Saved in:
Bibliographic Details
Main Authors: Norton, Adam, Flynn, Brian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.04736
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • The robotics research field lacks formalized definitions and frameworks for evaluating advanced capabilities including generalizability (the ability for robots to perform tasks under varied contexts) and reproducibility (the performance of a reproduced robot capability in different labs under the same experimental conditions). This paper presents an initial conceptual framework, MIRRER, that unites the concepts of performance evaluation, benchmarking, and reproduced/replicated experimentation in order to facilitate comparable robotics research. Several open issues with the application of the framework are also presented.