Special Robotics Seminar: Dr. Graeme Best, "Planning Algorithms for Multi-Robot Active Perception"
Monday, August 12, 2019
DeWalt Seminar Room (EGR 2164)
301 405 4358
Special Robotics Seminar
Planning Algorithms for Multi-Robot Active Perception
Robotic Decision Making Laboratory (RDML)
Oregon State University
A fundamental task of robotic systems is to use on-board sensors and
perception algorithms to understand high-level semantic properties of
an environment. The performance of perception algorithms can be
greatly improved by planning the motion of the robots to obtain
high-value observations. This motivates the problem of active
perception, where the goal is to plan the observation viewpoints for a
team of robots while considering both the motion constraints and the
perception objectives of the task at hand.
In this talk I will introduce a suite of algorithms for multi-robot
active perception, including decentralised Monte Carlo tree search
(Dec-MCTS), planning-aware communication, self-organising maps, and
spatiotemporal optimal stopping. These algorithms have been applied to
a variety of scenarios for marine environmental monitoring,
subterranean exploration, precision agriculture, active object
recognition, and task allocation.
Host: Michael Otte, Aerospace Engineering
Dr. Graeme Best is a Postdoctoral Scholar in the Robotic Decision
Making Laboratory (RDML) at Oregon State University, advised by Prof.
Geoffrey Hollinger. His research interests include planning algorithms
for multi-robot teams performing coordinated perception tasks, with an
emphasis on decentralised algorithms and probabilistic reasoning.
Applications include marine monitoring, subterranean exploration,
precision agriculture, and defence. Previously, he worked on projects
involving perception for legged robots, marine robotics operations,
and human-robot interaction. He completed his Ph.D. at the Australian
Centre for Field Robotics (ACFR) at the University of Sydney (2019).
He received the B.E. (Hons) (Electrical) and B.Sc. (Computer Science)
from Monash University (2014). He has also conducted research at the
CSIRO Robotics and Autonomous Systems Group and the DST Group Maritime