Indian-American computer scientist Ashutosh Saxena and his team at Cornell University have created a flying robot as smart as any bird, with a tremendous potential in search-and-rescue operations, they said.
Designed by Saxena, assistant professor at Cornell, the flying robot, the size of a card table is able to guide itself through forests, tunnels or damaged buildings. The toughest part is keeping the object from slamming into walls and tree branches.
Human controllers can't always react swiftly enough and the radio signals may not reach everywhere the robot goes, according to a Cornell statement. So, Saxena, who did his B.Tech. in 2004 from the Indian Institute of Technology (IIT) Kanpur, in a bid to overcome these limitations is building on methods he previously had developed to turn a flat video camera image into a 3-D model. He used 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.
The flying robot was tested in 53 autonomous flights in obstacle-rich environments -- including Cornell's Arts Quad -- succeeding in 51 cases, failing twice because of winds. The test vehicle is a quadrotor, a commercially available flying machine about the size of a card table with four helicopter rotors. Graduate students Ian Lenz and Mevlana Gemici trained the robot with 3-D pictures of such obstacles as tree branches, poles, fences and buildings. The robot's computer learns the characteristics all the images have in common, such as colour, shape and texture.
The resulting set of rules for deciding what is an obstacle is burned into a chip before the robot flies. In flight, the robot breaks the current 3-D image of its environment into small chunks 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. Saxena plans to improve the robot's ability to respond to environment variations such as winds and enable it to detect and avoid moving objects, like real birds. The results were presented at the International Conference on Intelligent Robots and Systems in Portugal during early October.
Ashutosh Saxena is an Assistant Professor in Computer Science Department at Cornell University. His research interests include machine learning and robotics perception, especially in the domain of personal robotics. He received his MS in 2006 and Ph.D. in 2009 from Stanford University, and his B.Tech. in 2004 from Indian Institute of Technology (IIT) Kanpur. He was a recipient of National Talent Scholar award in India and Google Faculty award in 2011. He was also named a Alfred P. Sloan Research Fellow in 2011 and a Microsoft Faculty Fellow in 2012. Ashutosh has developed Make3D (http://make3d.cs.cornell.edu), an algorithm that converts a single photograph into a 3D model. Tens of thousands of users used this technology to convert their pictures to 3D. He has also developed algorithms that enable robots (such as STAIR, POLAR, see http://pr.cs.cornell.edu) to perform household chores such as unload items from a dishwasher, place items in a fridge, etc. His work has received substantial amount of attention in popular press, including the front-page of New York Times, BBC, ABC, New Scientist, Discovery Science, and Wired Magazine. He has won best paper awards in 3DRR and IEEE ACE, and was named a co-chair of the IEEE technical committee on robot learning.