Fiches de cours

Caution, these contents corresponds to the coursebooks of last year

---

Deep learning for autonomous vehicles

CIVIL-459

Lecturer(s) :

Alahi Alexandre Massoud

Language:

English

Summary

Self-driving cars, delivery robots, or self-moving segways. Most of these AI-driven transportation systems rely on four pillars: 1-Sensing, 2-Perceiving, 3-Predicting, and 4-Acting steps. Students will learn the fundamentals behind these four pillars, i.e., the technology behind autonomous vehicles.

Content

Introduction to AI-driven systems

2. Sensing modalities

3. Perceiving: how to extract meaningful information from raw data?

                - Intro to machine learning (fundamentals to regression and classification)

                - Intro to deep learning (Neural Network, CNN, regularization techniques)

                - State-of-the-art techniques for localisation, detection, and tracking objects in the context of autonomous vehicles.

4- Predictive models

                - Intro to Recurrent Neural Networks

                - Learning to clone socially-accepted human behavior

5- Acting: challenges and ethical impacts

 

Students will implement perception tasks for autonomous vehicles and participate to a human-robot tandem race.

Keywords

Deep Learning, Autonomous Vehicle, Artificial intelligence, Machine learning, Self-driving car

Learning Prerequisites

Required courses

Fundamentals in Analysis, Linear algebra, Probability and Statistics.

Programming skills.

Learning Outcomes

By the end of the course, the student must be able to:

• Define the fundamental steps behind an AI-driven system
• Design the building steps of an autonomous vehicle
• Implement an algorithm for each step
• Explain and understand the challenges and ethical impacts

Teaching methods

Ex cathedra

Assessment methods

 Lab projects (in group): 30%

Midterm: 30%

Final project (in group): 40%