of the effects of the machine's actions in the form of a rule base, which is induced from experience. This bottom-up approach to rule development allows the model to adapt to changes in the environment. Each rule consists of a condition under which the rule is active, an action, the effect of the action on the environment, and an estimate of the probability of this effect occurring. The effect probabilities are used to model the uncertainty in the environment, permitting multiple possible effects for a single action under a particular set of conditions. The objective of the intelligent machine is to satisfy user-specified goals with maximum probability of success. PRIME fulfills this requirement in two ways: it continuously updates the rule base with the most recent information, to ensure the validity of the model; and it generates plans which have the maximum probability of achieving the goals, based on the probability estimates in the rule base. PRIME is composed of three main processes: exploration, generalization, and planning. In exploration, the machine executes various randomly chosen actions, observes the effects on the environment, and updates the rule base accordingly. This process is used to develop the rule base in simulation, as well as to supplement the current knowledge during normal operation. Generalization is the procedure used to induce general rules from experience, which is encoded in the form of specific rules. These general rules extend the machine's knowledge to situations which have not been encountered yet, thereby increasing the capability of the machine to plan effectively. Planning is the process of constructing an optimal sequence of actions to satisfy a goal, using the rule base to predict the effects of these actions and to determine the probability of success of the plan. The rule representation and many other data structures were specifically chosen to maximize the efficiency of these processes. A simulated environment was designed to test the performance of PRIME. The results of experimentation were largely negative. The main problem was that the domain coverage of the rules was inadequate for the number of rules stored in the rule base, due to redundancies in general rules and numerous rules covering ineffective actions. It was determined that a more efficient generalization, and some form of goal-directed exploration, are necessary in order to solve most of the current deficiencies in PRIME.

Miller, Scott A.↗
NASA NTRS1989

Robotic sampling system for an unmanned Mars mission

A major robotics opportunity for NASA will be the Mars Rover/Sample Return Mission which could be launched as early as the 1990s. The exploratory portion of this mission will include two autonomous subsystems: the rover vehicle and a sample handling system. The sample handling system is the key to the process of collecting Martian soils. This system could include a core drill, a general-purpose manipulator, tools, containers, a return canister, certification hardware and a labeling system. Integrated into a functional package, the sample handling system is analogous to a complex robotic workcell. Discussed here are the different components of the system, their interfaces, forseeable problem areas and many options based on the scientific goals of the mission. The various interfaces in the sample handling process (component to component and handling system to rover) will be a major engineering effort. Two critical evaluation criteria that will be imposed on the system are flexibility and reliability. It needs to be flexible enough to adapt to different scenarios and environments and acquire the most desirable specimens for return to Earth. Scientists may decide to change the distribution and ratio of core samples to rock samples in the canister. The long distance and duration of this planetary mission places a reliability burden on the hardware. The communication time delay between Earth and Mars minimizes operator interaction (teleoperation, supervisory modes) with the sample handler. An intelligent system will be required to plan the actions, make sample choices, interpret sensor inputs, and query unknown surroundings. A combination of autonomous functions and supervised movements will be integrated into the sample handling system.

Chun, Wendell↗
NASA NTRS2002

The Summer Robotic Autonomy Course

We offered a first Robotic Autonomy course this summer, located at NASA/Ames' new NASA Research Park, for approximately 30 high school students. In this 7-week course, students worked in ten teams to build then program advanced autonomous robots capable of visual processing and high-speed wireless communication. The course made use of challenge-based curricula, culminating each week with a Wednesday Challenge Day and a Friday Exhibition and Contest Day. Robotic Autonomy provided a comprehensive grounding in elementary robotics, including basic electronics, electronics evaluation, microprocessor programming, real-time control, and robot mechanics and kinematics. Our course then continued the educational process by introducing higher-level perception, action and autonomy topics, including teleoperation, visual servoing, intelligent scheduling and planning and cooperative problem-solving. We were able to deliver such a comprehensive, high-level education in robotic autonomy for two reasons. First, the content resulted from close collaboration between the CMU Robotics Institute and researchers in the Information Sciences and Technology Directorate and various education program/project managers at NASA/Ames. This collaboration produced not only educational content, but will also be focal to the conduct of formative and summative evaluations of the course for further refinement. Second, CMU rapid prototyping skills as well as the PI's low-overhead perception and locomotion research projects enabled design and delivery of affordable robot kits with unprecedented sensory- locomotory capability. Each Trikebot robot was capable of both indoor locomotion and high-speed outdoor motion and was equipped with a high-speed vision system coupled to a low-cost pan/tilt head. As planned, follow the completion of Robotic Autonomy, each student took home an autonomous, competent robot. This robot is the student's to keep, as she explores robotics with an extremely capable tool in the midst of a new community for roboticists. CMU provided undergraduate course credit for this official course, 16-162U, for 13 students, with all other students receiving course credit from National Hispanic University.

