Viability of Decisional DNA in Robotics

Abstract

The Decisional DNA is an artificial intelligence system that uses prior experiences to shape future decisions. Decisional DNA is written in the Set Of Experience Knowledge Structure (SOEKS) and is capable of capturing and reusing a broad range of data. Decisional DNA has been implemented in several fields including Alzheimer's diagnosis, geothermal energy and smart TV. Decisional DNA is well suited to use in robotics due to the large amount of data available and the generally repetitive nature of the tasks robots perform. However, there is very little evidence about the system's performance in this application. This project aims to assess the viability of SOEKS in robotics. Several knowledge representation approaches were explored then coded in the Java programming language. A hardware platform was constructed from readily available electronics and set up to be compatible with the Java language. Codes were installed on the hardware platform and tested by conducting a series of feature mapping tasks. Success of this project could lead to the future use of SOEKS in robot control.