Chalmers University of Technology: Sensor Fusion and Non-linear Filtering for Automotive Systems

Learn fundamental algorithms for sensor fusion and non-linear filtering with application to automotive perception systems.

9 weeks
10–20 hours per week
Instructor-paced
Instructor-led on a course schedule
Free

In this course, we will introduce you to the fundamentals of sensor fusion for automotive systems. Key concepts involve Bayesian statistics and how to recursively estimate parameters of interest using a range of different sensors.

The course is designed for students who seek to gain a solid understanding of Bayesian statistics and how to use it to fuse information from different sensors. We emphasize object positioning problems, but the studied techniques are applicable much more generally. The course contains a series of videos, quizzes and hand-on assignments where you get to implement many of the key techniques and build your own sensor fusion toolbox.

The course is self-contained, but we highly recommend that you also take the course ChM015x: Multi-target Tracking for Automotive Systems. Together, these courses give you an excellent foundation to tackle advanced problems related to perceiving the traffic situation around an autonomous vehicle using observations from a variety of different sensors, such as, radar, lidar and camera.

At a glance

• Institution: ChalmersX
• Subject: Engineering
• Prerequisites:

Mathematical statistics and MATLAB.

• Language: English
• Video Transcript: English
• Associated programs:
• Associated skills: Algorithms, Light Detection And Ranging (LiDAR), Autonomous Vehicles, Bayesian Statistics, Sensor Fusion

What you'll learn

Skip What you'll learn
• Basics of Bayesian statistics and recursive estimation theory
• Describe and model common sensors, and their measurements
• Compare typical motion models used for positioning, in order to know when to use them in practical problems
• Describe the essential properties of the Kalman filter (KF) and apply it on linear state space models
• Implement key nonlinear filters in Matlab, in order to solve problems with nonlinear motion and/or sensor models
• Select a suitable filter method by analysing the properties and requirements in an application

Syllabus

Skip Syllabus

Section 1 - Introduction and Primer in statistics
Section 2 - Bayesian statistics (Week 1)
Section 3 - State space models and optimal filters (Week 1)
Section 4 - The Kalman filter and its properties (Week 2-3)
Section 5 - Motion and measurements models (Week 2-3)
Section 6 - Non-linear filtering (Week 4)
Section 7 - Particle filter (Week 5)

Learner testimonials

Skip Learner testimonials

I found the course very useful and also very exciting. The content and structure of the course was very well planned. The way the concepts were explained was also very understandable and engaging. I learnt a lot during the course and will be using it a lot in my own work. I look forward to similar courses being offered in future.

Who can take this course?

Unfortunately, learners residing in one or more of the following countries or regions will not be able to register for this course: Iran, Cuba and the Crimea region of Ukraine. While edX has sought licenses from the U.S. Office of Foreign Assets Control (OFAC) to offer our courses to learners in these countries and regions, the licenses we have received are not broad enough to allow us to offer this course in all locations. edX truly regrets that U.S. sanctions prevent us from offering all of our courses to everyone, no matter where they live.