Juntong Lin
Papers
2
Total Citations
47
H-Index
2
About
Juntong Lin is a leading researcher in multi-robot systems and autonomous navigation, with a focus on leveraging deep reinforcement learning (DRL) to solve complex, real-world coordination challenges. His most influential work, "End-to-end Decentralized Multi-robot Navigation in Unknown Complex Environments via Deep Reinforcement Learning" (2019, 42 citations), introduces a novel DRL-based method that enables a robot team to navigate unknown environments while maintaining connectivity and avoiding collisions. This decentralized approach allows each robot to act independently, yet collectively achieve a shared goal—a breakthrough for scalable, robust swarm robotics. Lin further advanced the field with "Connectivity Guaranteed Multi-robot Navigation via Deep Reinforcement Learning" (2019, 5 citations), which explicitly addresses the critical challenge of preserving communication links during dynamic movement. By integrating connectivity constraints into the learning framework, his work ensures reliable team performance even in GPS-denied or hazardous settings. Lin’s contributions are foundational for applications in search-and-rescue, exploration, and autonomous logistics, demonstrating how DRL can bridge the gap between theoretical multi-agent systems and practical, deployable solutions. His research continues to inspire new approaches to decentralized, learning-based robot coordination.
Research Focus
Key Achievements
Top Papers
- 1
- 2