Papers
10
Total Citations
407
H-Index
6
About
Hammad Mazhar’s research lies at the intersection of robot learning, simulation, and perception, with a focus on creating unified frameworks that bridge the gap between virtual environments and real-world robotic tasks. His most influential work, *Orbit* (2023, 226 citations), is a modular simulation framework powered by NVIDIA Isaac Sim, designed to enable interactive robot learning with photo-realistic scenes and high-fidelity physics. This contribution has become a cornerstone for researchers developing and benchmarking manipulation and locomotion policies. Mazhar also made significant strides in perception with his work on RGB-D Local Implicit Functions (2021, 85 citations), which addresses the challenging problem of depth completion for transparent objects—a critical capability for robots operating in cluttered, real-world settings. Earlier in his career, he explored the mobility of light tracked vehicles on granular terrain (2013, 23 citations), using high-performance computing to characterize vehicle-terrain interactions for reconnaissance robots. His work on transferable task execution from pixels (2020, 40 citations) further demonstrates his ability to combine deep learning with symbolic planning, enabling robots to generalize learned skills to novel problems. Mazhar’s contributions have shaped both the tools and the theoretical foundations of modern robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2RGB-D Local Implicit Function for Depth Completion of Transparent Objects85 citations · 2021
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10Physics-Based Simulator for NEO Exploration Analysis & Modeling3 citations · 2011