Örebro Studies in Technology 69 I
ÖREBRO 2016 2016M
AS
OU
ME
H M
AN
SOU
RI A Co
ns
tra
in
t-B
as
ed A
ppr
oa
ch f
or H
ybr
id R
ea
so
ning i
n R
ob
oti
cs
issn 1650-8580 isbn 978-91-7529-145-1A Constraint-Based Approach for
Hybrid Reasoning in Robotics
MASOUMEH MANSOURI
Computer Science
masoumeh mansouri received her MSc degree (2011)
in Robotics and Intelligent Systems at Örebro University. Since then, she has been a doctoral student at the Centre for Applied Autonomous Sensor Systems (AASS) in Örebro, Sweden. Her research interests include knowledge represen-tation and reasoning, with a particular focus on applications in autonomous mobile robotics.
The quest of AI and Robotics researchers to realize fully AI-driven integrated robotic systems has not yet led to such realizations, in spite of great attainments in both research areas. This thesis claims that one of the major hindrances is the lack of attention to what we call “the hybrid reasoning problem”. This is the problem of jointly reasoning about hetero-geneous and inter-dependent aspects of the world, expressed in different forms and at different levels of abstraction. This thesis proposes an approach to hybrid reasoning (or integrated reasoning) for robot applications. The ap-proach constitutes a systematic way of achieving a domain-specific integration of reasoning capabilities. Its underpinning is to jointly reason about the sub-problems of an overall hybrid problem in the combined search space of mutual decisions. The proposed approach has been applied in several different domains, namely, a waiter robot, an automated industrial fleet management application, and a drill pattern planning problem in open-pit mining.