Measuring progress in robotics: benchmarking and the ‘measure-target confusion’

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureHoofdstukAcademicpeer review

Samenvatting

While it is often said that in order to qualify as a true science robotics should aspire to reproducible and measurable results that allow benchmarking, I argue that a focus on benchmarking will be a hindrance for progress. Several academic disciplines that have been led into pursuing only reproducible and measurable ‘scientific’ results—robotics should be careful not to fall into that trap. Results that can be benchmarked must be specific and context-dependent, but robotics targets whole complex systems independently of a specific context—so working towards progress on the technical measure risks missing that target. It would constitute aiming for the measure rather than the target: what I call ‘measure-target confusion’. The role of benchmarking in robotics shows that the more general problem to measure progress towards more intelligent machines will not be solved by technical benchmarks; we need a balanced approach with technical benchmarks, real-life testing and qualitative judgment.

Originele taal-2Engels
TitelMetrics of Sensory Motor Coordination and Integration in Robots and Animals
SubtitelHow to Measure the Success of Bioinspired Solutions with Respect to their Natural Models, and Against More ‘Artificial’ Solutions?
RedacteurenFabio Bonsignorio, Elena Messina, Angel P. del Pobil, John Hallam
Plaats van productieCham
UitgeverijSpringer
Pagina's169-179
Aantal pagina's11
ISBN van elektronische versie978-3-030-14126-4
ISBN van geprinte versie978-3-030-14124-0
DOI's
StatusGepubliceerd - 1 jan. 2020

Publicatie series

NaamCognitive Systems Monographs
Volume36
ISSN van geprinte versie1867-4925
ISSN van elektronische versie1867-4933

Vingerafdruk

Duik in de onderzoeksthema's van 'Measuring progress in robotics: benchmarking and the ‘measure-target confusion’'. Samen vormen ze een unieke vingerafdruk.

Citeer dit