Search NASA⌕ Search

SEARCH · Search NASA

Results for “CARTs”

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 199 records · Page 11

Lunar articulated remote transportation system

The students of the Florida A&M/Florida State University College of Engineering continued their design from 1988 to 1989 on a first generation lunar transportation vehicle for use on the surface of the Moon between the years 2010 and 2020. Attention is focused on specific design details on all components of the Lunar Articulated Remote Transportation System (Lunar ARTS). The Lunar ARTS will be a three-cart, six-wheeled articulated vehicle. Its purpose will be the transportation of astronauts and/or materials for excavation purposes at a short distance from the base (37.5 km). The power system includes fuel cells for both the primary system and the back-up system. The vehicle has the option of being operated in a manned or unmanned mode. The unmanned mode includes stereo imaging with signal processing for navigation. For manned missions the display console is a digital readout displayed on the inside of the astronaut's helmet. A microprocessor is also on board the vehicle. Other components of the vehicle include a double wishbone/flexible hemispherical wheel suspension; chassis; a steering system; motors; seat retraints; heat rejection systems; solar flare protection; dust protection; and meteoroid protection. A one-quarter scale dynamic model has been built to study the dynamic behavior of the vehicle. The dynamic model closely captures the mechanical and electrical details of the total design.

Source record↗

An architecture for designing fuzzy logic controllers using neural networks

Described here is an architecture for designing fuzzy controllers through a hierarchical process of control rule acquisition and by using special classes of neural network learning techniques. A new method for learning to refine a fuzzy logic controller is introduced. A reinforcement learning technique is used in conjunction with a multi-layer neural network model of a fuzzy controller. The model learns by updating its prediction of the plant's behavior and is related to the Sutton's Temporal Difference (TD) method. The method proposed here has the advantage of using the control knowledge of an experienced operator and fine-tuning it through the process of learning. The approach is applied to a cart-pole balancing system.

Berenji, Hamid R.↗

Astronauts give GRO a helping hand

The eighth mission of the Space Shuttle Atlantis, during which an emergency spacewalk was performed to help deploy the Gamma-Ray Observatory (GRO), is described and illustrated with extensive photographs. The countdown and liftoff are recalled, and a day-by-day history of the mission is provided. Particular attention is given to the Extravehicular Activity Development Flight Experiment, designed to obtain data for future spacewalks, and the Crew and Equipment Translation Aid, aimed at testing carts that spacewalking astronauts could use to move along the truss structure of the Space Station.

Schulling, Roelof L.↗

Neuromorphic learning of continuous-valued mappings from noise-corrupted data

The effect of noise on the learning performance of the backpropagation algorithm is analyzed. A selective sampling of the training set is proposed to maximize the learning of control laws by backpropagation, when the data have been corrupted by noise. The training scheme is applied to the nonlinear control of a cart-pole system in the presence of noise. The neural computation provides the neurocontroller with good noise-filtering properties. In the presence of plant noise, the neurocontroller is found to be more stable than the teacher. A novel perspective on the application of neural network technology to control engineering is presented.

Troudet, T.↗

Dolly For Heavy Towbar

Proposed lightweight dolly enables operator to cart heavy towbar to remote site over unpaved roads or rough terrain. Acts as simple, lightweight towed vehicle to support rear of towbar. Removed quickly at point of use. Saves labor, and eliminates need for truck and forklift.

Soper, Terry A.↗

Learning classification trees

Algorithms for learning classification trees have had successes in artificial intelligence and statistics over many years. How a tree learning algorithm can be derived from Bayesian decision theory is outlined. This introduces Bayesian techniques for splitting, smoothing, and tree averaging. The splitting rule turns out to be similar to Quinlan's information gain splitting rule, while smoothing and averaging replace pruning. Comparative experiments with reimplementations of a minimum encoding approach, Quinlan's C4 and Breiman et al. Cart show the full Bayesian algorithm is consistently as good, or more accurate than these other approaches though at a computational price.

Buntine, Wray↗

Introduction in IND and recursive partitioning

This manual describes the IND package for learning tree classifiers from data. The package is an integrated C and C shell re-implementation of tree learning routines such as CART, C4, and various MDL and Bayesian variations. The package includes routines for experiment control, interactive operation, and analysis of tree building. The manual introduces the system and its many options, gives a basic review of tree learning, contains a guide to the literature and a glossary, and lists the manual pages for the routines and instructions on installation.

