Max Robotics — Global Service Robot Directory + US Certification

About

Shujing Lyu is a rising researcher at the forefront of embodied AI and autonomous navigation, whose work bridges the critical gap between visual perception and intelligent decision-making in robotics. Her primary research areas span visual navigation, reinforcement learning, and simultaneous localization and mapping (SLAM), with a particular focus on enabling robots to operate effectively in complex, interactive environments. Lyu’s most impactful contribution, the VME-Transformer (2023, 19 citations), introduces a novel visual memory encoding mechanism that allows robotic systems to navigate cluttered spaces by intelligently displacing obstacles—a fundamental challenge in real-world deployment. She further advanced the field with GCENet (2024, 5 citations), a geometric correspondence estimation network that enhances tracking and loop detection in visual-inertial SLAM systems. Demonstrating her versatility, Lyu’s work on causally correct reinforcement learning (2024, 2 citations) tackles the pervasive problem of causal confusion, where algorithms learn spurious correlations instead of meaningful patterns. By developing methods for targeted intervention and input identification, she is helping to build more robust and generalizable RL agents. Lyu’s research trajectory—from memory-enhanced navigation to causal reasoning—positions her as a key contributor to the next generation of truly autonomous robots capable of understanding and interacting with the physical world.