Alexis Duburcq
Papers
3
Total Citations
26
H-Index
2
About
Alexis Duburcq is a leading researcher in the field of bipedal locomotion and robotic exoskeletons, with a primary focus on bridging the gap between simulation and real-world hardware for assistive humanoid robotics. His work centers on developing robust, hands-free dynamic walking and push-recovery capabilities for paraplegic users, most notably through the exoskeleton ATALANTE. Duburcq’s major contributions include pioneering the use of reinforcement learning for reactive stepping and balance recovery, as demonstrated in his most-cited paper (15 citations), which tackles the critical reality gap that often prevents simulated locomotion policies from transferring to physical robots. He also advanced online trajectory planning with his novel Guided Trajectory Learning algorithm, enabling computationally efficient, real-time motion generation. His impact is profoundly human-centered: his 2018 paper (9 citations) poignantly captures the emotional significance of his work, quoting users who, after standing in the exoskeleton, exclaimed, “I am tall again!” Duburcq’s research not only pushes the boundaries of control theory and machine learning but also restores mobility and dignity, making him a pivotal figure in assistive robotics and rehabilitation engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3