Papers
6
Total Citations
32
H-Index
4
About
Igor Boiko is a researcher whose work bridges control theory, robotics, and reinforcement learning. His key research areas include sliding-mode control, PID autotuning, and reinforcement learning for robotic systems. Boiko has made significant contributions to the development of autotuning mechanisms for robotic manipulators, introducing a method that combines modified relay feedback tests with optimization under uncertainty principles to streamline PID controller tuning. His work on generating periodic motion in underactuated systems through continuous and second-order sliding-mode algorithms has been foundational, with his 2006 papers on output excitation via sliding-modes receiving 7 and 5 citations respectively. Boiko has also advanced reinforcement learning applications, proposing fuzzy ensembles of RL policies for systems with variable parameters and exploring sim-to-real transfer for UAV navigation. His most cited work, a 2023 paper on PID autotuning for robotic manipulators, has garnered 11 citations, reflecting the practical impact of his research. Boiko's contributions are particularly notable for their focus on bridging theoretical control methods with real-world robotic applications, making his work valuable for both researchers and practitioners in robotics and automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Learning to Navigate Through Reinforcement Across the Sim2Real Gap3 citations · 2022
- 6Learning to Navigate Through Reinforcement Across the Sim2Real Gap2 citations · 2022