Konstantinos Tziortziotis
Papers
1
Total Citations
3
H-Index
1
About
Konstantinos Tziortziotis is a researcher at the forefront of intelligent control and autonomous navigation for marine robotics. His work focuses on developing advanced motion planning algorithms that enable floating robotic platforms to operate efficiently under real-world constraints, including environmental disturbances and sensor noise. Tziortziotis’s key contributions lie in the application of reinforcement learning to over-actuated systems—platforms with more control inputs than degrees of freedom—where he has pioneered methods for energy reduction during navigation in unknown environments. His highly cited 2018 paper introduces an online least-squares policy iteration scheme for value function approximation, a technique that allows robots to learn optimal, energy-efficient paths in real time despite measurement uncertainty. This work has garnered significant attention for its practical implications in autonomous marine operations, from environmental monitoring to offshore infrastructure inspection. Tziortziotis’s research bridges the gap between theoretical reinforcement learning and real-world robotic deployment, offering scalable solutions for complex, dynamic maritime settings. His achievements underscore a commitment to developing resilient, adaptive systems that push the boundaries of autonomous navigation under uncertainty.
Research Focus
Key Achievements
Top Papers
- 1