Predicting Performance of SLAM Algorithms
This addresses the need for ex-ante performance evaluation in autonomous robotics, offering a practical tool for algorithm selection and optimization, though it is incremental as it builds on existing SLAM methods.
The paper tackles the problem of predicting SLAM algorithm performance in unseen environments before execution, by modeling the relationship between performance and environmental features from simulated data, achieving predictions that enable pre-deployment assessment.
Among the abilities that autonomous mobile robots should exhibit, map building and localization are definitely recognized as fundamental. Consequently, countless algorithms for solving the Simultaneous Localization And Mapping (SLAM) problem have been proposed. Currently, their evaluation is performed ex-post, according to outcomes obtained when running the algorithms on data collected by robots in real or simulated environments. In this paper, we present a novel method that allows the ex-ante prediction of the performance of a SLAM algorithm in an unseen environment, before it is actually run. Our method collects the performance of a SLAM algorithm in a number of simulated environments, builds a model that represents the relationship between the observed performance and some geometrical features of the environments, and exploits such model to predict the performance of the algorithm in an unseen environment starting from its features.