Varun Lodaya

University of Toronto, Vector Institute

Papers

2

Total Citations

60

H-Index

2

About

Varun Lodaya’s research sits at the intersection of robotics, simulation, and dexterous manipulation, with a focus on bridging the sim-to-real gap for complex, real-world tasks. His most impactful work centers on transferring dexterous manipulation skills learned entirely in GPU-accelerated simulation to a remote, physical TriFinger robot. In a landmark 2022 paper (45 citations), Lodaya demonstrated a system that enables a three-fingered robot to manipulate objects to arbitrary 6-DoF poses—a challenging feat requiring high dexterity. By leveraging NVIDIA’s IsaacGym simulator and a keypoint-based representation rather than raw positions, his approach achieved robust sim-to-real transfer, allowing the robot to perform in-hand manipulation tasks that were previously difficult to realize outside simulation. An earlier version of this work (2021, 15 citations) laid the foundation, showing empirical benefits of keypoints for improved generalization. Lodaya’s contributions are notable for their practical impact: they open pathways for remote, scalable robot learning without physical hardware, reducing cost and risk. His work is a key reference for researchers in dexterous robotics, reinforcement learning, and sim-to-real transfer.

Research Focus

Key Achievements

2
H-Index
2
Papers
60
Total Citations
30
Avg Citations/Paper
🏆 Most Cited Paper
Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger
45 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 10
🏛 Institutions: University of Toronto, Vector Institute

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago