Vision Aided Navigation (086761): Fall 2017

The course focuses on fundamental topics in vision aided navigation (VAN) and simultaneous localization and mapping (SLAM), which are essential for autonomous operation in unknown, uncertain or dynamically changing environments.

Topics to be covered include: Bayesian inference, state of the art SLAM and VAN approaches, and bundle adjustment. Depending on progress, some of the following advanced topics will be also briefly covered: multi-robot cooperative localization and mapping, active SLAM and belief space planning, intro/overview of recent deep learning approaches.

We encourage student participation from multiple faculties/departments at the Technion.

  • Course syllabus and information sheet can be found here.
  • The course is managed via Piazza.
    Important – Sign up to the course here. Let me know (by email) if you do not have a Technion email.

When: Sundays, 13:30-16:30
Where: TBD

Course tentative schedule (will probably change during the semester):

Lecture week Date Topic
1 22.10.2017 Introduction, 3D rigid transformations, 6 DOF Poses
2 29.11.2017 Probability basics, Bayesian inference, Extended Kalman filter
3 05.11.2017 Projective camera geometry, Feature detection and matching
4 12.11.2017 Structure from Motion I, Multiple view geometry, Bundle adjustment
5 19.11.2017 SLAM and VAN
6 26.11.2017 Graphical Models, iSAM
7 03.12.2017 iSAM, visual-inertial SLAM
8 10.12.2017 Active SLAM, Belief space planning
9 24.12.2017 Midterm exam
10 31.12.2017 Cooperative navigation and SLAM I
11 07.01.2018 Cooperative navigation and SLAM II
12 14.01.2018 Project presentations
13 21.01.2018 Project presentations