OpenRatSLAM: an open source brain-based SLAM system

Abstract

RatSLAM is a navigation system based on the neural processes underlying navigation in the rodent brain, capable of operating with low resolution monocular image data. Seminal experiments using RatSLAM include mapping an entire suburb with a web camera and a long term robot delivery trial. This paper describes OpenRatSLAM, an open-source version of RatSLAM with bindings to the Robot Operating System framework to leverage advantages such as robot and sensor abstraction, networking, data playback, and visualization. OpenRatSLAM comprises connected ROS nodes to represent RatSLAM’s pose cells, experience map, and local view cells, as well as a fourth node that provides visual odometry estimates. The nodes are described with reference to the RatSLAM model and salient details of the ROS implementation such as topics, messages, parameters, class diagrams, sequence diagrams, and parameter tuning strategies. The performance of the system is demonstrated on three publicly available open-source datasets.

Appendices

Appendix A: Included datasets

The three datasets described in this paper are available online at http://wiki.qut.edu.au/display/cyphy/OpenRatSLAM+datasets. Details of the ROS bag files are provided below.

Note that the data in the New College dataset belongs to the original authors from Oxford University.

Appendix B: Installation instructions and tutorial

Installing dependencies

OpenRatSLAM depends on ROS packages: opencv2 and topological_nav_msgs and also on 3D graphics library Irrlicht. Irrlicht can be installed on Ubuntu with apt-get

sudo apt-get install libirrlicht-dev

Build instructions

Checkout the source from SVN:

svn checkout http://ratslam.googlecode.com/svn/branches/ratslam_rosratslam_ros

Setup ROS environment variables by typing:

. /opt/ros/fuerte/setup.sh

The OpenRatSLAM directory needs to be added to the environment variable ROS_PACKAGE_PATH.

export ROS_PACKAGE_PATH=$ROS_PACKAGE_PATH:/path/to/OpenRatSLAM

Then build OpenRatSLAM with

rosmake

Running OpenRatSLAM

To use one of the provided pre-packaged bag files, download the bag file for either:

$\bullet$ iRat 2011 in Australia

$\bullet$ Car in St Lucia 2007

$\bullet$ Oxford New College 2008 dataset

All datasets are available at https://wiki.qut.edu.au/display/cyphy/OpenRatSLAM+datasets.

Place the dataset in the OpenRatSLAM directory.

Run the dataset and RatSLAM by typing either

roslaunch irataus.launch

rosbag play irat_aus_28112011.bag

or

roslaunch stlucia.launch

rosbag play stlucia_2007.bag

or

roslaunch oxford_newcollege.launch

rosbag play oxford_newcollege.bag

Using rviz

The map created by OpenRatSLAM will be periodically published to rviz. To run rviz:

rosrun rviz rviz

Click on the ”Add” button down the bottom left of the window. Choose ”MarkerArray” from the list. In the field ”Marker Array Topic” on the left, click on the button with 3 dots. Choose the topic $<$my_robot$>$/ExperienceMap/MapMarker

Using OpenRatSLAM with a custom dataset

Creating a bag file

The easiest way to tune RatSLAM is using an offline dataset. Any robot providing camera images as sensor_msgs/CompressedImage and odometry as nav_msgs/Odometry can be used to create a dataset. The images and odometry must be in the form $<$my_robot$>$/camera/image and$<$my_robot$>$/odom.

To convert topic names to the correct format run:

rostopic echo $<$path/to/my/robot/camera$> {\vert }$ rostopic pub $<$my_robot$>$/camera/image sensor_msgs/CompressedImage & rostopic echo $<$path/to/my/robot/odom$> {\vert }$ rostopic pub $<$my_robot$>$/odom nav_msgs/Odometry &

Start recording into a bag file:

rosbag record -O $<$my_robot$>.$bag $<$my_robot$>$/camera/image $<$my_robot$>$/odom

Start the robot and collect the dataset. Press Ctrl-C at the terminal to finish recording.

Running the bag file

To run a custom bag file, a new config file and launch file are required.

Creating a new config file

In a terminal type

cd ratslam_ros

cp config/config_stlucia.txt config/config_$<$my_robot$>.$txt

gedit config/config_$<$my_robot$>.$txt

Change the first line

topic_root=stlucia

to

topic_root=$<$my_robot$>$

Creating a new launch file In the same terminal type

cp stlucia.launch $<$my_robot$>.$launch

gedit $<$my_robot$>.$launch

Replace all references to ”../config/config_stlucia.txt” with ”../config/config_$<$my_robot$>.$txt”

Comment out the visual odometry node to prevent it from running. Replace

$<$node name=”RatSLAMVisualOdometry” pkg=”ratslam_ros” type=”ratslam_vo” args=”../config/config_$<$my_robot$>.$txt _image_transport:=compressed” cwd=”node” required=”true” /$>$

with

$<$!– $<$node name=”RatSLAMVisualOdometry” pkg=”ratslam_ros” type=”ratslam_vo” args=”../config/config_$<$my_robot$>.$txt _image_transport:=compressed” cwd=”node” required=”true” /$>$–$>$

Running your dataset Your dataset can now be run the same way is the provided datsets:

roslaunch $<$my_robot$>.$launch

rosbag play $<$my_robot$>.$bag

Tuning parameters

Open the created config file

gedit config/config_$<$my_robot$>.$txt

Edit the settings under [ratslam]. Refer to Sect. 4 for parameter details.