{"id":49,"date":"2016-03-19T16:21:02","date_gmt":"2016-03-19T16:21:02","guid":{"rendered":"http:\/\/martinelectronics.co.uk\/wp\/?p=49"},"modified":"2016-03-19T16:22:42","modified_gmt":"2016-03-19T16:22:42","slug":"genetic-algorithms-making-a-robot-evolve","status":"publish","type":"post","link":"https:\/\/martinelectronics.co.uk\/wp\/?p=49","title":{"rendered":"Genetic Algorithms, Making a Robot Evolve"},"content":{"rendered":"
\"genetic<\/a>
genetic algorithms<\/figcaption><\/figure>\n

Evolution is a fact of life, it is the defining characteristic of life itself, but that doesn\u2019t mean a stupid robot can\u2019t evolve. For his entry into the Hackaday<\/a> Pi Zero contest, diemastermonkey<\/a> is doing just that: evolution for robots built around microcontrollers and a Raspberry Pi.<\/p>\n

The project is a physical extension to genetic algorithms. Just like DNA and proteins have no idea what they\u2019re actually doing, microcontrollers don\u2019t either. Instead of randomly switching up base pairs and amino acids, his project makes random connections pins depending on the values of those pins.<\/p>\n

The potential of these randomly programmed robots is only as good as the fitness function, and so far he has seen some surprising success. When putting these algorithms into a microcontroller connected to a tilting table mechanism and a PIR sensor, the robot eventually settled on a bit of code that would keep a ball in motion. You can check out the video of this below.<\/p>\n