Buntine, Wray↗

Lidar Development for the Atmospheric Radiation Measurement (ARM) Program

The Atmospheric Radiation Measurement (ARM) Program was initiated by the Department of Energy's Atmospheric and Climate Research Division (DOE/ACRD) to improve parameterizations of cloud radiative effects in general circulation models of the Earth's climate. The Instrument Development Program (IDP), a major component of ARM, is directed toward the improvement of radiometric and remote sensing instrumentation pertinent to near real-time characterizations of atmospheric parameters. The ultimate goal of this program is to provide state-of-the-art instruments suitable for installation and extended use in ARM's field measurement component, the Cloud and Radiation Testbed (CART).

Griffin, J.↗

Progress on control experiments of flexible structures

Progress at the NASA Langley Research Center in the area of control experiments for flexible structures is described. First the author presents the experimental results for a linear model which represents slewing maneuvers of a generic space station solar panel carried out to evaluate experimentally some control technologies. Then the status of the rotational/translational maneuvering experiment of a flexible steel panel carried by a translation cart is presented. Finally, experimental results of the NASA minimast testbed using velocity command stepper motors as reaction mass reactors are shown. All the test configurations are briefly described, including actuator and sensor, test setup, and test software. The status of some research activities oriented primarily to the experimental methods for control of flexible structures is presented.

Juang, Jer-Nan↗

Using new aggregation operators in rule-based intelligent control

A new aggregation operator is applied in the design of an approximate reasoning-based controller. The ordered weighted averaging (OWA) operator has the property of lying between the And function and the Or function used in previous fuzzy set reasoning systems. It is shown here that, by applying OWA operators, more generalized types of control rules, which may include linguistic quantifiers such as Many and Most, can be developed. The new aggregation operators, as tested in a cart-pole balancing control problem, illustrate improved performance when compared with existing fuzzy control aggregation schemes.

Berenji, Hamid R.↗

A reinforcement learning-based architecture for fuzzy logic control

This paper introduces a new method for learning to refine a rule-based fuzzy logic controller. A reinforcement learning technique is used in conjunction with a multilayer neural network model of a fuzzy controller. The approximate reasoning based intelligent control (ARIC) architecture proposed here learns by updating its prediction of the physical system's behavior and fine tunes a control knowledge base. Its theory is related to Sutton's temporal difference (TD) method. Because ARIC has the advantage of using the control knowledge of an experienced operator and fine tuning it through the process of learning, it learns faster than systems that train networks from scratch. The approach is applied to a cart-pole balancing system.

Berenji, Hamid R.↗

Introduction to IND and recursive partitioning, version 1.0

This manual describes the IND package for learning tree classifiers from data. The package is an integrated C and C shell re-implementation of tree learning routines such as CART, C4, and various MDL and Bayesian variations. The package includes routines for experiment control, interactive operation, and analysis of tree building. The manual introduces the system and its many options, gives a basic review of tree learning, contains a guide to the literature and a glossary, lists the manual pages for the routines, and instructions on installation.

Buntine, Wray↗

ATL Products Division's entries into the computer mass storage marketplace

The viewgraphs of a discussion on ATL Products Division's entries into the computer mass storage marketplace presented at the National Space Science Data Center (NSSDC) Mass Storage Workshop is included. Topics covered are product evolution including robotics; aperture storage module library; Broadcast Division's TCS2000 Video Cart and TCS90 Videocart System; high density systems business product lines; and storage and library management.

Zeiler, Fred↗

Full design of fuzzy controllers using genetic algorithms

This paper examines the applicability of genetic algorithms (GA) in the complete design of fuzzy logic controllers. While GA has been used before in the development of rule sets or high performance membership functions, the interdependence between these two components dictates that they should be designed together simultaneously. GA is fully capable of creating complete fuzzy controllers given the equations of motion of the system, eliminating the need for human input in the design loop. We show the application of this new method to the development of a cart controller.

