Papers
2
Total Citations
10
H-Index
2
About
Anton Savchenko is a researcher at the forefront of merging machine learning with advanced control theory, focusing on making optimization-based control algorithms more efficient and robust. His work primarily addresses the critical challenge of deploying model predictive control (MPC) in fast-moving applications and low-power edge devices, where computational resources are limited. Savchenko’s major contribution lies in developing a neural horizon MPC framework that leverages feed-forward neural networks to dramatically increase computational efficiency, a breakthrough detailed in his most-cited 2024 paper (6 citations). This approach enables real-time control in scenarios previously deemed too demanding for traditional MPC. Additionally, his 2018 work on robust predictive control for Lur’e systems introduces a set-based learning method to reduce conservatism in handling uncertain nonlinear dynamics, offering a less conservative alternative to worst-case solutions. With a growing citation impact, Savchenko’s research is paving the way for smarter, faster, and more reliable autonomous systems, making him a notable figure in the intersection of control theory and artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2