Teaching: Sensor Fusion and Scene Understanding for AD/ADAS at Centrale Nantes
Abstract
This lecture introduced the fundamental concepts, architectures, and practical challenges of sensor fusion and scene understanding for AD/ADAS systems. Topics included multi-sensor perception pipelines, probabilistic fusion, object tracking, and the role of neural networks in modern autonomous driving stacks, with emphasis on real-world deployment considerations.
Date
Mar 2, 2026 9:00 AM — 5:00 PM
Event
Location
Centrale Nantes
1 rue de la Noë, Nantes, Pays de la Loire 44321
This page describes the lectio magistralis delivered at Centrale Nantes for the Datasim program in March 2026.
The lecture covered:
- Overview of sensors used in autonomous driving (camera, LiDAR, radar, ultrasonic)
- Classical and modern approaches to sensor fusion
- Scene understanding for autonomous driving
- Neural network-based perception pipelines
- Real-world deployment challenges and considerations
Federico Camarda
AD/ADAS Sofware Engineer | PhD in Automation and Robotics
My work and research aim is to make vehicles smarter and safer.