Mykola Pechenizkiy
Papers
2
Total Citations
4
H-Index
2
About
Mykola Pechenizkiy is a leading researcher in reinforcement learning and human-robot collaboration, with a focus on creating intelligent, adaptive systems for real-world applications. His work bridges the gap between theoretical machine learning and practical robotics, particularly in dynamic and uncertain environments. One of his key contributions is in developing noise-filtering techniques for deep reinforcement learning, as demonstrated in his 2023 paper "Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning," which addresses how robots can selectively focus on relevant information—like a household robot ignoring irrelevant data to complete a task efficiently. This work has already garnered attention with 2 citations in its first year. In 2024, Pechenizkiy extended his impact to logistics with "Learning Efficient and Fair Policies for Uncertainty-Aware Collaborative Human-Robot Order Picking," where he tackles optimization problems in warehouse systems, allocating human pickers to autonomous mobile robots (AMRs) to improve both efficiency and fairness. This research is pivotal for the future of collaborative robotics, ensuring that AI systems not only perform tasks but do so equitably. Pechenizkiy’s work is shaping how robots learn, adapt, and cooperate with humans in complex, noisy, and resource-constrained settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2