Abstract: In many scientific discoveries, remote sensing alone is not sufficient for testing hypotheses. Robotic vehicles are enabling scientific technology for directly sampling and analyzing surface and subsurface compositions. Present-day robotic algorithms and systems lack sufficient robustness to operate reliably in environments that are unknown a priori. In this talk, I will describe new approaches to real-time robotic mapping and information gathering. My research explores novel mathematical algorithms for autonomy and their open-source implementation on real robots in challenging situations — my long-term vision is to obtain a human-level perception and autonomy for autonomous robots.

Bio: Maani Ghaffari received the Ph.D. degree from the Centre for Autonomous Systems (CAS), University of Technology Sydney, NSW, Australia, in 2017. He is currently an Assistant Research Scientist at the Robotics Institute and Department of Naval Architecture and Marine Engineering, University of Michigan, Ann Arbor, MI, USA. His research interests include applied mathematics, robotic perception, machine learning, and planning under uncertainty with applications in robotics and autonomous systems.