Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Task Graph”

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 37 records · Page 2

The effect of global visual flow on simulator sickness

Simulator-induced sickness is investigated in experiments performed at the NASA Ames Army Crew Station Research Facility using the fixed-base helmet-mounted-display flight simulator described by Lypaczewski et al. (1986). The focus of the tests was on the possible roles of (1) global visual flow, as defined by Warren et al. (1982), and (2) maneuvering intensity (in the conflict hypothesis of Reason and Brand, 1975). The results, based on subjective evaluations, physiological measurements, and physical tests on 19 Army helicopter pilots performing a 40-min river-valley following task, are presented in extensive tables and graphs and discussed. The data are found to be in agreement with (1) and inconsistent with (2), indicating more sickness at lower altitude instead of with increased maneuvering. Shorter simulator sessions and postponement of low-altitude work until later in the training period are recommended.

Sharkey, Thomas J.↗

Event driven executive

Tasks may be planned for execution on a single processor or are split up by the designer for execution among a plurality of signal processors. The tasks are modeled using a design aid called a precedence graph, from which a dependency table and a prerequisite table are established for reference within each processor. During execution, at the completion of a given task, an end of task interrupt is provided from any processor which has completed a task to any and all other processors including itself in which completion of that task is a prerequisite for commencement of any dependent tasks. The relevant updated data may be transferred by the processor either before or after signalling task completion to the processors needing the updated data prior to commencing execution of the dependent tasks. Coherency may be ensured, however, by sending the data before the interrupt. When the end of task interrupt is received in a processor, its dependency table is consulted to determine those tasks dependent upon completion of the task which has just been signalled as completed, and task dependency signals indicative thereof are provided and stored in a current status list of a prerequisite table. The current status of all current prerequisites are compared to the complete prerequisites listed for all affected tasks and those tasks for which the comparison indicates that all prerequisites have been met are queued for execution in a selected order.

Tulpule, Bhalchandra R.↗

Planning the FUSE Mission Using the SOVA Algorithm

Three documents discuss the Sustainable Objective Valuation and Attainability (SOVA) algorithm and software as used to plan tasks (principally, scientific observations and associated maneuvers) for the Far Ultraviolet Spectroscopic Explorer (FUSE) satellite. SOVA is a means of managing risk in a complex system, based on a concept of computing the expected return value of a candidate ordered set of tasks as a product of pre-assigned task values and assessments of attainability made against qualitatively defined strategic objectives. For the FUSE mission, SOVA autonomously assembles a week-long schedule of target observations and associated maneuvers so as to maximize the expected scientific return value while keeping the satellite stable, managing the angular momentum of spacecraft attitude- control reaction wheels, and striving for other strategic objectives. A six-degree-of-freedom model of the spacecraft is used in simulating the tasks, and the attainability of a task is calculated at each step by use of strategic objectives as defined by use of fuzzy inference systems. SOVA utilizes a variant of a graph-search algorithm known as the A* search algorithm to assemble the tasks into a week-long target schedule, using the expected scientific return value to guide the search.

Lanzi, James↗

Framework for Extensible, Asynchronous Task Scheduling (FEATS) in Fortran

Most parallel scientific programs contain compiler directives (pragmas) such as those from OpenMP, explicit calls to runtime library procedures such as those implementing the Message Passing Interface (MPI), or compiler-specific language extensions such as those provided by CUDA. By contrast, the recent Fortran standards empower developers to express parallel algorithms without directly referencing lower-level parallel programming models. Fortran’s parallel features place the language within the Partitioned Global Address Space (PGAS) class of programming models. When writing programs that exploit data-parallelism, application developers often find it straightforward to develop custom parallel algorithms. Problems involving complex, heterogeneous, staged calculations, however, pose much greater challenges. Such applications require careful coordination of tasks in a manner that respects dependencies prescribed by a directed acyclic graph. When rolling one’s own solution proves difficult, extending a customizable framework becomes attractive. The paper presents the design, implementation, and use of the Framework for Extensible Asynchronous Task Scheduling (FEATS), which we believe to be the first task-scheduling tool written in modern Fortran. We describe the benefits and compromises associated with choosing Fortran as the implementation language, and we propose ways in which future Fortran standards can best support the use case in this paper.

Modern Fortran↗

Data flow methods for dynamic system simulation - A CSSL-IV microcomputer network interface

A major problem in employing networks of microcomputers for the real-time simulation of complex systems is to allocate computational tasks to the various microcomputers in such a way that idle time and time lost in interprocess communication is minimized. The research reported in this paper is directed to the development of a software interface between a higher-level simulation language and a network of microcomputers. A CSSL-IV source program is translated to a data flow graph. This graph is then analyzed automatically so as to allocate computing tasks to the various processors.

Makoui, A.↗

An electronic pressure profile display system for aeronautic test facilities

The NASA Lewis Research Center has installed an Electronic Pressure Profile Display system. This system provides for the real-time display of pressure readings on high resolution graphics monitors. The Electronic Pressure Profile Display system will replace manometer banks currently used in aeronautic test facilities. The Electronic Pressure Profile Display system consists of an industrial type Digital Pressure Transmitter (DPT) unit which interfaces with a host computer. The host computer collects the pressure data from the DPT unit, converts it into engineering units, and displays the readings on a high resolution graphics monitor in bar graph format. Software was developed to accomplish the above tasks and also draw facility diagrams as background information on the displays. Data transfer between host computer and DPT unit is done with serial communications. Up to 64 channels are displayed with one second update time. This paper describes the system configuration, its features, and its advantages over existing systems.

Woike, Mark R.↗

An Electronic Pressure Profile Display system for aeronautic test facilities

The NASA Lewis Research Center has installed an Electronic Pressure Profile Display system. This system provides for the real-time display of pressure readings on high resolution graphics monitors. The Electronic Pressure Profile Display system will replace manometer banks currently used in aeronautic test facilities. The Electronic Pressure Profile Display system consists of an industrial type Digital Pressure Transmitter (DPI) unit which interfaces with a host computer. The host computer collects the pressure data from the DPI unit, converts it into engineering units, and displays the readings on a high resolution graphics monitor in bar graph format. Software was developed to accomplish the above tasks and also draw facility diagrams as background information on the displays. Data transfer between host computer and DPT unit is done with serial communications. Up to 64 channels are displayed with one second update time. This paper describes the system configuration, its features, and its advantages over existing systems.

Woike, Mark R.↗

Analysis of Human-Spacesuit Interaction

Astronauts sustain injuries of various natures such as finger delamination, joint pain, and redness due to their interaction with the space suit. The role of the Anthropometry and Biomechanics Facility is to understand the biomechanics, environmental variables, and ergonomics of the suit. This knowledge is then used to make suggestions for improvement in future iterations of the space suit assembly to prevent injuries while allowing astronauts maneuverability, comfort, and tactility. The projects I was involved in were the Extravehicular Mobility Unit (EMU) space suit stiffness study and the glove feasibility study. The EMU project looked at the forces exerted on the shoulder, arm, and wrist when subjects performed kinematic tasks with and without a pressurized suit. The glove study consisted of testing three conditions - the Series 4000 glove, the Phase VI glove, and the no glove condition. With more than forty channels of sensor data total, it was critical to develop programs that could analyze data with basic descriptive statistics and generate relevant graphs to help understand what happens within the space suit and glove. In my project I created a Graphical User Interface (GUI) in MATLAB that would help me visualize what each sensor was doing within a task. The GUI is capable of displaying overlain plots and can be synchronized with video. This was helpful during the stiffness testing to visualize how the forces on the arm acted while the subject performed tasks such as shoulder adduction/abduction and bicep curls. The main project of focus, however, was the glove comparison study. I wrote MATLAB programs which generated movies of the strain vectors during specific tasks. I also generated graphs that summarized the differences between each glove for the strain, shear and FSR sensors. Preliminary results indicate that the Phase VI glove places less strain and shear on the hand. Future work includes continued data analysis of surveys and sensor data. In the end, the ideal glove is one that provides more tactility for the astronauts but lessens injuries. Often times, a more tactile glove transmits forces better to the hand; thus, achieving a balance of both a tactile and safe glove is the main challenge present.

Thomas, Neha↗

Robot Acquisition of Active Maps Through Teleoperation and Vector Space Analysis

The work performed under this contract was in the area of intelligent robotics. The problem being studied was the acquisition of intelligent behaviors by a robot. The method was to acquire action maps that describe tasks as sequences of reflexive behaviors. Action maps (a.k.a. topological maps) are graphs whose nodes represent sensorimotor states and whose edges represent the motor actions that cause the robot to proceed from one state to the next. The maps were acquired by the robot after being teleoperated or otherwise guided by a person through a task several times. During a guided task, the robot records all its sensorimotor signals. The signals from several task trials are partitioned into episodes of static behavior. The corresponding episodes from each trial are averaged to produce a task description as a sequence of characteristic episodes. The sensorimotor states that indicate episode boundaries become the nodes, and the static behaviors, the edges. It was demonstrated that if compound maps are constructed from a set of tasks then the robot can perform new tasks in which it was never explicitly trained.

Peters, Richard Alan, II↗

Task scheduling in dataflow computer architectures

Dataflow computers provide a platform for the solution of a large class of computational problems, which includes digital signal processing and image processing. Many typical applications are represented by a set of tasks which can be repetitively executed in parallel as specified by an associated dataflow graph. Research in this area aims to model these architectures, develop scheduling procedures, and predict the transient and steady state performance. Researchers at NASA have created a model and developed associated software tools which are capable of analyzing a dataflow graph and predicting its runtime performance under various resource and timing constraints. These models and tools were extended and used in this work. Experiments using these tools revealed certain properties of such graphs that require further study. Specifically, the transient behavior at the beginning of the execution of a graph can have a significant effect on the steady state performance. Transformation and retiming of the application algorithm and its initial conditions can produce a different transient behavior and consequently different steady state performance. The effect of such transformations on the resource requirements or under resource constraints requires extensive study. Task scheduling to obtain maximum performance (based on user-defined criteria), or to satisfy a set of resource constraints, can also be significantly affected by a transformation of the application algorithm. Since task scheduling is performed by heuristic algorithms, further research is needed to determine if new scheduling heuristics can be developed that can exploit such transformations. This work has provided the initial development for further long-term research efforts. A simulation tool was completed to provide insight into the transient and steady state execution of a dataflow graph. A set of scheduling algorithms was completed which can operate in conjunction with the modeling and performance tools previously developed. Initial studies on the performance of these algorithms were done to examine the effects of application algorithm transformations as measured by such quantities as number of processors, time between outputs, time between input and output, communication time, and memory size.

