Silvia Ferrari

Silvia Ferrari

Adjunct Professor in the Department of Mechanical Engineering and Materials Science

Professor Ferrari's research aims at providing intelligent control systems with a higher degree of mathematical structure to guide their application and improve reliability. Decision-making processes are automated based on concepts drawn from control theory and the life sciences. Recent efforts have focused on the development of reconfigurable controllers implementing neural networks with procedural long-term memories. Full-scale simulations show that these controllers are capable of learning from new and unmodeled aircraft dynamics in real time, improving performance and even preventing loss of control in the event of control failures, nonlinear and near-stall dynamics, and parameter variations. New optimal control problems and methods based on computational geometry are being investigated to improve the effectiveness of integrated surveillance systems by networks of autonomous vehicles, such as, underwater gliders and ground robots.

Appointments and Affiliations

  • Adjunct Professor in the Department of Mechanical Engineering and Materials Science
  • Faculty Network Member of the Duke Institute for Brain Sciences

Contact Information

  • Office Location: 144 Hudson Hall, Box 90300, Durham, NC 27708
  • Email Address: silvia.ferrari@duke.edu

Education

  • Ph.D. Princeton University, 2002
  • M.A. Princeton University, 1999
  • B.S. Embry-Riddle Aeronautical University, 1997

Research Interests

Design and analysis of methods and algorithms for learning and computational intelligence. Theory and approximation properties of network models, such as neural and probabilistic networks, for the purpose of enhancing their learning abilities and improving reliability. Approximate dynamic programming and optimal control techniques, with applications in adaptive flight control and mobile sensor networks. Application of expert systems and systems theory to psychological and cognitive modeling from data.

Specialties

neural networks
Bayesian networks
Controls
Smart Technology

Courses Taught

  • ME 392: Undergraduate Projects in Mechanical Engineering
  • ME 492: Special Projects in Mechanical Engineering
  • ME 759: Special Readings in Mechanical Engineering

In the News

Representative Publications

  • Rudd, K; Foderaro, G; Zhu, P; Ferrari, S, A Generalized Reduced Gradient Method for the Optimal Control of Very-Large-Scale Robotic Systems, IEEE Transactions on Robotics, vol 33 no. 5 (2017), pp. 1226-1232 [10.1109/TRO.2017.2686439] [abs].
  • Oh-Descher, H; Beck, JM; Ferrari, S; Sommer, MA; Egner, T, Probabilistic inference under time pressure leads to a cortical-to-subcortical shift in decision evidence integration., NeuroImage, vol 162 (2017), pp. 138-150 [10.1016/j.neuroimage.2017.08.069] [abs].
  • Gemerek, JR; Ferrari, S; Albertson, JD, Fugitive gas emission rate estimation using multiple heterogeneous mobile sensors, ISOEN 2017 - ISOCS/IEEE International Symposium on Olfaction and Electronic Nose, Proceedings (2017) [10.1109/ISOEN.2017.7968897] [abs].
  • Clawson, TS; Fuller, SB; Wood, RJ; Ferrari, S, A blade element approach to modeling aerodynamic flight of an insect-scale robot, Proceedings of the American Control Conference (2017), pp. 2843-2849 [10.23919/ACC.2017.7963382] [abs].
  • Foderaro, G; Swingler, A; Ferrari, S, A Model-Based Approach to Optimizing Ms. Pac-Man Game Strategies in Real Time, IEEE Transactions on Computational Intelligence and AI in Games, vol 9 no. 2 (2017), pp. 153-165 [10.1109/TCIAIG.2016.2523508] [abs].