A reliable and comprehensive public WiFi fingerprinting database for researchers to implement and compare the indoor localization’s methods.The database contains RSSI information from 6 APs conducted in different days with the support of autonomous robot.

We use an autonomous robot to collect the WiFi fingerprint data. Our 3-wheel robot has multiple sensors including wheel odometer, an inertial measurement unit (IMU), a LIDAR, sonar sensors and a color and depth (RGB-D) camera. The robot can navigate to a target location to collect WiFi fingerprints automatically. The localization accuracy of the robot is 0.07 m ± 0.02 m. The dimension of the area is 21 m × 16 m. It has three long corridors. There are six APs and five of them provide two distinct MAC address for 2.4- and 5-GHz communications channels, respectively, except for one that only operates on 2.4-GHz frequency. There is one router can provide CSI information.


Database Folder name "RSSI_6AP_Experiments" which includes:

+ Nexus 4 database

+ Nexus 5 database

Training & Testing data are seperated & collected in different time with different locations.

* The general format for csv data file is:

-- X & Y & The list of RSSI

-- X | Y | RSSI Vector



First thanks for the datasets , but i found some errors:
you have mentioned some coordinates with x = 21 but the map length is 21 too, how is that possible??

Submitted by aymen saddem on Sat, 10/16/2021 - 13:20

Thanks Aymen for using our database and giving the feedback. Really appreciate it.
The exact dimension is 21.4 m which we modified the pdf floor map description accordingly.

Submitted by Tu Hoang on Sat, 11/13/2021 - 21:11

It is possible to inform the APs position?
Tks a lot

Submitted by h mm on Wed, 05/11/2022 - 03:14

It is possibile to inform the AP's position?

Submitted by Marcin Leplawy on Tue, 08/09/2022 - 17:26
Submitted by Brosnan Yuen on Sun, 03/24/2024 - 02:05

Dataset Files

Open Access dataset files are accessible to all logged in  users. Don't have a login?  Create a free IEEE account.  IEEE Membership is not required.