Extending HLSR to Support Scaling Up to Complex Models for Training, Simulation, and Robotics Navy SBIR FY2009.1 Sol No.: Navy SBIR FY2009.1 Topic No.: N091-086 Topic Title: Extending HLSR to Support Scaling Up to Complex Models for Training, Simulation, and Robotics Proposal No.: N091-086-0451 Firm: Soar Technology, Inc. 3600 Green Court Suite 600 Ann Arbor, Michigan 48105-2588 Contact: Randolph Jones Phone: (207) 649-1895 Web Site: www.soartech.com Abstract: A long-term, cost-effective approach to addressing increased mission complexity and cost is to increase automation in operations and training. Although a variety of automation exists, the next significant advance will be to automate decision-making processes that currently rely on human experts. Such experts take years to train and are only available for a limited time, whereas intelligent software systems can be copied without limit, and they do not age or retire. Although now technically feasible to build intelligent decision-making systems, it remains expensive and difficult to engineer them, as well as to carry out the necessary supporting research into psychological modeling. However, High-level languages for software engineering have proven extremely effective at reducing costs for the development of complex software. Soar Technology, Inc. proposes to bring similar effectiveness to decision-making system engineering, reducing the cost of development and maintenance by 4-5 times. We will accomplish this by extending an existing HLSR language and compiler with knowledge patterns for building increasingly complex and human-like models. While this effort will primarily payoff for engineered systems, we argue that it also will improve the cost effectiveness and scientific consistency of cognitive modeling research. Benefits: Soar Technology commits to releasing as the extended HLSR language specification and compiler produced under this SBIR as open source under a liberal license such as the well-known BSD license used for distribution of the Soar Kernel. In general, engineer tools do not have a large market and tools for building behavior models have only a small fraction of the overall engineering tools market. Therefore, our goal is to use HLSR to increase the size and viability of this market by making it much easier to create human behavior models. Given increased market size, other activities within this market are possible including sales of development tools and add-ons as well as increased sales of human behavior models themselves. The human behavior model market currently consists of simulation, games, and robotics. Most simulations and games use some sort of autonomous or semi-autonomous entities to help fill and expand the environment used to train or entertain the user. This has the twofold advantage of allowing the environment creator to create entities that behave in ways they can control as well as reducing manpower required to run a simulation event or game session. The gaming market is estimated to grow to roughly $50 billion by 2010 with games becoming more and more sophisticated and demanding more and more complex enties. The simulation and training market is similarly sized in the tens of billions of dollars. The robotics market is currently in its infancy. While robots currently do not use behavior models as sophisticated as a TAS model, advances in the lower level sensing and control modules of these robots (e.g., the DARPA grand challege) are providing the foundations for higher-level decision models. Soar Technology has participated recently in government funded efforts to introduce higher level decision making into robotic teams and we believe the future for this type of behavior model provides a significant growing market that we are poised through the development of development tools such as HLSR. Return