Gabriel Urbain
Papers
7
Total Citations
101
H-Index
5
About
Gabriel Urbain is a leading researcher at the intersection of soft robotics, bio-inspired control, and machine learning, with a focus on developing safer, more adaptable legged robots. His work addresses a fundamental challenge: how to design and control compliant, underactuated robots that can operate effectively in human-centered environments. Urbain’s major contributions include pioneering the use of mass–spring networks for optimal locomotion learning, demonstrating how morphological properties can be exploited to simplify control (44 citations). He has advanced the field by combining evolutionary algorithms with adaptive control strategies for quadruped locomotion (17 citations), and by introducing body randomization techniques that significantly reduce the sim-to-real gap for compliant robots (10 citations). His research on integrating spiking neural networks for reservoir computing into closed-loop control of compliant quadrupeds (10 citations) represents a novel bio-inspired approach. Urbain’s work on the HyQ robot, including stance control inspired by cerebellar mechanisms, has practical implications for real-world deployment. With over 100 total citations, his research is shaping the next generation of soft, safe, and intelligent robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Effect of compliance on morphological control of dynamic locomotion with HyQ15 citations · 2021
- 4
- 5
- 6
- 7