Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “natural user interfaces”

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 127 records · Page 7

Reinventing Image Detective: An Evidence-Based Approach to Citizen Science Online

Usability studies demonstrate that web users are notoriously impatient, spending as little as 15 seconds on a home page. How do you get users to stay long enough to understand a citizen science project? How do you get users to complete complex citizen science tasks online? Image Detective, a citizen science project originally developed by scientists and science engagement specialists at the NASA Johnson Space center to engage the public in the analysis of images taken from space by astronauts to help enhance NASA's online database of astronaut imagery, partnered with the CosmoQuest citizen science platform to modernize, offering new and improved options for participation in Image Detective. The challenge: to create a web interface that builds users' skills and knowledge, creating engagement while learning complex concepts essential to the accurate completion of tasks. The project team turned to usability testing for an objective understanding of how users perceived Image Detective and the steps required to complete required tasks. A group of six users was recruited online for unmoderated and initial testing. The users followed a think-aloud protocol while attempting tasks, and were recorded on video and audio. The usability test examined users' perception of four broad areas: the purpose of and context for Image Detective; the steps required to successfully complete the analysis (differentiating images of Earth's surface from those showing outer space and identifying common surface features); locating the image center point on a map of Earth; and finally, naming geographic locations or natural events seen in the image. Usability test findings demonstrated that the following best practices can increase participation in Image Detective and can be applied to the successful implementation of any citizen science project: (1) Concise explanation of the project, its context, and its purpose; (2) Including a mention of the funding agency (in this case, NASA); (3) A preview of the specific tasks required of participants; (4) A dedicated user interface for the actual citizen science interaction. In addition, testing revealed that users may require additional context when a task is complex, difficult, or unusual (locating a specific image and its center point on a map of Earth). Video evidence will be made available with this presentation.

Romano, Cia↗

Taking the MPI standard and the open MPI library to exascale

The Open MPI for Exascale (OMPI-X) project was one of two in the Exascale Computing Project (ECP) focused on advancing the MPI ecosystem. The OMPI-X team worked with other MPI Forum members to champion several important features for inclusion in the MPI 4.0, 4.1, and upcoming 5.0 MPI standard versions, in support of the needs of exascale applications and systems. The team also worked with the larger Open MPI community to bring implementations of these new features and other enhancements into Open MPI, one of the leading open-source implementations of the MPI interface. Here, this paper describes the motivation for the work of the OMPI-X project in the context of exascale computing needs, the nature of the resulting new capabilities in the MPI standard, and how they were implemented in the Open MPI library. Features include improved support for “MPI + X” programming models through partitioned communications and support for user-level threading, sessions, fault tolerance through the user-level fault mitigation (ULFM) and Reinit models, and other features. We also discuss enhancements to Open MPI providing improved performance and scalability for existing features, such as collective operations, one-sided operations, support for the Slingshot-11 interconnect of the initial exascale systems, and how the OMPI-X team worked to improve quality assurance for the Open MPI library, particularly on platforms of interest to the Department of Energy community.

97 MATHEMATICS AND COMPUTING↗

Machine-Learning-Based Mapping and Modeling of Solar Energy with Ultra-High Spatiotemporal Granularity

