Biomimetic Algorithms for System Optimization
Jason Lohn
Director, Carnegie Mellon Innovations Laboratory
Friday, March 21, 2014
Abstract -- Nature-inspired Algorithms for System Optimization
Current methods of designing and optimizing antennas by hand are time and labor intensive, limit complexity, and require significant expertise and experience. Nature-inspired, evolutionary design techniques can overcome these limitations by searching the design space and automatically finding effective solutions that would ordinarily not be found. In this talk, we present automated antenna design and optimization methods based on evolutionary algorithms. We present evolved antennas for a variety of aerospace applications, focusing on a project that produced antennas that flew on NASA’s Space Technology 5 (ST5) mission. We discuss the software tools we developed to automate the design of these evolved antennas which are the first ever artificially-evolved objects to fly in space.
Biography
Dr. Jason Lohn is an Associate Research Professor in Electrical and Computer Engineering at Carnegie Mellon University. He has worked at Google, NASA Ames Research Center, Stanford University, and IBM Corporation. He received his M.S. and Ph.D. in Electrical Engineering from the University of Maryland at College Park and his B.S. in Electrical Engineering from Lehigh University. He leads research in Evolvable Systems at Carnegie Mellon and NASA Ames and is closely affiliated with the growing field called evolvable hardware -- the study of how stochastic search algorithms can be used to design and configure electronic and mechanical hardware. He co-founded and chaired a series of successful NASA/DoD evolvable hardware workshops and conferences. He led a team of scientists and engineers to successfully evolve, develop and fly three evolved X-band antennas in space aboard NASA's Space Technology 5 mission in 2006.
He has co-founded a Silicon Valley startup company called X5 Systems to commercialize his work on advanced antenna synthesis and optimization algorithms. Dr. Lohn is a member of the IEEE, ACM, Sigma Xi, and Phi Kappa Phi. He has over 50 technical publications and has made contributions in automated hardware design, self-replicating systems, parallel processing, and neural networks. Dr. Lohn serves as an Associate Editor of IEEE Transactions on Evolutionary Computation.
Read more about him at: http://www.cmu.edu/silicon-valley/faculty-staff/lohn-jason.html