Papers
7
Total Citations
34
H-Index
4
About
Etienne Arlaud is an emerging robotics researcher whose work spans trajectory optimization, dexterous manipulation, sim-to-real transfer, and robust estimation — areas central to enabling capable, real-world autonomous systems. His most influential contribution, "ProxDDP: Proximal Constrained Trajectory Optimization" (2025, 12 citations), advances the mathematical foundations of motion planning by developing proximal numerical methods that meet the demanding speed requirements of real-time robot control. Complementing this, his work on parallel and proximal linear-quadratic methods pushes the boundaries of nonlinear model predictive control for whole-body robot systems. Arlaud has also made notable strides in robot learning. His "ViViDex" project demonstrates how human video demonstrations can be leveraged to train vision-based dexterous manipulation policies for multi-fingered robotic hands, addressing the persistent challenge of trajectory noise in imitation learning. His 2023 work on visual sim-to-real transfer tackles the critical domain gap between simulated training environments and physical deployment. Rounding out his profile, his Risk-Sensitive Extended Kalman Filter introduces principled uncertainty-awareness into state estimation pipelines. Across roughly 34 total citations, Arlaud is establishing himself as a versatile contributor to both the theoretical and applied frontiers of modern robotics.
Research Focus
Key Achievements
Top Papers
- 1ProxDDP: Proximal Constrained Trajectory Optimization12 citations · 2025
- 2ViViDex: Learning Vision-Based Dexterous Manipulation from Human Videos6 citations · 2025
- 3Robust Visual Sim-to-Real Transfer for Robotic Manipulation5 citations · 2023
- 4
- 5Risk-Sensitive Extended Kalman Filter3 citations · 2024
- 6Assembly Planning from Observations under Physical Constraints2 citations · 2022
- 7ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos2 citations · 2024