Workshop at ICRA in Brisbane, May 21, 2018
Organizers
F. Bonsignorio
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.
Signe A. Redfield
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.
A. P. del Pobil
This e-mail address is being protected from spambots. You need JavaScript enabled to view it.
Program
13:30 The R-Articles Life-Cycle
F.Bonsignorio, IEEE RAS TC-Pebras co-chair, coordinator of euRobotics TG on Experimental Methodology, Benchmarking, Competitions and Challenges
Institute of Biorobotics, SSSA, Pisa, Italy and Heron Robots
13:50 Reproducible Robotics in the Magazine
Bram Vanderborght
VUB, Belgium
Peter Corke
QUT, Australia
14:30 Data Sets for Reproducible Visual SLAM experiments
Davide Scaramuzza
University of Zurich, Switzerland
14:50 General Q&A and discussion ignition (to continue during the Tea Break)
15:00 Afternoon Tea
15:30 Benchmarking and Reproducible Robotics in Social Robotics
Amit Kumar Pandey
SoftBank Robotics
15:50 (Repeatable) Semantic Topological Exploration
Stefano Carpin
University of California Merced, USA
16:10 Verification of Autonomous Systems
Signe Redfield
Office of Naval Research, USA
16:30 A Simulation Platform for Benchmarking in Robotics
Olivier Michel
Cyberbotics, Switzerland, by Skype
16:50 Wrap up
Topics
In Robotics research the replicability and reproducibility of results and their objective evaluation and comparison has so far been lacking. This situation impairs both research progress and research result exploitation. However, the community has been aware of the issue for a long time and significant progress has recently been made in this area. In the September 2015 Robotics and Automation Magazine (RAM) special issue authors were asked to provide reproducible experiments (allowing a large degree of freedom about how to define reproducibility and good reporting format). That special issue had a large number of submissions covering almost every area in robotics. Starting in September 2017, RAM started to accept R-Articles (where ‘R’ stands for Reproducible). This workshop aims to discuss in detail the requisites of reproducible experiments in Robotics and their reporting, in order to improve the existing process. To make the discussion concrete we ask the prospective contributors to submit practical examples of reproducible papers that will be published as R-articles on the IEEE Robotics and Automation Magazine.
Check Back! We are uploading all the presentations!
Support
This workshop is supported by the IEEE RAS TC-Pebras. It is also meant as the TC-Pebras TC meeting.
These issues are core issues for RAS and IEEE and they certainly are for TC-Pebras.
