By Wennie Tabib, Kshitij Goel, John Yao, Curtis Boirum, and Nathan Michael
This presentation details recent work in leveraging aerial systems for autonomous cave surveying. Traditional methods of cave surveying are labor-intensive and dangerous due to the risk of hypothermia when collecting data over extended periods of time in cold and damp environments, the risk of injury when operating in darkness in rocky or muddy environments, and the potential structural instability of the subterranean environment. The vision to which we aspire is to miniaturize the technology to such an extent that several portable aerial systems could be easily and reliably deployed to cooperatively build a map of the environment while avoiding obstacles. To this end, we present an aerial system that produces a map of a cave without guidance from a human operator. The approach is tested in Laurel Caverns.
Wennie Tabib received a B.S. degree in computer science in 2012, M.S. degree in robotics in 2014, and Ph.D. degree in computer science in 2019 from Carnegie Mellon University, Pittsburgh, PA, USA.
She is a Postdoctoral Fellow in the Robotics Institute at Carnegie Mellon University. She researches perception, planning, and learning algorithms to enable safe autonomy in significantly three-dimensional, complex environments. Her current research develops methods to enable aerial systems to explore subterranean environments. Wennie is also a member of the National Speleological Society, Mid-Atlantic Karst Conservancy, Pittsburgh Grotto, and Loyalhanna Grotto.
Kshitij Goel received a B.Tech. degree in aerospace engineering in 2017 from the Indian Institute of Technology (IIT) Kharagpur, Kharagpur, WB, India. Kshitij is an M.S. student in Robotics at Carnegie Mellon University, researching fast motion planning for multirotors operating in unknown environments. His current work focuses on robustly deploying teams of multirotors to rapidly explore challenging real-world scenarios in real time.
John Yao received a B.A.Sc. degree in aerospace engineering from the University of Toronto, Toronto, Canada, in 2013 and an M.S. degree in robotics from Carnegie Mellon University (CMU), Pittsburgh, PA, USA, in 2016. John is a Ph.D. Candidate in the Robotics Institute at CMU. His research interests include visual-inertial state estimation and resource-constrained sensor fusion for autonomous robots.
Curtis Boirum received a B.S. degree in physical science from Eureka College, Eureka, IL, USA, in 2008. He received a B.S. and M.S. degree in mechanical engineering from Bradley University, Peoria, IL, USA, in 2009 and 2011, respectively. He received an M.S. degree in robotics from Carnegie Mellon University, Pittsburgh, PA, USA, in 2015. Curtis is a systems engineer for the Resilient Intelligent Systems Lab and designs, builds, and operates drones and ground robots ranging in size from 100 g to 7 kg.
Nathan Michael received a Ph.D. degree in mechanical engineering from the University of Pennsylvania, Philadelphia, PA, USA, in 2008. He is an Associate Research Professor in the Robotics Institute of Carnegie Mellon University; Director of the Resilient Intelligent Systems Lab; author of over 160 publications on control, perception, and cognition for resilient intelligent single and multirobot systems; nominee or recipient of nine best-paper awards; recipient of the Popular Mechanics Breakthrough Award and Robotics Society of Japan Best Paper Award (of 2014); PI of past and ongoing research programs supported by ARL, AFRL, DARPA, DOE, DTRA, NASA, NSF, ONR, and industry; and Chief Technical Officer of Shield AI. Nathan develops resilient intelligent autonomous systems capable of individual and collective intelligence through introspection, adaptation, and evolvement in challenging domains.