| Enhancing Simulation-Based Training Adversary Tactics via Evolution (ESTATE) |
15 JUN 2011 |
9 pages |
| Authors:
Brad Rosenberg; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
 | During the last reporting period, we had updated the ESTATE test environment (i.e. PROMPTER) to support third-party challenge generation and implement a testing framework to support simulated players, challenges, and performance. During this reporting period, we used this testing framework to evaluate different simulated player implementations and adaptive challenge generation components. |
|
| Enhancing Simulation-based Training Adversary Tactics Via Evolution (ESTATE) |
15 Mar 2011 |
8 pages |
| Authors:
Brad Rosenberg; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| During the indicated period, we have been in discussions with USMC Training and Education Command (TECOM) MAGTF Training Simulations Division (TSD) to inform the community of the training systems capabilities being developed under ESTATE along with the PROMPTER framework. Our discussions have led to potential interest from several different avenues including Marine Corps University, College of Distance Education and Training (CDET), the Marine Corps Warfighting Laboratory (MCWL), USMC Center for ... |
|
| Enhancing Simulation-Based Training Adversary Tactics via Evolution (ESTATE) |
15 DEC 2010 |
11 pages |
| Authors:
Brad Rosenberg; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| During the current reporting period, we presented ESTATE at the two-day ONR 341 Program Review for Harold Hawkins on 4-5 October 2010. The review included program presentations from ONR-funded performers on human cognitive performance predictors such as neural plasticity, working memory, and adaptive performance as well as population modeling and computational approaches for 21st Century Naval Operations. Interactions with the review participants helped us to consider future directions for the ... |
|
| Enhancing Simulation-based Training Adversary Tactics via Evolution (ESTATE) |
15 DEC 2010 |
55 pages |
| Authors:
Brad Rosenberg; James Niehaus; Max Metzger; Scott N. Reilly; Jordan Pollack; Bjorn Gunnarsson; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| To extend modern simulation-based training environments to incorporate tailored simulation-based training experiences to facilitate accelerated skills development and sustainment, we are developing a system for Enhancing Simulation-based Training Adversary Tactics via Evolution (ESTATE). The system consists of an off-line adaptation engine to extract a model of the trainee based on past performance and generate tailored challenge problems for on-line training. Off-line adaptation is performed using evolutionary algorithms (EAs) to search ... |
|
| Enhancing Simulation-based Training Adversary Tactics via Evolution (ESTATE) |
15 Sep 2010 |
9 pages |
| Authors:
Brad Rosenberg; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| During this reporting period we have concentrated on Task 4: Develop Trainee Model Processing. During our previous reporting period, our analyses indicated that under the MoneyBee experiment, students were learning through challenges, solving more difficult problems in less time as they gained experience. Our next step was then to understand the strategies employed by students to create models of different players for future experimentation. To understand the strategies employed, we ... |
|
| Semantic Search with Self-Maintaining Classes |
15 Jul 2010 |
12 pages |
| Authors:
Terry Patten; Stephen Hookway; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| The SBIR contract entitled Knowledge-based Access and Data Integration (KADI) resulted in a paper being presented at the 2010 International Conference on Semantic Web and Web Services held at Las Vegas, NV on 12-15 July-2010. |
|
| Enhancing Simulation-based Training Adversary Tactics via Evolution (ESTATE) |
15 Jun 2010 |
8 pages |
| Authors:
Brad Rosenberg; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| The goal of this task is to discover a method to measure student learning and to determine if students are gaining proficiency in this pre-algebra activity. This method will augment our student assessment and challenge adaptation techniques by providing a better estimate of student ability and Zone of Proximal Development (ZPD). Earlier exploration of the MoneyBee Dataset indicated that the students score better as they attempt more problems, but because ... |
|
| Enhancing Simulation-Based Training Adversary Tactics Via Evolution (ESTATE) |
15 Mar 2010 |
21 pages |
| Authors:
Brad Rosenberg; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| The following is the Contractor's Quarterly Status Report for the subject contract for the indicated period. During this reporting period work has concentrated on Task 2: Develop Mitigation Methods, Task 3: Enhance Adaptation Techniques, and Task 4: Develop Trainee Model Processing. During this reporting period, we researched, implemented, and evaluated a method for coevolution of strategy based game players and game challenges to prepare for use in ESTATE-based training. We ... |
|
| Enhancing Simulation-Based Training Adversary Tactics via Evolution (ESTATE) |
15-Dec-2009 |
11 pages |
| Authors:
Brad Rosenberg; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| During this reporting period work has concentrated on Task 4: Develop Trainee Model Processing. We focused on working on mining the existing MoneyBee data from our academic partner, Brandeis University, to examine student performance and began to construct a way to create a representation of strategies for future research. |
