Papers
49
Total Citations
447
H-Index
11
About
Askhat Diveev is a prominent researcher specializing in optimal control theory, evolutionary computation, and autonomous robotics. His work sits at a compelling intersection of classical control engineering and modern machine learning, with a particular focus on developing numerical methods for automatic control system synthesis. Diveev's most significant contribution is the formulation of **synthesized optimal control** — a novel framework for addressing optimal control problems under uncertainty — introduced in his 2020 paper that has already garnered 35 citations. He has been instrumental in advancing symbolic regression techniques, including variational genetic programming and Cartesian genetic programming, as practical tools for automatically generating feedback control laws for mobile and flying robots without human-designed controller structures. His highly cited 2018 study (55 citations) rigorously benchmarked evolutionary algorithms — including genetic algorithms, differential evolution, and particle swarm optimization — for robot trajectory optimization, providing the community with invaluable comparative guidance. Across his portfolio, he has consistently championed machine-made control synthesis as a form of machine learning control, bridging optimization theory with modern AI perspectives. With over 247 cumulative citations and contributions spanning mobile robotics, multi-robot systems, and automated controller design, Diveev's research offers students and practitioners powerful computational tools for tackling complex real-world control challenges.
Research Focus
Key Achievements
Top Papers
- 1
- 2Fundamentals of Synthesized Optimal Control35 citations · 2020
- 3
- 4
- 5
- 6
- 7
- 8
- 9Self-adjusting control for multi robot team by the network operator method14 citations · 2015
- 10Control Synthesis as Machine Learning Control by Symbolic Regression Methods13 citations · 2021