His main research topics are pattern recognition, machine learning, machine perception, robotics, computer vision and signal processing. His main research interest is in developing, evaluating and applying, in a practical way, techniques for adaptation and learning to autonomous systems interacting with the physical world. He has co-authored more than 50 (peer-reviewed) papers on international journals, 25 papers in International Books, and more than 150 (peer-reviewed) contributions to international conferences and workshops. He has been the principal investigator in national and international funded research projects on machine learning, autonomous robots, sensor fusion and benchmarking of autonomous and intelligent systems. His research in robotics started with the Milan Robocup Team a RoboCup team of six soccer robots equipped with custom panoramic vision sensors, adaptive color classification algorithms, and a conceptual model to integrate robot perception with information from teammates. After that he has worked on a complete 6DoF SLAM (i.e., Simultaneous Localization and Mapping) system based on multi-camera vision sporting hierarchical map decomposition through conditionally independent filtering.