Harnessing Complexity

Robots can learn to recognize objects and patterns fairly well, but to interpret and be able to act on visual input is much more difficult.  Researchers at the University of Maryland, funded by DARPA’s Mathematics of Sensing, Exploitation and Execution (MSEE) program, recently developed a system that enabled robots to process visual data from a series of “how to” cooking videos on YouTube. Based on what was shown on a video, robots were able to recognize, grab and manipulate the correct kitchen utensil or object and perform the demonstrated task with high accuracy—without additional human input or programming.  

Dr. Reza Ghanadan joined DARPA in 2013 as a program manager in the Defense Sciences Office. He has interests in data analytics, autonomy, machine learning and artificial intelligence in information and cyber-physical systems. At DARPA, he has been investigating the mathematical foundations and applications of these technologies to complex science and engineering problems, ranging from precision genomics and neuroscience, to robotics and human-machine collaboration.