ICON Seminar in Robotics: Prof. Melkior Ornik (UIUC)

Time: 3:30-4:30 pm Eastern Time, April 26 (Friday), 2024

Location: Purdue Graduate Student Center (PGSC) 105

Zoom Link: https://purdue-edu.zoom.us/j/98798335169?pwd=ZFNMdmZXendoQ1RCRDczM2dTR1RIdz09

Coffee and snacks will be provided.

Complex Teams on Complex Missions:

Interplay of Resources, Information, and the Environment

Abstract:

Fast, successful, and efficient planning is a core challenge for long-term autonomous missions performed by teams of agents. The obstacles are seemingly insurmountable. Individual agents face challenges in terms of resource limitations, limited sensing, computational power, and environmental complexities. In addition, team planning notoriously suffers from the curse of dimensionality and intricatices of communication patterns. As a result, application domains traditionally rely on human-driven solutions or simple heuristics to produce possibly vastly suboptimal plans. The purpose of this talk is to show that there may exist a middle road. By following three broad problems in planning – resource-constrained teams, time-optimal multi-target planning, and modular agents – we will show that understanding the structure of team interactions, as well as interactions with the environment, is key in developing computationally tractable solutions with minimal joint planning. In the relevant domains, our results demonstrate that such an approach can easily outperform existing benchmarks while retaining the capability to operate at an impressively large scale.

Speaker:

Melkior Ornik is an assistant professor in the Department of Aerospace Engineering at the University of Illinois Urbana-Champaign, also affiliated with the Coordinated Science Laboratory, as well as the Discovery Partners Institute in Chicago. He received his Ph.D. degree from the University of Toronto in 2017. His research focuses on developing theory and algorithms for control, learning and task planning in autonomous systems that operate in uncertain, changing, or adversarial environments, as well as in scenarios where only limited knowledge of the system is available. He is a senior member of IEEE and AIAA, his recent work has been extensively funded by NASA grants and Department of Defense programs, and he has been awarded the 2023 Air Force Young Investigator Program grant.

Recording:

https://youtu.be/mqOYaBQ2wVI

Organizers: Ziran Wang (ziran@purdue.edu), Nak-seung Patrick Hyun (nhyun@purdue.edu), & Tho Le (thovle@purdue.edu)