Lab 05

During the lab we will touch on the following topics:

• Lidar SLAM (Simultaneous Localization and Mapping),
• ICP (Iterative Closest Point) technique to align point clouds,
• Absolute Orientation problem as a part of ICP,
• Point-to-point and point-to-plane metrics,
• Making ICP robust to outliers.

At the seminar, we will deal with not only simulated examples, but also try to align point cloud scans taken from a real-world environment.

Please, download the lab scripts and data, lab05.zip.

During the lab, we will be using Jupyter notebook. It can be installed by running:

 pip install jupyter

Unzip the prepared files, launch the notebook and follow the instructions in it:

 unzip lab05.zip
 jupyter notebook icp.ipynb

Another option is to run the code using Google Colab . We provide a shared notebook: icp.ipynb . You can make a copy of the notebook into your Google Drive in order to be able to edit it and save the changes.

If you are new to Google Colab notebooks, please watch a tutorial to help you to get started, for example: https://youtu.be/RLYoEyIHL6A

Presentation: slides.

Point cloud sequences: data.

Follow the assignment of the homework HW4.