Xinmao Li

Southwest University of Science and Technology

Papers

Total Citations

H-Index

About

Xinmao Li is a robotics researcher whose work focuses on advancing the control and reliability of robotic manipulators through artificial intelligence and machine vision. His key research areas include deep reinforcement learning for manipulator control and fault-tolerant systems for robotic arms operating in hazardous environments. Li’s most cited work, “Manipulator Control Method Based on Deep Reinforcement Learning” (2020, 20 citations), addresses critical limitations in existing approaches by tackling the challenges of discretized action spaces and planar-only manipulation, offering a more robust framework for real-world robotic applications. His earlier paper, “Fault-tolerant control method of robotic arm based on machine vision” (2018, 6 citations), introduces an innovative joint angle visual detection method as a backup solution, significantly enhancing robotic arm reliability in radiation-prone settings—a vital contribution for nuclear and space exploration tasks. Li’s research bridges the gap between theoretical AI and practical robotics, with his work on fault tolerance and learning-based control laying groundwork for safer, more adaptable automation. His contributions are particularly notable for addressing real-world constraints, making his findings valuable for engineers and researchers developing resilient robotic systems for manufacturing, scientific exploration, and extreme environments.