Mustafa Haiderbhai

University of Toronto

Papers

6

Total Citations

32

H-Index

3

About

Mustafa Haiderbhai is a rising leader in autonomous surgical robotics, specializing in the critical challenge of sim-to-real transfer for dexterous manipulation. His research centers on enabling surgical robots—specifically the da Vinci Research Kit (dVRK)—to perform complex, non-repetitive tasks like cutting, tissue retraction, and needle threading through vision-based reinforcement learning. Haiderbhai’s major contribution lies in bridging the reality gap: his pioneering work on robust sim-to-real transfer demonstrates how domain randomization of camera, lighting, and physics parameters allows policies trained entirely in simulation to succeed on real hardware. His 2024 paper on “Sim2Real Rope Cutting” (15 citations) introduces a novel simulation framework for cutting deformable materials, a notoriously difficult problem due to dynamic tissue deformation and topological changes. He further advanced the field with “Learning Nonprehensile Dynamic Manipulation” (2023), tackling the underexplored area of pushing and pressing. Haiderbhai is also a core contributor to MuJoCo Playground (2025), an open-source framework designed to democratize robot learning by enabling rapid, GPU-accelerated policy training. His work is foundational for the next generation of autonomous surgical assistants, directly impacting patient outcomes by making robotic surgery safer and more reliable.

Research Focus

Key Achievements

3
H-Index
6
Papers
32
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
Sim2Real Rope Cutting With a Surgical Robot Using Vision-Based Reinforcement Learning
15 citations · 2024
📈 Most Prolific Year: 2024 (2 Papers)
🤝 Key Collaborators: 18
🏛 Institutions: University of Toronto

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago