The University of Texas at Dallas

Erik Jonsson School of Engineering and Computer Science

Content

Safe Autonomy with Deep Learning in Feedback Loop

 George J. Pappas

Safe Autonomy with Deep Learning in Feedback Loop
11:00 a.m., Friday, Jan. 24
TI Auditorium (ECSS 2.102)

Dr. George J. Pappas
University of Pennsylvania

ABSTRACT: Deep learning is an integral part of computer vision and perception and is now one of the main sensing modalities in autonomous robots, including driverless cars. The recent success of deep reinforcement learning in chess or AlphaGo suggests that robot planning control will soon be performed by deep learning in a model free manner, disrupting traditional model-based engineering design. However, recent crashes in driverless cars as well as adversarial attacks in deep networks has exposed the brittleness of deep learning perception which then leads to catastrophic decisions.

In this talk, we will show our approach in ensuring the robustness and safety of autonomous robots that use deep learning as a sensor in the control loop. Using ideas from robust control, we develop tools to analyze the robustness of deep networks that ensure that the perception of the environment is more accurate. Most importantly, we must quantify the uncertainty of correct classification of semantic objects in the environment. Autonomous mapping, planning and control needs to be embraced because it will mitigate the uncertainty caused by deep learning in the feedback loop, leading to autonomous robots that operate safely in unknown but learned environments.

BIOGRAPHY: Dr. George J. Pappas is the UPS Foundation Professor and Chair of the Department of Electrical and Systems Engineering at the University of Pennsylvania. He also holds a secondary appointment in the Departments of Computer and Information Sciences, and Mechanical Engineering and Applied Mechanics. Pappas is member of the GRASP Lab and the PRECISE Center and has previously served as the Deputy Dean for Research in the School of Engineering and Applied Science. His research focuses on control theory including hybrid systems, embedded systems, hierarchical and distributed control systems, with applications to unmanned aerial vehicles, distributed robotics, green buildings and biomolecular networks. He is a Fellow of IEEE and IFAC and has received several awards including the Antonio Ruberti Young Researcher Prize, the George S. Axelby Award, the O. Hugo Schuck Best Paper Award, the National Science Foundation PECASE and the George H. Heilmeier Faculty Excellence Award.

Footer

Departments