Papers
3
Total Citations
37
H-Index
3
About
Kele Xu is a leading researcher in multi-robot systems and multi-agent reinforcement learning (MARL), with a focus on enabling decentralized, adaptive cooperation among robotic swarms. His major contributions center on developing communication and learning frameworks that allow robots to collaborate effectively without centralized control. In his most-cited work, "Learning to Cooperate via an Attention-Based Communication Neural Network in Decentralized Multi-Robot Exploration" (2019, 26 citations), Xu introduced an attention mechanism that enables robots to selectively share and process information, significantly improving coordination in unknown environments. He further advanced the field with "Improving Fast Adaptation for Newcomers in Multi-Robot Reinforcement Learning System" (2019, 6 citations), addressing the critical challenge of integrating new robots into existing teams without retraining. His "Multi-Actor-Attention-Critic Reinforcement Learning for Central Place Foraging Swarms" (2021, 5 citations) extends these ideas to foraging tasks, demonstrating how decentralized agents can learn efficient, scalable strategies. Xu’s work is notable for replacing pre-designed heuristics with learned, attention-driven policies, making multi-robot systems more robust and adaptable—a key step toward real-world deployment in search-and-rescue, exploration, and environmental monitoring.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3