Pyry Matikainen
Papers
2
Total Citations
43
H-Index
2
About
Pyry Matikainen’s research lies at the intersection of robotics, computer vision, and machine learning, with a focus on robust perception and intelligent decision-making for autonomous systems. His most-cited work, “Sensor fusion for fiducial tags” (2017, 25 citations), addresses a critical challenge in robotics: achieving highly accurate pose estimation from single-frame RGBD data despite sensor noise. By fusing visual and depth information, Matikainen advanced the reliability of planar fiducial markers—a cornerstone technology for augmented reality and robot localization. In his earlier influential paper, “Multi-armed recommendation bandits for selecting state machine policies for robotic systems” (2013, 18 citations), he pioneered a novel approach to policy selection, treating the problem as a multi-armed bandit to efficiently choose control policies when evaluation is costly. This work demonstrated how reinforcement learning principles can optimize robot behavior in real-world tasks, such as simulated vacuuming. Matikainen’s contributions are notable for bridging theoretical frameworks with practical robotic challenges, offering scalable solutions that improve both perception accuracy and adaptive control. His research continues to inspire work in sensor fusion and learning-based policy selection for autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2