A team from Carnegie Mellon University's Robotics Institute and Sensible Machines has developed a small unmanned aerial system designed for assisting fire-fighting inside navy ships.
In a demonstration aboard a former U.S. Navy ship, the quadrotor, developed by the researchers and spin-off company Sensible Machines, flew autonomously through dark, smoke-filled compartments to map fires and locate victims.
Last fall’s demonstration, part of an Office of Naval Research (ONR) project called Damage Control Technologies for the 21st Century (DC-21), showed that a small drone can operate in the confined spaces inside a ship to rapidly gather situational information to guide firefighting and rescue efforts.
As part of the DC-21 concept, information gathered by the micro-flyer would be relayed to a large humanoid robot, the Shipboard Autonomous Firefighting Robot (SAFFiR), which would work with human firefighters to suppress fires and evacuate casualties.
“Flying autonomously through narrow doorways in darkness and smoke poses a number of technical challenges for these small drones,” says Sebastian Scherer, systems scientist at CMU’s Robotics Institute. “But this capability, known as ‘fast lightweight autonomy,’ will have numerous applications beyond shipboard fires, such as investigation of building fires and inspection of hazardous chemical tanks and power plant cooling towers.”
The challenges begin with the size of the drones, says the CMI institute. To fit through the 26-inch-wide hatches of the ex-USS Shadwell – a ship in Mobile, Ala., used to test firefighting techniques – Sensible Machines built a quadrotor just 23 inches wide and 12 inches high.
The drone was able to negotiate the tight spaces, but its smaller rotors reduced its efficiency, limiting flight time to about five minutes. Sensible Machines is now building a drone that is 16 inches wide with two larger, counter-rotating propellers. Scherer says the larger rotors work more efficiently and are anticipated to boost flight time to 30 minutes.
The primary sensor used by the drone to build its map of fire areas is a RGB-D camera, or depth camera, similar to that of a Kinect game controller. Because there’s less ambient light to interfere with the infrared light the camera projects, “it actually works better in the dark,” Scherer says.
In addition to the RGB-D camera, the drone uses a forward-looking infrared (FLIR) camera to detect fires and people and a downward-facing optical flow camera to monitor the motion of the drone itself.
The work for ONR was supported by a Small Business Innovation Research grant to Sensible Machines for which the Robotics Institute is a subcontractor.
Photo courtesy of ONR