Published on Apr 2, 2012
Even in peacetime, fires represent one of the greatest risks to the U.S. Naval Fleet.
To this end, the Naval Research Laboratory (NRL), with support from the Office of Naval Research, is conducting research and developing new technologies to enable shoulder-to-shoulder robotic damage control teammates.
The robot in this video is a research platform for testing software for cognitive robotics and human-robot interactions. The knowledge gained from this research will be applied to firefighting robots used on ships.
Through a combination of speech and visual recognition, the robot is able to identify trusted individuals, in this case, the human fire-fighting teammate.
The human is able to provide situational information to the robot by voice and gestural commands. Here, the human partner is telling Octavia the general location of the fire before she enters the compartment.
Using two infrared cameras, Octavia is able to localize the fire, allowing her to target it with the compressed air/water backpack.
Ongoing work is focused on improving the naturalness of the interactions so that the human partners can interact with the robot as if it were another human teammate. Additional work is focused on recognizing and characterizing the type and behavior of the fire so that proper extinguishing techniques can be used.
Navy Center for Applied Research in Artificial Intelligence
Office of Naval Research
For more NRL videos, visit http://www.nrl.navy.mil/media/videos/.
Video Credit: Navy Center for Applied Research in Artificial Intelligence
Standard YouTube License