Workshop at the Euron Annual General Meeting (Donostia-S.Sebastian, Spain, 10-12 March, 2010) colocated with the Europ Annual General Meeting
Organizers
This e-mail address is being protected from spambots. You need JavaScript enabled to view it. This e-mail address is being protected from spambots. You need JavaScript enabled to view it. This e-mail address is being protected from spambots. You need JavaScript enabled to view it.
Motivation
On the one hand, reliable benchmarks are called for in order to allow the comparison of the many research results in robotics research, so that their industrial application is eventually possible. On the other hand, if robotics aims to be regarded as serious science, replication of experiments deserves consciencious attention; it is necessary to be able to verify if and by which measure new procedures and algorithms proposed in research papers constitute a real advancement and can be used in new applications.
We have now been working on this issues for some time: what we need to go forward and allow and spread a fully replicable and measurable way of reporting in our discipline?
Workshop Highlights:
Seminar Format:
This forum was a public discussion of the challenges, problems, possible approaches and doubts raised, related to this program and to identify the possible ways to cope (or fail) with them. The forum consisted of presentations interleaved with a significant amount of additional time for discussions between the presentations and at the end of the half-day single track session.
Post Proceedings:
The speakers and the attendees will be invited to send a 'real' paper AFTER the discussion for a post proceedings book, with no hurry :-)
Program
Chair F Bonsignorio
9:00 - 9:10
Introduction
F Bonsignorio
9:10 - 9:40
FP7 Challenge 2 : Why benchmarking and standardisation are important
A Bajart
EU Commission DG INFSO
9:40 - 10:10
ROBOSKIN: Capturing Human Motion as a Benchmark for Humanoid Touch-triggered Protective Reflexes
T S Dahl A Palmer
University of Wales Newport Robotics Intelligence Lab
10:10 - 10:30
RAWSEEDS: hands-on benchmarking
A Bonarini M Matteucci G Fontana
Politecnico di Milano
D Sorrenti
University of Milano Bicocca
10:30 - 10:50
A proposal of benchmark tests for underactuated or compliant hands
G A Kragten J L Herder
Delft University of Technology Dept. of BioMechanical Engineering
10:50 - 11:00
Coffee Break
11:00 - 11:20
Micro Aerial Vehicle Navigation with a Single Omnidirectional Camera (no Laser, no GPS)
D Scaramuzza
ETH Zurich Autonomous Systems Lab
11:20 - 11:40
Teleworkbench: The Teleoperated Platform for Robotic Experiments
A Tanoto J Welzel
University of Paderborn Heinz Nixdorf Institute
F Werner U Rueckert
University of Bielefield Cognitive Interation Technology Centre of Excellence
11:40 - 12:10
BRICS: Enhancing software quality in robotics: implications on benchmarking
D Brugali
University of Bergamo, IEEE TC-Soft
12:10 - 12:30
Replication, benchmarking and the publishing process
F. Bonsignorio A. P. Del Pobil John Hallam
12:30 - 13:00
Open Discussion