Despite the rapid growth of solar energy, we still lack a dynamic, high-fidelity database that tracks the spatiotemporal variations of solar PVs and their associated infrastructures across different places at a spatially resolved scale. The absence of such data presents a barrier to various applications such as solar PV growth projection, solar energy integration, solar incentive design, and climate risk assessment. In this project, we aim to bridge this gap by developing AI-based algorithms to extract granular information about solar PV installations and their associated infrastructures (i.e., distribution grids) from widely available unstructured data like remote sensing images and street views. As a result, we have built the Solar Energy Atlas, a fine-grained, large-scale geospatial overlay of distributed solar PVs and distribution grids. On top of it, we have advanced the understanding of solar adoption and distribution grid vulnerability to climate-induced extremes. Our major contributions can be summarized as follow: (1) By developing new AI algorithms, we have built the most comprehensive solar PV spatiotemporal database covering the entire US. This is the first time we obtained the exact GPS locations, size, subtype, and installation year information for rooftop solar PVs across the US. This database can be used for solar PV growth projection, solar energy integration, solar energy policy analysis and design, and spatially-resolved climate risk assessment. (2) Leveraging this database, we have uncovered the socioeconomic driving factors that are correlated with earlier onset of solar adoption and higher saturated adoption levels. We have identified the heterogeneity in the effects of different types of financial incentives on solar adoption and provided implications for tailoring incentive design based on local income levels to promote equitable solar adoption. (3) We have developed a distribution grid GIS mapping algorithm which can obtain granular geospatial and topology information about distribution grids using multi-modal open data, reducing the dependency on hard-to-obtain smart meter data of conventional approaches. It shows effectiveness in both the U.S. and Sub-Saharan Africa. Using this algorithm, we have uncovered the non-uniform vulnerability of distribution grids to wildfires in California in the aspects of undergrounding protection and Distributed Energy Resources (DER) preparedness. This has provided important implications for improving the affordability and equity of grid adaptation approaches. (3) We have made our produced database publicly available and provided user-friendly interface to enable various stakeholders and the general public to interact with the data. We have also integrated the produced data into the Data Commons platform to enable the public to access the data and correlate it with other location-specific characteristics simply using natural language as queries. The impact of our project is three-fold: (1) New algorithms for mapping solar PVs and distribution grids across space and time, which are open source to facilitate researchers and industry; (2) New databases of solar PVs and distribution grids that have been made publicly available for engineering, social, and policy applications; (3) New understandings and actionable insights on the potential approaches to promoting solar adoption and reducing energy infrastructure vulnerabilities. In this report, we start by discussing the project background and motivation (section 5), followed by the overview of project objectives (section 6). Results and discussion for each task are presented in section 7. Significant accomplishments are summarized in section 8. This report will be concluded by discussing the paths forwards (section 9), products (section 10), and team roles (section 11).

14 SOLAR ENERGY↗

Laboratory process control using natural language commands from a personal computer

PC software is described which provides flexible natural language process control capability with an IBM PC or compatible machine. Hardware requirements include the PC, and suitable hardware interfaces to all controlled devices. Software required includes the Microsoft Disk Operating System (MS-DOS) operating system, a PC-based FORTRAN-77 compiler, and user-written device drivers. Instructions for use of the software are given as well as a description of an application of the system.

Will, Herbert A.↗

Integrated verification and testing system (IVTS) for HAL/S programs

The IVTS is a large software system designed to support user-controlled verification analysis and testing activities for programs written in the HAL/S language. The system is composed of a user interface and user command language, analysis tools and an organized data base of host system files. The analysis tools are of four major types: (1) static analysis, (2) symbolic execution, (3) dynamic analysis (testing), and (4) documentation enhancement. The IVTS requires a split HAL/S compiler, divided at the natural separation point between the parser/lexical analyzer phase and the target machine code generator phase. The IVTS uses the internal program form (HALMAT) between these two phases as primary input for the analysis tools. The dynamic analysis component requires some way to 'execute' the object HAL/S program. The execution medium may be an interpretive simulation or an actual host or target machine.

Senn, E. H.↗

Organizing Diverse, Distributed Project Information

SemanticOrganizer is a software application designed to organize and integrate information generated within a distributed organization or as part of a project that involves multiple, geographically dispersed collaborators. SemanticOrganizer incorporates the capabilities of database storage, document sharing, hypermedia navigation, and semantic-interlinking into a system that can be customized to satisfy the specific information-management needs of different user communities. The program provides a centralized repository of information that is both secure and accessible to project collaborators via the World Wide Web. SemanticOrganizer's repository can be used to collect diverse information (including forms, documents, notes, data, spreadsheets, images, and sounds) from computers at collaborators work sites. The program organizes the information using a unique network-structured conceptual framework, wherein each node represents a data record that contains not only the original information but also metadata (in effect, standardized data that characterize the information). Links among nodes express semantic relationships among the data records. The program features a Web interface through which users enter, interlink, and/or search for information in the repository. By use of this repository, the collaborators have immediate access to the most recent project information, as well as to archived information. A key advantage to SemanticOrganizer is its ability to interlink information together in a natural fashion using customized terminology and concepts that are familiar to a user community.

