Channel Charting Advances at Asilomar Conference on Signals, Systems and Computers

The Asilomar Conference on Signals, Systems, and Computers is a conference held yearly on the Asilomar conference grounds in California. This year, the Institute of Telecommunications (INUE) was represented with a presentation on the topic of Channel Charting.

Channel Charting is a machine learning technique that aims to create a virtual map of the radio environment in a self-supervised manner. It exploits so-called Channel State Information (CSI), which is information about the wireless propagation channel and its multi-path properties. CSI is produced at the base station as a by-product of communicating with end users, so there is not need to change anything about the communication protocol and the system works with existing devices.

The presentation given at Asilomar was entitled "Augmenting Channel Charting with Classical Wireless Source Localization Techniques" and it disccuses the possibility of improving absolute user localization with Channel Charting. This may be useful for applications like indoor localization. It was shown that Channel Charting can improve location accuracy compared to classical methods like triangulation or multilateration.