Robotics and Intelligent Systems
INL is working to develop a new class of robotic systems that can adjust their level of autonomy on the fly, leveraging their own intrinsic intelligence to meet whatever level of control is handed down from the user. These robots operate from a wide variety of platforms - from all-terrain vehicles to submersible robots or even whole colonies or "swarms" of interactive robots, each smaller than a human hand.
The trait common to all these systems is the ability to share initiatively between human and machine, permitting the system to cope with interruptions in communication links, component failures, and changes in operator workload, resources, and mission requirements.
Machine intelligence and adaptation begins with robust real-world sensing. INL is focusing on developing sensor-rich robots and fusion algorithms that enable the robots to fully "experience" and "understand" the environment. INL-engineered robotic systems combine refined sensing capabilities with one or more mechanical means to respond. Examples are the robots' ability to maneuver in difficult environments or to selectively relay critical information to other robots or human controllers.
INL's team has developed several critical advances in the use of Unmanned Aerial and Unmanned Ground Vehicles. One advance is called Robot Intelligence Kernel (RIK), a portable software package that revolutionizes robot capabilities and robot/operator relationships. It gives robots exceptional new levels of autonomy and intelligence. RIK can be applied in national security activities, search and rescue, as well as industrial applications where autonomy or intelligent control are needed but are unsafe for direct human interaction.