Max Robotics — Global Service Robot Directory + US Certification

About

Albert Tung is a robotics researcher whose work sits at the intersection of imitation learning, human-robot interaction, and scalable data collection for robotic manipulation. He is perhaps best known as a key contributor to **RoboTurk**, a pioneering crowdsourcing platform that transformed how robotic skill datasets are assembled. By enabling large-scale collection of human demonstrations via teleoperation, RoboTurk addressed a fundamental bottleneck in imitation learning research — the scarcity of high-quality training data — and has accumulated over 120 citations across its foundational and follow-up publications. Tung extended this work to multi-arm manipulation through collaborative teleoperation and explored error-aware learning strategies for mobile manipulation robots, broadening the scope of environments where imitation learning can succeed. His contributions culminated in the landmark **Open X-Embodiment** project (2024, 119 citations), a large-scale collaborative initiative that pooled diverse robotic datasets to train general-purpose RT-X models, drawing explicit parallels to the foundation model revolution in NLP and computer vision. Across his career, Tung's research has consistently pushed toward making robotic learning more scalable, generalizable, and practically deployable — making his work essential reading for anyone studying modern robot learning.