Keller, Richard M.↗

Natural Language Based Multimodal Interface for UAV Mission Planning

As the number of viable applications for unmanned aerial vehicle (UAV) systems increases at an exponential rate, interfaces that reduce the reliance on highly skilled engineers and pilots must be developed. Recent work aims to make use of common human communication modalities such as speech and gesture. This paper explores a multimodal natural language interface that uses a combination of speech and gesture input modalities to build complex UAV flight paths by defining trajectory segment primitives. Gesture inputs are used to define the general shape of a segment while speech inputs provide additional geometric information needed to fully characterize a trajectory segment. A user study is conducted in order to evaluate the efficacy of the multimodal interface.

Chandarana, Meghan↗

Procedure Parsing: A Method for Parsing Handwritten Documents into Computer-Based Procedures

The nuclear industry is heavily procedure driven, where almost everything has a step-by-step instruction that is expected to be followed in detail. Historically, these procedures were printed on paper copies. Recently, the industry transitioned towards electronic copies (i.e., PDFs on tablets). One major drive for this transition is the introduction of human error and loss of situation awareness when using paper copies. However, electronic copies of documents inherently have the same error traps as their paper cousins. Therefore, there is an increased interest in a way to utilize the information in the step-by-step guidance, but to present it in a dynamic manner that guides the user and adapts to any encountered conditions. Researchers at Idaho National Laboratory propose a flexible, automated method based on document parsing and augmented by natural language processing (NLP) techniques, to address these shortcomings and capitalize on these recent advancements in machine learning. The proposed method provides a cost-effective solution for computer-assisted procedure parsing of hand-written control room procedures, originally authored in Word or PDF formats, into instructions that can be displayed as computer-based procedures (CBP) in a modern graphical user interface. The researchers devised, implemented and demonstrated the Operating Procedure Extender for Novel Systems (OPENS) method in 2020. The key to OPENS is to map the original procedure text into a context-free grammar, tying content to equipment, locations, and other steps, actions, etc. This formal grammar is then used to isolate and define keywords and actions verbs, such as “measure” or “evaluate” and tie them to specific equipment referenced within that step or located in other steps, substeps, actions, subactions and tables throughout the procedure. OPENS generates an abstract syntax tree from the document which it uses to store a copy of this information in the open-standard, machine-readable and human-readable file formats XML and JSON. The XML is useful to preserve the relational aspects of the procedure for referencing tables and branching information so the user can be directed to the next appropriate active step based on the values entered for that step and previous steps. The JSON is useful for storing and exchanging data objects used to track responses to previous steps and state changes in simulated environments. In future iterations, these formats can also be used for storing more detailed information about input during plant operation or simulation. The techniques the researcher developed could further be improved by integration of recent advancements in machine learning. NLP methods could standardize documents, correct for grammatical error, and provide automated semantic validation. The researcher expects that self-supervised techniques applied to collections of natural language instructions could strengthen the model with broader context. All these methods together give us a practical way to automatically extract protocols from documents and user interactions, empowering researchers, procedure writers and nuclear operators while moving the industry forward.

