Publications‎ > ‎

Book Chapters

Robot Learning for Persistent Autonomy

posted May 29, 2016, 8:46 AM by Reza A   [ updated Jun 23, 2017, 8:58 PM ]

Petar kormushev, Seyed Reza Ahmadzadeh

Reference:
Petar Kormushev, Seyed Reza Ahmadzadeh, “Robot Learning for Persistent Autonomy”, Chapter in
Handling Uncertainty and Networked Structure in Robot Control (Lucian Busoniu, Levente Tamás, eds.),
Springer International Publishing, pp. 3-28, 2015.
Bibtex Entry:
@INBOOK{kormushev2015chapterrobot, AUTHOR={Kormushev, Petar and Ahmadzadeh, Seyed Reza}, EDITOR={Busoniu, Lucian and Tam{\'a}s, Levente}, TITLE={Robot Learning for Persistent Autonomy}, BOOKTITLE={Handling Uncertainty and Networked Structure in Robot Control}, YEAR={2015}, PUBLISHER={Springer International Publishing}, ADDRESS={Cham}, PAGES={3--28}, ISBN={978-3-319-26327-4}, DOI={10.1007/978-3-319-26327-4_1}, URL={http://dx.doi.org/10.1007/978-3-319-26327-4_1} }
DOI:
10.1007/978-3-319-26327-4_1
Abstract:
Autonomous robots are not very good at being autonomous. They work well in structured environments,
but fail quickly in the real world facing uncertainty and dynamically changing conditions. In this
chapter, we describe robot learning approaches that help to elevate robot autonomy to the next
level, the so-called 'persistent autonomy'. For a robot to be 'persistently autonomous' means to be
able to perform missions over extended time periods (e.g. days or months) in dynamic, uncertain
environments without need for human assistance. In particular, persistent autonomy is extremely
important for robots in difficult-to-reach environments such as underwater, rescue, and space
robotics. There are many facets of persistent autonomy, such as: coping with uncertainty, reacting
to changing conditions, disturbance rejection, fault tolerance, energy efficiency and so on. This
chapter presents a collection of robot learning approaches that address many of these facets.
Experiments with robot manipulators and autonomous underwater vehicles demonstrate the usefulness
of these learning approaches in real world scenarios.

PDF Preview:



Visuospatial Skill Learning

posted May 29, 2016, 8:44 AM by Reza A   [ updated Jun 23, 2017, 8:50 PM ]

Seyed Reza Ahmadzadeh, Petar Kormushev

Reference:
Seyed Reza Ahmadzadeh, Petar Kormushev, “Visuospatial Skill Learning”, Chapter in Handling
Uncertainty and Networked Structure in Robot Control (Lucian Busoniu, Levente Tamás, eds.),
Springer International Publishing, pp. 75-99, 2015.
Bibtex Entry:
@INBOOK{ahmadzadeh2015chaptervsl, AUTHOR={Ahmadzadeh, Seyed Reza and Kormushev, Petar}, EDITOR={Busoniu, Lucian and Tam{\'a}s, Levente}, TITLE={Visuospatial Skill Learning}, BOOKTITLE={Handling Uncertainty and Networked Structure in Robot Control}, YEAR={2015}, PUBLISHER={Springer International Publishing}, ADDRESS={Cham}, PAGES={75--99}, ISBN={978-3-319-26327-4}, DOI={10.1007/978-3-319-26327-4_4}, URL={http://dx.doi.org/10.1007/978-3-319-26327-4_4} }
DOI:
10.1007/978-3-319-26327-4_4
Abstract:
This chapter introduces Visuospatial Skill Learning (VSL), which is a novel interactive robot
learning approach. VSL is based on visual perception that allows a robot to acquire new skills by
observing a single demonstration while interacting with a tutor. The focus of VSL is placed on
achieving a desired goal configuration of objects relative to another. VSL captures the object’s
context for each demonstrated action. This context is the basis of the visuospatial representation
and encodes implicitly the relative positioning of the object with respect to multiple other
objects simultaneously. VSL is capable of learning and generalizing multi-operation skills from a
single demonstration, while requiring minimum a priori knowledge about the environment. Different
capabilities of VSL such as learning and generalization of object reconfiguration, classification,
and turn-taking interaction are illustrated through both simulation and real-world experiments.

PDF Preview:



1-2 of 2