Achieving human-level reasoning and decision-making for autonomous systems requires agents that are capable of reasoning through large volumes of knowledge. A key element is the ability to resolve conflicts, solve problems, and operate in ambiguous and uncertain situations in the same way as a human expert. To be truly useful, these agents must also be able to interact with humans and other agents in natural ways, communicating in domain-specific languages and explaining their behaviors when required. At Soar Technology, we develop these agents for use in training systems, exploratory experimentation, and for embedded control of unmanned and robotic systems.
The Problem
The military has a rich store of highly immersive flight simulations/simulators, but often only a single aircraft is represented, independent of a realistic operational environment. To add a high-fidelity second aircraft into a simulated exercise, another "full-up" simulator, along with its associated personnel, is required. Often to avoid these costs, simulation fidelity is sacrificed by using low-cost desktop simulations that do not provide the precision and accuracy necessary in modern simulated warfighting exercises.
The Solution: Knowledge-Rich Intelligent AgentsSoar Technology's TacAir-Soar offers fully autonomous synthetic forces with high-fidelity, realistic behaviors for a wide range of aircraft and missions. Users of TacAir-Soar realize direct cost savings due to reduced manpower requirements for training exercises or experiments.
TacAir-Soar entities are not limited to performing their prebriefed missions or following a script. They coordinate their actions through shared goals, planning and explicit communication. Even though each entity is autonomous, it does not act in isolation. Individual entities coordinate their actions using existing doctrine and C4I systems. As the mission develops, entities may change roles dynamically.
The key to simulation is believability, and the behaviors of TacAir-Soar entities are more realistic than any currently available system not controlled by a human. Because TacAir-Soar is based on a model of human cognition, it not only creates reasonable behaviors, but also chooses actions and makes decisions for similar reasons that a human would. TacAir-Soar’s knowledge base consists of over 7500 rules, making it among the largest fielded expert systems.
[ Read more about TacAir-Soar
. ]
©2008 Soar Technology, Inc. All rights reserved
Legal Notice | Site Map
- Tutorials
- Projects
- Publications
- Scientists
- Links
Intro to Cognitive Arch. Slides - IITSEC 2004