Scalable hardware uses reconfigurable electronics to design circuits for specific applications. Evolutionary hardware, like field-programmable gate arrays, adapts in real-time, creating optimal circuits with minimal human design. This technique has been applied to robotics, including aerospace control loops.
Scalable hardware uses reconfigurable electronics and an adaptive process to design ideal circuits for specific applications. The most common type of commercially available reconfigurable electronics is the field-programmable gate array (FPGA). By setting fitness metrics for the circuit, the scalable hardware can be programmed to automatically adapt to the activity at hand.
An important application of evolutionary hardware is in creating control loops for robots. Imagine a robot equipped with an evolving circuit whose job is to navigate through a room full of obstacles. The hardware is programmed to evolve in real time; circuits that minimize collisions with obstacles are “rewarded” and future directions of evolution are based on the characteristics of successful variants.
One rationale for using evolutionary hardware is that as our robotic systems become increasingly complex, modeling circuit designs using inefficient general-purpose computers will become strenuous. Using evolutionary hardware to solve a real-time adaptive control task, we use specialized computing to crawl through the search space with constant feedback from the real world. Evolutionary techniques enable automated manufacturing of circuit configurations that engineers may never have considered. Continuously creating circuit variations and testing those variations trades computing power for design intelligence.
Sometimes the term evolutionary hardware is also applied to static hardware that has been designed using evolutionary algorithms. But typically, it refers to the hardware itself that has the ability to evolve. The ultimate goal of evolutionary 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 needed.
The evolutionary hardware field is extremely recent, conceived in the summer of 1992. Hugo de Garis, an Artificial Intelligence researcher, is credited as its founder. Evolutionary hardware techniques have already been applied to many fields of robotics, including control loops for aerospace applications.
Protect your devices with Threat Protection by NordVPN
