Aitor Aguirre-Ortuzar
Papers
2
Total Citations
4
H-Index
1
About
Aitor Aguirre-Ortuzar is a researcher at the forefront of intelligent automation and human-machine interaction, with a focus on making complex systems more adaptive and user-friendly. His work centers on automated diagnosis and procedural learning in industrial environments, where he develops frameworks that enable machines to understand and improve their own operations. His most cited paper, "ADAPT: an Automatic Diagnosis of Activity and Processes in auTomation environments" (2020), introduces a system that leverages sensor and actuator data to diagnose processes in real time, with applications in staff training and operational efficiency. Building on this, his recent work "Novel automated interactive reinforcement learning framework with a constraint-based supervisor for procedural tasks" (2024) tackles the challenge of teaching robots complex motion tasks without the need for painstakingly engineered reward functions. By integrating a constraint-based supervisor, this framework makes reinforcement learning more practical for unstructured environments. Though early in his career, with citations steadily growing, Aguirre-Ortuzar’s contributions are laying the groundwork for more intuitive, autonomous systems that can learn from human interaction—a critical step toward the factories and robots of the future.
Research Focus
Key Achievements
Top Papers
- 1
- 2