Lijun Shan

Papers

Total Citations

H-Index

About

Lijun Shan is a researcher whose work bridges robotics, artificial intelligence, and precision mechanical systems. Their key research areas include robotic arm control, machine learning integration, and transmission error analysis in robotic components. Shan’s most notable contribution is their pioneering work on robot arm control using Unity3D machine learning, where they applied deep reinforcement learning strategies to train robotic arms through reward functions. This 2020 paper, cited 49 times, demonstrates how simulated environments can enable rapid, intelligent control of robotic manipulators, allowing them to locate and interact with objects efficiently after training. In earlier work, Shan conducted a detailed analysis of transmission errors in RV reducers used in robots (2015, 15 citations), contributing to improved precision in robotic joint mechanisms. This dual focus—combining AI-driven control with mechanical accuracy—positions Shan as a researcher advancing both the software and hardware sides of robotics. Their work is particularly relevant for students and engineers interested in reinforcement learning applications, simulation-to-real transfer, and the mechanical reliability of robotic systems.