Factor Graphs are graphical models that can represent a wide range of problems in Spatial AI, including - but not limited to SLAM, Visual and Lidar Odometry, Calibration, Structure from Motion, Model Predictive Control, and Image Classification. Effective methods to solve factor graphs are nowadays available.
This course aims to provide the students with a basic background on formalism and the techniques that can be used to solve these models.
We plan to present several practicals with small projects covering some of the topics included in this course.
The course is done within 20 hours of teaching and practical tests, is specifically thought for PhD programs but can be followed by anyone enrolled.
The syllabus might be adjusted based on the student's feedback.
Belief
Gaussian Distribution
Least Squares
Manifolds
Robust Cost Functions
Factor Graphs
Pose-Graphs
Bundle Adjustment
Use multiple sensors within Factor Graphs
SLAM and Bundle Adjustment Applications
Homework Presentation
Alternate Lagrangian
Synchronization
MPC
Continuous Time Estimation with Factor Graphs and Gaussian Processes
Belief Propagation and Message Passing on Factor Graphs
Continuous Time Estimation with Gaussian Belief Propagation and Gaussian Processes
Other Spatial AI Applications with Gaussian Belief Propagation
Final Quick Quiz
in presence: DIAG Sapienza, Via Ariosto 25, 00185, Rome, Italy
remotely: Via Zoom Link, shared with the people upon enrollment
May 26-30, 2025 @ 9:00-13:00
small quiz in class submitted through Google Forms on the last day
complete a small homeworks started in class, and finish by Sunday June 1st @ 23:59:59 (will be presented at the end of 28/05 lesson), send the homework as a .zip file with all necessary dependencies, email subject [FG25] Homework Submission
Please enroll using the following form. Info about the classroom and links to follow remotely will be sent to your email before the course.