Max Robotics — Global Service Robot Directory + US Certification

About

Yabiao Wang is a robotics researcher whose work spans autonomous navigation, robot programming by demonstration, and intelligent inspection systems. His key contributions lie at the intersection of deep reinforcement learning and real-world robotic applications, particularly for unmanned surface vehicles (USVs) and industrial automation. Wang’s most cited work, "Sim-to-Real: Mapless Navigation for USVs Using Deep Reinforcement Learning" (2022, 22 citations), addresses a critical gap in maritime robotics by enabling USVs to navigate without pre-built maps, using sim-to-real transfer to overcome the scarcity of real-world training data. This work has been foundational for researchers tackling autonomous navigation in unstructured aquatic environments. Earlier, Wang made notable advances in assembly task automation, proposing the "Assembly Graph" (AG) model for probabilistic spatial relation inference (2015, 9 citations) and a composite feature method for multi-class part recognition using random forests (2015, 2 citations). These contributions support robot programming by demonstration, allowing robots to learn assembly tasks from human demonstrations. More recently, Wang has applied his expertise to high-reliability robotics, designing a risk-driven transformer internal inspection robot (2023, 2 citations) for oil-immersed power transformers. His work consistently bridges simulation and reality, advancing practical, deployable robotic systems.