RatSLAM is a robot navigation system based on models of the rodent brain. On this page you'll find a list of people working on RatSLAM, as well as links to open source RatSLAM code and a list of RatSLAM publications.
An overview of the theoretical background and design of the RatSLAM system.
A video outlining the capabilities of the open source OpenRatSLAM system.
There are approximately 40 RatSLAM related publications, here we have highlighted some of the most important ones. Click on the hyperlinks to go to the publication download page.
Books / Monographs
M. J. Milford, G. Wyeth, D. Prasser, "RatSLAM: A Hippocampal Model for Simultaneous Localization and Mapping," in proceedings of the IEEE International Conference on Robotics and Automation, New Orleans, United States, 2004.
We have released two open source versions of RatSLAM that can be used as part of a robot navigation system or to process your own datasets. A good description of how the code works, how to tune the few parameters and the 3 provided datasets is available in the OpenRatSLAM paper. Please cite this paper if you use the code.
- C++ library version with Robot Operating System (ROS) wrapper and an OpenCv wrapper available from the Google Code. This version is fast and designed to work in real time. Each of the RatSLAM components is cleanly separated allowing easy substitution of your own modules.
- MATLAB version available from our wiki. This version uses many of the built in MATLAB functions to simplify the code. We have used the code to control a robot in real time however the code is more suited to easy offline processing of your datasets.
The code is maintained by Dr David Ball.
The RatSLAM project has received funding from various funding bodies, as listed here:
- Microsoft Research Faculty Fellowship 2013-2014, $100,000
- ARC Discovery Project Grant 2012-2014, "Brain-based Sensor Fusion for Navigating Robots", $140,000
- ARC & NHMRC Thinking Systems: Navigating Through Real and Conceptual Spaces 2006-2011, TS0669699, $3,300,000
- ARC Discovery Project Grant 2009-2011, “Talking with Robots: Evolving Grounded Language for Embodied Agents”, $200,000
- ARC Discovery Project Grant 2005-2007, “Enhancing Intelligent Robot Navigation with the Evolution of a Robot-Friendly Language”, $207,000
- ARC Discovery Project Grant 2003, “Robot Navigation From Nature: Simultaneous Localisation And Mapping Based On Hippocampal Models ”, $90,000
Collaborators (Past and Present)
Boston University, United States
The University of Nottingham, United Kingdom
University of Antwerp, Belgium
The Australian National University, Australia
The University of Queensland, Australia
Commonwealth Scientific and Industrial Research Organisation, Australia