ISTA- Sensor fusion navigation simulator: Integration of CARLA with an in-house IMU/GNSS-Simulator

 

The main goal of this thesis is to extend the ISTA in-house INS/GNSS-Simulation environment with the observation of LiDAR-System.

The driving idea behind using simulated observation of different sensors is to provide the developer with more flexibility, since it allows him to generate and test different scenarios under different conditions, without living his desk. In addition, the observation of the supporting devices, such as GNSS can be used with optimal quality.

D2_Simulator.png

Source: http://carla.org/

 

To this end the LiDAR-Observations can be simulated using an open source tool such as CARLA. This tool has been developed from the ground up to support development, training, and validation of autonomous driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specification of sensor suites, environmental conditions, full control of all static and dynamic actors, maps generation and much more.

 

Tasks:

  • To get familiar with the CARLA simulator
  • Identify advantages/disadvantages, constraints or use cases of CARLA for the purpose of the thesis
  • Configuration of the CARLA environment according to the outcome of the previous task (driving scenarios, configuration of sensors, etc…)
  • Developing the processing chain for the interface (Input/Output) between CARLA and the INS/GNSS-Simulator
  • Integration with the ISTA in-house INS/GNSS-Simulator
  • Analysis of the outcome of the extended ISTA-Simulator (CARLA + INS/GNSS Simulator), which can be programmed in MATLAB.
  • All task must be documented, specially: the chosen use cases, the final configuration of CARLA and the sensors, the integration of CARLA with the GNSS-INS simulator and the analysis of the extended simulator tool.

 

Optional:

  • Generate various stand-alone simulated LiDAR scenarios.

 

Requirements for the candidate are:

  • Interest to elaborate different sensor fusion topics!
  • Knowledge of LiDAR, GNSS and INS as a standalone sensors (or interest to self-learn how they work)
  • Basic knowledge of INS/GNSS integration
  • Programming skills, preferred are Python and C++
  • The ability to both work independently and to answer scientific questions

 

Start date: immediately

 

Duration: according to project work / thesis duration


Contact Person:

 

Daniela Sanchez Morales & Mohamed Bochkati

Institute of Space Technology and Space Applications (ISTA)

Faculty of Aerospace Engineering (LRT)

Universität der Bundeswehr München

Werner-Heisenberg-Weg 39, 85577 Neubiberg, Germany

Building 61, Room 1106

Phone: +49 89-6004-3056, Fax: +49 89-6004-2584

Email: daniela.sanchez@unibw.de