A Simple and Accurate Apollo-Trained Neural Network Controller for Mars Atmospheric Entry

<table class="table-group" id="tab5"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">Final position (m)</td><td class="align_center">-4748517.48, 3786633.63, 1949302.58</td><td class="align_center">Norm</td><td class="align_center">6378620.00</td></tr><tr><td class="align_left">Final velocity (m/s)</td><td class="align_center">101.69, -83.58, -35.31</td><td class="align_center">Norm</td><td class="align_center">136.28</td></tr><tr><td class="align_left">Target (m)</td><td class="align_center">-4744398.27, 3791753.35, 1953372.11</td><td class="align_center">Norm</td><td class="align_center">6379840.99</td></tr><tr><td class="align_left">Missed (m)</td><td class="align_center">4119.21, 5119.72, 4069.53</td><td class="align_center">Norm</td><td class="align_center">7729.19</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Nonlinear integration using 10-layer NN in the Earth model.</div>

International Journal of Aerospace Engineering

tab5

Table 5

Table 5: A Simple and Accurate Apollo-Trained Neural Network Controller for Mars Atmospheric Entry 