The 2008 Robotics Science and Systems Conference will be hosted by ETH Zurich, Switzerland, on June 25-28, 2008. The workshop proposal has been accepted to be held on June 28, and is co-organized by Angel P. del Pobil from Universitat Jaume I in Spain, John Hallam from the University of Southern Denmark, and Fabio Bonsignorio from Heron Robots (Italy).
As the complexity of current robotic and embodied intelligent systems grows, it is more and more necessary to define proper experimental approaches and benchmarking procedures. 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. New more successful implementations of concepts already presented in the literature, but not implemented with exhaustive experimental methodology, risk to be ignored, if appropriate benchmarking procedures are not in place, allowing comparing the actual practical results with reference to standard accepted procedures. Both replication and benchmarking are needed to foster a cumulative advancement of our knowledge of intelligent physical agents and even to correctly appreciate disruptive innovation in the science and technology of robots. Should we take inspiration from experimental practice in disciplines such as biology or medicine?
This workshop aims to provide a discussion forum on these topics and to identify guidelines for the future. The workshop will be organized in such a way as to generate fruitful discussions, it will consist of invited presentations (45 min. each) and regular presentations (25 min. each) with a significant amount of additional time for discussions. The primary audience of the workshop is intended to be researchers and practitioners both from academia and industry with an interest in experimental robotics. The workshop is also aimed at benchmarking and objectively evaluating performance of robots. Accordingly, it is envisioned to be useful for anyone who has an interest in quantitative performance evaluation of robots and/or robot algorithms. Some controversial issues will be discussed such as: measuring autonomy or information metrics of intelligent systems, or the concept itself of replicability or benchmarking of research results in robotics.