- This event has passed.
Fall 2022 GRASP Seminar: Nare Karapetyan, University of Maryland, “Area Coverage Path Planning: From Graphs to Field Deployments”
December 14, 2022 at 11:00 AM - 12:00 PM
This is a hybrid event with in-person attendance in Levine 307 and virtual attendance via Zoom.
Area coverage path planning is the problem of finding an efficient path that traverses the region of interest while avoiding existing obstacles. When dealing with real systems, the dynamic changes and uncertainties of the environments increase the state space exponentially and make these problems intractable. As such, exploiting the inherent geometric properties of the areas allows for redefining planning as a combinatorial optimization task. This helps to reduce the overhead complexity of the problem and break it into manageable subproblems for handling uncertainties.
In this talk, we will discuss a two-phase approach for generating a complete pipeline of robust exploration/coverage plans: (i) generate a global coverage plan and (ii) incorporate dynamic changes to adjust the plan. We will specifically discuss different coverage strategies for single and multi-robot systems that take into account obstacles and implicit geological properties of the environment and perform effective data collection suitable to the deployed sensors. We will also discuss how to incorporate uncertainties within these plans. Moreover, we will also see these methods deployed in the real world, automating scientific sampling operations.
University of Maryland
Nare Karapetyan is a postdoctoral associate at the Maryland Robotics Center at the University of Maryland (UMD), working with Dr. Dinesh Manocha and Dr. Pratap Tokekar. She received her Ph.D. from the University of South Carolina (UofSC) in Computer Science where she worked in the Autonomous Field Robotics Laboratory (AFRL) under the supervision of Dr. Ioannis Rekleitis. She has worked on the area coverage path planning problems both for two and three-dimensional areas, with particular applications in aquatic domains. She is currently developing exploration/coverage planning methods for a team of heterogeneous multi-robot systems operating under dynamic changes. She was awarded the prestigious Japan Society for the Promotion of Science (JSPS) postdoctoral fellowship and named Breakthrough Graduate Scholar 2022 by the UofSC. Nare is serving as an Associate Editor for the IROS Conference and IEEE Robotics & Automation Letter Editorial Board.