Carl Folkestad

California Institute of Technology

Papers

4

Total Citations

74

H-Index

3

About

Carl Folkestad is a leading researcher at the intersection of data-driven control, nonlinear dynamics, and safety-critical autonomy. His work centers on leveraging Koopman operator theory to transform complex, nonlinear robotic systems into tractable, high-dimensional linear or bilinear models—enabling real-time optimal and safe control. Folkestad’s major contributions include pioneering the synthesis of Control Barrier Functions (CBFs) with Koopman operators for safety-critical control, a breakthrough that guarantees system safety without the computational burden of traditional invariant set computation. His highly cited 2020 paper on this topic (36 citations) has become a foundational reference in the field. He further advanced the state of the art with KoopNet (2022, 32 citations), which jointly learns Koopman bilinear models and function dictionaries, demonstrating exceptional performance in quadrotor trajectory tracking. Folkestad’s work on Koopman-based Nonlinear Model Predictive Control (NMPC) and episodic Koopman learning for fast multirotor landing showcases his ability to bridge theory and practice, enabling agile, safe, and efficient autonomous systems. His research is widely recognized for making Koopman methods practical for real-world robotic applications.

Research Focus

Key Achievements

3
H-Index
4
Papers
74
Total Citations
19
Avg Citations/Paper
🏆 Most Cited Paper
Data-Driven Safety-Critical Control: Synthesizing Control Barrier Functions With Koopman Operators
36 citations · 2020
📈 Most Prolific Year: 2020 (2 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: California Institute of Technology

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago