Papers
6
Total Citations
186
H-Index
5
About
Charles Khazoom is a leading robotics researcher whose work sits at the intersection of human augmentation, humanoid locomotion, and real-time control. His research spans three key areas: supernumerary robotic limbs, whole-body model predictive control (MPC), and safe humanoid autonomy. Khazoom’s major contributions include pioneering a supernumerary robotic leg powered by magnetorheological actuators (71 citations) that can assist human walking by providing compliant, impact-resistant support—a novel departure from traditional exoskeletons. He has also advanced the state of the art in legged robot control by developing methods to tailor solution accuracy for fast whole-body MPC (39 citations), enabling real-time deployment of high-dimensional nonlinear controllers on humanoids. His work on combining control barrier functions with whole-body control (33 citations) provides formal safety guarantees for self-collision avoidance on the MIT Humanoid, a critical step toward safe human-robot interaction. Khazoom has also explored reinforcement learning for humanoid locomotion (21 citations) and model hierarchy predictive control for disturbance recovery (19 citations). His research is notable for bridging theoretical control guarantees with practical, real-time implementation on complex robotic platforms, making him a rising figure in humanoid robotics and assistive technologies.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Benchmarking Potential Based Rewards for Learning Humanoid Locomotion21 citations · 2023
- 5
- 6