99 GENERAL AND MISCELLANEOUS↗

GOATS - Orbitology Component

The GOATS Orbitology Component software was developed to specifically address the concerns presented by orbit analysis tools that are often written as stand-alone applications. These applications do not easily interface with standard JPL first-principles analysis tools, and have a steep learning curve due to their complicated nature. This toolset is written as a series of MATLAB functions, allowing seamless integration into existing JPL optical systems engineering modeling and analysis modules. The functions are completely open, and allow for advanced users to delve into and modify the underlying physics being modeled. Additionally, this software module fills an analysis gap, allowing for quick, high-level mission analysis trades without the need for detailed and complicated orbit analysis using commercial stand-alone tools. This software consists of a series of MATLAB functions to provide for geometric orbit-related analysis. This includes propagation of orbits to varying levels of generalization. In the simplest case, geosynchronous orbits can be modeled by specifying a subset of three orbit elements. The next case is a circular orbit, which can be specified by a subset of four orbit elements. The most general case is an arbitrary elliptical orbit specified by all six orbit elements. These orbits are all solved geometrically, under the basic problem of an object in circular (or elliptical) orbit around a rotating spheroid. The orbit functions output time series ground tracks, which serve as the basis for more detailed orbit analysis. This software module also includes functions to track the positions of the Sun, Moon, and arbitrary celestial bodies specified by right ascension and declination. Also included are functions to calculate line-of-sight geometries to ground-based targets, angular rotations and decompositions, and other line-of-site calculations. The toolset allows for the rapid execution of orbit trade studies at the level of detail required for the early stage of mission concept development.

Haber, Benjamin M.↗

GANpiler

Focal Area(s): Rather than augment or replace physical models with machine learning, we instead preserve the existing models and augment the underlying code with faster surrogate models created by generative adversarial networks (GAN). To leverage the performance optimization, we also propose a runtime system and user interfaces that allow prediction and tracking of accumulated error as well as dynamic, per-process decision making as to which model (if any) to use for each iteration. Science Challenge: This proposal sits at the nexus of two hard problems. First, climate models based on machine learning will be, by their nature, difficult to trust once their predictions begin diverging from the consensus. Second, compilers and hardware have been making only incremental performance gains for decades. GPGPUs have provided a welcome performance boost for codes that can take advantage of them, but there is no similar technology on the horizon to provide the next performance leap.

54 ENVIRONMENTAL SCIENCES↗

Technologies for Visualization in Computational Aerosciences

State-of-the-art research in computational aerosciences produces' complex, time-dependent datasets. Simulations can also be multidisciplinary in nature, coupling two or more physical disciplines such as fluid dynamics, structural dynamics, thermodynamics, and acoustics. Many diverse technologies are necessary for visualizing computational aerosciences simulations. This paper describes these technologies and how they contribute to building effective tools for use by domain scientists. These technologies include data management, distributed environments, advanced user interfaces, rapid prototyping environments, parallel computation, and methods to visualize the scalar and vector fields associated with computational aerosciences datasets.

Miceli, Kristina D.↗

Experiments in Nonlinear Adaptive Control of Multi-Manipulator, Free-Flying Space Robots

Sophisticated robots can greatly enhance the role of humans in space by relieving astronauts of low level, tedious assembly and maintenance chores and allowing them to concentrate on higher level tasks. Robots and astronauts can work together efficiently, as a team; but the robot must be capable of accomplishing complex operations and yet be easy to use. Multiple cooperating manipulators are essential to dexterity and can broaden greatly the types of activities the robot can achieve; adding adaptive control can ease greatly robot usage by allowing the robot to change its own controller actions, without human intervention, in response to changes in its environment. Previous work in the Aerospace Robotics Laboratory (ARL) have shown the usefulness of a space robot with cooperating manipulators. The research presented in this dissertation extends that work by adding adaptive control. To help achieve this high level of robot sophistication, this research made several advances to the field of nonlinear adaptive control of robotic systems. A nonlinear adaptive control algorithm developed originally for control of robots, but requiring joint positions as inputs, was extended here to handle the much more general case of manipulator endpoint-position commands. A new system modelling technique, called system concatenation was developed to simplify the generation of a system model for complicated systems, such as a free-flying multiple-manipulator robot system. Finally, the task-space concept was introduced wherein the operator's inputs specify only the robot's task. The robot's subsequent autonomous performance of each task still involves, of course, endpoint positions and joint configurations as subsets. The combination of these developments resulted in a new adaptive control framework that is capable of continuously providing full adaptation capability to the complex space-robot system in all modes of operation. The new adaptive control algorithm easily handles free-flying systems with multiple, interacting manipulators, and extends naturally to even larger systems. The new adaptive controller was experimentally demonstrated on an ideal testbed in the ARL-A first-ever experimental model of a multi-manipulator, free-flying space robot that is capable of capturing and manipulating free-floating objects without requiring human assistance. A graphical user interface enhanced the robot usability: it enabled an operator situated at a remote location to issue high-level task description commands to the robot, and to monitor robot activities as it then carried out each assignment autonomously.

