Max Robotics — Global Service Robot Directory + US Certification

About

Mingli Lu is a robotics researcher whose work centers on enabling mobile robots to perceive, navigate, and interact autonomously in complex, real-world environments. Her primary research areas include visual simultaneous localization and mapping (SLAM), robotic grasping, and autonomous navigation, with a particular focus on overcoming the challenges posed by dynamic and unknown settings. Lu’s most influential contribution is the YOLO-GGCNN grasping framework (52 citations), which integrates deep learning-based object detection with a generative grasping convolutional neural network, allowing mobile robots to reliably grasp objects in unfamiliar environments without prior knowledge. She has also made notable advances in SLAM robustness, developing methods such as an inpainting-based approach to detect and recover regions corrupted by dynamic objects, and a real-time RGB-D SLAM system that fuses semantic and depth information to maintain accuracy in crowded scenes. Her earlier work introduced an ant colony-inspired, random-finite-set formulation for SLAM, showcasing her innovative approach to bio-inspired algorithms. With multiple publications from 2018 to 2025, Lu is establishing herself as a rising contributor to practical, perception-driven robotics.