Prudhvi Gurram

Papers

Total Citations

H-Index

About

Prudhvi Gurram is a leading researcher at the intersection of computer vision, human-robot interaction, and synthetic data generation. His work focuses on enabling intuitive, non-verbal communication between humans and autonomous systems, with a particular emphasis on vision-based gesture recognition. In his highly cited 2020 paper, "Vision-Based Gesture Recognition in Human-Robot Teams Using Synthetic Data" (30 citations), Gurram tackled a critical bottleneck in robotics: the scarcity of annotated real-world training data. He pioneered a deep learning framework that leverages synthetic imagery to train robust RGB-based gesture classifiers—enabling robots to interpret commands like “follow me” without costly manual data collection. This contribution has significant implications for deploying collaborative robots in dynamic, unstructured environments. By demonstrating that models trained on synthetic data can generalize effectively to real-world scenarios, Gurram’s work accelerates the development of more responsive and autonomous human-robot teams. His research not only advances the field of embodied AI but also provides a scalable, cost-effective pathway for training perception systems, making him a key figure in the future of seamless human-machine collaboration.