Max Robotics — Global Service Robot Directory + US Certification

About

Hamparsum Bozdogan’s research lies at the intersection of statistical model selection, information complexity, and multi-sensor fusion, with a particular focus on robotics and autonomous systems. His most influential work, “Sensor Selection Using Information Complexity for Multi-sensor Mobile Robot Localization” (2007, 15 citations), introduced a novel algorithm that leverages probabilistic reasoning and Bayes filters to minimize sensor measurement uncertainty. This approach enables mobile robots to achieve robust global self-localization by intelligently selecting the most informative sensors in real time. Bozdogan further advanced this line of inquiry in “Uncertainty minimization in multi-sensor localization systems using model selection theory” (2008), where he applied his expertise in information complexity to handle multimodality sensors in dynamic environments. His contributions also extend to computer vision, notably in “On handling uncertainty in the fundamental matrix for scene and motion adaptive pose recovery” (2008), which reduces risk in camera ego-motion estimation. With “MuFeSaC: Learning When to Use Which Feature Detector” (2007), Bozdogan pioneered adaptive feature detection, demonstrating a deep commitment to principled, uncertainty-aware methods that remain foundational for researchers working on sensor integration and autonomous navigation.