Seminar: High-performance Autonomous Vehicles and Systems

Autonomous vehicles hold the potential for tremendous societal impact. However, substantial societal and economic barriers remain before their widespread adoption.  For instance, for societal acceptance, they must guarantee safety; and for economic viability, they must deliver high performance. In this talk, we present planning and control algorithms for autonomous vehicles, both at the vehicle level and at the systems level, that guarantee high performance. At the vehicle level, we introduce novel algorithms for agile mobility. The new algorithms construct arbitrarily good solutions for stochastic optimal control problems using compressed computation algorithms. The running time of the new algorithms scales polynomially with dimension and the rank of the optimal cost-to-go function. We demonstrate the new algorithms on various problems, including the agile maneuvering of a micro aerial vehicle. At the systems level, we present coordination algorithms for two problems. First, we consider a fleet of autonomous vehicles passing through an intersection. The new algorithms extend existing algorithms for management of data networks to systems with dynamics, and they provide provable guarantees on performance and safety. Second, we consider a system of trucks that aim to save energy via platooning. We study the energy-delay tradeoffs. We show that open-loop policies perform almost as good as feedback policies for scheduling.

About the Speaker

Sertac Karaman is the Class of '48 Career Development Chair Associate Professor of Aeronautics and Astronautics at the Massachusetts Institute of Technology. He has obtained B.S. degrees in mechanical engineering and in computer engineering from the Istanbul Technical University, Turkey, in 2007; an S.M. degree in mechanical engineering from MIT in 2009; and a Ph.D. degree in electrical engineering and computer science also from MIT in 2012. His research interests lie in the broad areas of robotics and control theory. In particular, he studies the applications of probability theory, stochastic processes, stochastic geometry, formal methods, and optimization for the design and analysis of high-performance cyber-physical systems. The application areas of his research include driverless cars, unmanned aerial vehicles, distributed aerial surveillance systems, air traffic control, certification and verification of control systems software, and many others. He is the recipient of an Army Research Office Young Investigator Award in 2015, National Science Foundation Faculty Career Development (CAREER) Award in 2014, AIAA Wright Brothers Graduate Award in 2012, and an NVIDIA Fellowship in 2011.

Hosted by Professor Levent Guvenc.