<?xml version="1.0" standalone="yes"?>
<Paper uid="A97-1005">
  <Title>QuickSet: Multimodal Interaction for Simulation Set-up and Control</Title>
  <Section position="3" start_page="20" end_page="20" type="intro">
    <SectionTitle>
3. QUICKSET
</SectionTitle>
    <Paragraph position="0"> To address these simulation interface problems, and motivated by the above results, we have developed QuickSet (see Figure 1) a collaborative, handheld, multimodal system for configuring military simulations based on LeatherNet \[5\], a system used in training platoon leaders and company commanders at the USMC base at 29 Palms, California. LeatherNet simulations are created using the ModSAF simulator \[10\] and can be visualized in a CAVE-based virtual reality environment \[11, 26\] called CommandVu (see Figure 2 -- QuickSet systems are on the soldiers' tables). In addition to LeatherNet, QuickSet is being used in a second effort called Exlnit (Exercise Initialization), that will enable users to create division-sized exercises. Because of the use of OAA, QuickSet can interoperate with agents from CommandTalk [14], which provides a speech-only interface to ModSAF.</Paragraph>
    <Paragraph position="1"> QuickSet runs on both desktop and hand-held PC's, communicating over wired and wireless LAN's, or modem links. The system combines speech and pen-based gesture input on multiple 3-1b hand-held PCs (Fujitsu Stylistic 1000), which communicate via wireless LAN through the Open Agent Architecture (OAA) 2 [8], to ModSAF, and also to CommandVu. With this highly portable device, a user can create entities, establish &amp;quot;control measures&amp;quot; (e.g., objectives, checkpoints, etc.), draw and label various lines and areas, (e.g., landing zones) and give the entities behavior.</Paragraph>
    <Paragraph position="2"> agent-based architecture was chosen to support this application because it offers easy connection to legacy applications, and the ability to run the same set of software components in a variety of hardware configurations, ranging from stand-alone on the handheld PC, to distributed operation across numerous workstations and PCs.</Paragraph>
    <Paragraph position="3"> Additionally, the architecture supports mobility in that lighter weight agents can run on the handheld, while more computationally-intensive processing can be migrated elsewhere on the network. The agents may be written in any programming language (here, Quintus Prolog, Visual C++, Visual Basic, and Java), as long as they communicate via an interagent communication language. The configuration of agents used in the Quickset system is illustrated in Figure 3. A brief description of each agent follows:  In the remainder of the paper, we illustrate the system briefly, describe its components, and discuss its application. QuickSet interface: On the handheld PC is a getreferenced map of the region such that entities displayed on the map are registered to their positions on the actual terrain, and thereby to their positions on each of the various user interfaces connected to the simulation. The map interface agent provides the usual pan and zoom capabilities, multiple overlays, icons, etc. The user can draw directly on the map, in order to create points, lines, and areas. The user can create entities, give them behavior, and watch the simulation unfold from the handheld. When the pen is placed on the screen, the speech recognizer is activated, thereby allowing users to speak and gesture simultaneously. Speech recognition agent: The speech recognition agent used in QuickSet employs either IBM's VoiceType Application Factory or VoiceType 3.0 recognizers. The recognizers use an HMM-based continuous speaker-independent speech recognition technology for PC's under Windows 95/NT. Currently, the system has a vocabulary of 450 words. It produces a single most likely interpretation of an utterance.</Paragraph>
    <Paragraph position="4"> Gesture recognition agent: OGI's gesture recognition agent processes all pen input from a PC screen or tablet.</Paragraph>
    <Paragraph position="5"> The agent weights the results of both HMM and neural net recognizers, producing a combined score for each of the possible recognition results. Currently, 45 gestures can be recognized, resulting in the creation of 21 military symbols, irregular shapes, and various types of lines.</Paragraph>
    <Paragraph position="6">  CommandVu virtual display of distributed interactive simulation.</Paragraph>
  </Section>
class="xml-element"></Paper>