Mengfei Yu

About

Mengfei Yu is a researcher advancing the frontier of intelligent robotic systems, with a primary focus on adaptive calibration and reinforcement learning. Yu’s major contributions lie in revolutionizing hand-to-eye calibration—a critical process for ensuring precision in industrial robotics—by replacing static, one-time calibration methods with dynamic, self-adaptive frameworks. In their highly cited 2023 work, "Neurodynamics Adaptive Reward and Action for Hand-to-Eye Calibration With Deep Reinforcement Learning" (6 citations), Yu introduced a novel deep reinforcement learning algorithm that enables a robotic manipulator to continuously recalibrate itself, maintaining accuracy even as the relative hand-eye position shifts. This breakthrough addresses a fundamental limitation of traditional calibration, which degrades over time. Building on this, Yu’s 2022 paper "Continuous Self-adaptive Calibration by Reinforcement Learning" (2 citations) further formalized the concept, demonstrating how reinforcement learning can create a perpetually self-correcting system. Though early in their career, Yu’s work is already shaping the future of autonomous manufacturing and vision-based robotics, offering a path toward truly intelligent, self-maintaining production lines.

Research Focus

Key Achievements

Top Papers

1. 1
   Neurodynamics Adaptive Reward and Action for Hand-to-Eye Calibration With Deep Reinforcement Learning

   6 citations · 2023
2. 2
   Continuous Self-adaptive Calibration by Reinforcement Learning

   2 citations · 2022

Key Collaborators

Contact & Links