Shreya Gummadi
Papers
1
Total Citations
6
H-Index
1
About
Dr. Shreya Gummadi is a pioneering researcher at the intersection of federated learning, autonomous robotics, and bandwidth-efficient distributed systems. Her work addresses critical challenges in decentralized machine learning, particularly for visual robot navigation, where data privacy and communication constraints are paramount. Her most influential contribution, "Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning for Autonomous Visual Robot Navigation" (2024), has already garnered 6 citations, demonstrating its immediate impact. This work introduces a novel clustering-based approach that significantly reduces bandwidth consumption while maintaining model accuracy—a breakthrough for real-world robotic deployments where connectivity is limited. By moving beyond vanilla federated learning's single-model paradigm, Dr. Gummadi enables heterogeneous robot teams to learn collaboratively without compromising privacy or overwhelming network resources. Her research is particularly notable for bridging theoretical federated learning frameworks with practical robotic applications, offering scalable solutions for autonomous navigation in dynamic environments. Dr. Gummadi's work is essential reading for researchers in distributed robotics, privacy-preserving AI, and edge computing, as it provides a blueprint for efficient, privacy-aware learning in resource-constrained autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1