SEARCH · Search NASA
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.
The feasibility of real-time processing schemes using artificial neural networks (ANNs) is investigated. A rationale for digital neural nets is presented and a general processor architecture for control applications is illustrated. Research results on ANN structures for real-time applications are given. Research results on ANN algorithms for real-time control are also shown.
An imaging system which applies knowledge-based technology to supervise and control both sensor hardware and computation in the imaging system is described. It includes the development of an imaging system breadboard which brings together into one system work that we and others have pursued for LaRC for several years. The goal is to combine Digital Signal Processing (DSP) with Knowledge-Based Processing and also include Neural Net processing. The system is considered a smart camera. Imagine that there is a microgravity experiment on-board Space Station Freedom with a high frame rate, high resolution camera. All the data cannot possibly be acquired from a laboratory on Earth. In fact, only a small fraction of the data will be received. Again, imagine being responsible for some experiments on Mars with the Mars Rover: the data rate is a few kilobits per second for data from several sensors and instruments. Would it not be preferable to have a smart system which would have some human knowledge and yet follow some instructions and attempt to make the best use of the limited bandwidth for transmission. The system concept, current status of the breadboard system and some recent experiments at the Mars-like Amboy Lava Fields in California are discussed.
Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.
The Intensity Dependent Spread (IDS) is an adaptive algorithm which is modified according to the local intensity in the scene. (This results in a nonlinear process which cannot take advantage of rather nice linear transform methods.) The computation is similar to a neural net whereby intensity information is moving from each input pixel to a set of surrounding output pixels in a manner described by Cornsweet and Yellott. A prototype of a very large scale integration IDS processor is being developed and implemented in a workstation environment. The workstation consists of a SUN 3/260 and a DATACUBE pipeline processor. The IDS prototype is a board set which operates in the DATA CUBE processor. The SUN 3/260 performs control, background processing, IDS simulation and image display functions.
In the present technological society, there is a major need to build machines that would execute intelligent tasks operating in uncertain environments with minimum interaction with a human operator. Although some designers have built smart robots, utilizing heuristic ideas, there is no systematic approach to design such machines in an engineering manner. Recently, cross-disciplinary research from the fields of computers, systems AI and information theory has served to set the foundations of the emerging area of the design of intelligent machines. Since 1977 Saridis has been developing an approach, defined as Hierarchical Intelligent Control, designed to organize, coordinate and execute anthropomorphic tasks by a machine with minimum interaction with a human operator. This approach utilizes analytical (probabilistic) models to describe and control the various functions of the intelligent machine structured by the intuitively defined principle of Increasing Precision with Decreasing Intelligence (IPDI) (Saridis 1979). This principle, even though resembles the managerial structure of organizational systems (Levis 1988), has been derived on an analytic basis by Saridis (1988). The purpose is to derive analytically a Boltzmann machine suitable for optimal connection of nodes in a neural net (Fahlman, Hinton, Sejnowski, 1985). Then this machine will serve to search for the optimal design of the organization level of an intelligent machine. In order to accomplish this, some mathematical theory of the intelligent machines will be first outlined. Then some definitions of the variables associated with the principle, like machine intelligence, machine knowledge, and precision will be made (Saridis, Valavanis 1988). Then a procedure to establish the Boltzmann machine on an analytic basis will be presented and illustrated by an example in designing the organization level of an Intelligent Machine. A new search technique, the Modified Genetic Algorithm, is presented and proved to converge to the minimum of a cost function. Finally, simulations will show the effectiveness of a variety of search techniques for the intelligent machine.
Existing NASA supported scientific data bases are usually developed, managed and populated in a tedious, error prone and self-limiting way in terms of what can be described in a relational Data Base Management System (DBMS). The next generation Earth remote sensing platforms, i.e., Earth Observation System, (EOS), will be capable of generating data at a rate of over 300 Mbs per second from a suite of instruments designed for different applications. What is needed is an innovative approach that creates object-oriented databases that segment, characterize, catalog and are manageable in a domain-specific context and whose contents are available interactively and in near-real-time to the user community. Described here is work in progress that utilizes an artificial neural net approach to characterize satellite imagery of undefined objects into high-level data objects. The characterized data is then dynamically allocated to an object-oriented data base where it can be reviewed and assessed by a user. The definition, development, and evolution of the overall data system model are steps in the creation of an application-driven knowledge-based scientific information system.
