A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Times of learning/group</td><td class="align_center">User #1</td><td class="align_center">User #2</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">400/A1</td><td class="align_center">30</td><td class="align_center">21</td></tr><tr><td class="align_left">550/A2</td><td class="align_center">13</td><td class="align_center">16</td></tr><tr><td class="align_left">700/A3</td><td class="align_center">12</td><td class="align_center">13</td></tr><tr><td class="align_left">850/A4</td><td class="align_center">9</td><td class="align_center">7</td></tr><tr><td class="align_left">1000/A5</td><td class="align_center">20</td><td class="align_center">17</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Number of failures for different experimenters’ human-robot collaboration results.</div>

Computational Intelligence and Neuroscience

tab4

Table 4

Table 4: A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning 