Dominik Endres
Papers
4
Total Citations
67
H-Index
3
About
Dominik Endres is a leading researcher in humanoid robotics, specializing in the intersection of optimal control, movement primitives, and machine learning. His work centers on generating complex, dynamically feasible walking sequences for humanoid robots, with a particular focus on the HRP-2 platform. Endres’s major contribution is the development of the COCoMoPL framework, a novel approach that combines optimal control with learned movement primitives to produce stable, energy-efficient gaits. This method solves high-dimensional optimal control problems using detailed dynamic models, then distills the solutions into reusable movement primitives that can be adapted to new tasks. His most-cited paper, "COCoMoPL: A Novel Approach for Humanoid Walking Generation" (2017, 29 citations), along with related works (2016, 22 citations; 2015, 13 citations), demonstrates the power of this hybrid approach for generating complex walking sequences. Endres has also explored modeling coordinated human body motion through structured dynamic representations. His work has significant implications for advancing autonomous humanoid locomotion, bridging the gap between simulation and real-world deployment, and inspiring new directions in robot learning and control.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4