WiFi Localization

Important: all material posted in this page is subject to a pending patent.

IROS 2012

This material is presented as part of the IROS 2012 paper "Classification and Regression for WiFi Localization of Heterogeneous Robot Teams in Unknown Environments". Copyright and all rights are retained by authors or by other copyright holders. Personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage. Specifically, the work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Code and datasets used in the paper (Matlab implementation)

readme_iros_2012.txt: Highly recommended download, which describes the files included in the various downloads below.

[Everything]- Recommended download, which includes everything: raw data, processed data, trained datastructures for each algorithm, and code. This is huge file (4GB) hosted on a different server.

Since all of the data, especialy the trained data structures for each algorithm, makes for a large download, we also provide downloads for the raw data, processed data, trained datastructures for each algorithm, and code separately. Care should be taken when using these partial downloads, however, since they are likely to be dependent on each other. The most likely scenario would be to download everything, except for the trained datastructures, and run the appropriate code that will learn those datastructures (this, however, will take a long time if ran on all data samples and all algorithms). Care should be taken to keep the file and directory structure incorporated in the zip files. 

• Raw Data ucm-wifi-localizer_raw-data.zip. (28M)
• Processed data [zip] (757MB, hosted on a different server)
• Tranined datastructures [zip] (1.5 GB, hosted on a different server)
• Code ucm-wifi-localizer_code.zip.

Video:

Accompanying video

ICRA 2014

This material is presented as part of the ICRA 2014 paper, "An Online Random Forest for Real-Time WiFi Localization of Heterogeneous Robot Teams". Copyright and all rights are retained by authors or by other copyright holders. Personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage. Specifically, the work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Code and datasets used in the paper (Matlab implementation)

readme_icra_2014.txt (7.1KB) - Highly recommended download, which describes the files included in the various downloads below.

[Everything] [zip] - Recommended download, which includes everything: raw data, processed data, trained datastructures for each algorithm, and code. This is huge file (4GB) hosted on a different server.

   Since all of the data, especialy the trained data structures for each algorithm, makes for a large download, we also provide downloads for the raw data, processed data, trained datastructures for each algorithm, and code separately. Care should be taken when using these partial downloads, however, since they are likely to be dependent on each other. The most likely scenario would be to download everything, except for the trained datastructures, and run the appropriate code that will learn those datastructures (this, however, will take a long time if ran on all data samples and all algorithms). Care should be taken to keep the file and directory structure incorporated in the zip files. 

•    Raw Data  Raw Data [zip] (28MB) 
•    Processed Data [zip] (757MB)
•    Trained Datastructures [zip] (3.6GB)
•    Code [zip] (26KB)

Video

All videos are encoded with MPEG-4 Part 10 and consequentely require an x264 decoder.