Örebro Studies in Technology 72 I
ÖREBRO 2016 2016U
W
E K
ÖC
KE
M
AN
N
Co
ns
tra
in
t-b
as
ed M
eth
od
s f
or H
um
an
-a
w
are P
la
nn
ing
issn 1650-8580 isbn 978-91-7529-159-8Constraint-based Methods for
Human-aware Planning
UWE KÖCKEMANN
Information technology
uwe köckemann received his MSc in Autonomous Systems
from the Department of Computer Science, University of Applied Sciences Bonn-Rhein-Sieg, Germany in 2010. In 2011 he became a doctoral student at the Center of Applied Auto- nomous Sensor Systems (AASS) in Örebro, Sweden. His research interests are integrating automated planning with reasoning about time, resources, humans, and other types of knowledge. As more robots and sensors are deployed in work and home environments, there is a growing need for these devices to act with some de-gree of autonomy to fulfill their purpose. Automated planning can be used to synthesize plans of action that achieve this. However, the automated planning problem changes when considered in the context of environments popula-ted by humans. Humans have their own plans, and automatically generapopula-ted plans should not interfere with these. We refer to this as social accepta-bility. Opportunities for proactive behavior often arise during execution. The planner should be able to identify these opportunities and proactively plan ac-cordingly. Both social acceptability and proactivity require automated planning to identify relevant situations from available information, that is, to be context-aware. Also, planning may have to consider cooperation with humans to reach common goals or to enable robots and humans to support one another. This thesis proposes a constraint-based human-aware planner that addresses the issues above.