Back to professors

Mechanical Engineering

Sasha Davydov

Assistant Professor

Member, Ken Kennedy Institute

Dr. Davydov's research is on modern data-driven engineering problems at the intersection of control, machine learning, and optimization. He is broadly interested in robust nonlinear control theory and modern machine learning methods to enable the reliable control of complex engineering systems with applications in robotics and autonomous vehicles. His work spans

Public Rice profile source

Average rating

4.1

5 temporary mock ratings

Difficulty

3.1

course-linked average

Courses

4

in seeded sections

Public profile

Biography

Dr. Davydov's research is on modern data-driven engineering problems at the intersection of control, machine learning, and optimization. He is broadly interested in robust nonlinear control theory and modern machine learning methods to enable the reliable control of complex engineering systems with applications in robotics and autonomous vehicles. His work spans

Research areas

Modern data-driven engineering problems at the intersection of control, machine learning, and optimization. Robust nonlinear control theory and modern machine learning methods to enable reliable control of complex engineering systems.

Courses taught

MECH 490

Mech Eng Research Projects

Independent investigation of a specific topic or problem in mechanical engineering. Research under the direction of a selected faculty member. Repeatable for Credit.

Mechanical EngineeringNone1-4 credits
4.17.2hAvila, Raudel, Brake, Matthew, Davydov, Sasha, Dugnani, Roberto, Elliott, Matthew, Fregly, BJ, Ghonasgi, Keya, Ghorbel, Fathi, Higgs, C. Fred, Kong, Yong Lin, Lillehoj, Peter, Moreto, Jose, O'Malley, Marcia, Preston, Daniel, Sanchez, Vanessa, Schaefer, Laura, Tezduyar, Tayfun, Trevas, David, Wehmeyer, Geoff, Yavas, Denizhan

MECH 609

Learning-Based Control

For several engineering systems, there are no good first-principles approaches for the design of controllers for them. While ad-hoc control strategies may work, we will investigate the potential for machine learning-based approaches. In this course, we will focus on when we can attain theoretical guarantees using learning-based approaches to control. The course will present a selected background in nonlinear control and neural networks and then spend most of the remaining time on neural Lyapunov functions, neural barrier functions, and neural contraction metrics.

Mechanical EngineeringNone3 credits
4.311.8hDavydov, Sasha

MECH 611

Independent Study

Repeatable for Credit.

Mechanical EngineeringNone1-9 credits
3.36.3hAvila, Raudel, Brake, Matthew, Davydov, Sasha, Fregly, BJ, Ghonasgi, Keya, Ghorbel, Fathi, Higgs, C. Fred, Kong, Yong Lin, Lillehoj, Peter, O'Malley, Marcia, Preston, Daniel, Sanchez, Vanessa, Spanos, Pol, Tezduyar, Tayfun, Wehmeyer, Geoff

MECH 800

Research And Thesis

This course is for MS or PhD students working on their thesis research. Repeatable for Credit.

Mechanical EngineeringNone1-15 credits
3.27.4hAvila, Raudel, Brake, Matthew, Davydov, Sasha, Fregly, BJ, Ghonasgi, Keya, Ghorbel, Fathi, Higgs, C. Fred, Kong, Yong Lin, Lillehoj, Peter, O'Malley, Marcia, Preston, Daniel, Sanchez, Vanessa, Schaefer, Laura, Spanos, Pol, Tezduyar, Tayfun, Wehmeyer, Geoff

Recent comments