Main Page

ROAMFREE (Robust Odometry Applying Multisensor Fusion to Reduce Estimation Errors) is a joint research project of Politecnico di Milano and Università degli Studi di Milano-Bicocca. ROAMFREE focuses on robust odometry based on multisensor fusion; its expected output includes a novel probabilistic formal framework for multisensor odometry.

The aims of the project are:

  • detailed analysis of the problem of robust odometry based on multisensor fusion;
  • design and realization of the ROAMFREE framework for multisensor odometry and of a set of logic sensors;
  • implementation of calibration techniques for single logic sensors;
  • validation and demonstration of logic sensors in real situations;
  • implementation of calibration techniques for single logic sensors;
  • validation and demonstration of the framework with different configurations of logic sensors;
  • study and implementation of methods and techniques for mutual calibration between different logic sensors;
  • study of modules implementing active exploration strategies, i.e. determining robot trajectories that optimize the quality of the odometric information produced.

The ROAMFREE Sensor Fusion Library is a C++/Python, ROS compatible, software package which delivers out-of-the-box online 6DOF pose tracking and sensor parameter self calibration. Thanks to its rich logical sensors and kinematics library it can fit to virtually any robotic platform. It is released under the GNU Lesser General Public License.


This project has been funded by MIUR: Ministero dell'Istruzione dell'Università e della Ricerca.
The project's logo is "Tin Cow" by loopydave.