Papers
1
Total Citations
2
H-Index
1
About
Yannis Salteris is a rising researcher at the intersection of robotics, simulation, and manufacturing, whose work focuses on bridging the gap between digital physics engines and real-world contact-rich assembly tasks. His most-cited paper, "Benchmark of the Physics Engine MuJoCo and Learning-based Parameter Optimization for Contact-rich Assembly Tasks" (2023), introduces a systematic framework for evaluating and tuning the widely-used MuJoCo simulator to better model the complex dynamics of robotic assembly. By combining rigorous benchmarking with learning-based parameter optimization, Salteris demonstrates how simulation fidelity can be improved for tasks requiring precise physical interaction, such as peg-in-hole insertions and part mating. This work is foundational for researchers seeking to use simulation not just for visualization, but for reliable policy learning and robot training. Though early in his career, with his top paper already garnering 2 citations, Salteris is establishing a reputation for methodical, impactful work that directly addresses the simulation-to-reality gap—a critical challenge in modern robotics and automated manufacturing. His contributions are paving the way for more robust, data-efficient robot learning in industrial settings.
Research Focus
Key Achievements
Top Papers
- 1