Evolvable hardware uses reconfigurable electronics and an adaptive process to design circuits ideal for specific applications. The most popular commercially available type of reconfigurable electronics is the FPGA (field-programmable gate array). By setting fitness metrics for the circuit, evolvable hardware can be programmed to automatically adapt to the task at hand.
One prominent application of evolvable hardware is in the creation of control circuits for robots. Imagine a robot equipped with an evolvable circuit whose task is to navigate through a room filled with obstacles. The hardware is programmed to evolve in real time; circuits that minimize collisions with obstacles are "rewarded" and future directions for evolution are based upon features of the successful variants.
One motivation for using evolvable hardware is that as our robotics systems become increasingly complex, modelling circuit designs using inefficient general-purpose computers will become tiresome. By using evolvable hardware to solve an adaptive control task in realtime, we employ specialized computing to crawl through the search space with constant feedback from the real world. Evolutionary techniques allow the automated production of circuit configurations that engineers may never have considered. The continuous creation of circuit variations and tests on those variations trades computing power for design intelligence.
Sometimes the term evolvable hardware is also applied to static hardware that has been designed using evolutionary algorithms. But typically, it refers to the hardware itself having the capability to evolve. The ultimate goal of evolvable hardware is to create a general-purpose module that can be plugged into anything that requires electronics, producing an optimal circuit base with minimal human design intelligence necessary.
The field of evolvable hardware is extremely recent, conceived in the summer of 1992. Hugo de Garis, an Artificial Intelligence researcher, is credited as its founder. Evolvable hardware techniques have already been applied to many fields of robotics, including control circuits for aerospace applications.