Homaifar, Abdollah↗

Structure identification in fuzzy inference using reinforcement learning

In our previous work on the GARIC architecture, we have shown that the system can start with surface structure of the knowledge base (i.e., the linguistic expression of the rules) and learn the deep structure (i.e., the fuzzy membership functions of the labels used in the rules) by using reinforcement learning. Assuming the surface structure, GARIC refines the fuzzy membership functions used in the consequents of the rules using a gradient descent procedure. This hybrid fuzzy logic and reinforcement learning approach can learn to balance a cart-pole system and to backup a truck to its docking location after a few trials. In this paper, we discuss how to do structure identification using reinforcement learning in fuzzy inference systems. This involves identifying both surface as well as deep structure of the knowledge base. The term set of fuzzy linguistic labels used in describing the values of each control variable must be derived. In this process, splitting a label refers to creating new labels which are more granular than the original label and merging two labels creates a more general label. Splitting and merging of labels directly transform the structure of the action selection network used in GARIC by increasing or decreasing the number of hidden layer nodes.

Berenji, Hamid R.↗

Tree Classification Software

This paper introduces the IND Tree Package to prospective users. IND does supervised learning using classification trees. This learning task is a basic tool used in the development of diagnosis, monitoring and expert systems. The IND Tree Package was developed as part of a NASA project to semi-automate the development of data analysis and modelling algorithms using artificial intelligence techniques. The IND Tree Package integrates features from CART and C4 with newer Bayesian and minimum encoding methods for growing classification trees and graphs. The IND Tree Package also provides an experimental control suite on top. The newer features give improved probability estimates often required in diagnostic and screening tasks. The package comes with a manual, Unix 'man' entries, and a guide to tree methods and research. The IND Tree Package is implemented in C under Unix and was beta-tested at university and commercial research laboratories in the United States.

Buntine, Wray↗

Systems engineering studies of lunar base construction

Many ingenious concepts have been proposed for lunar base construction, but few systematic studies exist which relate time-consistent lunar base construction technologies and the choice of lunar base approach with the long-term SEI objectives - i.e., lunar indigenous base construction and Mars Exploration equipment development. To fill this gap, CSC has taken a two-pronged approach. First, the Center undertook basic geotechnical investigations of lunar soil, fabrication of a scale prototype of a lunar construction crane, a multi-robot construction team laboratory experiment, and a preliminary design of lunar base structures. Second, during Jun. and Jul. 1991 two lunar base construction systems engineering studies were accomplished - a 'near term lunar base' study, and a 'far-term lunar base' study. The goals of these studies were to define the major lunar base construction research problems in consistent technology/construction frameworks, and to define design requirements for construction equipment such as a lunar crane and a regolith mover. The 'near-term lunar base' study examined three different construction concepts for a lunar base comprised of pre-fabricated, pre-tested, Space Station Freedom-type modules, which would be covered with regolith shielding. Concept A used a lunar crane for unloading and transportation; concept B, a winch and cart; and concept C, a walker to move the modules from the landing site to the base site and assemble them. To evaluate the merits of each approach, calculations were made of mass efficiency measure, source mass, reliability, far-term base mass, Mars base mass, and base assembly time. The model thus established was also used to define the requirements for crane speed and regolith mover m(sup 3)/sec rates. A major problem addressed is how to 'mine' the regolith and stack it over the habitats as shielding. To identify when the cost of using indigenous lunar materials to construct the base exceeds the cost of development and delivery of the equipment for processing lunar materials, a study of construction of a candidate sintered regolith 'far term lunar base' was undertaken. A technique was devised for casting slabs of sintered (basaltic) regolith and assembling these into a hemispherical (or geodesic) dome. The major problem occurs with the inner liner. At 14.7 psi and 20 percent oxygen internal atmosphere, the entire structure is in tension, even with the regolith load. Also, another study has indicated that at 14.7 psi major resupply of air will be needed because of leakage, and astronauts may have to engage in extensive pre-breathing and post-breathing for extravehicular activity (EVA) tasks, thus detracting from useful mission work time. An alternative is to operate part of the base at, say, 5 psi and 70 percent oxygen, or to equip the astronauts with hard suits at 8.3 psi or greater. All of these choices directly influence base design and construction techniques.

Morgenthaler, George W.↗

Full design of fuzzy controllers using genetic algorithms

This paper examines the applicability of genetic algorithms in the complete design of fuzzy logic controllers. While GA has been used before in the development of rule sets or high performance membership functions, the interdependence between these two components dictates that they should be designed together simultaneously. GA is fully capable of creating complete fuzzy controllers given the equations of motion of the system, eliminating the need for human input in the design loop. We show the application of this new method to the development of a cart controller.

Homaifar, Abdollah↗