Introduction
High-quality datasets are a key enabler for data-driven methods in autonomous driving and mobile robotics. This is particularly true in unstructured environments and private areas (e.g., campuses, industrial sites, private roads), where vehicle behavior and interactions can differ substantially from public-road scenarios. In these contexts, collecting representative data of vehicle operation and VRU (Vulnerable Road Users) interactions is essential to support the development and validation of perception, prediction, and motion planning algorithms.
Goals
This thesis aims to define and implement a manual-driving data acquisition pipeline for dataset creation. The main goal is to design a robust, reusable acquisition setup and to perform experimental campaigns to collect and store data in a format suitable for downstream data-driven processing.
The thesis student’s work will include:
- Definition of the hardware/software architecture of a prototypical, ROS2-based platform for data acquisition, based on a distributed architecture and multi-sensor setup.
- Experimental testing aimed at acquiring data and saving it in a format suitable for its use in data-driven algorithms (e.g., structured logs, synchronized topics, metadata and calibration/configuration artifacts).
Optional extensions (for a stronger thesis)
- ROS2;
- Python and/or Matlab;
- Ubuntu Linux;
- Basic familiarity with Docker (can be learned during the thesis).
- During the thesis, the student will also study techniques for reliable data logging and storage; if data analysis is included, basic machine learning concepts will be introduced as needed.
Contact
Stefano Arrigoni: stefano.arrigoni@polimi.it
For inquiries and further information, please email the first author, copying the other authors in CC