Mohammadmahdi Moslemi
Papers
1
Total Citations
3
H-Index
1
About
Mohammadmahdi Moslemi is a robotics researcher advancing the frontier of agile, bio-inspired locomotion through model-free deep reinforcement learning. His most-cited work, "Squat and tuck jump maneuver for single-legged robot with an active toe joint," demonstrates a novel approach to achieving dynamic jumping behaviors—a critical challenge in legged robotics. By integrating an active toe joint, Moslemi’s research enables a single-legged robot to perform complex squat-and-tuck maneuvers, mimicking the explosive, coordinated movements seen in animals. This contribution not only enhances the understanding of balance and control in underactuated systems but also provides a scalable framework for more versatile, energy-efficient robots. With 3 citations on this paper, his work is gaining traction among researchers focused on reinforcement learning for real-world robotic tasks. Moslemi’s approach stands out for its reliance on model-free methods, which bypass the need for complex system modeling, making his techniques more adaptable to diverse robotic platforms. His research holds promise for applications in search-and-rescue, exploration, and assistive robotics, where robust, agile movement is essential.
Research Focus
Key Achievements
Top Papers
- 1