Dominique Orban
Papers
1
Total Citations
3
H-Index
1
About
Dominique Orban is a leading figure in numerical optimization and its application to robotics and control systems. His research centers on developing efficient algorithms for large-scale optimization, with a particular focus on primal-dual methods and their implementation on modern parallel architectures. Orban’s most notable contribution is the introduction of a Primal-Dual iLQR framework for GPU-accelerated learning and control in legged robots, a breakthrough that enables both temporal and state-space parallelization through a parallel associative scan to solve the primal-dual Karush-Kuhn-Tucker (KKT) systems. This work, already garnering 3 citations since its 2025 publication, demonstrates his ability to bridge theoretical optimization with practical, high-performance robotics. By leveraging GPU parallelization, Orban’s approach significantly enhances the speed and scalability of Model Predictive Control (MPC) for dynamic locomotion, addressing critical challenges in real-time robot control. His contributions are shaping the future of autonomous systems, making him a key researcher for students and engineers interested in the intersection of optimization theory, parallel computing, and robotic autonomy.
Research Focus
Key Achievements
Top Papers
- 1