Max Robotics — Global Service Robot Directory + US Certification

About

Zhaojun Deng is a leading researcher at the intersection of robotic perception, computer vision, and precision optical measurement. His work focuses on enabling mobile robots to robustly understand and navigate their environments, even under challenging conditions. A central contribution is in **visual place recognition (VPR)** , where he has pioneered novel approaches to improve performance in low-light environments. His "Dark-Enhanced Net" (2024, 11 citations) offers an end-to-end solution for robust place recognition in darkness, a critical step toward truly general-purpose robotic navigation. Deng has also advanced the efficiency of VPR systems through **feature-level knowledge distillation**, introducing a "Soft-Hard Labels Teaching Paradigm" (2024, 20 citations) that allows compact models to learn from deeper, more powerful networks without sacrificing accuracy. Beyond vision algorithms, he has made notable contributions to **precision optical metrology**, developing a Risley-prism-based visual tracing method for robot guidance (2020, 11 citations) and a flexible, generation-on-demand system for non-cooperative 6DOF pose measurement (2022, 11 citations). His work directly addresses the computational and environmental bottlenecks that limit real-world robot deployment, making him a key figure in the push toward more capable and resilient autonomous systems.