ERASER - OpenLicht Knowledge Base

Overview

There are a few subprojects in this repository:

• Base
  • eraser-base: The core part of the framework containing the grammar, various attributes, the parser for model specification files, and Java classes for the openHAB communication via MQTT
• Utility
  • commons.color: Utilities for converting color spaces (XYZ, RGB, HSB)
  • project-template: Template to quickly create new subprojects used by make-new-project.py
• Demos
  • integration and openhab-mock: Playground projects testing some features
  • skywriter-hue-integration: The first real demonstrator integrating the Skywriter gesture recogintion with a Hue using a simple rule
• Machine Learning Integration
  • org.openhab.action.machinelearn: openHAB connector of the Machine Learning Part (implemented by Kay)
  • org.openlicht.action.reinforcementlearning: Reinforcement-Learning of preferences (implemented by Kay)
  • stub.org.openhab.core.scriptengine.action: Stub to make the other two projects build

Setup and Building

This project uses Gradle as the build tool. For detailed information, see setup guidelines

Running the demo

There is a demo project, as explained above to showcase the framework. To start it, run ./gradlew :skywriter-hue-integration:run

This demo is intended to run with a pre-configured openHAB instance and has some hard-coded settings. It will first try to connect to an MQTT broker (with a hard-coded IP) to listen on changes of item states. There is one rule implemented, namely to listen on changes of the item skywriter_xyz expecting MQTT messages of the form XVALUE,YVALUE,ZVALUE, and to change to state of another item iris1_item representing the HSB value of a Hue Iris.

Trivia

The name Eraser is a small pun on the term eRACR, which is an extension of RACR for event recognition. It was chosen to ease the search for a good repository image as it is based on a film.