Akhil Appu Shetty

Papers

Total Citations

H-Index

About

Akhil Appu Shetty is a robotics researcher whose work lies at the intersection of learning-based control, computer vision, and manipulation in unstructured environments. His research focuses on enabling robots to perform dynamic, contact-rich tasks that require both precision and adaptability—challenges central to advancing autonomous systems beyond controlled lab settings. In his notable work on the cup-and-ball game, Shetty developed a learning-based control strategy that allows a robot to master this classic task using only noisy camera observations, effectively addressing key issues of system nonlinearity, contact forces, and precise terminal positioning. This approach demonstrates how robots can learn complex motor skills from high-dimensional sensory input, a critical step toward more robust real-world manipulation. While his most-cited paper has garnered 3 citations, it represents foundational thinking in the integration of model-based and learning-based methods for dynamic tasks. Shetty’s contributions are particularly relevant for researchers exploring how robots can acquire dexterous skills through vision-guided reinforcement learning, bridging the gap between simulation and noisy physical environments.