Michael Vollert

Papers

Total Citations

H-Index

About

Michael Vollert’s research centers on advancing visual perception and localization for humanoid robots, with a focus on bridging the gap between physical environments and internal world models. His major contributions include developing robust, real-time 6D active visual localization systems that enable humanoid robots to overcome perceptual limitations through particle filtering in CAD environments—a key step toward highly integrated simulation, sensing, and planning. He also pioneered a ground-truth uncertainty model for visual depth perception, systematically addressing how internal and external noise sources affect critical skills like self-localization, object recognition, and tracking. While his most-cited work, “Robust real-time 6D active visual localization for humanoid robots” (2014), has garnered 11 citations, and his uncertainty model (2012) has 3 citations, these papers represent foundational efforts in making humanoid robots more reliable and autonomous in real-world settings. Vollert’s work is particularly notable for its practical integration of theory and application, offering actionable frameworks for improving robot perception under uncertainty—a challenge that remains central to the field. His research continues to inspire engineers and roboticists seeking to enhance robot autonomy through more accurate, uncertainty-aware visual systems.