LCSR Seminar: Joshua Mangelson “Steps Towards Intelligent Autonomous Underwater Inspection and Data Collection”
Link for Live Seminar
Link for Recorded seminars – 2022/2023 school year
Over 70% of our world is underwater, but less than 1% of the world’s oceans have been mapped at resolutions greater than 100m per pixel. Regular inspection, mapping, and data collection in marine environments is essential for a whole host of reasons including gaining a scientific understanding of our planet, civil infrastructure maintenance, and safe navigation. However, manual inspection/data collection using divers is expensive, dangerous, time-consuming, and tedious work.
In this talk, I will discuss the use of autonomous underwater vehicles (AUVs) and autonomous surface vessels (ASVs) to automatically and intelligently map, inspect, and collect information in unstructured marine environments. In particular, we will discuss the problems present in this space as well as the contributions my lab is making towards addressing these problems, including i) the development of a general-purpose marine robotics testbed at BYU, ii) the development of a marine robotics simulator called HoloOcean (https://holoocean.readthedocs.io/en/stable/), iii) advancements in marine robotic localization using Lie groups, and iv) preliminary results towards expert-guided topic modeling and intelligent data collection.
Dr. Joshua Mangelson holds PhD and Masters degrees in Robotics from the University of Michigan. After completing his degre, he served as a post-doctoral fellow at Carnegie Mellon University before joining the Electrical and Computer Engineering faculty at Brigham Young University in 2020. His qualifications include demonstrated expertise in robotic perception, mapping, and localization with a particular focus on marine robotics. He has extensive experience leading marine robotic field trials in various locations around the world including San Diego, Hawaii, Boston, northern Michigan, and Utah. In 2018, his work on multi-robot mapping received the Best Multi-Robot Paper Award at the IEEE ICRA conference and 1st-Place in the IEEE OCEANS Student Poster Competition. He is currently serving as an associate editor for The International Journal of Robotics Research (IJRR) and the IEEE/RSJ IROS Conference.