Papers
1
Total Citations
2
H-Index
1
About
Yongjin Mu is a researcher at the forefront of intelligent automation, specializing in reinforcement learning, robotics, and warehouse logistics optimization. His work addresses critical operational challenges in automated warehouses, particularly the battery management of Automated Guided Vehicles (AGVs)—a problem that directly impacts throughput and efficiency. In his most cited paper, "Battery Management for Warehouse Robots via Average-Reward Reinforcement Learning" (2022), Mu pioneered a novel approach by modeling battery management as a Markov Decision Process (MDP) and applying deep reinforcement learning to optimize charging and usage schedules. This contribution provides a scalable, data-driven solution for prolonging robot uptime while minimizing disruptions, offering significant practical value for modern logistics. With 2 citations and growing recognition, Mu’s research bridges the gap between theoretical reinforcement learning and real-world industrial applications. His work is particularly notable for addressing the underexplored average-reward criterion, which better aligns with continuous warehouse operations than traditional discounted reward frameworks. For students and researchers in robotics and operations research, Mu’s studies offer a compelling case study in applying AI to tangible, high-impact problems in automation.
Research Focus
Key Achievements
Top Papers
- 1