Atta Oveisi
Papers
2
Total Citations
10
H-Index
2
About
Atta Oveisi is a researcher whose work bridges system identification, control theory, and robotics, with a particular focus on advancing the reliability and efficiency of complex dynamical systems. His key research areas include optimal experiment design for multi-input multi-output (MIMO) systems, nonparametric uncertainty quantification, and deep reinforcement learning for robotic control. Oveisi’s most cited work, "Optimal Input Excitation Design for Nonparametric Uncertainty Quantification of Multi-Input Multi-Output Systems" (2018, 8 citations), provides critical insight into how input signal design impacts the accuracy of frequency-domain modeling, specifically for obtaining the best linear approximation (BLA) of MIMO systems—a foundational contribution for engineers seeking robust system identification. In a more recent study, "Exploring reward shaping in discrete and continuous action spaces: A deep reinforcement learning study on Turtlebot3" (2024, 2 citations), he demonstrates practical applications of reinforcement learning in robotics, investigating how reward function design can guide autonomous agents to optimal solutions in complex environments. While his citation counts reflect a growing influence, Oveisi’s work is notable for its methodological rigor and direct relevance to real-world control challenges, making him a promising voice in the intersection of theoretical system analysis and applied robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2