Ioannis Ch. Paschalidis
Papers
9
Total Citations
77
H-Index
5
About
Ioannis Ch. Paschalidis is a leading researcher at the intersection of robotics, control theory, and machine learning, with a primary focus on developing intelligent decision-making algorithms for autonomous systems operating under uncertainty. His most significant contributions lie in the application of reinforcement learning—particularly actor-critic methods—to robot motion control and temporal logic specifications. His seminal 2015 paper, "Temporal logic motion control using actor–critic methods" (30 citations), pioneered a framework for deploying robots that must satisfy complex, high-level task specifications while navigating noisy environments with imperfect sensors and actuators. This work, alongside his 2018 study on learning policies for Markov Decision Processes from data (17 citations), has been instrumental in bridging the gap between formal verification and data-driven control. Paschalidis has also explored practical applications in healthcare, developing posture detection methods using wireless body area networks (5 citations). His research on distributed actor-critic methods for sensor network coverage (2007) further demonstrates his versatility in multi-agent systems. With a career spanning foundational theory and real-world deployment, Paschalidis continues to shape how robots learn and act reliably in uncertain, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1Temporal logic motion control using actor–critic methods30 citations · 2015
- 2Learning Policies for Markov Decision Processes From Data17 citations · 2018
- 3Temporal logic motion control using actor-critic methods7 citations · 2012
- 4
- 5Posture detection with body area networks5 citations · 2011
- 6
- 7
- 8Formation Detection with Wireless Sensor Networks2 citations · 2014
- 9