Maurice Rahme
Papers
2
Total Citations
15
H-Index
2
About
Maurice Rahme is a robotics researcher whose work focuses on bridging the gap between simulation and real-world deployment for legged robots, particularly low-cost quadrupedal platforms. His key contributions lie in demonstrating that surprisingly simple control policies can enable complex locomotion on rough terrain. In his most cited work, "Linear Policies are Sufficient to Enable Low-Cost Quadrupedal Robots to Traverse Rough Terrain" (10 citations), Rahme showed that a linear policy—far simpler than deep neural networks—can effectively modulate open-loop trajectory generators on inexpensive, 3D-printed robots with position-controlled hobby servos. This finding challenges the assumption that complex controllers are necessary for robust locomotion. His earlier work, "Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion" (5 citations), introduced D²-GMB, a framework combining dynamics and domain randomization with offline reinforcement learning to enhance open-loop gaits. This approach enables robots to traverse uneven terrain without requiring foot impact sensing, a significant step toward practical, low-cost robotic systems. Rahme’s research is notable for its emphasis on algorithmic simplicity and hardware accessibility, making advanced locomotion capabilities more attainable for the broader robotics community.
Research Focus
Key Achievements
Top Papers
- 1
- 2