Varun Lodaya
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
Top Papers
- 1
- 2