|
| Enhancing Simulation-Based Training Adversary Tactics via Evolution (ESTATE) |
15-Sep-2009 |
15 pages |
| Authors:
CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| During this reporting period, we extended our work in the conceptual formulation of ESTATE for Challenge/Response games. We explored and refined aspects of item response theory to support assessment and learning Challenge/Response games. We constructed multiple simulations to test our theoretical hypotheses. |
|
| Enhancing Simulation-based Training Adversary Tactics via Evolution (ESTATE) |
15 Jun 2009 |
8 pages |
| Authors:
Brad Rosenberg; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| The following is the Contractor's Quarterly Status Report for the subject contract for the indicated period. During this reporting period work has concentrated on Task 1: Identify Training Goals, Task 4: Develop Trainee Model Processing, and Task 6: Perform Simulation-based Training System Integration |
|
| Enabling Robust C2 Systems through Evolvable Human-in-the-Loop Data Fusion |
Jun-2009 |
30 pages |
| Authors:
Eric Carlson; Emilie Roth; Jonathan Pfautz; Gerald Powell; Sean Guarino; Samuel Mahoney; Ted Fichtl; Mike Farry; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| Data fusion systems are being increasingly used to support military planning, decision making, and command and control functions in general. Typically, these systems are designed around the current capabilities of particular data collectors (e.g., sensors) and available processing algorithms. These algorithms incorporate an ontology that reflects the designer's perception of key concepts in the world (e.g., types of threats, classes of vehicles to be tracked) and how these can be ... |
|
| Enhancing Simulation-Based Training Adversary Tactics via Evolution (ESTATE) |
15-Mar-2009 |
7 pages |
| Authors:
Brad Rosenberg; Jordan Pollack; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| A kickoff briefing was held on 2 Feb 2009 at the Office of Naval Research in Arlington, VA. Present were Brad Rosenberg (Principal Investigator) from Charles River Analytics and Prof. Jordan Pollack (Technical Advisor) from Brandeis University. From the Office of Naval Research, Dr. Harold Hawkins (Program Officer) and Ms. Annetta Burger were present. Brad Rosenberg led the discussion, which explored the program motivation, approach, and goals for the base ... |
|
| Culturally Aware Agents for Training Environments (CAATE): Phase I Final Report |
Jan-2009 |
54 pages |
| Authors:
Jonathan Pfautz; Scott N Reilly; Clare Bayley; David Koelle; Stephen Marotta; Michael Keeney; Michael J Singer; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| Recently, the U.S. Army has conducted a wide range of missions within the context of very different cultures and languages. These missions often require junior leaders and Soldiers to interact and communicate effectively with people whose cultures, languages, lifestyles, and beliefs are very different from those found in the U.S. Computer-based training in virtual environments has the potential to train Soldiers to rehearse missions with a sound knowledge of the ... |
|
| Assessing the Impact of Haptic Peripheral Displays for UAV Operators |
MAR 2008 |
71 pages |
| Authors:
B. Donmez; H. D. Graham; M. L. Cummings; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| Objectives: A pilot study was conducted to investigate the effectiveness of continuous haptic peripheral displays in supporting multiple UAV supervisory control. Background: Previous research shows that continuous auditory peripheral displays can enhance operator performance in monitoring events that are continuous in nature, such as monitoring how well UAVs stay on their pre-planned courses. This research also shows that auditory alerts can be masked by other auditory information. Command and control ... |
|
| A Toolkit for Building Hybrid, Multi-Resolution PMESII Models |
NOV 2007 |
66 pages |
| Authors:
John A. Bachman; Karen A. Harper; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| A software toolkit for constructing, integrating, debugging, validating and verifying, and maintaining heterogeneous Political, Military, Economic, Social Information, and Infrastructure (PMESII) models in support of a Commander's Predictive Environment (CPE) was developed. This development environment is based upon Charles River Analytic's Graphical Agent Development Environment (GRADE), and provides intuitive graphical tools supporting the development of new models and adaptation of existing PMESII models. The component-based software architecture enables the injection ... |
|
| A Framework for Building and Reasoning with Adaptive and Interoperable PMESII Models |
NOV 2007 |
122 pages |
| Authors:
John Langton; Subrata Das; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| A framework for the development and integration of Political, Military, Economic, Social, Information, and Infrastructure (PMESII) models in support of a Commander's Predictive Environment (CPE) was investigated and developed. Key challenges were allowing analysts to share their models, interconnect their models, and explore the relationships between elements in a network of integrated models. Areas explored included how to translate between different interfaces, ontologies, sub-domains, and formalisms, e.g., Bayesian networks or ... |
|
| The Role of Meta-Information in C2 Decision-Support Systems |
JUN 2006 |
|
| Authors:
Jonathan Pfautz; Emilie Roth; Ann Bisantz; Gina Thomas-Meyers; James Llinas; Adam Fouse; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
 | Command and control (C2) in complex, dynamic, high-risk warfighting environments is clearly challenging, particularly because of the increasing complexity of available technology for processing and presenting information. Commanders need to understand and act on large volumes of information from a variety of sources and are particularly challenged by the need to reason about the qualifiers of that information, which we will refer to as meta-information (e.g., uncertainty, recency, pedigree). We ... |
|
| Web-Enabled ATR/Fusion Development System |
13 JAN 2001 |
|
| Authors:
Harald Ruda; David Yanchus; Mikhail Zingman; Vitaly Ablavsky; Magnus Snorrason; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| With the quickly escalating number of sources for national intelligence, surveillance, and reconnaissance data, there is a corresponding need to quickly develop ATR and fusion algorithms that provide useful information. We have designed a Web-Enabled ATR/Fusion Development System (WEADS) that will allow distributed development and execution of AIR and fusion algorithms using currently available infrastructures. The WEADS prototype has been built using a previously existing prototype system that provides a ... |
|
| Framework for Automatic Target Recognition Optimization |
31 OCT 97 |
81 pages |
| Authors:
Harald Ruda; Magnus Snorrason; David Shue; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| We have designed a framework for the optimization of Automatic Target Recognition (ATR) algorithms. Successful ATR algorithms are complex, with non- linear components and feedback between components, and thus do not lend themselves to traditional analytical optimization methods. A prototype of the designed framework has been implemented with a visual programming interface that simultaneously aids design decisions and provides opportunities for improvements and optimizations. This framework is applicable to individual ... |
|
| Agent-Enhanced Electronic Classroom on the Web |
SEP 97 |
66 pages |
| Authors:
James M. Mazzu; Alfred J. Deluca; Joshua Seadia; Subrata K. Das; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| This report documents an effort to develop a prototype Agent Enhanced Electronic Classroom (eClass) that uses intelligent agents as tutors and coaches. In this Phase 1 project, we worked alongside the UMass Dartmouth Division of Continuing Education to investigate an electronic classroom architecture which will complement the training objectives of the Five Pillars of the WF XXI Campaign. The architecture developed incorporates intelligent software agent technology capable of personalizing course ... |
|
| VIEW: Visualization and Interactive Elicitation Workstation -- A Tool for Representing the Commander's Mental Model of the Battlefield |
DEC 96 |
100 pages |
| Authors:
Greg Zacharias; Christine Illgen; Mehran Asdigha; Jake Yara; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| This research assessed development of a Visualization and Interactive Elicitation Workstation (VIEW) for inferring and representing mental models of the battlefield. The prototype is composed of two subsystems: a Visualization subsystem and a Knowledge Elicitation (KE) subsystem. The Visualization subsystem is composed of three interlinked modules: (1) a Tactical Visualization Interface providing liked displays for visualizing the battlefield; (2) an Object Database providing a common object representation for environmental and ... |
|
| An Intelligent Flight Trainer for Initial Entry Rotary Wing Training |
MAY 96 |
91 pages |
| Authors:
Sandeep S. Mulgund; Greg L. Zacharias; Mehran Asdigha; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| The Army Research Institute (ARI) has developed and demonstrated the UH-1 Training Research Simulator (TRS), and shown it to be effective in providing low-cost, effective simulator-based basic training of initial-entry rotary wing (IERW) maneuvers. The system integrates technologies of distributed computational processing and computer image generators in a configuration that has the potential for minimizing dependence on a dedicated instructor pilot. Six empirical studies have demonstrated the system's effectiveness in ... |
|
| Design Study for Passive Sensor Altitude and Terrain Awareness System |
JUN 95 |
120 pages |
| Authors:
Adam X. Miao; Greg L. Zacharias; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| This Phase II effort completed the successful enhancement, implementation, and demonstration of the passive sensor Altitude and Terrain Awareness System (ATAS) operation using both computer generated and real imagery. The products of this effort include: (1) a test bed and an overall architecture of ATAS that comprises both the real-time image generation and real-time egomotion and terrain shape estimation; and (2) hardware and software specifications for a real-time flight rated ... |
|
| A Neural Expert Approach to Self Designing Flight Control Systems |
21 APR 94 |
70 pages |
| Authors:
Sherif M. Botros; Alper K. Caglayan; Greg L. Zacharias; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| Based on the simulations performed in this phase I study, we show that Hopfield and RBF feedfoward network architectures may have a great potential in the control of nonlinear systems. In particular, Hopfield implementation of Lagrange multiplier method is suitable for real-time adaptive optimal control. Similarly, RBF feedforward neural network architectures are suitable for learning inverse dynamics and inverse trim in aircraft FCS applications. In addition, RBF feedfoward are easier ... |
|
| A Neural/Expert Based Client Server Architecture for MITE ITS |
FEB 94 |
50 pages |
| Authors:
J. M. Mazzu; S. M. Botros; A. K. Caglayan; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| A MITE (multi-node, interactive, task-sharing, expert-instruction) system, in general, is responsible for determining task allocation strategies for members of a team who must work together over a computer network to accomplish an overall objective. The MITE system must adapt to changing skill and performance levels of the team members and continually reallocate the tasks to insure optimal team performance. In order to best allocate tasks among team members, the MITE ... |
|
| Active Noise Cancellation Stethoscope. Phase 1 |
15 AUG 93 |
58 pages |
| Authors:
Greg L. Zacharias; Adam X. Miao; James A. Moore; Robert D. Collier; Mehran Asdigha; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| This Phase I study demonstrated the basic feasibility of developing a hybrid active/passive noise canceling stethoscope for rotorcraft aeromedical evacuation use. The hybrid design makes full use of active and passive noise reduction techniques, and incorporates: (1) primary and reference stethoscopes to pickup the relevant patient sounds and to measure the surrounding ambient noise environment; (2) a hybrid noise canceling headset used by the medic to listen to the transduced ... |
|
| Design for Tactical Situation Awareness Display |
15 JUN 92 |
93 pages |
| Authors:
Greg L. Zacharias; Paul G. Gonsalves; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| Because of continuing advances in on-board sensors, computers, and displays, we can expect to see significant growth in the amount of information presented to rotorcraft crews by next-generation tactical situation displays. If unchecked, this growth will easily exceed the crew's capability for dealing with the available on-board information base in a timely and effective fashion. A range of technologies are now being proposed to provide appropriate levels of information management ... |
|
| An Alternative Concept for Aeroassisted Orbit Transfers |
AUG 91 |
77 pages |
| Authors:
Paul G. Gonsalves; Scott M. Allen; Alper K. Caglayan; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| The primary results of this study are identification of possible new applications of aeroassisted orbital transfers to LightSat/TacSats and the feasibility evaluation of an on-line neural network implementation of an atmospheric trajectory/guidance scheme. AOT scenarios involve 2 distinct categories: on-orbit multiple-pass 'soft maneuvers' and the single-pass deep penetration into the atmosphere 'hard maneuver'. Due to propellant limitations, the soft maneuver is very conducive to address LightSat/TacSat orbital transfer requirements. Possible ... |
|
| An Expert System Approach to Global Fault Detection and Isolation Design |
JAN 90 |
50 pages |
| Authors:
S. M. Allen; A. K. Caglayan; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| The primary objective of this research is the development and demonstration of a global Failure Detection and Identification (FDI) Design Assistant (DA) prototype based on expert system technology. A global FDI algorithm performs its detection, isolation and estimation function by assessing the global effects of a hardware fault and surface damage on the closed-loop aircraft dynamics. Since changes in the flight control law affect the signature of a hardware fault ... |
|
| Model-Based Method for Terrain-Following Display Design |
15 JUN 89 |
124 pages |
| Authors:
Paul G. Gonsalves; Edward W. Kneller; Greg L. Zacharias; Ralph J. St John; Bradley D. Purvis; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| A model-based method for terrain-following display design and evaluation is described. The basic approach centers on the use of a pilot/ vehicle/display model based on the optimal control model (OCM), which combines general knowledge of human perception and performance, with specific knowledge of terrain-following aircraft and avionics capabilities. A real-time terrain- following simulation facility was developed, implemented, and exercised to provide an experimental basis for validating model-based display designs, and ... |
|
| Hierarchical Damage Tolerant Controllers for Smart Structures |
MAR 89 |
68 pages |
| Authors:
A. K. Caglayan; S. M. Allen; S. J. Edwards; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| This report summarizes the research and developement results of the SBIR Phase I study entitled Hierarchical Damage Tolerant Controllers for Smart Structures supported by U.S. Air Force under Contract No. F33615-88-C-3212. The major aim of this study is the investigation and definition of a baseline architecture for a smart aerospace structure which can detect and isolate structural damage in real-time and provide on-line reconfiguration of the structure's control system under ... |
|
| Modular Affective Reasoning-Based Versatile Introspective Architecture (MARVIN) |
|
32 pages |
| Authors:
Scott N Reilly; Sean Guarino; Mike Reposa; CHARLES RIVER ANALYTICS INC CAMBRIDGE MA
|
| Report developed under SBIR Contract for Topic #SB072-009. In this Phase I study, we demonstrated that affect-inspired, self-aware mechanisms can significantly improve the performance of computational systems in cases of limited resources. We designed four affect-inspired adaptation mechanisms and argue that all of these mechanisms have the ability to positively impact the performance of various types of computational systems. We developed a MINIX-based implementation of an affective attention and resource ... |
|
Reports by Corporate Author
