Max Robotics — Global Service Robot Directory + US Certification

About

Dong An is a leading researcher at the intersection of embodied AI, robot vision, and intelligent navigation. His work spans two decades, from foundational advances in real-time obstacle avoidance for mobile robots—where his 2004 paper on laser radar-based methods (52 citations) introduced key improvements to Potential Field approaches—to cutting-edge developments in vision-language navigation (VLN). An’s most influential contribution is **ETPNav** (2024, 64 citations), which proposes an evolving topological planning framework that enables agents to follow natural language instructions in continuous, unstructured environments. This work addresses a critical challenge in embodied AI, with direct applications in autonomous navigation, search and rescue, and human-robot interaction. More recently, An has pioneered zero-shot VLN under real-world constraints (2025), tackling the difficult problem of navigating without expert demonstrations or prior environmental knowledge. His comprehensive surveys on multimodal fusion and vision-language models for robot vision (2025) have quickly become essential references, synthesizing the field’s rapid progress. With over 140 citations across his most-cited works, An continues to shape how robots perceive, reason, and move through the world.