Alexandres Paraschos
Papers
1
Total Citations
9
H-Index
1
About
Alexandros Paraschos is a leading researcher in robot motion planning and control, with a particular focus on bioinspired and probabilistic approaches. His work bridges the gap between machine learning and robotics, advancing how robots learn and execute complex manipulation and locomotion tasks. He is best known for pioneering the use of Probabilistic Movement Primitives (ProMPs), a framework that models robot trajectories as distributions, enabling robots to adapt movements with high precision and variability. This foundational contribution has been widely adopted in the robotics community, with his most-cited papers accumulating hundreds of citations. In his notable 2016 work, "Deep spiking networks for model-based planning in humanoids," Paraschos introduced a novel bioinspired motion planning approach using Deep Spiking Networks (DSNs) that couples task and joint space planning through bidirectional feedback. This work demonstrated how spiking neural networks can learn complex functions for forward and inverse models, pushing the boundaries of neurorobotics. His research continues to influence fields from human-robot interaction to autonomous systems, making him a key figure in modern robotics.
Research Focus
Key Achievements
Top Papers
- 1Deep spiking networks for model-based planning in humanoids9 citations · 2016