Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2022 Dec 27;3:e30. doi: 10.1017/wtc.2022.29

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2022

This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.

PMC Copyright notice

Figure 4. — Schematic representation of the implemented pipeline for compliance error compensation. Three main sources of data are used: motion capture of human segments (triangles, ) and robot segments (circles, ) and robot-sensor derived data (rhombus). The latter and the are used to construct the feature vector for the gradient boosting algorithm. The variable is used as the target variable. The data from the eight study participants are then arranged such that six participants are part of the training set, one is used for the validation set, and one for the model testing set. This splitting strategy was repeated eight times to show the model generalizability across the data of all of the study participants.

Inline graphic — Schematic representation of the implemented pipeline for compliance error compensation. Three main sources of data are used: motion capture of human segments (triangles, ) and robot segments (circles, ) and robot-sensor derived data (rhombus). The latter and the are used to construct the feature vector for the gradient boosting algorithm. The variable is used as the target variable. The data from the eight study participants are then arranged such that six participants are part of the training set, one is used for the validation set, and one for the model testing set. This splitting strategy was repeated eight times to show the model generalizability across the data of all of the study participants.