Katsinis, Constantine↗

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.↗

Generation of precedence relations for mechanical assemblies

Planning of assembly sequences is essential to the manufacturing system design process. Several methodologies have been proposed to represent all the feasible assembly sequences. In this thesis, three algorithms are presented to generate three sets of precedence relations based on all the infeasible assembly tasks, all the infeasible assembly states, and all the feasible assembly sequences, respectively. The equivalence of the resulting sets of precedence relations to the AND/OR graph is established. A new property, the real time property, of a representation of assembly sequences is defined and discussed. A representation of assembly sequences is said to have the real time property, if it is possible to generate the next assembly task by testing locally in the representation, and it will guarantee that the generated assembly task will not lead the assembly sequence to a dead end situation, in which no feasible assembly task can be performed any more. It is shown that the correctness and completeness of one representation can not guarantee the real time property of the representation. It is proven that the directed graph representation and the set of precedence relations based on all the infeasible assembly states have the real time property, while the AND/OR graph representation and the set of precedence relations based on all the infeasible assembly tasks do not have the real time property. Finally in the thesis, the PLEIDEAS system, a PLanning Environment for Integrated DEsign of Assembly Systems, is described and illustrated by an example.

Zhang, Hui↗

Performance prediction of concurrent systems

Concurrent systems are computers that use multiple processors to solve a single problem. A means to predict the application performance on these systems is a useful tool in many areas of concurrent system research. A computationally efficient and accurate method to predict performance for a class of parallel computations on concurrent systems is described. A parallel computation is modeled as a task system with precedence relationships expressed as a series parallel directed acyclic graph. Resources in concurrent systems are modeled as service centers in queueing network models. Using these two models as inputs, the method outputs predictions of both the time to complete the computation and the concurrent system utilization. The algorithm used is based on the approximate Mean Value Analysis in queueing network modeling with extensions to model concurrency in the computation. The new algorithm was validated against both detailed simulation and actual execution on a commercial multiprocessor.

Mak, Victor W. K.↗

SPROC: A multiple-processor DSP IC

A large, single-chip, multiple-processor, digital signal processing (DSP) integrated circuit (IC) fabricated in HP-Cmos34 is presented. The innovative architecture is best suited for analog and real-time systems characterized by both parallel signal data flows and concurrent logic processing. The IC is supported by a powerful development system that transforms graphical signal flow graphs into production-ready systems in minutes. Automatic compiler partitioning of tasks among four on-chip processors gives the IC the signal processing power of several conventional DSP chips.

Davis, R.↗

Task planning and control synthesis for robotic manipulation in space applications

Space-based robotic systems for diagnosis, repair and assembly of systems will require new techniques of planning and manipulation to accomplish these complex tasks. Results of work in assembly task representation, discrete task planning, and control synthesis which provide a design environment for flexible assembly systems in manufacturing applications, and which extend to planning of manipulatiuon operations in unstructured environments are summarized. Assembly planning is carried out using the AND/OR graph representation which encompasses all possible partial orders of operations and may be used to plan assembly sequences. Discrete task planning uses the configuration map which facilitates search over a space of discrete operations parameters in sequential operations in order to achieve required goals in the space of bounded configuration sets.

Sanderson, A. C.↗

Automation - Changes in cognitive demands and mental workload

The effect of partial automation on mental workloads in man/machine tasks is investigated experimentally. Subjective workload measures are obtained from six subjects after performance of a task battery comprising two manual (flight-path control, FC, and target acquisition, TA) tasks and one decisionmaking (engine failure, EF) task; the FC task was performed in both a fully manual (altitude and lateral control) mode and in a semiautomated mode (autmatic latitude control). The performance results and subjective evaluations are presented in graphs and characterized in detail. The automation is shown to improve objective performance and lower subjective workload significantly in the combined FC/TA task, but not in the FC task alone or in the FC/EF task.

Tsang, Pamela S.↗

Predicting performance of parallel computations

An accurate and computationally efficient method for predicting the performance of a class of parallel computations running on concurrent systems is described. A parallel computation is modeled as a task system with precedence relationships expressed as a series-parallel directed acyclic graph. Resources in a concurrent system are modeled as service centers in a queuing network model. Using these two models as inputs, the method outputs predictions of expected execution time of the parallel computation and the concurrent system utilization. The method is validated against both detailed simulation and actual execution on a commercial multiprocessor. Using 100 test cases, the average error of the prediction when compared to simulation statistics is 1.7 percent, with a standard deviation of 1.5 percent; the maximum error is about 10 percent.

Mak, Victor W.↗