Evolvable hardware using evolutionary computation to design and optimize hardware systems

J.D. Lohn, G.S. Hornby
<span title="">2006</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/x56wk4aznnehjnnlaxh66hctcq" style="color: black;">IEEE Computational Intelligence Magazine</a> </i> &nbsp;
T he central idea behind evolvable hardware is to gain the ability to automatically design and optimize electrical and mechanical structures by harnessing the power of an evolutionary algorithm. For example, one could apply a genetic algorithm to automatically design an airplane wing to maximize lift and minimize drag. The range of applications is wide and encompasses of multitude of application domains: jet engines, trusses, chip design and fabrication, antenna design, controller algorithms,
more &raquo; ... tical systems, robotics, and a wide array of engineering optimization problems to improve metrics such as cost, power, size, thermal properties, and manufacturability. At one level, the evolutionary algorithm is simply looking for combinations of input parameters to accomplish a hardware optimization problem of some sort. At a deeper level, the algorithm is searching and exploiting design spaces induced by the physics of the materials used to build the hardware. In this sense, the EA is exploring the dark corners of what is combinatorially possible given the imposed natural (physics) and artificial (human-specified) design constraints. These are subspaces that humans have left unexplored, and they can indeed be small corners or in some cases large expanses of virgin territory. A carefully constructed evolutionary algorithm will have little bias to limit it to only the known areas of the design space. Although cliched, "out-of-the-box thinking" captures the essence of what the algorithm is doing. As a result, many Abstract: Evolvable hardware lies at the intersection of evolutionary computation and physical design. Through the use of evolutionary computation methods, the field seeks to develop a variety of technologies that enable automatic design, adaptation, and reconfiguration of electrical and mechanical hardware systems in ways that outperform conventional techniques. This article surveys evolvable hardware with emphasis on some of the latest developments, many of which deliver performance exceeding traditional methods. As such, the field of evolvable hardware is just now starting to emerge from the research laboratory and into mainstream hardware applications.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mci.2006.1597058">doi:10.1109/mci.2006.1597058</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jzkzpv7anvavbl5ebc6cdu42z4">fatcat:jzkzpv7anvavbl5ebc6cdu42z4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20081006005120/http://ti.arc.nasa.gov/people/jlohn/Papers/ci-magazine-Feb2006.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c0/98/c09849b307689d6dcb308b24a7bb49b802b64638.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mci.2006.1597058"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>