Chen, Vincent Wei-Kang↗

Development of a Space Radiation Monte-Carlo Computer Simulation Based on the FLUKE and Root Codes

The radiation environment in space is a complex problem to model. Trying to extrapolate the projections of that environment into all areas of the internal spacecraft geometry is even more daunting. With the support of our CERN colleagues, our research group in Houston is embarking on a project to develop a radiation transport tool that is tailored to the problem of taking the external radiation flux incident on any particular spacecraft and simulating the evolution of that flux through a geometrically accurate model of the spacecraft material. The output will be a prediction of the detailed nature of the resulting internal radiation environment within the spacecraft as well as its secondary albedo. Beyond doing the physics transport of the incident flux, the software tool we are developing will provide a self-contained stand-alone object-oriented analysis and visualization infrastructure. It will also include a graphical user interface and a set of input tools to facilitate the simulation of space missions in terms of nominal radiation models and mission trajectory profiles. The goal of this project is to produce a code that is considerably more accurate and user-friendly than existing Monte-Carlo-based tools for the evaluation of the space radiation environment. Furthermore, the code will be an essential complement to the currently existing analytic codes in the BRYNTRN/HZETRN family for the evaluation of radiation shielding. The code will be directly applicable to the simulation of environments in low earth orbit, on the lunar surface, on planetary surfaces (including the Earth) and in the interplanetary medium such as on a transit to Mars (and even in the interstellar medium). The software will include modules whose underlying physics base can continue to be enhanced and updated for physics content, as future data become available beyond the timeframe of the initial development now foreseen. This future maintenance will be available from the authors of FLUKA as part of their continuing efforts to support the users of the FLUKA code within the particle physics community. In keeping with the spirit of developing an evolving physics code, we are planning as part of this project, to participate in the efforts to validate the core FLUKA physics in ground-based accelerator test runs. The emphasis of these test runs will be the physics of greatest interest in the simulation of the space radiation environment. Such a tool will be of great value to planners, designers and operators of future space missions, as well as for the design of the vehicles and habitats to be used on such missions. It will also be of aid to future experiments of various kinds that may be affected at some level by the ambient radiation environment, or in the analysis of hybrid experiment designs that have been discussed for space-based astronomy and astrophysics. The tool will be of value to the Life Sciences personnel involved in the prediction and measurement of radiation doses experienced by the crewmembers on such missions. In addition, the tool will be of great use to the planners of experiments to measure and evaluate the space radiation environment itself. It can likewise be useful in the analysis of safe havens, hazard migration plans, and NASA's call for new research in composites and to NASA engineers modeling the radiation exposure of electronic circuits. This code will provide an important complimentary check on the predictions of analytic codes such as BRYNTRN/HZETRN that are presently used for many similar applications, and which have shortcomings that are more easily overcome with Monte Carlo type simulations. Finally, it is acknowledged that there are similar efforts based around the use of the GEANT4 Monte-Carlo transport code currently under development at CERN. It is our intention to make our software modular and sufficiently flexible to allow the parallel use of either FLUKA or GEANT4 as the physics transport engine.

Pinsky, L. S.↗

A study of the very high order natural user language (with AI capabilities) for the NASA space station common module

The requirements are identified for a very high order natural language to be used by crew members on board the Space Station. The hardware facilities, databases, realtime processes, and software support are discussed. The operations and capabilities that will be required in both normal (routine) and abnormal (nonroutine) situations are evaluated. A structure and syntax for an interface (front-end) language to satisfy the above requirements are recommended.

