We build intelligent agents that make explainable and autonomous decisions. These agents can help the Warfighter in multiple ways, such as
- Creating novel courses of action. We can generate likely adversary reactions to friendly actions, compare courses of action and determine which is best, and explain the reasoning behind decisions.
- Training Warfighters in simulated environments. Training in simulation allows for a breadth of experience not possible with live training, and populating simulations with intelligent agents allows training to be done inexpensively because other humans need not be directly involved.
- Performing temporal scene understanding. Contemporary computer vision algorithms can identify objects, and relationships, but they can’t understand what is happening because they don’t have the concepts to map them to. We build those concepts and can recognize them in sensor data.
- Giving intelligence to robots. Now that robots can do simple actions, they need concepts to put together smart sequences of actions for intelligent behavior.