Max Robotics — Global Service Robot Directory + US Certification

About

Xiangqun Chen’s research bridges the critical intersection of artificial intelligence security and industrial robotics, with a focus on making autonomous systems both safer and more reliable. Her most cited work, “Adversarial Attacks on Monocular Depth Estimation” (2020, 14 citations), reveals how deep neural networks—even those excelling at computer vision tasks like depth estimation—remain vulnerable to carefully crafted adversarial examples, raising urgent concerns for real-world deployment. This foundational contribution has helped shape the conversation around AI robustness in perception systems. Alongside this security focus, Chen has driven significant advances in industrial predictive maintenance. Her 2021 paper on robot lubricating oil state evaluation using support vector regression (8 citations) demonstrates how IIoT data can enable intelligent equipment-state prediction. She has also tackled practical challenges in automotive manufacturing, including a review of predictive maintenance for industrial robots (2023) and a statistical process control approach for spot-welding systems at Beijing Benz (2021, 2 citations). Her work on policy-based access control for robotic applications (2019, 5 citations) further addresses the security gaps in Robot Operating System (ROS) architectures. With a portfolio spanning adversarial machine learning, IIoT-driven prognostics, and robotic cybersecurity, Chen is shaping the future of trustworthy, intelligent automation in manufacturing.