Open Automaton Project

Objective

Welcome to the homepage of the Open Automaton Project. The purpose of this project is to engineer modular software and electronic components, from which it is possible to assemble an intelligent PC-based mobile robot suitable for home or office environments.

All source code is distributed under the terms of the GNU General Public License. If you are not familiar with this license, please check out this very thorough FAQ about the GNU GPL.

Motivation

Moore's Law has allowed modern mass-produced PC hardware to catch up with the demanding requirements of advanced vision processing and artificial intelligence. Based on current state-of-the-art PC mainboard technology, it is viable to build an intelligent mobile robot with stereo vision, for the price of a good PC.

This project aims to fill the gap between the powerful mobile robot platforms typically used by researchers, and the small rug-roving robots with limited processing power that are popular with hobbyists.

The first decade of the 21^st century could well see the rise of the affordable and useful domestic mobile robot. This project aims to provide some of the building blocks that could make this possible.

Scope

When this project was first conceived, its scope was to include devising a standard framework of hardware and software interfaces that define the contracts between interconnected hardware and software components. However, there is now well implemented modular open source code for mobile robots that arguably constitutes "de-facto" standards (see the Player/Stage project, for example). So rather than re-invent the wheel, the Open Automaton Project now focuses on implementation rather than defining standards.

The specific project goals are:

(i)	Design a coherent set of modular components (hardware and software) that conform to standards (where possible), and implement the functionality of an intelligent mobile robot. Use pre-built components that are readily available where possible (and when such pre-built components are affordable).
(ii)	Minimize cost. It should be possible to build a robot for around the price of a PC (target: US$1,500 to $2,000). Consumer grade hardware components are to be used in preference to professional grade products.
(iii)	Focus on stereo vision as the primary spatial sensor to produce useful space occupancy data. Central to the success of this project is the implementation of a functioning low-cost real-time vision system. The prevalence of FireWire-enabled WebCams and mainboards makes this goal reachable from the standpoint of cost; the difficult part here is the software.

Mailing List

If you would like to stay abreast of news and developments, please join the discussion mailing list. Your email address will be kept confidential.

An archive of the messages that have already been posted to the mailing list is available on this page.

Community Wiki Pages

The OAP Community Web Site is a place where people interested in the project can contribute material and share ideas. Here you will find profiles of some of the robot builders and their droids, as well as useful resources such circuit board layouts and bills of materials.