Nourbakhsh, Illah R.↗
NASA NTRS1994

Using generic tool kits to build intelligent systems

The Intelligent Systems and Robots Center at Sandia National Laboratories is developing technologies for the automation of processes associated with environmental remediation and information-driven manufacturing. These technologies, which focus on automated planning and programming and sensor-based and model-based control, are used to build intelligent systems which are able to generate plans of action, program the necessary devices, and use sensors to react to changes in the environment. By automating tasks through the use of programmable devices tied to computer models which are augmented by sensing, requirements for faster, safer, and cheaper systems are being satisfied. However, because of the need for rapid cost-effect prototyping and multi-laboratory teaming, it is also necessary to define a consistent approach to the construction of controllers for such systems. As a result, the Generic Intelligent System Controller (GISC) concept has been developed. This concept promotes the philosophy of producing generic tool kits which can be used and reused to build intelligent control systems.

Miller, David J.↗
NASA NTRS2005

Intelligent Life-Extending Controls for Aircraft Engines Studied

Current aircraft engine controllers are designed and operated to provide desired performance and stability margins. Except for the hard limits for extreme conditions, engine controllers do not usually take engine component life into consideration during the controller design and operation. The end result is that aircraft pilots regularly operate engines under unnecessarily harsh conditions to strive for optimum performance. The NASA Glenn Research Center and its industrial and academic partners have been working together toward an intelligent control concept that will include engine life as part of the controller design criteria. This research includes the study of the relationship between control action and engine component life as well as the design of an intelligent control algorithm to provide proper tradeoffs between performance and engine life. This approach is expected to maintain operating safety while minimizing overall operating costs. In this study, the thermomechanical fatigue (TMF) of a critical component was selected to demonstrate how an intelligent engine control algorithm can significantly extend engine life with only a very small sacrifice in performance. An intelligent engine control scheme based on modifying the high-pressure spool speed (NH) was proposed to reduce TMF damage from ground idle to takeoff. The NH acceleration schedule was optimized to minimize the TMF damage for a given rise-time constraint, which represents the performance requirement. The intelligent engine control scheme was used to simulate a commercial short-haul aircraft engine.

Guo, Ten-Huei↗
NASA NTRS1994

General purpose architecture for intelligent computer-aided training

An intelligent computer-aided training system having a general modular architecture is provided for use in a wide variety of training tasks and environments. It is comprised of a user interface which permits the trainee to access the same information available in the task environment and serves as a means for the trainee to assert actions to the system; a domain expert which is sufficiently intelligent to use the same information available to the trainee and carry out the task assigned to the trainee; a training session manager for examining the assertions made by the domain expert and by the trainee for evaluating such trainee assertions and providing guidance to the trainee which are appropriate to his acquired skill level; a trainee model which contains a history of the trainee interactions with the system together with summary evaluative data; an intelligent training scenario generator for designing increasingly complex training exercises based on the current skill level contained in the trainee model and on any weaknesses or deficiencies that the trainee has exhibited in previous interactions; and a blackboard that provides a common fact base for communication between the other components of the system. Preferably, the domain expert contains a list of 'mal-rules' which typifies errors that are usually made by novice trainees. Also preferably, the training session manager comprises an intelligent error detection means and an intelligent error handling means. The present invention utilizes a rule-based language having a control structure whereby a specific message passing protocol is utilized with respect to tasks which are procedural or step-by-step in structure. The rules can be activated by the trainee in any order to reach the solution by any valid or correct path.

Loftin, R. Bowen↗
NASA NTRS1994

DYNACLIPS (DYNAmic CLIPS): A dynamic knowledge exchange tool for intelligent agents

In a dynamic environment, intelligent agents must be responsive to unanticipated conditions. When such conditions occur, an intelligent agent may have to stop a previously planned and scheduled course of actions and replan, reschedule, start new activities and initiate a new problem solving process to successfully respond to the new conditions. Problems occur when an intelligent agent does not have enough knowledge to properly respond to the new situation. DYNACLIPS is an implementation of a framework for dynamic knowledge exchange among intelligent agents. Each intelligent agent is a CLIPS shell and runs a separate process under SunOS operating system. Intelligent agents can exchange facts, rules, and CLIPS commands at run time. Knowledge exchange among intelligent agents at run times does not effect execution of either sender and receiver intelligent agent. Intelligent agents can keep the knowledge temporarily or permanently. In other words, knowledge exchange among intelligent agents would allow for a form of learning to be accomplished.

