Tapan Sharma
Papers
1
Total Citations
12
H-Index
1
About
Tapan Sharma is a roboticist whose research lies at the intersection of reinforcement learning, manipulation, and autonomous systems, with a particular focus on enabling robots to perform complex, real-world tasks. His most notable contribution, "PourNet," introduces a novel framework that combines curriculum learning and curiosity-driven exploration to train robots to pour liquids with remarkable precision—a notoriously difficult challenge due to the unpredictable nature of fluid dynamics. This work, which has garnered 12 citations since its 2022 publication, demonstrates how robots can learn robust pouring policies without explicit models of fluid behavior, marking a significant step toward practical, adaptive manipulation in unstructured environments. Sharma’s approach not only advances the field of robotic manipulation but also highlights the power of curiosity-based learning in overcoming sparse reward scenarios. His research is particularly impactful for applications in domestic service, industrial automation, and healthcare, where precise liquid handling is critical. As a rising scholar, Sharma’s work exemplifies how integrating reinforcement learning with physical intuition can bridge the gap between simulation and real-world robotic performance, making him a promising voice in the next generation of robotics researchers.
Research Focus
Key Achievements
Top Papers
- 1