Title: Decentralized Real-time Trajectory Planning for Multi-robot Navigation in Cluttered Environments
Abstract: Multi robot collision free and deadlock free navigation in cluttered environments with static and dynamic obstacles is a fundamental problem for many real world applications. Dynamic obstacles can additionally be interactive, i.e., changing their behaviors depending on the behaviors of other objects. In this talk, I will focus on a series of decision making algorithms we have developed, with a particular emphasis on decentralized real time trajectory planning, to enable multi robot navigation in such environments. Practicality of the developed approaches is a central focus of ours, such that we design our systems and algorithms under assumptions that can be realized in the real world. Central concerns of our treatment are embracing on board compute, memory, and storage limitations of robotic systems, not relying on communication for safe operation, and explicitly accounting for communication imperfections, allowing navigation with imperfect a priori knowledge, embracing controller trajectory tracking errors and accounting for them, working with minimal sensing and estimation capabilities, and achieving highly reactive collision avoidance behavior.
Bio: Baskın Şenbaşlar earned his B.S. degree in Computer Engineering in 2017 from Middle East Technical University, Ankara, Turkey. During his undergraduate studies, he started working on robots at KOVAN Research Lab in Ankara, Turkey, under the guidance of Prof. Erol Şahin. In 2019, he received his M.S. degree in Computer Science from the University of Southern California, Los Angeles, USA, as a Fulbright grantee. Throughout his master’s program, he engaged in research on decentralized multi-robot trajectory planning at the Automatic Coordination of Teams (ACT) Lab, advised by Prof. Nora Ayanian. In 2023, Baskın completed his Ph.D. in Computer Science at the University of Southern California, Los Angeles, USA, as an Annenberg Fellowship recipient. His doctoral research was conducted under the mentorship of Gaurav S. Sukhatme in the Robotic Embedded Systems Lab (RESL). Shortly thereafter, in the same year, he joined NVIDIA as a Senior Software Engineer, working on behavior planning for autonomous vehicles. Baskın’s research interests encompass (decentralized) trajectory planning, control, and decision-making for (multi-)robot navigation.