Papers
10
Total Citations
445
H-Index
8
About
Fernando Gama is a leading researcher at the intersection of graph neural networks (GNNs) and decentralized multi-agent systems. His core contributions lie in developing learning-based controllers that enable robot swarms and multi-robot teams to coordinate effectively using only local information and sparse communication—moving beyond traditional hand-crafted heuristics. Gama’s most influential work, “Graph Neural Networks for Decentralized Multi-Robot Path Planning” (2020), has garnered 263 citations, establishing a foundational framework for using GNNs to learn communication and control policies in decentralized settings. He has further advanced the field by integrating vision-based learning in “VGAI: End-to-End Learning of Vision-Based Decentralized Controllers for Robot Swarms” (2021), enabling robots to act from raw visual inputs. His research also tackles the challenge of time-varying network topologies through distributed online learning, as seen in his “Wide and Deep Graph Neural Network” papers. By bridging graph signal processing, deep learning, and robotics, Gama’s work is shaping the future of scalable, autonomous systems in applications ranging from smart grids to search-and-rescue missions.
Research Focus
Key Achievements
Top Papers
- 1Graph Neural Networks for Decentralized Multi-Robot Path Planning263 citations · 2020
- 2
- 3Wide and Deep Graph Neural Network With Distributed Online Learning25 citations · 2022
- 4Graph Neural Networks for Decentralized Multi-Robot Path Planning23 citations · 2019
- 5
- 6Graphs, Convolutions, and Neural Networks.15 citations · 2020
- 7Wide and Deep Graph Neural Networks with Distributed Online Learning12 citations · 2021
- 8From Graph Filters to Graph Neural Networks12 citations · 2020
- 9Graph Neural Networks for Decentralized Controllers8 citations · 2021
- 10