Gill, E. N.↗

Informing Wildfire Needs: The Expanded User Interface of NASA's Fire Information for Resource Management System (Firms)

As the global community continues to experience, and respond to, living in a changing environment, access to tools, technologies, and timely data utilized by an increasingly diverse set of stakeholders is increasing. This year, 2023, has thus far seen an unprecedented number of extreme events, increasingly driven by changes in the climate and a strong 2023 ENSO pattern. In Canada, a record number of wildfires, and associated weather events, evacuations, and infrastructure and habitat destruction has taken place, and is ongoing. Large swaths of Greece have experienced similar wildfire destruction. Most recently, Maui has experienced destructive wildfires, and early 2023 saw massive wildfires in Chile. NASA's Fire Information for Resource Management System, or FIRMS, has a fifteen-year history of providing timely and comprehensive data and information on wildfires to stakeholders. FIRMS was initially developed in 2007 by the University of Maryland, with funds from NASA's Applied Sciences Program and the United Nations Food and Agriculture Organization (UN FAO), to provide near real-time active fire Locations to natural resource managers that faced challenges obtaining timely satellite-derived fire information. FIRMS has consistently evolved to address the needs of stakeholders Living in a changing environment; in 2012 it transitioned to NASA LANCE and in 2021 through a partnership between NASA and the US Forest Service, an updated version of FIRMS was released for the US and Canada. As NASA and other federal agencies continue to accelerate Open Science through integrated efforts such as the Year of Open Science, the provision of readily discoverable, findable, accessible, interoperable, reusable data represents a major focus to facilitate equitable outcomes. FIRMS supports this acceleration in Open Science by continuing to provision data and information for its traditional user base, while addressing the novel user needs of an increasingly diverse set of stakeholders seeking robust, reliable, transparently generated data and information. Increasingly, FIRMS is utilized by citizen scientists and individuals directly affected by wildfires - through evacuations, risks to structures/homes, poor air quality. etc. FIRMS has also been Leveraged to detect and assess the impacts resulting from ongoing conflicts. This further highlights the multi-faceted impacts of wildfires and other events. In the Fall of 2023, FIRMS will release an expanded User Interface (UI). This interface captures and reflects the needs of, and input from, a multitude of users. These users range from federal agency representatives to non-government organizations to the private sector to citizen science entities. To respond to this expansive and diverse user need base, the updated FIRMS UI will capture a range of features to support those beginning to explore the range of data and tools available to inform wildfire awareness and knowledge. These users are supported through a Basic Mode interface, furnishing access to a light set of functionalities that provision straight-forward, readily usable information and data, and ingestible knowledge. The Advanced Mode interface supports those stakeholder groups already proficient in navigating FIRMS. These stakeholders, representing fire managers and others, perform active fire management and tactical wildfire response activities. For these stakeholders, additional datasets have been included which require in-depth knowledge of both the utility as well as the caveats of such datasets. Additional functionalities have also been embedded to aid specific user queries. The expanded UI will introduce a new Experimental Mode. The focus of this UI will be to support the provision of emerging and innovative datasets that are in development for review and comment by the user community Examples include post-fire products generated by NASA's Earth Information System (EIS) Fire. This presentation will provide an overview of the expanded FIRMS UI. We will discuss how this UI is designed to be scalable and support the unique needs of an expanding and diverse user base. We will highlight key features, elements, and datasets, and describe how user needs have informed and guided the design of the UI. We will also share recent use cases to convey, and increase awareness, among conference participants. As the global community faces more extreme wildfires, due to climate variability and change, there is an increased need for reliable data to inform, manage, and mitigate the impacts of these events. Through this work, NASA FIRMS is striving to level the playing field, by making information accessible to all; from policy makers to the private sector to historically marginalized communities. In doing so, NASA is promoting the all-hands-on-deck response needed to minimize the impacts of wildfires and harness the strengths of open science to address the greatest environmental challenge faced.