For practical industrial applications, the development of trainable robots is an important and immediate objective. Therefore, the developing of flexible intelligence directly applicable to training is emphasized. It is generally agreed upon by the AI community that the fusion of expert systems, neural networks, and conventionally programmed modules (e.g., a trajectory generator) is promising in the quest for autonomous robotic intelligence. Autonomous robot development is hindered by integration and architectural problems. Some obstacles towards the construction of more general robot control systems are as follows: (1) Growth problem; (2) Software generation; (3) Interaction with environment; (4) Reliability; and (5) Resource limitation. Neural networks can be successfully applied to some of these problems. However, current implementations of neural networks are hampered by the resource limitation problem and must be trained extensively to produce computationally accurate output. A generalization of conventional neural nets is proposed, and an architecture is offered in an attempt to address the above problems.
The Navlab project, which seeks to build an autonomous robot that can operate in a realistic environment with bad weather, bad lighting, and bad or changing roads, is discussed. The perception techniques developed for the Navlab include road-following techniques using color classification and neural nets. These are discussed with reference to three road-following systems, SCARF, YARF, and ALVINN. Three-dimensional perception using three types of terrain representation (obstacle maps, terrain feature maps, and high-resolution maps) is examined. It is noted that perception continues to be an obstacle in developing autonomous vehicles.
A versatile neural-net model is explained in terms familiar to computer scientists and engineers. It is called the sparse distributed memory, and it is a random-access memory for very long words (for patterns with thousands of bits). Its potential utility is the result of several factors: (1) a large pattern representing an object or a scene or a moment can encode a large amount of information about what it represents; (2) this information can serve as an address to the memory, and it can also serve as data; (3) the memory is noise tolerant--the information need not be exact; (4) the memory can be made arbitrarily large and hence an arbitrary amount of information can be stored in it; and (5) the architecture is inherently parallel, allowing large memories to be fast. Such memories can become important components of future computers.
The objectives of the program are: (1) to further the professional knowledge of qualified engineering and science faculty members; (2) to stimulate an exchange of ideas between participants and NASA; (3) to enrich and refresh the research and teaching activities of participant's institutions; and (4) to contribute to the research objectives of the NASA Centers. A compilation of the final reports on the research projects done by the faculty fellows during the summer of 1991 are presented. Some of the topics covered include: collision avoidance for rover vehicles, bioinstrumentation, neural nets, total quality management of flexible space structures, project scheduling, nondestructive tests, orthostatic intolerance to bedrest, hypersonic reentry simulation, measuring human energy expenditure, tribological models, trace element movement in Anarctic ice, gastrointestinal function, and computer assisted instruction.
The objective of the workshop was to explore the role of human factors in facilitating the introduction of artificial intelligence (AI) to advanced air traffic control (ATC) automation concepts. AI is an umbrella term which is continually expanding to cover a variety of techniques where machines are performing actions taken based upon dynamic, external stimuli. AI methods can be implemented using more traditional programming languages such as LISP or PROLOG, or they can be implemented using state-of-the-art techniques such as object-oriented programming, neural nets (hardware or software), and knowledge based expert systems. As this technology advances and as increasingly powerful computing platforms become available, the use of AI to enhance ATC systems can be realized. Substantial efforts along these lines are already being undertaken at the FAA Technical Center, NASA Ames Research Center, academic institutions, industry, and elsewhere. Although it is clear that the technology is ripe for bringing computer automation to ATC systems, the proper scope and role of automation are not at all apparent. The major concern is how to combine human controllers with computer technology. A wide spectrum of options exists, ranging from using automation only to provide extra tools to augment decision making by human controllers to turning over moment-by-moment control to automated systems and using humans as supervisors and system managers. Across this spectrum, it is now obvious that the difficulties that occur when tying human and automated systems together must be resolved so that automation can be introduced safely and effectively. The focus of the workshop was to further explore the role of injecting AI into ATC systems and to identify the human factors that need to be considered for successful application of the technology to present and future ATC systems.
Limitations associated with the binary phase-only filter often used in optical correlators are presently circumvented in the writing of complex-valued data on a gray-scale spatial light modulator through the use of a computer-generated hologram (CGH) algorithm. The CGH encodes complex-valued data into nonnegative real CGH data in such a way that it may be encoded in any of the available gray-scale spatial light modulators. A CdS liquid-crystal light valve is used for the complex-valued CGH encoding; computer simulations and experimental results are compared, and the use of such a CGH filter as the synapse hologram in a holographic optical neural net is discussed.
