DCL Seminar: Jingjin Yu - Toward Scalable and Optimal Collaborative Autonomy

Decision and Control Laboratory

Coordinated Science Laboratory

“Toward Scalable and Optimal Collaborative Autonomy”

Jingjin Yu, Ph.D.

Assistant Professor

Rutgers University

Wednesday, March 27, 2019

3:00pm – 4:00pm

CSL Auditorium (B02)

___________________________________________________________________________________________________________________________________________________________________

Abstract:
Individual robots are becoming increasingly autonomous and capable. Today, it is possible to reliably operate a large number of robots with just a few people. However, comparatively, less is known about how to efficiently work multi-robot systems to optimally and collaboratively solve tasks at large scale. In this talk, I will examine some challenging collaborative autonomy tasks spanning target assignment, motion planning, and perimeter monitoring. For example, in a multi-robot motion planning scenario, applicable to warehouse automation and autonomous driving settings, as the density of robots increases, it becomes increasingly difficult to coordinate the collision-free motion while simultaneously providing good optimality guarantees on task completion time. For all aforementioned problems, we developed efficient methods for optimally or near-optimally solving them that scale to hundreds of robots or more.

Bio:
Jingjin Yu is an Assistant Professor in the Department of Computer Science at Rutgers University, New Brunswick. He received his B.S. from the Univ. of Sci. and Tech. of China in 1998. He obtained his M.S. in Computer Science (2010) and Ph.D. in Electrical and Computer Engineering (2013) from Univ. Illinois, where he briefly stayed as a postdoctoral researcher. He was a postdoctoral researcher at the Massachusetts Institute of Technology from 2013 to 2015. He is broadly interested in the area of algorithmic robotics and control, focusing on issues related to optimality, complexity, and the design of efficient methods for single- and multi-robot systems.