I try my best to release my software to the public in a timely manner so that other researchers/enthusiasts may find it useful for their own work. I would really appreciate that you please attribute my work correctly in your code, publications etc.


slam_karto_g2o: Is a C++ ROS package for pose-graph SLAM with g2o. All you need is wheel odometry and a laser scanner to run this node.


slam_karto_gtsam: Is a C++ ROS package for pose-graph SLAM with GTSAM. All you need is wheel odometry and a laser scanner to run this node.


slam_karto_sesync: Is a C++ ROS package for pose-graph SLAM with SE-SYNC. All you need is wheel odometry and a laser scanner to run this node.


py_slam_dataset: Is a python utility for pose-graph SLAM. You can use it to generate a dataset (very useful to test a solver) and plot the solver output. It gives you flexibility to generate arbitrarily large datasets with different noise params.


Belief Space Planning with OMPL (C++) : This application is an implementation of Multi-Modal Motion Planning (M3P) and Feedback Information Road Maps (FIRM) with OMPL. M3P enables lost robots to localize, FIRM is a multi-query approach for planning under uncertainty which is a belief-space variant of probabilistic roadmap. Our goal is to make this software open source so as to enable the motion planning community to use belief space planners for exciting new applications.


RFM-SLAM: MATLAB code for  “RFM-SLAM: Exploiting Relative Feature Measurements to Separate Orientation and Position Estimation in SLAM“, In Proc. IEEE International Conference on Robotics and Automation (ICRA), Singapore, May 29 – June 3, 201


Belief Space iLQG: Belief Space Motion Planning Using iLQG. Builds on top of iLQG (Iterative Linear Quadratic Gaussian Control) Matlab implementation by Yuval Tassa and the paper “Motion Planning under Uncertainty using Iterative Local Optimization in Belief Space“, Van den berg et al., International Journal of Robotics Research, 2012


FIRM MATLAB Toolbbox : This application is an implementation of Feedback Information Road Maps (FIRM) in MATLAB. There are easy to use demos with a GUI.


GPS MATLAB Toolbox : This is a collection of matlab scripts to simulate the Global Positioning System. Feel free to use this in your research. You can use this package for example to simulate the coordinates computed by a GPS receiver  mounted on an aircraft flying anywhere on the earth. It simulates clock errors, atmospheric delays, carrier-phase differential GPS etc.


Feedback / Reporting Bugs
I would really appreciate feedback/criticism for my work. Please report bugs by creating an issue on the project’s github page.