Max Robotics — Global Service Robot Directory + US Certification

About

Fawei Ge is a researcher advancing the reliability of autonomous systems through robust visual localization in long-term, dynamic environments. Her work addresses a critical challenge in autonomous driving and robotics: maintaining accurate place recognition despite drastic changes in season, illumination, and weather. Ge’s key contributions center on developing intelligent frameworks that combine deep representation learning with domain adaptation. Her most-cited paper, “Learning robust representation and sequence constraint for retrieval-based long-term visual place recognition” (2024, 6 citations), introduces a method that learns resilient visual features while leveraging temporal sequence constraints to improve retrieval accuracy. In “Double-Domain Adaptation Semantics for Retrieval-Based Long-Term Visual Localization” (2023, 5 citations), she tackles the problem of domain shift caused by environmental variance, proposing a dual-domain adaptation strategy to bridge the gap between training and deployment conditions. Her latest work, “MDAG-Net: Multidomain Association-Guided Network” (2025), further refines this approach by integrating multi-domain associations. Through these contributions, Ge is helping to build the perceptual backbone for next-generation autonomous vehicles, ensuring they can navigate reliably across time and changing conditions.