Program Overview

MACHINE LEARNING FOR AUTOMATED DRIVING

Overview

The teaching unit proposes the theory and application of state-of-the-art techniques in deep learning for automated driving, particularly concerning context perception and prediction.

Aims and Content

Learning Outcomes

The course provides students with advanced knowledge and solid understanding of the state of the art machine learning techniques used in automated driving, particularly with regard to context perception and prediction. The course also introduces tiny machine learning firmware on microcontrollers for field deployment. The student will develop analytical and design skills through a project.

Aims and Learning Outcomes

The main objective of the teaching unit is for the student to gain a broad knowledge of state-of-the-art deep learning techniques for automated driving. For each topic covered, the student will have the opportunity to learn the theoretical foundations and study application code. Examples are proposed in order to verify the acquisition of knowledge and stimulate its application. The examples will use the Python language and the libraries sk-learn, sk-time, Keras/Tensorflow, PyTorch.

The teaching unit will stimulate the students to analyze the computational load of the various deep learning models and think of possible hardware optimizations.

The project that will be agreed upon for the examination is aimed at stimulating and verifying in the field the student's design and implementation skills, and acquired knowledge.

The learning outcomes concern the realization of the mentioned learning objectives. At the end of the teaching unit, the student will be able to analyze and design state-of-the-art deep learning solutions for context perception and evolution prediction.

Prerequisites

• Digital systems electronics
• Fundamentals of programming
• Tiny Machine learning

Teaching Methods

Lectures face-to-face, with use of slides, and examples/exercises carried out on the PC, mainly using the sk-learn, sk-time, Keras/Tensorflow, PyTorch libraries, in Python language. Student reception. Proposal, implementation, and discussion of a project.

Students with valid certifications for Specific Learning Disorders (SLDs), disabilities, or other educational needs are invited to contact the teacher and the School's contact person for disability at the beginning of teaching to agree on possible teaching arrangements that, while respecting the teaching objectives, take into account individual learning patterns.

Syllabus/Content

• Introduction to machine learning for automated driving
• Training & pre-training of multilayer perceptrons
• Optimizers
• Regularization
• CNN architectures and training
• Attention mechanism
• Object detection
• Semantic / panoptic segmentation
• Timeseries classification and prediction
• LSTM, 1D convolution
• Transformers and Large Language Models
• Transformers for image processing
• Vision Language Models
• Trustworthy Machine Learning (explainability and robustness)
• Unsupervised machine learning (clustering, anomaly, novelty detection)

Recommended Reading/Bibliography

• A. Geron, Hands-On Machine Learning With Scikit-Learn and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent, O' Reilly
• I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, The MIT Press
• Documentation of the used libraries
• Lecture notes and other material (typically, scientific papers) suggested by the lecturer during the course

Non-attending students may contact the lecturer to agree on the best arrangements.

Teachers and Exam Board

• Professor: Francesco Bellotti
• Exam Board:
  • Francesco Bellotti (President)
  • Matteo Fresta
  • Luca Lazzaroni
  • Riccardo Berta (President Substitute)

Lessons

Lessons Start

The lesson calendar is available.

Class Schedule

The timetable for this course is available.

Exams

Exam Description

Project work on an application example of machine learning for automated driving.

Students with valid certifications for Specific Learning Disorders (SLDs), disabilities, or other educational needs are invited to contact the teacher and the DITEN contact person for disability to agree on the possible use of specific modalities and supports that will be determined on a case-by-case basis, according to the University regulation for the inclusion and right to study of students with disabilities or specific learning disorders.

Assessment Methods

The exam aims at verifying through a project the knowledge acquisition and solid understanding of the state of the art machine learning techniques used in automated driving, particularly with regard to context perception and prediction. The project may involve tiny machine learning deployment.

Evaluation will take place at the various stages of project preparation: definition talks, design/implementation of the solution, final discussion of a paper describing the work done.

The lecturer will also keep in mind the student's participation during the course.

Students with valid certifications for Specific Learning Disorders (SLDs), disabilities, or other educational needs are invited to contact the teacher and the DITEN contact person for disability to agree on the possible use of specific modalities and supports that will be determined on a case-by-case basis, according to the University regulation for the inclusion and right to study of students with disabilities or specific learning disorders.

Exam Schedule

• 07/01/2026, 09:00, GENOVA, Oral
• 30/01/2026, 09:00, GENOVA, Oral
• 13/02/2026, 09:00, GENOVA, Oral
• 03/06/2026, 09:00, GENOVA, Oral
• 01/07/2026, 09:00, GENOVA, Oral
• 24/07/2026, 09:00, GENOVA, Oral
• 02/09/2026, 09:00, GENOVA, Oral

Further Information

Ask the professor for other information not included in this description of the teaching unit.