Jenny Hewson↗

An overview of the EOSDIS V0 information management system: Lessons learned from the implementation of a distributed data system

The EOSDIS Version 0 system, released in July, 1994, is a working prototype of a distributed data system. One of the purposes of the V0 project is to take several existing data systems and coordinate them into one system while maintaining the independent nature of the original systems. The project is a learning experience and the lessons are being passed on to the architects of the system which will distribute the data received from the planned EOS satellites. In the V0 system, the data resides on heterogeneous systems across the globe but users are presented with a single, integrated interface. This interface allows users to query the participating data centers based on a wide set of criteria. Because this system is a prototype, we used many novel approaches in trying to connect a diverse group of users with the huge amount of available data. Some of these methods worked and others did not. Now that V0 has been released to the public, we can look back at the design and implementation of the system and also consider some possible future directions for the next generation of EOSDIS.

Ryan, Patrick M.↗

OpenPATH and Itinerum Integration: A Case Study of Merging Open-Source Projects: Preprint

Throughout the transportation sector, multiple mobility tracking platforms have been developed independently, in parallel, with similar use cases and infrastructure. Maintaining such platforms on an individual level can result in duplicated effort. Innovation within the field could be slowed by the limited resource of people working on extremely similar projects. We provide a case study in how such platforms can be combined with low effort and provide an example in the mobility domain of what the resulting integration points, modules and ownership may look like. OpenPATH (formerly e-mission) and Itinerum are two examples of similar independently developed human mobility tracking platforms that extend beyond standard traffic data collection. Due to the open source nature of the projects, members from both teams decided to merge the functionality, thereby only hosting a single data collection process and limiting maintenance of separate intake platforms. On the front-end, specific questionnaire functionality from Itinerum, mainly the ability to display and return questions and results focused on sociodemographic attributes, was integrated into the OpenPATH user interface. On the back-end, an export pipeline stage was created to transport collected data back to the Itinerum database. Upon completion, the OpenPATH application retained its original functionality while adding the ability to export data for future data sharing and creating an avenue to incorporate Itinerum hosted questions and answers. Itinerum benefits from the rich feature set and infrastructure of OpenPATH without losing needed elements such as the questionnaire component. This case study, within the transportation sector, illustrates the various configurations in which open source software can be developed, maintained and deployed.

ADVANCED PROPULSION SYSTEMS↗

Improved Open-Microphone Speech Recognition

Many current and future NASA missions make extreme demands on mission personnel both in terms of work load and in performing under difficult environmental conditions. In situations where hands are impeded or needed for other tasks, eyes are busy attending to the environment, or tasks are sufficiently complex that ease of use of the interface becomes critical, spoken natural language dialog systems offer unique input and output modalities that can improve efficiency and safety. They also offer new capabilities that would not otherwise be available. For example, many NASA applications require astronauts to use computers in micro-gravity or while wearing space suits. Under these circumstances, command and control systems that allow users to issue commands or enter data in hands-and eyes-busy situations become critical. Speech recognition technology designed for current commercial applications limits the performance of the open-ended state-of-the-art dialog systems being developed at NASA. For example, today's recognition systems typically listen to user input only during short segments of the dialog, and user input outside of these short time windows is lost. Mistakes detecting the start and end times of user utterances can lead to mistakes in the recognition output, and the dialog system as a whole has no way to recover from this, or any other, recognition error. Systems also often require the user to signal when that user is going to speak, which is impractical in a hands-free environment, or only allow a system-initiated dialog requiring the user to speak immediately following a system prompt. In this project, SRI has developed software to enable speech recognition in a hands-free, open-microphone environment, eliminating the need for a push-to-talk button or other signaling mechanism. The software continuously captures a user's speech and makes it available to one or more recognizers. By constantly monitoring and storing the audio stream, it provides the spoken dialog manager extra flexibility to recognize the signal with no audio gaps between recognition requests, as well as to rerecognize portions of the signal, or to rerecognize speech with different grammars, acoustic models, recognizers, start times, and so on. SRI expects that this new open-mic functionality will enable NASA to develop better error-correction mechanisms for spoken dialog systems, and may also enable new interaction strategies.

Abrash, Victor↗