A Robot Calibration Method Based on Joint Angle Division and an Artificial Neural Network

<table class="fixed-width table-group" id="tab5"><tr><td><table class="table"><colgroup><col style="width:17.10em"/><col style="width:4.48em"/><col style="width:5.41em"/><col style="width:5.49em"/></colgroup><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left"> </td><td class="align_center">Average</td><td class="align_center">Minimum</td><td class="align_center">Maximum</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">After geometric error compensation</td><td class="align_center">9</td><td class="align_center">7.86</td><td class="align_center">14.01</td></tr><tr><td class="align_left">Compensation through the BP network</td><td class="align_center">6.5</td><td class="align_center">5.12</td><td class="align_center">10.22</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The results calibrated by the ANN model directly (cm).</div>

Mathematical Problems in Engineering

tab5

Table 5

Table 5: A Robot Calibration Method Based on Joint Angle Division and an Artificial Neural Network 