[robotics-worldwide] Call for Last Minute Contributions and Short Remarks RSS2012 Workshop: From theory to practice of performance comparison and result replications in Robotics Research in Sydney, Australia, July 12th, 2012

Fabio Bonsignorio fabio.bonsignorio at uc3m.es
Tue Jun 12 09:29:34 PDT 2012


Apologies for multiple postings
---------------------------------------------------------

Dear All,
this is to invite you to participate actively the the RSS2012 Workshop
on the leap from
theory to practice of performance comparison and result replications
in Robotics Research
http://www.heronrobots.com/EuronGEMSig/gem-sig-events/from-theory-to-practice-rss-2012
The workshop will be on July 12th in the morning.
We are looking for short last minute proposal and short (3 min)
statements on the topic.
We aim at a real working session with 4 30 min presentations from
Wolfram Burgard (Freiburg Univ.) , Juan D. Tardos (Zaragoza Univ.),
Siddharta Srinavasa (Carnegie Mellon) and me (Carlos III Univ.) aiming
to frame a factual discussion.
**We will try to organize a streaming of the workshop and we will
enable a Facebook chat**
In 2008 we proposed a set of general guidelines to improve
experimentalmethodology and reporting in robotics in order to
facilitate experiment replication and performance evaluation and
comparison.
We are now at a point where it is possible to give concrete directions
for experiment planning and execution, potentially affecting the
content of obtained results, not only their 'production process'.
One of the raised objections is the huge variety of subfields in robotics.
The objective of this workshop will be to identify and outline the
common ground between two subareas of research: Visual Servoing and
SLAM.
It is time to pass from theory to practice, we will discuss the issues
and provide examples.
This workshop will be preceded to another one on May 18th at ICRA in
St.Paul, where you are warmly invited:
http://www.heronrobots.com/EuronGEMSig/gem-sig-events/conditions-for-replicable-experiments-and-performance-comparison-in-robotics-research-icra-2012
We will discuss these issues and we welcome your opinions on the matter
All the best
Fabio, John and Angel

Call for  last minute contributions and short statements

Due date: July 10th!

2012 Robotics: Science and Systems Workshop
>From theory to practice of performance comparison and result
replications in Robotics Research

Half-day workshop to be held in conjuntion with the 2012 Robotics:
Science and Systems Conference in Sydney, Australia  on July 12 in the morning.
http://www.roboticsconference.org/



Abstract:

In 2008 we proposed a set of general guidelines to improve
experimentalmethodology and reporting in robotics in order to
facilitate experiment replication and performance evaluation and
comparison.
We are now at a point where it is possible to give concrete directions
for experiment planning and execution, potentially affecting the
content of obtained results, not only their 'production process'.
One of the raised objections is the huge variety of subfields in robotics.
The objective of this workshop will be to identify and outline the
common ground between two subareas of research: Visual Servoing and
SLAM.
It is time to pass from theory to practice, we will discuss the issues
and provide examples.

Description of the proposed content:

The proposers are co-chairs of three technical committees and interest
groups on Good Experimental Methods, Performance Evaluation and
Benchmarking: EURON GEM SIG, Euron II Benchmarking WP and IEEE TC
PEBRAS. We have organized a significant number of workshops on the
topics of performance evaluation, benchmarks, and good experimental
methods) in the latest years.
The interest has been growing since the first workshop at IROS 2006,
contributors included EU FP7 representatives like Anne Bajart and
Libor Kral (head of Challenge 2 unit) and these ideas have been
incorporated in the latest FP7 Calls to the effect that many EU-funded
projects now include specific workpackages about performance
evaluation and benchmarking. In 2008 we proposed a set of general
guidelines to improve experimental methodology and reporting in
robotics in order to facilitate experiment replication and performance
evaluation and comparison. We are now at a point where it is possible
to give concrete directions for experiment planning and execution,
potentially affecting the content of obtained results, not only their
'production process'.
One of the raised objections is the huge variety of subfields in robotics.
The objective of this workshop will be to identify and outline the
common ground between two subareas of research: Visual Servoing and
SLAM.This will be done by selecting a few outstanding researchers on
these fields who proved sensitive to the issues and ask them to
discuss it in detail.
The contributors will be encouraged to provide relevant data and
information to evaluate and replicate their results, whereas on the
web and/or other digital support.
The post-proceedings including the extended digital material will be
part of a prospective  publication, either as a journal special issue
or an edited book.




Tentative schedule:

9:00-10:30 Reference experiences in Visual Servoing and SLAM
10:30-11:00 Coffee Break
11:00-12:30 A common ground between Visual Servoing and SLAM: Research
Contents and Experimental Methods



--
CONFIDENTIAL AND PRE-DECISIONAL INFORMATION


Fabio P. Bonsignorio
IEEE Senior Member

Ceo
Heron Robots s.r.l.
Via R.Ceccardi 1/18
I-16121 Genova
Italy
www.heronrobots.com

Professor
Banco de Santander Chair of Excellence in Robotics
Universidad Carlos III de Madrid
Edificio Agustín de Betancourt, Despacho 1.3B01
Avda. Universidad, 30
28911 Leganés
Spain


More information about the robotics-worldwide mailing list