Archive

“Role-Based Reward Decomposition for Legged Locomotion Reinforcement Learning” (with Panos Trahanias) has been accepted at IEEE/RSJ IROS 2026 — partitioning locomotion rewards by stance and swing roles stabilizes multi-objective learning, validated on a real Unitree Go2 and extended to the G1 biped. I will present it at the conference this September.

Our extended journal account of the RAICAM doctoral network’s research sprints and field demonstrations is now out in Robotics and Autonomous Systems, vol. 203.

“Sim-to-Real Reinforcement Learning for Ball-Balancing Locomotion on Quadruped Robots” (with Hamidreza Raei, Arash Ajoudani, and Panos Trahanias) was presented at the IEEE/ASME International Conference on Advanced Intelligent Mechatronics in Genova — a Unitree Go2 walks while keeping a ball balanced on a plate on its back.

“AgiPIX: Bridging Simulation and Reality in Indoor Aerial Inspection” (led by Sasanka Kuruppu Arachchige) was presented at the 2026 International Conference on Unmanned Aircraft Systems.

Our low-cost air–ground robotic team for nuclear power plant inspection — built in three weeks and field-tested at the EnRicH 2025 trials in AKW Zwentendorf — was presented at IEEE SSRR 2025, with a full open-source release.

“Manipulate as Human: Learning Task-oriented Manipulation Skills by Adversarial Motion Priors” (with Ziqi Ma and Yue Gao) is out in Robotica, vol. 43, no. 6.

“Optimal Torque Distribution via Dynamic Adaptation for Quadrupedal Locomotion on Slippery Terrains” (with Despina-Ekaterini Argiropoulos, Michael Maravgakis, Dimitrios Papageorgiou, and Panos Trahanias) was presented at IEEE ICRA 2025.

“Learning Capability to Enhance Locomotion Control and Planning for Legged Robots” (with Yue Gao and Yang Zhang) appeared at the 2024 IEEE International Conference on Real-time Computing and Robotics (RCAR).

I am serving as a teaching assistant in the Department of Computer Science at the University of Crete.

I joined the Computer Vision and Robotics Laboratory at FORTH (Heraklion, Greece) as a PhD fellow of the Marie Skłodowska-Curie Actions RAICAM network, continuing my research on legged robots.

“Manipulate as Human: Learning Task-oriented Manipulation Skills by Adversarial Motion Priors” (with Ziqi Ma and Yue Gao) was submitted to IEEE ICRA 2024.

“Learning Capability to Enhance Locomotion Control and Planning for Legged Robots” (with Yue Gao) was submitted to the IEEE Robotics & Automation Magazine.

Our paper “CapPlanner: Adaptable to Various Topology and Locomotion Capability for Hexapod Robots” was selected as a finalist for the Best Paper in Biomimetics award at IEEE ROBIO 2022.

The skating and skiing robots we built and field-tested at real winter resorts were part of the Beijing 2022 Winter Olympics torch relay activities.