Papers
2
Total Citations
95
H-Index
2
About
Ankush Gupta is a researcher at the intersection of robotics, computer vision, and machine learning, with a focus on enabling autonomous systems to operate more effectively in complex, real-world environments. His work addresses two critical challenges: improving robotic perception and automating delicate surgical tasks. In his influential 2013 study on autonomous suturing (89 citations), Gupta pioneered a method for trajectory transfer through non-rigid registration, demonstrating a fast and robust approach to a time-consuming surgical procedure. This work holds particular promise for reducing surgeon fatigue and enabling remote tele-surgery where latency complicates manual control. More recently, Gupta has tackled the fundamental question of how robots can better understand their surroundings. His 2021 paper, "Representation Matters," explores whether a single, generally useful lower-dimensional representation can be learned from high-dimensional observations to dramatically improve data-efficiency in reinforcement learning for robotics. By investigating how structured representations can enhance both perception and exploration, Gupta is helping to build the foundational algorithms that will allow robots to learn and adapt with limited data, pushing the boundaries of what autonomous systems can achieve in the real world.
Research Focus
Key Achievements
Top Papers
- 1
- 2