Max Robotics — Global Service Robot Directory + US Certification

About

Wee-Hong Ong is a robotics researcher whose work spans autonomous navigation, human-robot interaction, and intelligent perception systems. His research focuses on three core areas: reinforcement learning for robot navigation, real-time face detection and tracking, and open-world recognition for autonomous systems. Ong’s most impactful work includes pioneering the use of LEGO sensors for remote-controlled robots (6 citations) and developing comparative analyses of Deep Q-Learning, Q-Learning, and SARSA for robot local navigation (6 citations). He has made notable contributions to robust face detection systems, introducing margin-based region of interest techniques combined with multi-task convolutional neural networks and template matching (5 citations). His recent work on deep reinforcement learning-based mapless crowd navigation, which incorporates perceived risk of moving crowds for mobile robots (2 citations), addresses critical challenges in generalization and scalability. Ong’s research also extends to unsupervised domain-specific open-world recognition (3 citations), advancing machine learning models that can recognize unknown classes and learn continually. His work on implementing ROS autonomous navigation on the Parallax Eddie platform demonstrates practical applications of his theoretical contributions. With a total of 28 citations across his most-cited papers, Ong continues to push boundaries in making robots more intelligent, perceptive, and capable of navigating complex, dynamic environments.