Siji Chen
Papers
2
Total Citations
5
H-Index
2
About
Siji Chen is a rising researcher at the forefront of swarm robotics and multi-agent systems, with a focused expertise in decentralized control and graph-based deep learning. Their work addresses a critical challenge in the field: enabling robot swarms to perform complex, coordinated tasks using only local information. Chen’s major contribution lies in pioneering the use of Spatio-Temporal Graph Neural Networks (ST-GNNs) to bridge the gap between fully centralized and purely local control policies. By incorporating both spatial and temporal dependencies, their models allow individual agents to effectively infer global flocking behaviors from the limited data of immediate neighbors. Though early in their career, Chen’s foundational papers—including "Learning Decentralized Flocking Controllers with Spatio-Temporal Graph Neural Network" (2024) and "Spatial Temporal Graph Neural Networks for Decentralized Control of Robot Swarms" (2023)—have already garnered attention for solving a long-standing limitation in imitation learning for swarms. This innovative approach promises more scalable, robust, and communication-efficient autonomous systems, marking Chen as a key contributor to the next generation of intelligent, decentralized robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2