Raymobtime is a methodology for collecting realistic datasets for simulating wireless communications. It uses ray-tracing and 3D scenarios with mobility and time evolution, for obtaining consistency over time, frequency and space. We incorporate simulations of LIDAR (via Blensor), cameras (via Blender) and positions to enable investigations using machine learning and other techniques. We have been using Remcom’s Wireless Insite for ray-tracing and the open source Simulator of Urban Mobility (SUMO) for mobility simulation (of vehicles, pedestrians, drones, etc). We also use Cadmapper and Open Street Map to simplify importing realistic outdoor scenarios. For more details, please check our publications.
UFPA, UNIFESSPA and North Carolina State University (NCSU), invite you to participate in the ITU Artificial Intelligence/Machine Learning in 5G Challenge, a competition which is scheduled to run from now until the end of the year. Participation in the Challenge is free of charge and open to all interested parties from countries that are a member of ITU. If you are interested in one of the following topics below, please signal your interest by filling out the form on the website. Detailed information about the Challenge can be found in the document in 5G networks. A Primer, available on the Challenge website.
| Dataset name | Wireless Insite Version | 3D scenario | Frequency | Number of receivers and type | Time between scenes | Time between episodes | Number of episodes | Number of scenes per episode | Number of valid channels |
|---|---|---|---|---|---|---|---|---|---|
| s000 | 3.2 | Rosslyn | 60GHz | 10 Mobile | 100 ms | 30 s | 116 | 50 | 41K |
| s001 | 3.2 | Rosslyn | 2.8; 5 GHz | 10 Fixed | 5 ms | 37 s | 200 | 10 | 20K |
| s002 | 3.2 | Rosslyn | 2.8; 60 GHz | 10 Fixed | 1 s | 3 s | 1800 | 1 | 18K |
| s003 | 3.2 | Rosslyn | 2.8; 5 GHz | 10 Fixed | 1 ms | 35 s | 200 | 10 | 20K |
| s004 | 3.2 | Rosslyn | 60 GHz | 10 Mobile | 1 s | 30 s | 5000 | 1 | 35K |
| s005 | 3.2 | Rosslyn | 2.8; 5 GHz | 10 Fixed | 10 ms | 35 s | 125 | 80 | 100K |
| s006 | 3.2 | Rosslyn | 28; 60 GHz | 10 Fixed | 1 ms | 35 s | 200 | 10 | 20K |
| Dataset name | Wireless Insite Version | 3D scenario | Frequency | Number of receivers and type | Time between scenes | Time between episodes | Number of episodes | Number of scenes per episode | Number of valid channels |
|---|---|---|---|---|---|---|---|---|---|
| s007 | 3.3 | Beijing | 2.8; 60 GHz | 10 Mobile | 1 s | 5 s | 50 | 40 | 15K |
| s008 | 3.2 | Rosslyn | 60GHz | 10 Mobile | 0.1 s | 30 s | 2086 | 1 | 11K |
| s009 | 3.3 | Rosslyn | 60GHz | 10 Mobile | 0.1 s | 30 s | 2000 | 1 | 10K |
| Dataset name | Wireless Insite Version | 3D scenario | Frequency | Number of Transmitters | Number of Receivers | Time between scenes | Time between episodes | Number of episodes | Number of scenes per episode | Number of valid channels |
|---|---|---|---|---|---|---|---|---|---|---|
| v001 | 3.3 | Rosslyn | 60 GHz | 2 | 5 | 100 ms | 30 s | 20 | 50 | 8.5k |
| v002 | 3.3 | Rosslyn | 60 GHz | 1 | 5 | 0.1 s | 0.1 s | 2500 | 1 | 12.5K |
Links of interest:
- Wiki with technical information about the datasets (file format, definitions of episode and scene, etc.)
- General Code in Python and Matlab / Octave for reading and interpreting Raymobtime files (hdf5 files).
- Code in Python for baseline systems associated to the 2020 ITU Artificial Intelligence/Machine Learning in 5G Challenge
Example of ray-tracing simulation in a 3D scenario with the received powers of each ray indicated in colors.Please feel free to create an issue at our Github.
LASSE/UFPA TEAM
WSIL/UT AUSTIN TEAM
