Radar detection simulation for various driving scenarios in multiple sensor setup

2023-2024 tavasz

Nincs megadva

Téma leírása

Robust and reliable environmental perception is a key aspect for the safe operation of highly automated road vehicles. In the last decade, radar sensors have already been used with success in various driver assistant systems offering comfort and safety features such as adaptive cruise control, dead spot monitoring, and automatic emergency braking. With their proven performance, radars are considered among the primary sensors for future environment sensing systems as well. While the current driver assistance systems are mainly based on a single front radar setup, the tendency is to use multiple sensors to process the entire surrounding of the vehicle.

During the development of environment modelling algorithms, one of the most challenging tasks is to provide appropriate ground truth data for testing purposes. One option for getting the necessary test data is the post-processing (e.g., labeling) of real-world measurements. However, this method has serious cost implications, and it is often complicated to find the desired driving scenario among the recorded data.  Another possibility is the simulation of sensor data.

This topic aims to provide a flexible framework for the generation of radar detections in case of various road topologies and sensor setups. The main objectives are:

  • Road geometry generation
    • Generate the road geometry based on a road topology definition (straight, curved and transition segments, lanes, guardrails, junctions, etc.)
  • Radar detection generation for multiple sensors
    • Simulate labeled radar detections based on the generated road geometry and the defined number and position of the sensors.
    • Consider the asynchronous clock signals of the sensors.
  • Validation and assessment
    • Develop metrics to compare the simulated radar detection data to real world measurements.


To solve the task, the student receives help from the staff of the Continental AI Development Center.

If you are interested in the topic, be sure to contact Dávid Sik by email before applying, indicating the selected topic, training level, major and the planned project subject.

Külső partner: Continental Autonomous Mobility Hungary

Maximális létszám: 1 fő