Computer scientists at Cornell University say such a device, able to guide itself through forests, tunnels or damaged buildings, could have tremendous value in search-and-rescue operations.
The researchers' test vehicle is a quadrotor, a commercially available flying machine about the size of a card table with four helicopter rotors.
Computer science Professor Ashutosh Saxena have equipped it with 3-D cameras to create a model of the vehicle's environment using such cues as converging straight lines, the apparent size of familiar objects and what objects are in front of or behind each other -- the same cues humans unconsciously use to supplement their stereoscopic vision.
In flight the robot splits the 3-D image of its environment into small segments based on obvious boundaries, decides which ones are obstacles and computes a path through them as close as possible to the route it has been told to follow, the researchers said.
Saxena said he hopes to improve the robot's ability to respond to environment variations such as winds and enable it to detect and avoid moving objects such as real birds, a Cornell release reported.