Cengeloglu, Yilmaz↗
NASA NTRS1987

Types of verbal interaction with instructable robots

An instructable robot is one that accepts instruction in some natural language such as English and uses that instruction to extend its basic repertoire of actions. Such robots are quite different in conception from autonomously intelligent robots, which provide the impetus for much of the research on inference and planning in artificial intelligence. Examined here are the significant problem areas in the design of robots that learn from vebal instruction. Examples are drawn primarily from our earlier work on instructable robots and recent work on the Robotic Aid for the physically disabled. Natural-language understanding by machines is discussed as well as in the possibilities and limits of verbal instruction. The core problem of verbal instruction, namely, how to achieve specific concrete action in the robot in response to commands that express general intentions, is considered, as are two major challenges to instructability: achieving appropriate real-time behavior in the robot, and extending the robot's language capabilities.

Crangle, C.↗
NASA NTRS1996

Advanced Environmental Monitoring and Control Program: Strategic Plan

Human missions in space, from short-duration shuttle missions lasting no more than several days to the medium-to-long-duration missions planned for the International Space Station, face a number of hazards that must be understood and mitigated for the mission to be carried out safely. Among these hazards are those posed by the internal environment of the spacecraft itself; through outgassing of toxic vapors from plastics and other items, failures or off-nominal operations of spacecraft environmental control systems, accidental exposure to hazardous compounds used in experiments: all present potential hazards that while small, may accumulate and pose a danger to crew health. The first step toward mitigating the dangers of these hazards is understanding the internal environment of the spacecraft and the compounds contained within it. Future spacecraft will have integrated networks of redundant sensors which will not only inform the crew of hazards, but will pinpoint the problem location and, through analysis by intelligent systems, recommend and even implement a course of action to stop the problem. This strategic plan details strategies to determine NASA's requirements for environmental monitoring and control systems for future spacecraft, and goals and objectives for a program to answer these needs.

Schmidt, Gregory↗
NASA NTRS2006

Advanced Technologies for Future Spacecraft Cockpits and Space-based Control Centers

The National Aeronautics and Space Administration (NASA) is embarking on a new era of Space Exploration, aimed at sending crewed spacecraft beyond Low Earth Orbit (LEO), in medium and long duration missions to the Lunar surface, Mars and beyond. The challenges of such missions are significant and will require new technologies and paradigms in vehicle design and mission operations. Current roles and responsibilities of spacecraft systems, crew and the flight control team, for example, may not be sustainable when real-time support is not assured due to distance-induced communication lags, radio blackouts, equipment failures, or other unexpected factors. Therefore, technologies and applications that enable greater Systems and Mission Management capabilities on-board the space-based system will be necessary to reduce the dependency on real-time critical Earth-based support. The focus of this paper is in such technologies that will be required to bring advance Systems and Mission Management capabilities to space-based environments where the crew will be required to manage both the systems performance and mission execution without dependence on the ground. We refer to this concept as autonomy. Environments that require high levels of autonomy include the cockpits of future spacecraft such as the Mars Exploration Vehicle, and space-based control centers such as a Lunar Base Command and Control Center. Furthermore, this paper will evaluate the requirements, available technology, and roadmap to enable full operational implementation of onboard System Health Management, Mission Planning/re-planning, Autonomous Task/Command Execution, and Human Computer Interface applications. The technology topics covered by the paper include enabling technology to perform Intelligent Caution and Warning, where the systems provides directly actionable data for human understanding and response to failures, task automation applications that automate nominal and Off-nominal task execution based on human input or integrated health state-derived conditions. Shifting from Systems to Mission Management functions, we discuss the role of automated planning applications (tactical planning) on-board, which receive data from the other cockpit automation systems and evaluate the mission plan against the dynamic systems and mission states and events, to provide the crew with capabilities that enable them to understand, change, and manage the timeline of their mission. Lastly, we discuss the role of advanced human interface technologies that organize and provide the system md mission information to the crew in ways that maximize their situational awareness and ability to provide oversight and control of aLl the automated data and functions.

Garcia-Galan, Carlos↗