The paper examines software techniques for classifying remotely sensed data such that the number of computational steps and the amount of resources are bounded. The combination of both neural network and expert system methodology for classifying these data based on land use/land cover categories is examined. The method involves pipelining images through a neural net for initial classification and then through the expert system which resolves the ambiguous classifications. As with any pipeline, every component must have approximately equivalent run-times or otherwise a bottleneck will occur. If real-time is a requirement, each of the components must execute within a bounded number of steps. Attention is focused on the real-time system technique, which is argued to prevent a bottleneck for this data classification application.
A relatively simple, modular, low mass, low cost robot is being developed for space EVA that is large enough to be independently mobile on a space station or platform exterior, yet versatile enough to accomplish many vital tasks. The robot comprises two long flexible links connected by a rotary joint, with 2-DOF 'wrist' joints and grippers at each end. It walks by gripping pre-positioned attachment points, such as trusswork nodes, and alternately shifting its base of support from one foot (gripper) to the other. The robot can perform useful tasks such as visual inspection, material transport, and light assembly by manipulating objects with one gripper, while stabilizing itself with the other. At SOAR '90, we reported development of 1/3 scale robot hardware, modular trusswork to serve as a locomotion substrate, and a gravity compensation system to allow laboratory tests of locomotion strategies on the horizontal face of the trusswork. In this paper, we report on project progress including the development of: (1) adaptive control for automatic adjustment to loads; (2) enhanced manipulation capabilities; (3) machine vision, including the use of neural nets, to guide autonomous locomotion; (4) locomotion between orthogonal trusswork faces; and (5) improved facilities for gravity compensation and telerobotic control.
There is currently a great deal of interest in using response surfaces in the optimization of aircraft performance. The objective function and/or constraint equations involved in these optimization problems may come from numerous disciplines such as structures, aerodynamics, environmental engineering, etc. In each of these disciplines, the mathematical complexity of the governing equations usually dictates that numerical results be obtained from large computer programs such as a finite element method program. Thus, when performing optimization studies, response surfaces are a convenient way of transferring information from the various disciplines to the optimization algorithm as opposed to bringing all the sundry computer programs together in a massive computer code. Response surfaces offer another advantage in the optimization of aircraft structures. A characteristic of these types of optimization problems is that evaluation of the objective function and response equations (referred to as a functional evaluation) can be very expensive in a computational sense. Because of the computational expense in obtaining functional evaluations, the present study was undertaken to investigate under-determinined approximations. An under-determined approximation is one in which there are fewer training pairs (pieces of information about a function) than there are undetermined parameters (coefficients or weights) associated with the approximation. Both polynomial approximations and neural net approximations were examined. Three main example problems were investigated: (1) a function of one design variable was considered; (2) a function of two design variables was considered; and (3) a 35 bar truss with 4 design variables was considered.
This document provides a report on research activities carried out with the support of NASA grant NAG 5-1174, the Structure of Circumstellar Shells, funded under the Astrophysics Data Program. The research carried out with the support of this grant is a study of the properties of circumstellar dust shells for which spectra are available through IRAS low resolution spectrometry (LRS). This research consisted of the development and application of models of axisymmetric circumstellar shells and a preliminary survey of the applicability of neural nets for analysis of the IRAS LRS spectra of circumstellar dust shells.
The mathematical formulation of the engineering optimization problem is given. Evaluation of the objective function and constraint equations can be very expensive in a computational sense. Thus, it is desirable to use as few evaluations as possible in obtaining its solution. In solving the equation, one approach is to develop approximations to the objective function and/or restraint equations and then to solve the equation using the approximations in place of the original functions. These approximations are referred to as response surfaces. The desirability of using response surfaces depends upon the number of functional evaluations required to build the response surfaces compared to the number required in the direct solution of the equation without approximations. The present study is concerned with evaluating the performance of response surfaces so that a decision can be made as to their effectiveness in optimization applications. In particular, this study focuses on how the quality of approximations is effected by design selection. Polynomial approximations and neural net approximations are considered.
In this paper we discuss approximations between neural nets, fuzzy expert systems, fuzzy controllers, and continuous processes.