English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Robustness and resilience of simultaneous localization and mapping (SLAM) arecritical requirements for modern autonomous robotic systems. One of theessential steps to achieve robustness and resilience is the ability of SLAM tohave an integrity measure for its localization estimates, and thus, haveinternal fault tolerance mechanisms to deal with performance degradation. Inthis work, we introduce a novel method for predicting SLAM localization errorbased on the characterization of raw sensor inputs. The proposed method relieson using a random forest regression model trained on 1-D global pooled featuresthat are generated from characterized raw sensor data. The model is validatedby using it to predict the performance of ORB-SLAM3 on three different datasetsrunning on four different operating modes, resulting in an average predictionaccuracy of up to 94.7\%. The paper also studies the impact of 12 different 1-Dglobal pooling functions on regression quality, and the superiority of 1-Dglobal averaging is quantitatively proven. Finally, the paper studies thequality of prediction with limited training data, and proves that we are ableto maintain proper prediction quality when only 20 \% of the training examplesare used for training, which highlights how the proposed model can optimize theevaluation footprint of SLAM systems.

Prediction of SLAM ATE Using an Ensemble Learning Regression Model and 1-D Global Pooling of Data Characterization