Xiangyan Kong

Papers

Total Citations

H-Index

About

Xiangyan Kong is a leading researcher in multi-agent systems and intelligent path planning, with a focus on integrating model predictive control (MPC) and deep reinforcement learning to solve complex navigation challenges. Their most cited work, "Multi-Agent Path Planning based on MPC and DDPG" (2021), addresses the critical problem of mixed static and dynamic obstacle avoidance in highly dynamic environments. Kong identified a key limitation in traditional grid-based path planning—artificially constrained headings that yield longer paths than true shortest routes—and proposed a novel hybrid framework that combines MPC’s predictive optimization with DDPG’s adaptive learning. This contribution has garnered 4 citations, reflecting its emerging impact on autonomous navigation and robotics. Kong’s research bridges theoretical control methods with practical multi-agent coordination, offering solutions for applications in drone swarms, warehouse logistics, and autonomous vehicles. By tackling the trade-off between path optimality and real-time adaptability, Kong’s work advances the frontier of intelligent motion planning, inspiring further exploration into deep learning-driven control systems for dynamic environments.